Merge remote-tracking branch 'lsk/v3.10/topic/arm64-dma' into lsk-v3.10-arm64-misc

Conflicts: arch/arm64/Kconfig arch/arm64/mm/dma-mapping.c mm/Kconfig
2026-06-08 03:40:35 +09:00 · 2014-05-24 14:04:44 +01:00
parent 2036aef6cd 6d08693da9
commit ea3518bfc0
21 changed files with 640 additions and 178 deletions
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -101,14 +101,23 @@ style to do this even if your device holds the default setting,
 because this shows that you did think about these issues wrt. your
 device.

-The query is performed via a call to dma_set_mask():
+The query is performed via a call to dma_set_mask_and_coherent():

-	int dma_set_mask(struct device *dev, u64 mask);
+	int dma_set_mask_and_coherent(struct device *dev, u64 mask);

-The query for consistent allocations is performed via a call to
-dma_set_coherent_mask():
+which will query the mask for both streaming and coherent APIs together.
+If you have some special requirements, then the following two separate
+queries can be used instead:

-	int dma_set_coherent_mask(struct device *dev, u64 mask);
+	The query for streaming mappings is performed via a call to
+	dma_set_mask():
+
+		int dma_set_mask(struct device *dev, u64 mask);
+
+	The query for consistent allocations is performed via a call
+	to dma_set_coherent_mask():
+
+		int dma_set_coherent_mask(struct device *dev, u64 mask);

 Here, dev is a pointer to the device struct of your device, and mask
 is a bit mask describing which bits of an address your device
@@ -137,7 +146,7 @@ exactly why.

 The standard 32-bit addressing device would do something like this:

-	if (dma_set_mask(dev, DMA_BIT_MASK(32))) {
+	if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
@@ -171,22 +180,20 @@ the case would look like this:

 	int using_dac, consistent_using_dac;

-	if (!dma_set_mask(dev, DMA_BIT_MASK(64))) {
+	if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) {
 		using_dac = 1;
 	   	consistent_using_dac = 1;
-		dma_set_coherent_mask(dev, DMA_BIT_MASK(64));
-	} else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) {
+	} else if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) {
 		using_dac = 0;
 		consistent_using_dac = 0;
-		dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
 	} else {
 		printk(KERN_WARNING
 		       "mydev: No suitable DMA available.\n");
 		goto ignore_this_device;
 	}

-dma_set_coherent_mask() will always be able to set the same or a
-smaller mask as dma_set_mask(). However for the rare case that a
+The coherent coherent mask will always be able to set the same or a
+smaller mask as the streaming mask. However for the rare case that a
 device driver only uses consistent allocations, one would have to
 check the return value from dma_set_coherent_mask().

@@ -199,9 +206,9 @@ address you might do something like:
 		goto ignore_this_device;
 	}

-When dma_set_mask() is successful, and returns zero, the kernel saves
-away this mask you have provided.  The kernel will use this
-information later when you make DMA mappings.
+When dma_set_mask() or dma_set_mask_and_coherent() is successful, and
+returns zero, the kernel saves away this mask you have provided.  The
+kernel will use this information later when you make DMA mappings.

 There is a case which we are aware of at this time, which is worth
 mentioning in this documentation.  If your device supports multiple
--- a/Documentation/DMA-API.txt
+++ b/Documentation/DMA-API.txt
@@ -141,6 +141,14 @@ won't change the current mask settings.  It is more intended as an
 internal API for use by the platform than an external API for use by
 driver writers.

+int
+dma_set_mask_and_coherent(struct device *dev, u64 mask)
+
+Checks to see if the mask is possible and updates the device
+streaming and coherent DMA mask parameters if it is.
+
+Returns: 0 if successful and a negative error if not.
+
 int
 dma_set_mask(struct device *dev, u64 mask)

--- a/arch/arm/include/asm/dma-contiguous.h
+++ b/arch/arm/include/asm/dma-contiguous.h
@@ -2,10 +2,9 @@
 #define ASMARM_DMA_CONTIGUOUS_H

 #ifdef __KERNEL__
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA

 #include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>

 void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size);

--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -358,7 +358,7 @@ static int __init atomic_pool_init(void)
 	if (!pages)
 		goto no_pages;

