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

…/git/jbarnes/pci-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jbarnes/pci-2.6: (21 commits)
  x86/PCI: use dev_printk when possible
  PCI: add D3 power state avoidance quirk
  PCI: fix bogus "'device' may be used uninitialized" warning in pci_slot
  PCI: add an option to allow ASPM enabled forcibly
  PCI: disable ASPM on pre-1.1 PCIe devices
  PCI: disable ASPM per ACPI FADT setting
  PCI MSI: Don't disable MSIs if the mask bit isn't supported
  PCI: handle 64-bit resources better on 32-bit machines
  PCI: rewrite PCI BAR reading code
  PCI: document pci_target_state
  PCI hotplug: fix typo in pcie hotplug output
  x86 gart: replace to_pages macro with iommu_num_pages
  x86, AMD IOMMU: replace to_pages macro with iommu_num_pages
  iommu: add iommu_num_pages helper function
  dma-coherent: add documentation to new interfaces
  Cris: convert to using generic dma-coherent mem allocator
  Sh: use generic per-device coherent dma allocator
  ARM: support generic per-device coherent dma mem
  Generic dma-coherent: fix DMA_MEMORY_EXCLUSIVE
  x86: use generic per-device dma coherent allocator
  ...

arch/arm/Kconfig

@@ -17,6 +17,7 @@ config ARM
 	select HAVE_KRETPROBES if (HAVE_KPROBES)
 	select HAVE_FTRACE if (!XIP_KERNEL)
 	select HAVE_DYNAMIC_FTRACE if (HAVE_FTRACE)
+	select HAVE_GENERIC_DMA_COHERENT
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and

arch/arm/mm/consistent.c

@@ -274,6 +274,11 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 void *
 dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
 {
+	void *memory;
+
+	if (dma_alloc_from_coherent(dev, size, handle, &memory))
+		return memory;
+
 	if (arch_is_coherent()) {
 		void *virt;
 
@@ -362,6 +367,9 @@ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr
 
 	WARN_ON(irqs_disabled());
 
+	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
+		return;
+
 	if (arch_is_coherent()) {
 		kfree(cpu_addr);
 		return;

arch/cris/arch-v32/drivers/Kconfig

@@ -641,6 +641,7 @@ config PCI
        bool
        depends on ETRAX_CARDBUS
        default y
+       select HAVE_GENERIC_DMA_COHERENT
 
 config ETRAX_IOP_FW_LOAD
 	tristate "IO-processor hotplug firmware loading support"

arch/cris/arch-v32/drivers/pci/dma.c

@@ -15,35 +15,16 @@
 #include <linux/pci.h>
 #include <asm/io.h>
 
-struct dma_coherent_mem {
-	void		*virt_base;
-	u32		device_base;
-	int		size;
-	int		flags;
-	unsigned long	*bitmap;
-};
-
 void *dma_alloc_coherent(struct device *dev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t gfp)
 {
 	void *ret;
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
 	int order = get_order(size);
 	/* ignore region specifiers */
 	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
 
-	if (mem) {
-		int page = bitmap_find_free_region(mem->bitmap, mem->size,
-						     order);
-		if (page >= 0) {
-			*dma_handle = mem->device_base + (page << PAGE_SHIFT);
-			ret = mem->virt_base + (page << PAGE_SHIFT);
-			memset(ret, 0, size);
-			return ret;
-		}
-		if (mem->flags & DMA_MEMORY_EXCLUSIVE)
-			return NULL;
-	}
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
+		return ret;
 
 	if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
 		gfp |= GFP_DMA;
@@ -60,90 +41,9 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 void dma_free_coherent(struct device *dev, size_t size,
 			 void *vaddr, dma_addr_t dma_handle)
 {
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
 	int order = get_order(size);
 
-	if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base + (mem->size << PAGE_SHIFT))) {
-		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
-
-		bitmap_release_region(mem->bitmap, page, order);
-	} else
+	if (!dma_release_from_coherent(dev, order, vaddr))
 		free_pages((unsigned long)vaddr, order);
 }
 
