diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index ea5eb5f79ad..257033c691f 100644
--- a/arch/arm/Kconfig
+++ b/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
diff --git a/arch/arm/mm/consistent.c b/arch/arm/mm/consistent.c
index 333a82a3717..db7b3e38ef1 100644
--- a/arch/arm/mm/consistent.c
+++ b/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;
diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig
index 2a92cb1886c..7a64fcef9d0 100644
--- a/arch/cris/arch-v32/drivers/Kconfig
+++ b/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"
diff --git a/arch/cris/arch-v32/drivers/pci/dma.c b/arch/cris/arch-v32/drivers/pci/dma.c
index e0364654fc4..fbe65954ee6 100644
--- a/arch/cris/arch-v32/drivers/pci/dma.c
+++ b/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);
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 7bfb0d219d6..0b88dc462d7 100644
--- a/arch/sh/Kconfig
+++ b/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
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 8277982d093..b2ce014401b 100644
--- a/arch/sh/mm/consistent.c
+++ b/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)
 {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b6fa2877b17..3d0f2b6a5a1 100644
--- a/arch/x86/Kconfig
+++ b/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
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 74697408576..22d7d050905 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/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;
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 37544123896..8dbffb846de 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -192,124 +192,6 @@ static __init int iommu_setup(char *p)
 }
 early_param("iommu", iommu_setup);
 
-#ifdef CONFIG_X86_32
-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(bus_addr, size);
-	if (!mem_base)
-		goto out;
-
-	dev->dma_mem = kzalloc(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 pos, err;
-	int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1);
-
-	pages >>= PAGE_SHIFT;
-
-	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);
-
-static int dma_alloc_from_coherent_mem(struct device *dev, ssize_t size,
-				       dma_addr_t *dma_handle, void **ret)
-{
-	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);
-		}
-		if (mem->flags & DMA_MEMORY_EXCLUSIVE)
-			*ret = NULL;
-	}
-	return (mem != NULL);
-}
-
-static int dma_release_coherent(struct device *dev, int order, void *vaddr)
-{
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
-
-	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);
-		return 1;
-	}
-	return 0;
-}
-#else
-#define dma_alloc_from_coherent_mem(dev, size, handle, ret) (0)
-#define dma_release_coherent(dev, order, vaddr) (0)
-#endif /* CONFIG_X86_32 */
-
 int dma_supported(struct device *dev, u64 mask)
 {
 	struct dma_mapping_ops *ops = get_dma_ops(dev);
@@ -379,7 +261,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* ignore region specifiers */
 	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
 
-	if (dma_alloc_from_coherent_mem(dev, size, dma_handle, &memory))
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
 		return memory;
 
 	if (!dev) {
@@ -484,7 +366,7 @@ void dma_free_coherent(struct device *dev, size_t size,
 
 	int order = get_order(size);
 	WARN_ON(irqs_disabled());	/* for portability */
-	if (dma_release_coherent(dev, order, vaddr))
+	if (dma_release_from_coherent(dev, order, vaddr))
 		return;
 	if (ops->unmap_single)
 		ops->unmap_single(dev, bus, size, 0);
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 744126e6495..49285f8fd4d 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -67,9 +67,6 @@ static u32 gart_unmapped_entry;
 	(((x) & 0xfffff000) | (((x) >> 32) << 4) | GPTE_VALID | GPTE_COHERENT)
 #define GPTE_DECODE(x) (((x) & 0xfffff000) | (((u64)(x) & 0xff0) << 28))
 
-#define to_pages(addr, size) \
-	(round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT)
-
 #define EMERGENCY_PAGES 32 /* = 128KB */
 
 #ifdef CONFIG_AGP
@@ -241,7 +238,7 @@ nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
 static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 				size_t size, int dir)
 {
-	unsigned long npages = to_pages(phys_mem, size);
+	unsigned long npages = iommu_num_pages(phys_mem, size);
 	unsigned long iommu_page = alloc_iommu(dev, npages);
 	int i;
 
@@ -304,7 +301,7 @@ static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
 		return;
 
 	iommu_page = (dma_addr - iommu_bus_base)>>PAGE_SHIFT;
-	npages = to_pages(dma_addr, size);
+	npages = iommu_num_pages(dma_addr, size);
 	for (i = 0; i < npages; i++) {
 		iommu_gatt_base[iommu_page + i] = gart_unmapped_entry;
 		CLEAR_LEAK(iommu_page + i);
@@ -387,7 +384,7 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start,
 		}
 