-	if (IS_ENABLED(CONFIG_CMA))
+	if (IS_ENABLED(CONFIG_DMA_CMA))
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
 					      atomic_pool_init);
 	else
@@ -670,7 +670,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
 	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
-	else if (!IS_ENABLED(CONFIG_CMA))
+	else if (!IS_ENABLED(CONFIG_DMA_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
 	else
 		addr = __alloc_from_contiguous(dev, size, prot, &page, caller);
@@ -759,7 +759,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		__dma_free_buffer(page, size);
 	} else if (__free_from_pool(cpu_addr, size)) {
 		return;
-	} else if (!IS_ENABLED(CONFIG_CMA)) {
+	} else if (!IS_ENABLED(CONFIG_DMA_CMA)) {
 		__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -28,6 +28,7 @@ config ARM64
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DMA_ATTRS
+	select HAVE_DMA_CONTIGUOUS
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_GENERIC_HARDIRQS
@@ -82,7 +83,7 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y

-config ZONE_DMA32
+config ZONE_DMA
 	def_bool y

 config ARCH_DMA_ADDR_T_64BIT
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -84,6 +84,13 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 {
 }

+/*
+ * Cache maintenance functions used by the DMA API. No to be used directly.
+ */
+extern void __dma_map_area(const void *, size_t, int);
+extern void __dma_unmap_area(const void *, size_t, int);
+extern void __dma_flush_range(const void *, const void *);
+
 /*
 * Copy user data from/to a page which is mapped into a different
 * processes address space.  Really, we want to allow our "user
--- a/arch/arm64/include/asm/dma-contiguous.h
+++ b/arch/arm64/include/asm/dma-contiguous.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (c) 2013, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _ASM_DMA_CONTIGUOUS_H
+#define _ASM_DMA_CONTIGUOUS_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_DMA_CMA
+
+#include <linux/types.h>
+
+static inline void
+dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
+
+#endif
+#endif
+
+#endif
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -25,7 +25,10 @@

 #define ARCH_HAS_DMA_GET_REQUIRED_MASK

+#define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops coherent_swiotlb_dma_ops;
+extern struct dma_map_ops noncoherent_swiotlb_dma_ops;

 static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
@@ -35,6 +38,11 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 		return dev->archdata.dma_ops;
 }

+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	dev->archdata.dma_ops = ops;
+}
+
 #include <asm-generic/dma-mapping-common.h>

 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
@@ -81,8 +89,12 @@ static inline void dma_mark_clean(void *addr, size_t size)
 {
 }

-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flags)
+#define dma_alloc_coherent(d, s, h, f)	dma_alloc_attrs(d, s, h, f, NULL)
+#define dma_free_coherent(d, s, h, f)	dma_free_attrs(d, s, h, f, NULL)
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flags,
+				    struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 	void *vaddr;
@@ -90,13 +102,14 @@ static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 	if (dma_alloc_from_coherent(dev, size, dma_handle, &vaddr))
 		return vaddr;

-	vaddr = ops->alloc(dev, size, dma_handle, flags, NULL);
+	vaddr = ops->alloc(dev, size, dma_handle, flags, attrs);
 	debug_dma_alloc_coherent(dev, size, *dma_handle, vaddr);
 	return vaddr;
 }

-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t dev_addr)
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t dev_addr,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);

@@ -104,7 +117,7 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 		return;

 	debug_dma_free_coherent(dev, size, vaddr, dev_addr);
-	ops->free(dev, size, vaddr, dev_addr, NULL);
+	ops->free(dev, size, vaddr, dev_addr, attrs);
 }

 /*
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -303,7 +303,7 @@ static int __init arm64_device_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
-arch_initcall(arm64_device_init);
+arch_initcall_sync(arm64_device_init);

 static DEFINE_PER_CPU(struct cpu, cpu_data);