-int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
-				dma_addr_t device_addr, size_t size, int flags)
-{
-	void __iomem *mem_base;
-	int pages = size >> PAGE_SHIFT;
-	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
-
-	if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
-		goto out;
-	if (!size)
-		goto out;
-	if (dev->dma_mem)
-		goto out;
-
-	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
-
-	mem_base = ioremap(bus_addr, size);
-	if (!mem_base)
-		goto out;
-
-	dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
-	if (!dev->dma_mem)
-		goto iounmap_out;
-	dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!dev->dma_mem->bitmap)
-		goto free1_out;
-
-	dev->dma_mem->virt_base = mem_base;
-	dev->dma_mem->device_base = device_addr;
-	dev->dma_mem->size = pages;
-	dev->dma_mem->flags = flags;
-
-	if (flags & DMA_MEMORY_MAP)
-		return DMA_MEMORY_MAP;
-
-	return DMA_MEMORY_IO;
-
- free1_out:
-	kfree(dev->dma_mem);
- iounmap_out:
-	iounmap(mem_base);
- out:
-	return 0;
-}
-EXPORT_SYMBOL(dma_declare_coherent_memory);
-
-void dma_release_declared_memory(struct device *dev)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-
-	if(!mem)
-		return;
-	dev->dma_mem = NULL;
-	iounmap(mem->virt_base);
-	kfree(mem->bitmap);
-	kfree(mem);
-}
-EXPORT_SYMBOL(dma_release_declared_memory);
-
-void *dma_mark_declared_memory_occupied(struct device *dev,
-					dma_addr_t device_addr, size_t size)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-	int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	int pos, err;
-
-	if (!mem)
-		return ERR_PTR(-EINVAL);
-
-	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
-	err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
-	if (err != 0)
-		return ERR_PTR(err);
-	return mem->virt_base + (pos << PAGE_SHIFT);
-}
-EXPORT_SYMBOL(dma_mark_declared_memory_occupied);

arch/sh/Kconfig

@@ -11,6 +11,7 @@ config SUPERH
 	select HAVE_CLK
 	select HAVE_IDE
 	select HAVE_OPROFILE
+	select HAVE_GENERIC_DMA_COHERENT
 	help
 	  The SuperH is a RISC processor targeted for use in embedded systems
 	  and consumer electronics; it was also used in the Sega Dreamcast

arch/sh/mm/consistent.c

@@ -28,21 +28,10 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t gfp)
 {
 	void *ret, *ret_nocache;
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
 	int order = get_order(size);
 
-	if (mem) {
-		int page = bitmap_find_free_region(mem->bitmap, mem->size,
-						     order);
-		if (page >= 0) {
-			*dma_handle = mem->device_base + (page << PAGE_SHIFT);
-			ret = mem->virt_base + (page << PAGE_SHIFT);
-			memset(ret, 0, size);
-			return ret;
-		}
-		if (mem->flags & DMA_MEMORY_EXCLUSIVE)
-			return NULL;
-	}
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
+		return ret;
 
 	ret = (void *)__get_free_pages(gfp, order);
 	if (!ret)
@@ -72,11 +61,7 @@ void dma_free_coherent(struct device *dev, size_t size,
 	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
 	int order = get_order(size);
 
-	if (mem && vaddr >= mem->virt_base && vaddr < (mem->virt_base + (mem->size << PAGE_SHIFT))) {
-		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
-
-		bitmap_release_region(mem->bitmap, page, order);
-	} else {
+	if (!dma_release_from_coherent(dev, order, vaddr)) {
 		WARN_ON(irqs_disabled());	/* for portability */
 		BUG_ON(mem && mem->flags & DMA_MEMORY_EXCLUSIVE);
 		free_pages((unsigned long)phys_to_virt(dma_handle), order);
@@ -85,83 +70,6 @@ void dma_free_coherent(struct device *dev, size_t size,
 }
 EXPORT_SYMBOL(dma_free_coherent);
 