 		addr = phys_addr;
-		pages = to_pages(s->offset, s->length);
+		pages = iommu_num_pages(s->offset, s->length);
 		while (pages--) {
 			iommu_gatt_base[iommu_page] = GPTE_ENCODE(addr);
 			SET_LEAK(iommu_page);
@@ -470,7 +467,7 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 
 		seg_size += s->length;
 		need = nextneed;
-		pages += to_pages(s->offset, s->length);
+		pages += iommu_num_pages(s->offset, s->length);
 		ps = s;
 	}
 	if (dma_map_cont(dev, start_sg, i - start, sgmap, pages, need) < 0)
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index ff3a6a33634..4bdaa590375 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -23,7 +23,8 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d)
 		pci_read_config_byte(d, reg++, &busno);
 		pci_read_config_byte(d, reg++, &suba);
 		pci_read_config_byte(d, reg++, &subb);
-		DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb);
+		dev_dbg(&d->dev, "i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno,
+			suba, subb);
 		if (busno)
 			pci_scan_bus_with_sysdata(busno);	/* Bus A */
 		if (suba < subb)
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index a09505806b8..5807d1bc73f 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -128,10 +128,8 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				pr = pci_find_parent_resource(dev, r);
 				if (!r->start || !pr ||
 				    request_resource(pr, r) < 0) {
-					printk(KERN_ERR "PCI: Cannot allocate "
-						"resource region %d "
-						"of bridge %s\n",
-						idx, pci_name(dev));
+					dev_err(&dev->dev, "BAR %d: can't "
+						"allocate resource\n", idx);
 					/*
 					 * Something is wrong with the region.
 					 * Invalidate the resource to prevent
@@ -166,15 +164,15 @@ static void __init pcibios_allocate_resources(int pass)
 			else
 				disabled = !(command & PCI_COMMAND_MEMORY);
 			if (pass == disabled) {
-				DBG("PCI: Resource %08lx-%08lx "
-				    "(f=%lx, d=%d, p=%d)\n",
-				    r->start, r->end, r->flags, disabled, pass);
+				dev_dbg(&dev->dev, "resource %#08llx-%#08llx "
+					"(f=%lx, d=%d, p=%d)\n",
+					(unsigned long long) r->start,
+					(unsigned long long) r->end,
+					r->flags, disabled, pass);
 				pr = pci_find_parent_resource(dev, r);
 				if (!pr || request_resource(pr, r) < 0) {
-					printk(KERN_ERR "PCI: Cannot allocate "
-						"resource region %d "
-						"of device %s\n",
-						idx, pci_name(dev));
+					dev_err(&dev->dev, "BAR %d: can't "
+						"allocate resource\n", idx);
 					/* We'll assign a new address later */
 					r->end -= r->start;
 					r->start = 0;
@@ -187,8 +185,7 @@ static void __init pcibios_allocate_resources(int pass)
 				/* Turn the ROM off, leave the resource region,
 				 * but keep it unregistered. */
 				u32 reg;
-				DBG("PCI: Switching off ROM of %s\n",
-					pci_name(dev));
+				dev_dbg(&dev->dev, "disabling ROM\n");
 				r->flags &= ~IORESOURCE_ROM_ENABLE;
 				pci_read_config_dword(dev,
 						dev->rom_base_reg, &reg);
@@ -257,8 +254,7 @@ void pcibios_set_master(struct pci_dev *dev)
 		lat = pcibios_max_latency;
 	else
 		return;
-	printk(KERN_DEBUG "PCI: Setting latency timer of device %s to %d\n",
-		pci_name(dev), lat);
+	dev_printk(KERN_DEBUG, &dev->dev, "setting latency timer to %d\n", lat);
 	pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);
 }
 
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 6a06a2eb059..fec0123b33a 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -436,7 +436,7 @@ static int pirq_vlsi_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
 {
 	WARN_ON_ONCE(pirq >= 9);
 	if (pirq > 8) {
-		printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq);
+		dev_info(&dev->dev, "VLSI router PIRQ escape (%d)\n", pirq);
 		return 0;
 	}
 	return read_config_nybble(router, 0x74, pirq-1);
@@ -446,7 +446,7 @@ static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
 {
 	WARN_ON_ONCE(pirq >= 9);
 	if (pirq > 8) {
-		printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq);
+		dev_info(&dev->dev, "VLSI router PIRQ escape (%d)\n", pirq);
 		return 0;
 	}
 	write_config_nybble(router, 0x74, pirq-1, irq);
@@ -492,15 +492,17 @@ static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq
 	irq = 0;
 	if (pirq <= 4)
 		irq = read_config_nybble(router, 0x56, pirq - 1);
-	printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n",
-		dev->vendor, dev->device, pirq, irq);
+	dev_info(&dev->dev,
+		 "AMD756: dev [%04x/%04x], router PIRQ %d get IRQ %d\n",
+		 dev->vendor, dev->device, pirq, irq);
 	return irq;
 }
 
 static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
 {
-	printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n",
-		dev->vendor, dev->device, pirq, irq);
+	dev_info(&dev->dev,
+		 "AMD756: dev [%04x/%04x], router PIRQ %d set IRQ %d\n",
+		 dev->vendor, dev->device, pirq, irq);
 	if (pirq <= 4)
 		write_config_nybble(router, 0x56, pirq - 1, irq);
 	return 1;
@@ -730,7 +732,6 @@ static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router,
 	switch (device) {
 	case PCI_DEVICE_ID_AL_M1533:
 	case PCI_DEVICE_ID_AL_M1563:
-		printk(KERN_DEBUG "PCI: Using ALI IRQ Router\n");
 		r->name = "ALI";
 		r->get = pirq_ali_get;
 		r->set = pirq_ali_set;
@@ -840,11 +841,9 @@ static void __init pirq_find_router(struct irq_router *r)
 			h->probe(r, pirq_router_dev, pirq_router_dev->device))
 			break;
 	}
-	printk(KERN_INFO "PCI: Using IRQ router %s [%04x/%04x] at %s\n",
-		pirq_router.name,
-		pirq_router_dev->vendor,
-		pirq_router_dev->device,
-		pci_name(pirq_router_dev));
+	dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x/%04x]\n",
+		 pirq_router.name,
+		 pirq_router_dev->vendor, pirq_router_dev->device);
 
 	/* The device remains referenced for the kernel lifetime */
 }
@@ -877,7 +876,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	/* Find IRQ pin */
 	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
 	if (!pin) {
-		DBG(KERN_DEBUG " -> no interrupt pin\n");
+		dev_dbg(&dev->dev, "no interrupt pin\n");
 		return 0;
 	}
 	pin = pin - 1;
@@ -887,20 +886,20 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	if (!pirq_table)
 		return 0;
 
-	DBG(KERN_DEBUG "IRQ for %s[%c]", pci_name(dev), 'A' + pin);
 	info = pirq_get_info(dev);
 	if (!info) {
-		DBG(" -> not found in routing table\n" KERN_DEBUG);
+		dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n",
+			'A' + pin);
 		return 0;
 	}
 	pirq = info->irq[pin].link;
 	mask = info->irq[pin].bitmap;
 	if (!pirq) {
-		DBG(" -> not routed\n" KERN_DEBUG);
+		dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin);
 		return 0;
 	}
-	DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask,
-		pirq_table->exclusive_irqs);
+	dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x",
+		'A' + pin, pirq, mask, pirq_table->exclusive_irqs);
 	mask &= pcibios_irq_mask;
 