--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -166,3 +166,88 @@ ENTRY(__flush_dcache_area)
 	dsb	sy
 	ret
 ENDPROC(__flush_dcache_area)
+
+/*
+ *	__dma_inv_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+__dma_inv_range:
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	tst	x1, x3				// end cache line aligned?
+	bic	x1, x1, x3
+	b.eq	1f
+	dc	civac, x1			// clean & invalidate D / U line
+1:	tst	x0, x3				// start cache line aligned?
+	bic	x0, x0, x3
+	b.eq	2f
+	dc	civac, x0			// clean & invalidate D / U line
+	b	3f
+2:	dc	ivac, x0			// invalidate D / U line
+3:	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	2b
+	dsb	sy
+	ret
+ENDPROC(__dma_inv_range)
+
+/*
+ *	__dma_clean_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+__dma_clean_range:
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+1:	dc	cvac, x0			// clean D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_clean_range)
+
+/*
+ *	__dma_flush_range(start, end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(__dma_flush_range)
+	dcache_line_size x2, x3
+	sub	x3, x2, #1
+	bic	x0, x0, x3
+1:	dc	civac, x0			// clean & invalidate D / U line
+	add	x0, x0, x2
+	cmp	x0, x1
+	b.lo	1b
+	dsb	sy
+	ret
+ENDPROC(__dma_flush_range)
+
+/*
+ *	__dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(__dma_map_area)
+	add	x1, x1, x0
+	cmp	w2, #DMA_FROM_DEVICE
+	b.eq	__dma_inv_range
+	b	__dma_clean_range
+ENDPROC(__dma_map_area)
+
+/*
+ *	__dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(__dma_unmap_area)
+	add	x1, x1, x0
+	cmp	w2, #DMA_TO_DEVICE
+	b.ne	__dma_inv_range
+	ret
+ENDPROC(__dma_unmap_area)
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -21,34 +21,277 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
+#include <linux/amba/bus.h>

 #include <asm/cacheflush.h>

 struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);

+static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
+				 bool coherent)
+{
+	if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+		return pgprot_writecombine(prot);
+	else if (!coherent)
+		return pgprot_dmacoherent(prot);
+	return prot;
+}
+
 static void *__dma_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags,
 				  struct dma_attrs *attrs)
 {
-	if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
-		flags |= GFP_DMA32;
-	return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+		flags |= GFP_DMA;
+	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+		struct page *page;
+
+		size = PAGE_ALIGN(size);
+		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+							get_order(size));
+		if (!page)
+			return NULL;
+
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
+		return page_address(page);
+	} else {
+		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+	}
 }

 static void __dma_free_coherent(struct device *dev, size_t size,
 				void *vaddr, dma_addr_t dma_handle,
 				struct dma_attrs *attrs)
 {
-	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+	if (dev == NULL) {
+		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+		phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
+		dma_release_from_contiguous(dev,
+					phys_to_page(paddr),
+					size >> PAGE_SHIFT);
+	} else {
+		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+	}
 }