-int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
-				dma_addr_t device_addr, size_t size, int flags)
-{
-	void __iomem *mem_base = NULL;
-	int pages = size >> PAGE_SHIFT;
-	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
-
-	if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
-		goto out;
-	if (!size)
-		goto out;
-	if (dev->dma_mem)
-		goto out;
-
-	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
-
-	mem_base = ioremap_nocache(bus_addr, size);
-	if (!mem_base)
-		goto out;
-
-	dev->dma_mem = kmalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
-	if (!dev->dma_mem)
-		goto out;
-	dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!dev->dma_mem->bitmap)
-		goto free1_out;
-
-	dev->dma_mem->virt_base = mem_base;
-	dev->dma_mem->device_base = device_addr;
-	dev->dma_mem->size = pages;
-	dev->dma_mem->flags = flags;
-
-	if (flags & DMA_MEMORY_MAP)
-		return DMA_MEMORY_MAP;
-
-	return DMA_MEMORY_IO;
-
- free1_out:
-	kfree(dev->dma_mem);
- out:
-	if (mem_base)
-		iounmap(mem_base);
-	return 0;
-}
-EXPORT_SYMBOL(dma_declare_coherent_memory);
-
-void dma_release_declared_memory(struct device *dev)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-
-	if (!mem)
-		return;
-	dev->dma_mem = NULL;
-	iounmap(mem->virt_base);
-	kfree(mem->bitmap);
-	kfree(mem);
-}
-EXPORT_SYMBOL(dma_release_declared_memory);
-
-void *dma_mark_declared_memory_occupied(struct device *dev,
-					dma_addr_t device_addr, size_t size)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-	int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	int pos, err;
-
-	if (!mem)
-		return ERR_PTR(-EINVAL);
-
-	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
-	err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
-	if (err != 0)
-		return ERR_PTR(err);
-	return mem->virt_base + (pos << PAGE_SHIFT);
-}
-EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
-
 void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		    enum dma_data_direction direction)
 {

arch/x86/Kconfig

@@ -30,6 +30,7 @@ config X86
 	select HAVE_FTRACE
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
+	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 
 config ARCH_DEFCONFIG

arch/x86/kernel/amd_iommu.c

@@ -29,9 +29,6 @@
 
 #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
 
-#define to_pages(addr, size) \
-	 (round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT)
-
 #define EXIT_LOOP_COUNT 10000000
 
 static DEFINE_RWLOCK(amd_iommu_devtable_lock);
@@ -185,7 +182,7 @@ static int iommu_flush_pages(struct amd_iommu *iommu, u16 domid,
 		u64 address, size_t size)
 {
 	int s = 0;
-	unsigned pages = to_pages(address, size);
+	unsigned pages = iommu_num_pages(address, size);
 
 	address &= PAGE_MASK;
 
@@ -557,8 +554,8 @@ static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu,
 	if (iommu->exclusion_start &&
 	    iommu->exclusion_start < dma_dom->aperture_size) {
 		unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
-		int pages = to_pages(iommu->exclusion_start,
-				iommu->exclusion_length);
+		int pages = iommu_num_pages(iommu->exclusion_start,
+					    iommu->exclusion_length);
 		dma_ops_reserve_addresses(dma_dom, startpage, pages);
 	}
 
@@ -767,7 +764,7 @@ static dma_addr_t __map_single(struct device *dev,
 	unsigned int pages;
 	int i;
 
-	pages = to_pages(paddr, size);
+	pages = iommu_num_pages(paddr, size);
 	paddr &= PAGE_MASK;
 
 	address = dma_ops_alloc_addresses(dev, dma_dom, pages);
@@ -802,7 +799,7 @@ static void __unmap_single(struct amd_iommu *iommu,
 	if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size))
 		return;
 
-	pages = to_pages(dma_addr, size);
+	pages = iommu_num_pages(dma_addr, size);
 	dma_addr &= PAGE_MASK;
 	start = dma_addr;