 	/* Work around broken HP Pavilion Notebooks which assign USB to
@@ -930,10 +929,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 		if (pci_probe & PCI_USE_PIRQ_MASK)
 			newirq = 0;
 		else
-			printk("\n" KERN_WARNING
-				"PCI: IRQ %i for device %s doesn't match PIRQ mask - try pci=usepirqmask\n"
-				KERN_DEBUG, newirq,
-				pci_name(dev));
+			dev_warn(&dev->dev, "IRQ %d doesn't match PIRQ mask "
+				 "%#x; try pci=usepirqmask\n", newirq, mask);
 	}
 	if (!newirq && assign) {
 		for (i = 0; i < 16; i++) {
@@ -944,39 +941,35 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 				newirq = i;
 		}
 	}
-	DBG(" -> newirq=%d", newirq);
+	dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin, newirq);
 
 	/* Check if it is hardcoded */
 	if ((pirq & 0xf0) == 0xf0) {
 		irq = pirq & 0xf;
-		DBG(" -> hardcoded IRQ %d\n", irq);
-		msg = "Hardcoded";
+		msg = "hardcoded";
 	} else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
 	((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
-		DBG(" -> got IRQ %d\n", irq);
-		msg = "Found";
+		msg = "found";
 		eisa_set_level_irq(irq);
 	} else if (newirq && r->set &&
 		(dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
-		DBG(" -> assigning IRQ %d", newirq);
 		if (r->set(pirq_router_dev, dev, pirq, newirq)) {
 			eisa_set_level_irq(newirq);
-			DBG(" ... OK\n");
-			msg = "Assigned";
+			msg = "assigned";
 			irq = newirq;
 		}
 	}
 
 	if (!irq) {
-		DBG(" ... failed\n");
 		if (newirq && mask == (1 << newirq)) {
-			msg = "Guessed";
+			msg = "guessed";
 			irq = newirq;
-		} else
+		} else {
+			dev_dbg(&dev->dev, "can't route interrupt\n");
 			return 0;
+		}
 	}
-	printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq,
-		pci_name(dev));
+	dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin, irq);
 
 	/* Update IRQ for all devices with the same pirq value */
 	while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) {
@@ -996,17 +989,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 			(!(pci_probe & PCI_USE_PIRQ_MASK) || \
 			((1 << dev2->irq) & mask))) {
 #ifndef CONFIG_PCI_MSI
-				printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n",
-				       pci_name(dev2), dev2->irq, irq);
+				dev_info(&dev2->dev, "IRQ routing conflict: "
+					 "have IRQ %d, want IRQ %d\n",
+					 dev2->irq, irq);
 #endif
 				continue;
 			}
 			dev2->irq = irq;
 			pirq_penalty[irq]++;
 			if (dev != dev2)
-				printk(KERN_INFO
-					"PCI: Sharing IRQ %d with %s\n",
-					irq, pci_name(dev2));
+				dev_info(&dev->dev, "sharing IRQ %d with %s\n",
+					 irq, pci_name(dev2));
 		}
 	}
 	return 1;
@@ -1025,8 +1018,7 @@ static void __init pcibios_fixup_irqs(void)
 		 * already in use.
 		 */
 		if (dev->irq >= 16) {
-			DBG(KERN_DEBUG "%s: ignoring bogus IRQ %d\n",
-				pci_name(dev), dev->irq);
+			dev_dbg(&dev->dev, "ignoring bogus IRQ %d\n", dev->irq);
 			dev->irq = 0;
 		}
 		/*
@@ -1070,12 +1062,12 @@ static void __init pcibios_fixup_irqs(void)
 					irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
 							PCI_SLOT(bridge->devfn), pin);
 					if (irq >= 0)
-						printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n",
-							pci_name(bridge), 'A' + pin, irq);
+						dev_warn(&dev->dev, "using bridge %s INT %c to get IRQ %d\n",
+							 pci_name(bridge),
+							 'A' + pin, irq);
 				}
 				if (irq >= 0) {
-					printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n",
-						pci_name(dev), 'A' + pin, irq);
+					dev_info(&dev->dev, "PCI->APIC IRQ transform: INT %c -> IRQ %d\n", 'A' + pin, irq);
 					dev->irq = irq;
 				}
 			}
@@ -1231,25 +1223,24 @@ static int pirq_enable_irq(struct pci_dev *dev)
 				irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
 						PCI_SLOT(bridge->devfn), pin);
 				if (irq >= 0)
-					printk(KERN_WARNING
-						"PCI: using PPB %s[%c] to get irq %d\n",
-						pci_name(bridge),
-						'A' + pin, irq);
+					dev_warn(&dev->dev, "using bridge %s "
+						 "INT %c to get IRQ %d\n",
+						 pci_name(bridge), 'A' + pin,
+						 irq);
 				dev = bridge;
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
-				printk(KERN_INFO
-					"PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n",
-					pci_name(dev), 'A' + pin, irq);
+				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
+					 "INT %c -> IRQ %d\n", 'A' + pin, irq);
 				dev->irq = irq;
 				return 0;
 			} else
-				msg = " Probably buggy MP table.";
+				msg = "; probably buggy MP table";
 		} else if (pci_probe & PCI_BIOS_IRQ_SCAN)
 			msg = "";
 		else
-			msg = " Please try using pci=biosirq.";
+			msg = "; please try using pci=biosirq";
 
 		/*
 		 * With IDE legacy devices the IRQ lookup failure is not
@@ -1259,9 +1250,8 @@ static int pirq_enable_irq(struct pci_dev *dev)
 				!(dev->class & 0x5))
 			return 0;
 
-		printk(KERN_WARNING
-			"PCI: No IRQ known for interrupt pin %c of device %s.%s\n",
-			'A' + pin, pci_name(dev), msg);
+		dev_warn(&dev->dev, "can't find IRQ for PCI INT %c%s\n",
+			 'A' + pin, msg);
 	}
 	return 0;
 }
diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c
index f4b16dc11da..1177845d318 100644
--- a/arch/x86/pci/numaq_32.c
+++ b/arch/x86/pci/numaq_32.c
@@ -131,13 +131,14 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d)
 	u8 busno, suba, subb;
 	int quad = BUS2QUAD(d->bus->number);
 