-static struct dma_map_ops coherent_swiotlb_dma_ops = {
+static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
+				     dma_addr_t *dma_handle, gfp_t flags,
+				     struct dma_attrs *attrs)
+{
+	struct page *page, **map;
+	void *ptr, *coherent_ptr;
+	int order, i;
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
+	if (!ptr)
+		goto no_mem;
+	map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
+	if (!map)
+		goto no_map;
+
+	/* remove any dirty cache lines on the kernel alias */
+	__dma_flush_range(ptr, ptr + size);
+
+	/* create a coherent mapping */
+	page = virt_to_page(ptr);
+	for (i = 0; i < (size >> PAGE_SHIFT); i++)
+		map[i] = page + i;
+	coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
+			    __get_dma_pgprot(attrs, pgprot_default, false));
+	kfree(map);
+	if (!coherent_ptr)
+		goto no_map;
+
+	return coherent_ptr;
+
+no_map:
+	__dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
+no_mem:
+	*dma_handle = ~0;
+	return NULL;
+}
+
+static void __dma_free_noncoherent(struct device *dev, size_t size,
+				   void *vaddr, dma_addr_t dma_handle,
+				   struct dma_attrs *attrs)
+{
+	void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+
+	vunmap(vaddr);
+	__dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
+}
+
+static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir,
+				     struct dma_attrs *attrs)
+{
+	dma_addr_t dev_addr;
+
+	dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
+	__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+
+	return dev_addr;
+}
+
+
+static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
+				 size_t size, enum dma_data_direction dir,
+				 struct dma_attrs *attrs)
+{
+	__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+	swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+				  int nelems, enum dma_data_direction dir,
+				  struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i, ret;
+
+	ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
+	for_each_sg(sgl, sg, ret, i)
+		__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+			       sg->length, dir);
+
+	return ret;
+}
+
+static void __swiotlb_unmap_sg_attrs(struct device *dev,
+				     struct scatterlist *sgl, int nelems,
+				     enum dma_data_direction dir,
+				     struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+				 sg->length, dir);
+	swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
+}
+
+static void __swiotlb_sync_single_for_cpu(struct device *dev,
+					  dma_addr_t dev_addr, size_t size,
+					  enum dma_data_direction dir)
+{
+	__dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+	swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
+}
+
+static void __swiotlb_sync_single_for_device(struct device *dev,
+					     dma_addr_t dev_addr, size_t size,
+					     enum dma_data_direction dir)
+{
+	swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
+	__dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+}
+
+static void __swiotlb_sync_sg_for_cpu(struct device *dev,
+				      struct scatterlist *sgl, int nelems,
+				      enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+				 sg->length, dir);
+	swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
+}
+
+static void __swiotlb_sync_sg_for_device(struct device *dev,
+					 struct scatterlist *sgl, int nelems,
+					 enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
+	for_each_sg(sgl, sg, nelems, i)
+		__dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+			       sg->length, dir);
+}
+
+/* vma->vm_page_prot must be set appropriately before calling this function */
+static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			     void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+	int ret = -ENXIO;
+	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
+					PAGE_SHIFT;
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+	unsigned long off = vma->vm_pgoff;
+
+	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      vma->vm_end - vma->vm_start,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
+static int __swiotlb_mmap_noncoherent(struct device *dev,
+		struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
+{
+	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, false);
+	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+static int __swiotlb_mmap_coherent(struct device *dev,
+		struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
+{
+	/* Just use whatever page_prot attributes were specified */
+	return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+struct dma_map_ops noncoherent_swiotlb_dma_ops = {
+	.alloc = __dma_alloc_noncoherent,
+	.free = __dma_free_noncoherent,
+	.mmap = __swiotlb_mmap_noncoherent,
+	.map_page = __swiotlb_map_page,
+	.unmap_page = __swiotlb_unmap_page,
+	.map_sg = __swiotlb_map_sg_attrs,
+	.unmap_sg = __swiotlb_unmap_sg_attrs,
+	.sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
+	.sync_single_for_device = __swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device = __swiotlb_sync_sg_for_device,
+	.dma_supported = swiotlb_dma_supported,
+	.mapping_error = swiotlb_dma_mapping_error,
+};
+EXPORT_SYMBOL(noncoherent_swiotlb_dma_ops);
+
+struct dma_map_ops coherent_swiotlb_dma_ops = {
 	.alloc = __dma_alloc_coherent,
 	.free = __dma_free_coherent,
+	.mmap = __swiotlb_mmap_coherent,
 	.map_page = swiotlb_map_page,
 	.unmap_page = swiotlb_unmap_page,
 	.map_sg = swiotlb_map_sg_attrs,
@@ -60,13 +303,48 @@ static struct dma_map_ops coherent_swiotlb_dma_ops = {
 	.dma_supported = swiotlb_dma_supported,
 	.mapping_error = swiotlb_dma_mapping_error,
 };
+EXPORT_SYMBOL(coherent_swiotlb_dma_ops);

-void __init arm64_swiotlb_init(void)
+static int dma_bus_notifier(struct notifier_block *nb,
+			    unsigned long event, void *_dev)
 {
-	dma_ops = &coherent_swiotlb_dma_ops;
-	swiotlb_init(1);
+	struct device *dev = _dev;
+
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
+
+	if (of_property_read_bool(dev->of_node, "dma-coherent"))
+		set_dma_ops(dev, &coherent_swiotlb_dma_ops);
+
+	return NOTIFY_OK;
 }

