| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410 | /* *  linux/arch/arm/mm/dma-mapping.c * *  Copyright (C) 2000-2004 Russell King * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. * *  DMA uncached mapping support. */#include <linux/module.h>#include <linux/mm.h>#include <linux/gfp.h>#include <linux/errno.h>#include <linux/list.h>#include <linux/init.h>#include <linux/device.h>#include <linux/dma-mapping.h>#include <linux/dma-contiguous.h>#include <linux/highmem.h>#include <linux/memblock.h>#include <linux/slab.h>#include <linux/iommu.h>#include <linux/io.h>#include <linux/vmalloc.h>#include <linux/sizes.h>#include <asm/memory.h>#include <asm/highmem.h>#include <asm/cacheflush.h>#include <asm/tlbflush.h>#include <asm/mach/arch.h>#include <asm/dma-iommu.h>#include <asm/mach/map.h>#include <asm/system_info.h>#include <asm/dma-contiguous.h>#include "mm.h"/* * The DMA API is built upon the notion of "buffer ownership".  A buffer * is either exclusively owned by the CPU (and therefore may be accessed * by it) or exclusively owned by the DMA device.  These helper functions * represent the transitions between these two ownership states. * * Note, however, that on later ARMs, this notion does not work due to * speculative prefetches.  We model our approach on the assumption that * the CPU does do speculative prefetches, which means we clean caches * before transfers and delay cache invalidation until transfer completion. * */static void __dma_page_cpu_to_dev(struct page *, unsigned long,		size_t, enum dma_data_direction);static void __dma_page_dev_to_cpu(struct page *, unsigned long,		size_t, enum dma_data_direction);/** * arm_dma_map_page - map a portion of a page for streaming DMA * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @page: page that buffer resides in * @offset: offset into page for start of buffer * @size: size of buffer to map * @dir: DMA transfer direction * * Ensure that any data held in the cache is appropriately discarded * or written back. * * The device owns this memory once this call has completed.  The CPU * can regain ownership by calling dma_unmap_page(). */static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page,	     unsigned long offset, size_t size, enum dma_data_direction dir,	     struct dma_attrs *attrs){	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))		__dma_page_cpu_to_dev(page, offset, size, dir);	return pfn_to_dma(dev, page_to_pfn(page)) + offset;}static dma_addr_t arm_coherent_dma_map_page(struct device *dev, struct page *page,	     unsigned long offset, size_t size, enum dma_data_direction dir,	     struct dma_attrs *attrs){	return pfn_to_dma(dev, page_to_pfn(page)) + offset;}/** * arm_dma_unmap_page - unmap a buffer previously mapped through dma_map_page() * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices * @handle: DMA address of buffer * @size: size of buffer (same as passed to dma_map_page) * @dir: DMA transfer direction (same as passed to dma_map_page) * * Unmap a page streaming mode DMA translation.  The handle and size * must match what was provided in the previous dma_map_page() call. * All other usages are undefined. * * After this call, reads by the CPU to the buffer are guaranteed to see * whatever the device wrote there. */static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle,		size_t size, enum dma_data_direction dir,		struct dma_attrs *attrs){	if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),				      handle & ~PAGE_MASK, size, dir);}static void arm_dma_sync_single_for_cpu(struct device *dev,		dma_addr_t handle, size_t size, enum dma_data_direction dir){	unsigned int offset = handle & (PAGE_SIZE - 1);	struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));	__dma_page_dev_to_cpu(page, offset, size, dir);}static void arm_dma_sync_single_for_device(struct device *dev,		dma_addr_t handle, size_t size, enum dma_data_direction dir){	unsigned int offset = handle & (PAGE_SIZE - 1);	struct page *page = pfn_to_page(dma_to_pfn(dev, handle-offset));	__dma_page_cpu_to_dev(page, offset, size, dir);}struct dma_map_ops arm_dma_ops = {	.alloc			= arm_dma_alloc,	.free			= arm_dma_free,	.mmap			= arm_dma_mmap,	.get_sgtable		= arm_dma_get_sgtable,	.map_page		= arm_dma_map_page,	.unmap_page		= arm_dma_unmap_page,	.map_sg			= arm_dma_map_sg,	.unmap_sg		= arm_dma_unmap_sg,	.sync_single_for_cpu	= arm_dma_sync_single_for_cpu,	.sync_single_for_device	= arm_dma_sync_single_for_device,	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,	