-	printk("PCI: Searching for i450NX host bridges on %s\n", pci_name(d));
+	dev_info(&d->dev, "searching for i450NX host bridges\n");
 	reg = 0xd0;
 	for(pxb=0; pxb<2; pxb++) {
 		pci_read_config_byte(d, reg++, &busno);
 		pci_read_config_byte(d, reg++, &suba);
 		pci_read_config_byte(d, reg++, &subb);
-		DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb);
+		dev_dbg(&d->dev, "i450NX PXB %d: %02x/%02x/%02x\n",
+			pxb, busno, suba, subb);
 		if (busno) {
 			/* Bus A */
 			pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, busno));
diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c
index dd376f7ad09..d5b4ef89887 100644
--- a/drivers/acpi/pci_slot.c
+++ b/drivers/acpi/pci_slot.c
@@ -76,9 +76,9 @@ static struct acpi_pci_driver acpi_pci_slot_driver = {
 };
 
 static int
-check_slot(acpi_handle handle, int *device, unsigned long *sun)
+check_slot(acpi_handle handle, unsigned long *sun)
 {
-	int retval = 0;
+	int device = -1;
 	unsigned long adr, sta;
 	acpi_status status;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
@@ -89,32 +89,27 @@ check_slot(acpi_handle handle, int *device, unsigned long *sun)
 	if (check_sta_before_sun) {
 		/* If SxFy doesn't have _STA, we just assume it's there */
 		status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
-		if (ACPI_SUCCESS(status) && !(sta & ACPI_STA_DEVICE_PRESENT)) {
-			retval = -1;
+		if (ACPI_SUCCESS(status) && !(sta & ACPI_STA_DEVICE_PRESENT))
 			goto out;
-		}
 	}
 
 	status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
 	if (ACPI_FAILURE(status)) {
 		dbg("_ADR returned %d on %s\n", status, (char *)buffer.pointer);
-		retval = -1;
 		goto out;
 	}
 
-	*device = (adr >> 16) & 0xffff;
-
 	/* No _SUN == not a slot == bail */
 	status = acpi_evaluate_integer(handle, "_SUN", NULL, sun);
 	if (ACPI_FAILURE(status)) {
 		dbg("_SUN returned %d on %s\n", status, (char *)buffer.pointer);
-		retval = -1;
 		goto out;
 	}
 
+	device = (adr >> 16) & 0xffff;
 out:
 	kfree(buffer.pointer);
-	return retval;
+	return device;
 }
 
 struct callback_args {
@@ -144,7 +139,8 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 	struct callback_args *parent_context = context;
 	struct pci_bus *pci_bus = parent_context->pci_bus;
 
-	if (check_slot(handle, &device, &sun))
+	device = check_slot(handle, &sun);
+	if (device < 0)
 		return AE_OK;
 
 	slot = kmalloc(sizeof(*slot), GFP_KERNEL);
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 1323a43285d..ad27e9e225a 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -1103,7 +1103,7 @@ static inline void dbg_ctrl(struct controller *ctrl)
 	dbg("  Power Indicator      : %3s\n", PWR_LED(ctrl)    ? "yes" : "no");
 	dbg("  Hot-Plug Surprise    : %3s\n", HP_SUPR_RM(ctrl) ? "yes" : "no");
 	dbg("  EMI Present          : %3s\n", EMI(ctrl)        ? "yes" : "no");
-	dbg("  Comamnd Completed    : %3s\n", NO_CMD_CMPL(ctrl)? "no" : "yes");
+	dbg("  Command Completed    : %3s\n", NO_CMD_CMPL(ctrl)? "no" : "yes");
 	pciehp_readw(ctrl, SLOTSTATUS, &reg16);
 	dbg("Slot Status            : 0x%04x\n", reg16);
 	pciehp_readw(ctrl, SLOTCTRL, &reg16);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 15af618d36e..18354817173 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -126,7 +126,16 @@ static void msix_flush_writes(unsigned int irq)
 	}
 }
 
-static void msi_set_mask_bits(unsigned int irq, u32 mask, u32 flag)
+/*
+ * PCI 2.3 does not specify mask bits for each MSI interrupt.  Attempting to
+ * mask all MSI interrupts by clearing the MSI enable bit does not work
+ * reliably as devices without an INTx disable bit will then generate a
+ * level IRQ which will never be cleared.
+ *
+ * Returns 1 if it succeeded in masking the interrupt and 0 if the device
+ * doesn't support MSI masking.
+ */
+static int msi_set_mask_bits(unsigned int irq, u32 mask, u32 flag)
 {
 	struct msi_desc *entry;
 
@@ -144,8 +153,7 @@ static void msi_set_mask_bits(unsigned int irq, u32 mask, u32 flag)
 			mask_bits |= flag & mask;
 			pci_write_config_dword(entry->dev, pos, mask_bits);
 		} else {
-			__msi_set_enable(entry->dev, entry->msi_attrib.pos,
-					 !flag);
+			return 0;
 		}
 		break;
 	case PCI_CAP_ID_MSIX:
@@ -161,6 +169,7 @@ static void msi_set_mask_bits(unsigned int irq, u32 mask, u32 flag)
 		break;
 	}
 	entry->msi_attrib.masked = !!flag;
+	return 1;
 }
 
 void read_msi_msg(unsigned int irq, struct msi_msg *msg)
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 7764768b6a0..89a2f0fa10f 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/module.h>
+#include <linux/pci-aspm.h>
 #include <acpi/acpi.h>
 #include <acpi/acnamesp.h>
 #include <acpi/acresrc.h>
@@ -372,6 +373,12 @@ static int __init acpi_pci_init(void)
 		printk(KERN_INFO"ACPI FADT declares the system doesn't support MSI, so disable it\n");
 		pci_no_msi();
 	}
+
+	if (acpi_gbl_FADT.boot_flags & BAF_PCIE_ASPM_CONTROL) {
+		printk(KERN_INFO"ACPI FADT declares the system doesn't support PCIe ASPM, so disable it\n");
+		pcie_no_aspm();
+	}
+
 	ret = register_acpi_bus_type(&acpi_pci_bus);
 	if (ret)
 		return 0;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e9c356236d2..0a3d856833f 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -572,6 +572,10 @@ int pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 		if (!ret)
 			pci_update_current_state(dev);
 	}
+	/* This device is quirked not to be put into D3, so
+	   don't put it in D3 */
+	if (state == PCI_D3hot && (dev->dev_flags & PCI_DEV_FLAGS_NO_D3))
+		return 0;
 
 	error = pci_raw_set_power_state(dev, state);
 