+static struct notifier_block platform_bus_nb = {
+	.notifier_call = dma_bus_notifier,
+};
+
+static struct notifier_block amba_bus_nb = {
+	.notifier_call = dma_bus_notifier,
+};
+
+extern int swiotlb_late_init_with_default_size(size_t default_size);
+
+static int __init swiotlb_late_init(void)
+{
+	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
+
+	/*
+	 * These must be registered before of_platform_populate().
+	 */
+	bus_register_notifier(&platform_bus_type, &platform_bus_nb);
+	bus_register_notifier(&amba_bustype, &amba_bus_nb);
+
+	dma_ops = &noncoherent_swiotlb_dma_ops;
+
+	return swiotlb_late_init_with_default_size(swiotlb_size);
+}
+arch_initcall(swiotlb_late_init);
+
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096

 static int __init dma_debug_do_init(void)
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,8 @@
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>

 #include <asm/prom.h>
 #include <asm/sections.h>
@@ -66,22 +68,22 @@ static int __init early_initrd(char *p)
 }
 early_param("initrd", early_initrd);

-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
-
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma32 = min;
+	unsigned long max_dma = min;

 	memset(zone_size, 0, sizeof(zone_size));

-#ifdef CONFIG_ZONE_DMA32
 	/* 4GB maximum for 32-bit only capable devices */
-	max_dma32 = max(min, min(max, MAX_DMA32_PFN));
-	zone_size[ZONE_DMA32] = max_dma32 - min;
-#endif
-	zone_size[ZONE_NORMAL] = max - max_dma32;
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		unsigned long max_dma_phys =
+			(unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
+		max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+		zone_size[ZONE_DMA] = max_dma - min;
+	}
+	zone_size[ZONE_NORMAL] = max - max_dma;

 	memcpy(zhole_size, zone_size, sizeof(zhole_size));

@@ -91,15 +93,15 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)

 		if (start >= max)
 			continue;
-#ifdef CONFIG_ZONE_DMA32
-		if (start < max_dma32) {
-			unsigned long dma_end = min(end, max_dma32);
-			zhole_size[ZONE_DMA32] -= dma_end - start;
+
+		if (IS_ENABLED(CONFIG_ZONE_DMA) && start < max_dma) {
+			unsigned long dma_end = min(end, max_dma);
+			zhole_size[ZONE_DMA] -= dma_end - start;
 		}
-#endif
-		if (end > max_dma32) {
+
+		if (end > max_dma) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma32);
+			unsigned long normal_start = max(start, max_dma);
 			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
 		}
 	}
@@ -172,6 +174,8 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(base, size);
 	}

+	dma_contiguous_reserve(0);
+
 	memblock_allow_resize();
 	memblock_dump_all();
 }
@@ -282,8 +286,6 @@ void __init mem_init(void)
 	unsigned long reserved_pages, free_pages;
 	struct memblock_region *reg;

-	arm64_swiotlb_init();
-
 	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;

 #ifndef CONFIG_SPARSEMEM_VMEMMAP
--- a/arch/x86/include/asm/dma-contiguous.h
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -4,7 +4,6 @@
 #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) { }
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -202,11 +202,9 @@ config DMA_SHARED_BUFFER
 	  APIs extension; the file's descriptor can then be passed on to other
 	  driver.

-config CMA
-	bool "Contiguous Memory Allocator"
-	depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK
-	select MIGRATION
-	select MEMORY_ISOLATION
+config DMA_CMA
+	bool "DMA Contiguous Memory Allocator"
+	depends on HAVE_DMA_CONTIGUOUS && CMA
 	help
 	  This enables the Contiguous Memory Allocator which allows drivers
 	  to allocate big physically-contiguous blocks of memory for use with
@@ -215,17 +213,7 @@ config CMA
 	  For more information see <include/linux/dma-contiguous.h>.
 	  If unsure, say "n".

