X86: integrate CMA with DMA-mapping subsystem

This patch adds support for CMA to dma-mapping subsystem for x86
architecture that uses common pci-dma/pci-nommu implementation. This
allows to test CMA on KVM/QEMU and a lot of common x86 boxes.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Kyungmin Park <kyungmin.park@samsung.com>
CC: Michal Nazarewicz <mina86@mina86.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>

arch/x86/Kconfig

@@ -31,6 +31,7 @@ config X86
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_FRAME_POINTERS
 	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS if !SWIOTLB
 	select HAVE_KRETPROBES
 	select HAVE_OPTPROBES
 	select HAVE_FTRACE_MCOUNT_RECORD

arch/x86/include/asm/dma-contiguous.h

@@ -0,0 +1,13 @@
+#ifndef ASMX86_DMA_CONTIGUOUS_H
+#define ASMX86_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+#include <asm-generic/dma-contiguous.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif

arch/x86/include/asm/dma-mapping.h

@@ -13,6 +13,7 @@
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 #include <asm-generic/dma-coherent.h>
+#include <linux/dma-contiguous.h>
 
 #ifdef CONFIG_ISA
 # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24)
@@ -62,6 +63,10 @@ extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_addr, gfp_t flag,
 					struct dma_attrs *attrs);
 
+extern void dma_generic_free_coherent(struct device *dev, size_t size,
+				      void *vaddr, dma_addr_t dma_addr,
+				      struct dma_attrs *attrs);
+
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
 	if (!dev->dma_mask)

arch/x86/kernel/pci-dma.c

@@ -100,14 +100,18 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 struct dma_attrs *attrs)
 {
 	unsigned long dma_mask;
-	struct page *page;
+	struct page *page = NULL;
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	dma_addr_t addr;
 
 	dma_mask = dma_alloc_coherent_mask(dev, flag);
 
 	flag |= __GFP_ZERO;
 again:
-	page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
+	if (!(flag & GFP_ATOMIC))
+		page = dma_alloc_from_contiguous(dev, count, get_order(size));
+	if (!page)
+		page = alloc_pages_node(dev_to_node(dev), flag, get_order(size));
 	if (!page)
 		return NULL;
 
@@ -127,6 +131,16 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 	return page_address(page);
 }
 
+void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
+			       dma_addr_t dma_addr, struct dma_attrs *attrs)
+{
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page *page = virt_to_page(vaddr);
+
+	if (!dma_release_from_contiguous(dev, page, count))
+		free_pages((unsigned long)vaddr, get_order(size));
+}
+
 /*
  * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel
  * parameter documentation.

arch/x86/kernel/pci-nommu.c

@@ -74,12 +74,6 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 	return nents;
 }
 
-static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
-				dma_addr_t dma_addr, struct dma_attrs *attrs)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
 static void nommu_sync_single_for_device(struct device *dev,
 			dma_addr_t addr, size_t size,
 			enum dma_data_direction dir)
@@ -97,7 +91,7 @@ static void nommu_sync_sg_for_device(struct device *dev,
 
 struct dma_map_ops nommu_dma_ops = {
 	.alloc			= dma_generic_alloc_coherent,
-	.free			= nommu_free_coherent,
+	.free			= dma_generic_free_coherent,
 	.map_sg			= nommu_map_sg,
 	.map_page		= nommu_map_page,
 	.sync_single_for_device = nommu_sync_single_for_device,

arch/x86/kernel/setup.c

@@ -50,6 +50,7 @@
 #include <asm/pci-direct.h>
 #include <linux/init_ohci1394_dma.h>
 #include <linux/kvm_para.h>
+#include <linux/dma-contiguous.h>
 
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -934,6 +935,7 @@ void __init setup_arch(char **cmdline_p)
 	}
 #endif
 	memblock.current_limit = get_max_mapped();
+	dma_contiguous_reserve(0);
 
 	/*
 	 * NOTE: On x86-32, only from this point on, fixmaps are ready for use.