@@ -1123,6 +1127,12 @@ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable)
 }
 
 /**
+ * pci_target_state - find an appropriate low power state for a given PCI dev
+ * @dev: PCI device
+ *
+ * Use underlying platform code to find a supported low power state for @dev.
+ * If the platform can't manage @dev, return the deepest state from which it
+ * can generate wake events, based on any available PME info.
  */
 pci_power_t pci_target_state(struct pci_dev *dev)
 {
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index f82495583e6..9a7c9e1408a 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -55,7 +55,7 @@ struct pcie_link_state {
 	struct endpoint_state endpoints[8];
 };
 
-static int aspm_disabled;
+static int aspm_disabled, aspm_force;
 static DEFINE_MUTEX(aspm_lock);
 static LIST_HEAD(link_list);
 
@@ -510,6 +510,7 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev)
 {
 	struct pci_dev *child_dev;
 	int child_pos;
+	u32 reg32;
 
 	/*
 	 * Some functions in a slot might not all be PCIE functions, very
@@ -519,6 +520,19 @@ static int pcie_aspm_sanity_check(struct pci_dev *pdev)
 		child_pos = pci_find_capability(child_dev, PCI_CAP_ID_EXP);
 		if (!child_pos)
 			return -EINVAL;
+
+		/*
+		 * Disable ASPM for pre-1.1 PCIe device, we follow MS to use
+		 * RBER bit to determine if a function is 1.1 version device
+		 */
+		pci_read_config_dword(child_dev, child_pos + PCI_EXP_DEVCAP,
+			&reg32);
+		if (!(reg32 & PCI_EXP_DEVCAP_RBER && !aspm_force)) {
+			printk("Pre-1.1 PCIe device detected, "
+				"disable ASPM for %s. It can be enabled forcedly"
+				" with 'pcie_aspm=force'\n", pci_name(pdev));
+			return -EINVAL;
+		}
 	}
 	return 0;
 }
@@ -802,11 +816,23 @@ void pcie_aspm_remove_sysfs_dev_files(struct pci_dev *pdev)
 
 static int __init pcie_aspm_disable(char *str)
 {
-	aspm_disabled = 1;
+	if (!strcmp(str, "off")) {
+		aspm_disabled = 1;
+		printk(KERN_INFO "PCIe ASPM is disabled\n");
+	} else if (!strcmp(str, "force")) {
+		aspm_force = 1;
+		printk(KERN_INFO "PCIe ASPM is forcedly enabled\n");
+	}
 	return 1;
 }
 
-__setup("pcie_noaspm", pcie_aspm_disable);
+__setup("pcie_aspm=", pcie_aspm_disable);
+
+void pcie_no_aspm(void)
+{
+	if (!aspm_force)
+		aspm_disabled = 1;
+}
 
 #ifdef CONFIG_ACPI
 #include <acpi/acpi_bus.h>
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index b1724cf31b6..7098dfb0744 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -163,28 +163,7 @@ static inline unsigned int pci_calc_resource_flags(unsigned int flags)
 	return IORESOURCE_MEM;
 }
 
-/*
- * Find the extent of a PCI decode..
- */
-static u32 pci_size(u32 base, u32 maxbase, u32 mask)
-{
-	u32 size = mask & maxbase;	/* Find the significant bits */
-	if (!size)
-		return 0;
-
-	/* Get the lowest of them to find the decode size, and
-	   from that the extent.  */
-	size = (size & ~(size-1)) - 1;
-
-	/* base == maxbase can be valid only if the BAR has
-	   already been programmed with all 1s.  */
-	if (base == maxbase && ((base | size) & mask) != mask)
-		return 0;
-
-	return size;
-}
-
-static u64 pci_size64(u64 base, u64 maxbase, u64 mask)
+static u64 pci_size(u64 base, u64 maxbase, u64 mask)
 {
 	u64 size = mask & maxbase;	/* Find the significant bits */
 	if (!size)
@@ -202,117 +181,142 @@ static u64 pci_size64(u64 base, u64 maxbase, u64 mask)
 	return size;
 }
 