-if CMA
-
-config CMA_DEBUG
-	bool "CMA debug messages (DEVELOPMENT)"
-	depends on DEBUG_KERNEL
-	help
-	  Turns on debug messages in CMA.  This produces KERN_DEBUG
-	  messages for every CMA call as well as various messages while
-	  processing calls such as dma_alloc_from_contiguous().
-	  This option does not affect warning and error messages.
-
+if  DMA_CMA
 comment "Default contiguous memory area size:"

 config CMA_SIZE_MBYTES
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -6,7 +6,7 @@ obj-y			:= core.o bus.o dd.o syscore.o \
 			   attribute_container.o transport_class.o \
 			   topology.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
-obj-$(CONFIG_CMA) += dma-contiguous.o
+obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
 obj-$(CONFIG_HAS_DMA)	+= dma-mapping.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -96,7 +96,7 @@ static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
 #endif

 /**
- * dma_contiguous_reserve() - reserve area for contiguous memory handling
+ * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
 * @limit: End address of the reserved memory (optional, 0 for any).
 *
 * This function reserves memory from early allocator. It should be
@@ -124,22 +124,29 @@ void __init dma_contiguous_reserve(phys_addr_t limit)
 #endif
 	}

-	if (selected_size) {
+	if (selected_size && !dma_contiguous_default_area) {
 		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
 			 (unsigned long)selected_size / SZ_1M);

-		dma_declare_contiguous(NULL, selected_size, 0, limit);
+		dma_contiguous_reserve_area(selected_size, 0, limit,
+					    &dma_contiguous_default_area);
 	}
 };

 static DEFINE_MUTEX(cma_mutex);

-static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
+static int __init cma_activate_area(struct cma *cma)
 {
-	unsigned long pfn = base_pfn;
-	unsigned i = count >> pageblock_order;
+	int bitmap_size = BITS_TO_LONGS(cma->count) * sizeof(long);
+	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
+	unsigned i = cma->count >> pageblock_order;
 	struct zone *zone;

+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+
+	if (!cma->bitmap)
+		return -ENOMEM;
+
 	WARN_ON_ONCE(!pfn_valid(pfn));
 	zone = page_zone(pfn_to_page(pfn));

@@ -153,92 +160,53 @@ static __init int cma_activate_area(unsigned long base_pfn, unsigned long count)
 		}
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
+
 	return 0;
 }

-static __init struct cma *cma_create_area(unsigned long base_pfn,
-				     unsigned long count)
-{
-	int bitmap_size = BITS_TO_LONGS(count) * sizeof(long);
-	struct cma *cma;
-	int ret = -ENOMEM;
-
-	pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count);
-
-	cma = kmalloc(sizeof *cma, GFP_KERNEL);
-	if (!cma)
-		return ERR_PTR(-ENOMEM);
-
-	cma->base_pfn = base_pfn;
-	cma->count = count;
-	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-
-	if (!cma->bitmap)
-		goto no_mem;
-
-	ret = cma_activate_area(base_pfn, count);
-	if (ret)
-		goto error;
-
-	pr_debug("%s: returned %p\n", __func__, (void *)cma);
-	return cma;
-
-error:
-	kfree(cma->bitmap);
-no_mem:
-	kfree(cma);
-	return ERR_PTR(ret);
-}
-
-static struct cma_reserved {
-	phys_addr_t start;
-	unsigned long size;
-	struct device *dev;
-} cma_reserved[MAX_CMA_AREAS] __initdata;
-static unsigned cma_reserved_count __initdata;
+static struct cma cma_areas[MAX_CMA_AREAS];
+static unsigned cma_area_count;

 static int __init cma_init_reserved_areas(void)
 {
-	struct cma_reserved *r = cma_reserved;
-	unsigned i = cma_reserved_count;
+	int i;

-	pr_debug("%s()\n", __func__);
-
-	for (; i; --i, ++r) {
-		struct cma *cma;
-		cma = cma_create_area(PFN_DOWN(r->start),
-				      r->size >> PAGE_SHIFT);
-		if (!IS_ERR(cma))
-			dev_set_cma_area(r->dev, cma);
+	for (i = 0; i < cma_area_count; i++) {
+		int ret = cma_activate_area(&cma_areas[i]);
+		if (ret)
+			return ret;
 	}
+
 	return 0;
 }
 core_initcall(cma_init_reserved_areas);

 /**
- * dma_declare_contiguous() - reserve area for contiguous memory handling
- *			      for particular device
- * @dev:   Pointer to device structure.
- * @size:  Size of the reserved memory.
- * @base:  Start address of the reserved memory (optional, 0 for any).
+ * dma_contiguous_reserve_area() - reserve custom contiguous area
+ * @size: Size of the reserved area (in bytes),
+ * @base: Base address of the reserved area optional, use 0 for any
 * @limit: End address of the reserved memory (optional, 0 for any).
+ * @res_cma: Pointer to store the created cma region.
 *
- * This function reserves memory for specified device. It should be
- * called by board specific code when early allocator (memblock or bootmem)
- * is still activate.
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory. This function allows to create custom reserved areas for specific
+ * devices.
 */
-int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
-				  phys_addr_t base, phys_addr_t limit)
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+				       phys_addr_t limit, struct cma **res_cma)
 {
-	struct cma_reserved *r = &cma_reserved[cma_reserved_count];
+	struct cma *cma = &cma_areas[cma_area_count];
 	phys_addr_t alignment;
+	int ret = 0;

 	pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__,
 		 (unsigned long)size, (unsigned long)base,
 		 (unsigned long)limit);

 	/* Sanity checks */
-	if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) {
+	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
 		pr_err("Not enough slots for CMA reserved regions!\n");
 		return -ENOSPC;
 	}
@@ -256,7 +224,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	if (base) {
 		if (memblock_is_region_reserved(base, size) ||
 		    memblock_reserve(base, size) < 0) {
-			base = -EBUSY;
+			ret = -EBUSY;
 			goto err;
 		}
 	} else {
@@ -266,7 +234,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 		 */
 		phys_addr_t addr = __memblock_alloc_base(size, alignment, limit);
 		if (!addr) {
-			base = -ENOMEM;
+			ret = -ENOMEM;
 			goto err;
 		} else {
 			base = addr;
@@ -277,10 +245,11 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	 * Each reserved area must be initialised later, when more kernel
 	 * subsystems (like slab allocator) are available.
 	 */
-	r->start = base;
-	r->size = size;
-	r->dev = dev;
-	cma_reserved_count++;
+	cma->base_pfn = PFN_DOWN(base);
+	cma->count = size >> PAGE_SHIFT;
+	*res_cma = cma;
+	cma_area_count++;
+
 	pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
 		(unsigned long)base);

@@ -289,7 +258,7 @@ int __init dma_declare_contiguous(struct device *dev, phys_addr_t size,
 	return 0;
 err:
 	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
-	return base;
+	return ret;
 }

 /**
--- a/include/asm-generic/dma-contiguous.h
+++ b/include/asm-generic/dma-contiguous.h
@@ -1,28 +0,0 @@
-#ifndef ASM_DMA_CONTIGUOUS_H
-#define ASM_DMA_CONTIGUOUS_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_CMA
-
-#include <linux/device.h>
-#include <linux/dma-contiguous.h>
-
-static inline struct cma *dev_get_cma_area(struct device *dev)
-{
-	if (dev && dev->cma_area)
-		return dev->cma_area;
-	return dma_contiguous_default_area;
-}
-
-static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
-{
-	if (dev)
-		dev->cma_area = cma;
-	if (!dev && !dma_contiguous_default_area)
-		dma_contiguous_default_area = cma;
-}
-
-#endif
-#endif
-
-#endif
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -698,7 +698,7 @@ struct device {

 	struct dma_coherent_mem	*dma_mem; /* internal for coherent mem
 					     override */
-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA
 	struct cma *cma_area;		/* contiguous memory area for dma
 					   allocations */
 #endif
--- a/include/linux/dma-contiguous.h
+++ b/include/linux/dma-contiguous.h
@@ -57,7 +57,7 @@ struct cma;
 struct page;
 struct device;

-#ifdef CONFIG_CMA
+#ifdef CONFIG_DMA_CMA

 /*
 * There is always at least global CMA area and a few optional device
@@ -67,9 +67,53 @@ struct device;

 extern struct cma *dma_contiguous_default_area;