-static inline int is_64bit_memory(u32 mask)
+enum pci_bar_type {
+	pci_bar_unknown,	/* Standard PCI BAR probe */
+	pci_bar_io,		/* An io port BAR */
+	pci_bar_mem32,		/* A 32-bit memory BAR */
+	pci_bar_mem64,		/* A 64-bit memory BAR */
+};
+
+static inline enum pci_bar_type decode_bar(struct resource *res, u32 bar)
 {
-	if ((mask & (PCI_BASE_ADDRESS_SPACE|PCI_BASE_ADDRESS_MEM_TYPE_MASK)) ==
-	    (PCI_BASE_ADDRESS_SPACE_MEMORY|PCI_BASE_ADDRESS_MEM_TYPE_64))
-		return 1;
-	return 0;
+	if ((bar & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) {
+		res->flags = bar & ~PCI_BASE_ADDRESS_IO_MASK;
+		return pci_bar_io;
+	}
+
+	res->flags = bar & ~PCI_BASE_ADDRESS_MEM_MASK;
+
+	if (res->flags == PCI_BASE_ADDRESS_MEM_TYPE_64)
+		return pci_bar_mem64;
+	return pci_bar_mem32;
+}
+
+/*
+ * If the type is not unknown, we assume that the lowest bit is 'enable'.
+ * Returns 1 if the BAR was 64-bit and 0 if it was 32-bit.
+ */
+static int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
+			struct resource *res, unsigned int pos)
+{
+	u32 l, sz, mask;
+
+	mask = type ? ~PCI_ROM_ADDRESS_ENABLE : ~0;
+
+	res->name = pci_name(dev);
+
+	pci_read_config_dword(dev, pos, &l);
+	pci_write_config_dword(dev, pos, mask);
+	pci_read_config_dword(dev, pos, &sz);
+	pci_write_config_dword(dev, pos, l);
+
+	/*
+	 * All bits set in sz means the device isn't working properly.
+	 * If the BAR isn't implemented, all bits must be 0.  If it's a
+	 * memory BAR or a ROM, bit 0 must be clear; if it's an io BAR, bit
+	 * 1 must be clear.
+	 */
+	if (!sz || sz == 0xffffffff)
+		goto fail;
+
+	/*
+	 * I don't know how l can have all bits set.  Copied from old code.
+	 * Maybe it fixes a bug on some ancient platform.
+	 */
+	if (l == 0xffffffff)
+		l = 0;
+
+	if (type == pci_bar_unknown) {
+		type = decode_bar(res, l);
+		res->flags |= pci_calc_resource_flags(l) | IORESOURCE_SIZEALIGN;
+		if (type == pci_bar_io) {
+			l &= PCI_BASE_ADDRESS_IO_MASK;
+			mask = PCI_BASE_ADDRESS_IO_MASK & 0xffff;
+		} else {
+			l &= PCI_BASE_ADDRESS_MEM_MASK;
+			mask = (u32)PCI_BASE_ADDRESS_MEM_MASK;
+		}
+	} else {
+		res->flags |= (l & IORESOURCE_ROM_ENABLE);
+		l &= PCI_ROM_ADDRESS_MASK;
+		mask = (u32)PCI_ROM_ADDRESS_MASK;
+	}
+
+	if (type == pci_bar_mem64) {
+		u64 l64 = l;
+		u64 sz64 = sz;
+		u64 mask64 = mask | (u64)~0 << 32;
+
+		pci_read_config_dword(dev, pos + 4, &l);
+		pci_write_config_dword(dev, pos + 4, ~0);
+		pci_read_config_dword(dev, pos + 4, &sz);
+		pci_write_config_dword(dev, pos + 4, l);
+
+		l64 |= ((u64)l << 32);
+		sz64 |= ((u64)sz << 32);
+
+		sz64 = pci_size(l64, sz64, mask64);
+
+		if (!sz64)
+			goto fail;
+
+		if ((sizeof(resource_size_t) < 8) && (sz64 > 0x100000000ULL)) {
+			dev_err(&dev->dev, "can't handle 64-bit BAR\n");
+			goto fail;
+		} else if ((sizeof(resource_size_t) < 8) && l) {
+			/* Address above 32-bit boundary; disable the BAR */
+			pci_write_config_dword(dev, pos, 0);
+			pci_write_config_dword(dev, pos + 4, 0);
+			res->start = 0;
+			res->end = sz64;
+		} else {
+			res->start = l64;
+			res->end = l64 + sz64;
+		}
+	} else {
+		sz = pci_size(l, sz, mask);
+
+		if (!sz)
+			goto fail;
+
+		res->start = l;
+		res->end = l + sz;
+	}
+
+ out:
+	return (type == pci_bar_mem64) ? 1 : 0;
+ fail:
+	res->flags = 0;
+	goto out;
 }
 
 static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 {
-	unsigned int pos, reg, next;
-	u32 l, sz;
-	struct resource *res;
+	unsigned int pos, reg;
 
-	for(pos=0; pos<howmany; pos = next) {
-		u64 l64;
-		u64 sz64;
-		u32 raw_sz;
-
-		next = pos+1;
-		res = &dev->resource[pos];
-		res->name = pci_name(dev);
+	for (pos = 0; pos < howmany; pos++) {
+		struct resource *res = &dev->resource[pos];
 		reg = PCI_BASE_ADDRESS_0 + (pos << 2);
-		pci_read_config_dword(dev, reg, &l);
-		pci_write_config_dword(dev, reg, ~0);
-		pci_read_config_dword(dev, reg, &sz);
-		pci_write_config_dword(dev, reg, l);
-		if (!sz || sz == 0xffffffff)
-			continue;
-		if (l == 0xffffffff)
-			l = 0;
-		raw_sz = sz;
-		if ((l & PCI_BASE_ADDRESS_SPACE) ==
-				PCI_BASE_ADDRESS_SPACE_MEMORY) {
-			sz = pci_size(l, sz, (u32)PCI_BASE_ADDRESS_MEM_MASK);
-			/*
-			 * For 64bit prefetchable memory sz could be 0, if the
-			 * real size is bigger than 4G, so we need to check
-			 * szhi for that.
-			 */
-			if (!is_64bit_memory(l) && !sz)
-				continue;
-			res->start = l & PCI_BASE_ADDRESS_MEM_MASK;
-			res->flags |= l & ~PCI_BASE_ADDRESS_MEM_MASK;
-		} else {
-			sz = pci_size(l, sz, PCI_BASE_ADDRESS_IO_MASK & 0xffff);
-			if (!sz)
-				continue;
-			res->start = l & PCI_BASE_ADDRESS_IO_MASK;
-			res->flags |= l & ~PCI_BASE_ADDRESS_IO_MASK;
-		}
-		res->end = res->start + (unsigned long) sz;
-		res->flags |= pci_calc_resource_flags(l) | IORESOURCE_SIZEALIGN;
-		if (is_64bit_memory(l)) {
-			u32 szhi, lhi;
-
-			pci_read_config_dword(dev, reg+4, &lhi);
-			pci_write_config_dword(dev, reg+4, ~0);
-			pci_read_config_dword(dev, reg+4, &szhi);
-			pci_write_config_dword(dev, reg+4, lhi);
-			sz64 = ((u64)szhi << 32) | raw_sz;
-			l64 = ((u64)lhi << 32) | l;
-			sz64 = pci_size64(l64, sz64, PCI_BASE_ADDRESS_MEM_MASK);
-			next++;
-#if BITS_PER_LONG == 64
-			if (!sz64) {
-				res->start = 0;
-				res->end = 0;
-				res->flags = 0;
-				continue;
-			}
-			res->start = l64 & PCI_BASE_ADDRESS_MEM_MASK;
-			res->end = res->start + sz64;
-#else
-			if (sz64 > 0x100000000ULL) {
-				dev_err(&dev->dev, "BAR %d: can't handle 64-bit"
-					" BAR\n", pos);
-				res->start = 0;
-				res->flags = 0;
-			} else if (lhi) {
-				/* 64-bit wide address, treat as disabled */
-				pci_write_config_dword(dev, reg,
-					l & ~(u32)PCI_BASE_ADDRESS_MEM_MASK);
-				pci_write_config_dword(dev, reg+4, 0);
-				res->start = 0;
-				res->end = sz;
-			}
-#endif
-		}
+		pos += __pci_read_base(dev, pci_bar_unknown, res, reg);
 	}
+
 	if (rom) {
+		struct resource *res = &dev->resource[PCI_ROM_RESOURCE];
 		dev->rom_base_reg = rom;
-		res = &dev->resource[PCI_ROM_RESOURCE];
-		res->name = pci_name(dev);
-		pci_read_config_dword(dev, rom, &l);
-		pci_write_config_dword(dev, rom, ~PCI_ROM_ADDRESS_ENABLE);
-		pci_read_config_dword(dev, rom, &sz);
-		pci_write_config_dword(dev, rom, l);
-		if (l == 0xffffffff)
-			l = 0;
-		if (sz && sz != 0xffffffff) {
-			sz = pci_size(l, sz, (u32)PCI_ROM_ADDRESS_MASK);
-			if (sz) {
-				res->flags = (l & IORESOURCE_ROM_ENABLE) |
-				  IORESOURCE_MEM | IORESOURCE_PREFETCH |
-				  IORESOURCE_READONLY | IORESOURCE_CACHEABLE |
-				  IORESOURCE_SIZEALIGN;
-				res->start = l & PCI_ROM_ADDRESS_MASK;
-				res->end = res->start + (unsigned long) sz;
-			}
-		}
+		res->flags = IORESOURCE_MEM | IORESOURCE_PREFETCH |
+				IORESOURCE_READONLY | IORESOURCE_CACHEABLE |
+				IORESOURCE_SIZEALIGN;
+		__pci_read_base(dev, pci_bar_mem32, res, rom);
 	}
 }
 