+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	if (dev && dev->cma_area)
+		return dev->cma_area;
+	return dma_contiguous_default_area;
+}
+
+static inline void dev_set_cma_area(struct device *dev, struct cma *cma)
+{
+	if (dev)
+		dev->cma_area = cma;
+}
+
+static inline void dma_contiguous_set_default(struct cma *cma)
+{
+	dma_contiguous_default_area = cma;
+}
+
 void dma_contiguous_reserve(phys_addr_t addr_limit);
-int dma_declare_contiguous(struct device *dev, phys_addr_t size,
-			   phys_addr_t base, phys_addr_t limit);
+
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+				       phys_addr_t limit, struct cma **res_cma);
+
+/**
+ * dma_declare_contiguous() - reserve area for contiguous memory handling
+ *			      for particular device
+ * @dev:   Pointer to device structure.
+ * @size:  Size of the reserved memory.
+ * @base:  Start address of the reserved memory (optional, 0 for any).
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory for specified device. It should be
+ * called by board specific code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+
+static inline int dma_declare_contiguous(struct device *dev, phys_addr_t size,
+					 phys_addr_t base, phys_addr_t limit)
+{
+	struct cma *cma;
+	int ret;
+	ret = dma_contiguous_reserve_area(size, base, limit, &cma);
+	if (ret == 0)
+		dev_set_cma_area(dev, cma);
+
+	return ret;
+}

 struct page *dma_alloc_from_contiguous(struct device *dev, int count,
 				       unsigned int order);
@@ -80,8 +124,22 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,

 #define MAX_CMA_AREAS	(0)

+static inline struct cma *dev_get_cma_area(struct device *dev)
+{
+	return NULL;
+}
+
+static inline void dev_set_cma_area(struct device *dev, struct cma *cma) { }
+
+static inline void dma_contiguous_set_default(struct cma *cma) { }
+
 static inline void dma_contiguous_reserve(phys_addr_t limit) { }

+static inline int dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+				       phys_addr_t limit, struct cma **res_cma) {
+	return -ENOSYS;
+}
+
 static inline
 int dma_declare_contiguous(struct device *dev, phys_addr_t size,
 			   phys_addr_t base, phys_addr_t limit)
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -97,6 +97,30 @@ static inline int dma_set_coherent_mask(struct device *dev, u64 mask)
 }
 #endif

+/*
+ * Set both the DMA mask and the coherent DMA mask to the same thing.
+ * Note that we don't check the return value from dma_set_coherent_mask()
+ * as the DMA API guarantees that the coherent DMA mask can be set to
+ * the same or smaller than the streaming DMA mask.
+ */
+static inline int dma_set_mask_and_coherent(struct device *dev, u64 mask)
+{
+	int rc = dma_set_mask(dev, mask);
+	if (rc == 0)
+		dma_set_coherent_mask(dev, mask);
+	return rc;
+}
+
+/*
+ * Similar to the above, except it deals with the case where the device
+ * does not have dev->dma_mask appropriately setup.
+ */
+static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
+{
+	dev->dma_mask = &dev->coherent_dma_mask;
+	return dma_set_mask_and_coherent(dev, mask);
+}
+
 extern u64 dma_get_required_mask(struct device *dev);

 static inline unsigned int dma_get_max_seg_size(struct device *dev)
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -480,3 +480,27 @@ config FRONTSWAP

 config GENERIC_EARLY_IOREMAP
 	bool
+
+config CMA
+	bool "Contiguous Memory Allocator"
+	depends on HAVE_MEMBLOCK
+	select MIGRATION
+	select MEMORY_ISOLATION
+	help
+	  This enables the Contiguous Memory Allocator which allows other
+	  subsystems to allocate big physically-contiguous blocks of memory.
+	  CMA reserves a region of memory and allows only movable pages to
+	  be allocated from it. This way, the kernel can use the memory for
+	  pagecache and when a subsystem requests for contiguous area, the
+	  allocated pages are migrated away to serve the contiguous request.
+
+	  If unsure, say "n".
+
+config CMA_DEBUG
+	bool "CMA debug messages (DEVELOPMENT)"
+	depends on DEBUG_KERNEL && CMA
+	help
+	  Turns on debug messages in CMA.  This produces KERN_DEBUG
+	  messages for every CMA call as well as various messages while
+	  processing calls such as dma_alloc_from_contiguous().
+	  This option does not affect warning and error messages.