@@ -1053,7 +1057,8 @@ int pci_scan_slot(struct pci_bus *bus, int devfn)
 		}
 	}
 
-	if (bus->self)
+	/* only one slot has pcie device */
+	if (bus->self && nr)
 		pcie_aspm_init_link_state(bus->self);
 
 	return nr;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 12d489395fa..0fb36507428 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -923,6 +923,19 @@ static void __init quirk_ide_samemode(struct pci_dev *pdev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82801CA_10, quirk_ide_samemode);
 
+/*
+ * Some ATA devices break if put into D3
+ */
+
+static void __devinit quirk_no_ata_d3(struct pci_dev *pdev)
+{
+	/* Quirk the legacy ATA devices only. The AHCI ones are ok */
+	if ((pdev->class >> 8) == PCI_CLASS_STORAGE_IDE)
+		pdev->dev_flags |= PCI_DEV_FLAGS_NO_D3;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, PCI_ANY_ID, quirk_no_ata_d3);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, PCI_ANY_ID, quirk_no_ata_d3);
+
 /* This was originally an Alpha specific thing, but it really fits here.
  * The i82375 PCI/EISA bridge appears as non-classified. Fix that.
  */
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index 1ebbe883f78..13a3d9ad92d 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -277,6 +277,7 @@ enum acpi_prefered_pm_profiles {
 #define BAF_LEGACY_DEVICES              0x0001
 #define BAF_8042_KEYBOARD_CONTROLLER    0x0002
 #define BAF_MSI_NOT_SUPPORTED           0x0008
+#define BAF_PCIE_ASPM_CONTROL           0x0010
 
 #define FADT2_REVISION_ID               3
 #define FADT2_MINUS_REVISION_ID         2
diff --git a/include/asm-arm/dma-mapping.h b/include/asm-arm/dma-mapping.h
index f41335ba633..45329fca1b6 100644
--- a/include/asm-arm/dma-mapping.h
+++ b/include/asm-arm/dma-mapping.h
@@ -7,6 +7,8 @@
 
 #include <linux/scatterlist.h>
 
+#include <asm-generic/dma-coherent.h>
+
 /*
  * DMA-consistent mapping functions.  These allocate/free a region of
  * uncached, unwrite-buffered mapped memory space for use with DMA
diff --git a/include/asm-cris/dma-mapping.h b/include/asm-cris/dma-mapping.h
index cb2fb25ff8d..da8ef8e8f84 100644
--- a/include/asm-cris/dma-mapping.h
+++ b/include/asm-cris/dma-mapping.h
@@ -14,6 +14,8 @@
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
 #ifdef CONFIG_PCI
+#include <asm-generic/dma-coherent.h>
+
 void *dma_alloc_coherent(struct device *dev, size_t size,
 			   dma_addr_t *dma_handle, gfp_t flag);
 
diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h
new file mode 100644
index 00000000000..85a3ffaa024
--- /dev/null
+++ b/include/asm-generic/dma-coherent.h
@@ -0,0 +1,32 @@
+#ifndef DMA_COHERENT_H
+#define DMA_COHERENT_H
+
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
+/*
+ * These two functions are only for dma allocator.
+ * Don't use them in device drivers.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+				       dma_addr_t *dma_handle, void **ret);
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
+
+/*
+ * Standard interface
+ */
+#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+extern int
+dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+			    dma_addr_t device_addr, size_t size, int flags);
+
+extern void
+dma_release_declared_memory(struct device *dev);
+
+extern void *
+dma_mark_declared_memory_occupied(struct device *dev,
+				  dma_addr_t device_addr, size_t size);
+#else
+#define dma_alloc_from_coherent(dev, size, handle, ret) (0)
+#define dma_release_from_coherent(dev, order, vaddr) (0)
+#endif
+
+#endif
diff --git a/include/asm-sh/dma-mapping.h b/include/asm-sh/dma-mapping.h
index 6c0b8a2de14..627315ecdb5 100644
--- a/include/asm-sh/dma-mapping.h
+++ b/include/asm-sh/dma-mapping.h
@@ -5,6 +5,7 @@
 #include <linux/scatterlist.h>
 #include <asm/cacheflush.h>
 #include <asm/io.h>
+#include <asm-generic/dma-coherent.h>
 
 extern struct bus_type pci_bus_type;
 
diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
index 0eaa9bf6011..ad9cd6d49bf 100644
--- a/include/asm-x86/dma-mapping.h
+++ b/include/asm-x86/dma-mapping.h
@@ -249,25 +249,5 @@ static inline int dma_get_cache_alignment(void)
 
 #define dma_is_consistent(d, h)	(1)
 
-#ifdef CONFIG_X86_32
-#  define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
-struct dma_coherent_mem {
-	void		*virt_base;
-	u32		device_base;
-	int		size;
-	int		flags;
-	unsigned long	*bitmap;
-};
-
-extern int
-dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
-			    dma_addr_t device_addr, size_t size, int flags);
-
-extern void
-dma_release_declared_memory(struct device *dev);
-
-extern void *
-dma_mark_declared_memory_occupied(struct device *dev,
-				  dma_addr_t device_addr, size_t size);
-#endif /* CONFIG_X86_32 */
+#include <asm-generic/dma-coherent.h>
 #endif
diff --git a/include/linux/iommu-helper.h b/include/linux/iommu-helper.h
index c975caf7538..f8598f58394 100644
--- a/include/linux/iommu-helper.h
+++ b/include/linux/iommu-helper.h
@@ -8,3 +8,4 @@ extern unsigned long iommu_area_alloc(unsigned long *map, unsigned long size,
 				      unsigned long align_mask);
 extern void iommu_area_free(unsigned long *map, unsigned long start,
 			    unsigned int nr);
+extern unsigned long iommu_num_pages(unsigned long addr, unsigned long len);
diff --git a/include/linux/pci-aspm.h b/include/linux/pci-aspm.h
index a1a1e618e99..91ba0b338b4 100644
--- a/include/linux/pci-aspm.h
+++ b/include/linux/pci-aspm.h
@@ -27,6 +27,7 @@ extern void pcie_aspm_init_link_state(struct pci_dev *pdev);
 extern void pcie_aspm_exit_link_state(struct pci_dev *pdev);
 extern void pcie_aspm_pm_state_change(struct pci_dev *pdev);
 extern void pci_disable_link_state(struct pci_dev *pdev, int state);
+extern void pcie_no_aspm(void);
 #else
 static inline void pcie_aspm_init_link_state(struct pci_dev *pdev)
 {
@@ -40,6 +41,10 @@ static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev)
 static inline void pci_disable_link_state(struct pci_dev *pdev, int state)
 {
 }
+
+static inline void pcie_no_aspm(void)
+{
+}
 #endif
 
 #ifdef CONFIG_PCIEASPM_DEBUG /* this depends on CONFIG_PCIEASPM */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 1d296d31abe..825be3878f6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -124,6 +124,8 @@ enum pci_dev_flags {
 	 * generation too.
 	 */
 	PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG = (__force pci_dev_flags_t) 1,
+	/* Device configuration is irrevocably lost if disabled into D3 */
+	PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2,
 };
 
 typedef unsigned short __bitwise pci_bus_flags_t;
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index 19958b92990..450684f7eaa 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -374,6 +374,7 @@
 #define  PCI_EXP_DEVCAP_ATN_BUT	0x1000	/* Attention Button Present */
 #define  PCI_EXP_DEVCAP_ATN_IND	0x2000	/* Attention Indicator Present */
 #define  PCI_EXP_DEVCAP_PWR_IND	0x4000	/* Power Indicator Present */
+#define  PCI_EXP_DEVCAP_RBER	0x8000	/* Role-Based Error Reporting */
 #define  PCI_EXP_DEVCAP_PWR_VAL	0x3fc0000 /* Slot Power Limit Value */
 #define  PCI_EXP_DEVCAP_PWR_SCL	0xc000000 /* Slot Power Limit Scale */
 #define PCI_EXP_DEVCTL		8	/* Device Control */
diff --git a/init/Kconfig b/init/Kconfig
index 43d6989c275..250e02c8f8f 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -802,6 +802,10 @@ config PROC_PAGE_MONITOR
 
 endmenu		# General setup
 
+config HAVE_GENERIC_DMA_COHERENT
+	bool
+	default n
+
 config SLABINFO
 	bool
 	depends on PROC_FS
diff --git a/kernel/Makefile b/kernel/Makefile
index 54f69837d35..4e1d7df7c3e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -84,6 +84,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_MARKERS) += marker.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FTRACE) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
new file mode 100644
index 00000000000..7517115a8cc
--- /dev/null
+++ b/kernel/dma-coherent.c
@@ -0,0 +1,154 @@
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/kernel.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+	void		*virt_base;
+	u32		device_base;
+	int		size;
+	int		flags;
+	unsigned long	*bitmap;
+};
+
+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(bus_addr, size);
+	if (!mem_base)
+		goto out;
+
+	dev->dma_mem = kzalloc(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 pos, err;
+	int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1);
+
+	pages >>= PAGE_SHIFT;
+
+	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);
+
+/**
+ * Try to allocate memory from the per-device coherent area.
+ *
+ * @dev:	device from which we allocate memory
+ * @size:	size of requested memory area
+ * @dma_handle:	This will be filled with the correct dma handle
+ * @ret:	This pointer will be filled with the virtual address
+ * 		to allocated area.
+ *
+ * This function should be only called from per-arch %dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return %ret.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+				       dma_addr_t *dma_handle, void **ret)
+{
+	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);
+		} else if (mem->flags & DMA_MEMORY_EXCLUSIVE)
+			*ret = NULL;
+	}
+	return (mem != NULL);
+}
+
+/**
+ * Try to free the memory allocated from per-device coherent memory pool.
+ * @dev:	device from which the memory was allocated
+ * @order:	the order of pages allocated
+ * @vaddr:	virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if
+ * %dma_release_coherent() should proceed with releasing memory from
+ * generic pools.
+ */
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
+{
+	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+	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);
+		return 1;
+	}
+	return 0;
+}
diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index a3b8d4c3f77..889ddce2021 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c
@@ -80,3 +80,11 @@ void iommu_area_free(unsigned long *map, unsigned long start, unsigned int nr)
 	}
 }
 EXPORT_SYMBOL(iommu_area_free);
+
+unsigned long iommu_num_pages(unsigned long addr, unsigned long len)
+{
+	unsigned long size = roundup((addr & ~PAGE_MASK) + len, PAGE_SIZE);
+
+	return size >> PAGE_SHIFT;
+}
+EXPORT_SYMBOL(iommu_num_pages);