.sync_sg_for_device	= arm_dma_sync_sg_for_device,	.set_dma_mask		= arm_dma_set_mask,};EXPORT_SYMBOL(arm_dma_ops);static void *arm_coherent_dma_alloc(struct device *dev, size_t size,	dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs);static void arm_coherent_dma_free(struct device *dev, size_t size, void *cpu_addr,				  dma_addr_t handle, struct dma_attrs *attrs);struct dma_map_ops arm_coherent_dma_ops = {	.alloc			= arm_coherent_dma_alloc,	.free			= arm_coherent_dma_free,	.mmap			= arm_dma_mmap,	.get_sgtable		= arm_dma_get_sgtable,	.map_page		= arm_coherent_dma_map_page,	.map_sg			= arm_dma_map_sg,	.set_dma_mask		= arm_dma_set_mask,};EXPORT_SYMBOL(arm_coherent_dma_ops);static u64 get_coherent_dma_mask(struct device *dev){	u64 mask = (u64)arm_dma_limit;	if (dev) {		mask = dev->coherent_dma_mask;		/*		 * Sanity check the DMA mask - it must be non-zero, and		 * must be able to be satisfied by a DMA allocation.		 */		if (mask == 0) {			dev_warn(dev, "coherent DMA mask is unset\n");			return 0;		}		if ((~mask) & (u64)arm_dma_limit) {			dev_warn(dev, "coherent DMA mask %#llx is smaller "				 "than system GFP_DMA mask %#llx\n",				 mask, (u64)arm_dma_limit);			return 0;		}	}	return mask;}static void __dma_clear_buffer(struct page *page, size_t size){	void *ptr;	/*	 * Ensure that the allocated pages are zeroed, and that any data	 * lurking in the kernel direct-mapped region is invalidated.	 */	ptr = page_address(page);	if (ptr) {		memset(ptr, 0, size);		dmac_flush_range(ptr, ptr + size);		outer_flush_range(__pa(ptr), __pa(ptr) + size);	}}/* * Allocate a DMA buffer for 'dev' of size 'size' using the * specified gfp mask.  Note that 'size' must be page aligned. */static struct page *__dma_alloc_buffer(struct device *dev, size_t size, gfp_t gfp){	unsigned long order = get_order(size);	struct page *page, *p, *e;	page = alloc_pages(gfp, order);	if (!page)		return NULL;	/*	 * Now split the huge page and free the excess pages	 */	split_page(page, order);	for (p = page + (size >> PAGE_SHIFT), e = page + (1 << order); p < e; p++)		__free_page(p);	__dma_clear_buffer(page, size);	return page;}/* * Free a DMA buffer.  'size' must be page aligned. */static void __dma_free_buffer(struct page *page, size_t size){	struct page *e = page + (size >> PAGE_SHIFT);	while (page < e) {		__free_page(page);		page++;	}}#ifdef CONFIG_MMU#ifdef CONFIG_HUGETLB_PAGE#error ARM Coherent DMA allocator does not (yet) support huge TLB#endifstatic void *__alloc_from_contiguous(struct device *dev, size_t size,				     pgprot_t prot, struct page **ret_page);static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,				 pgprot_t prot, struct page **ret_page,				 const void *caller);static void *__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,	const void *caller){	struct vm_struct *area;	unsigned long addr;	/*	 * DMA allocation can be mapped to user space, so lets	 * set VM_USERMAP flags too.	 */	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,				  caller);	if (!area)		return NULL;	addr = (unsigned long)area->addr;	area->phys_addr = __pfn_to_phys(page_to_pfn(page));	if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {		vunmap((void *)addr);		return NULL;	}	return (void *)addr;}static void __dma_free_remap(void *cpu_addr, size_t size){	unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;	struct vm_struct *area = find_vm_area(cpu_addr);	if (!area || (area->flags & flags) != flags) {		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);		return;	}	unmap_kernel_range((unsigned long)cpu_addr, size);	vunmap(cpu_addr);}#define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256Kstruct dma_pool {	size_t size;	spinlock_t lock;	unsigned long *bitmap;	unsigned long nr_pages;	void *vaddr;	struct page **pages;};static struct dma_pool atomic_pool = {	.size = DEFAULT_DMA_COHERENT_POOL_SIZE,};static int __init early_coherent_pool(char *p){	atomic_pool.size = memparse(p, &p);	return 0;}early_param("coherent_pool", early_coherent_pool);void __init init_dma_coherent_pool_size(unsigned long size){	/*	 * Catch any attempt to set the pool size too late.	 */	BUG_ON(atomic_pool.vaddr);	/*	 * Set architecture specific coherent pool size only if	 * it has not been changed by kernel command line parameter.	 */	if (atomic_pool.size == DEFAULT_DMA_COHERENT_POOL_SIZE)		atomic_pool.size = size;}/* * Initialise the coherent pool for atomic allocations. */static int __init atomic_pool_init(void){	struct dma_pool *pool = &atomic_pool;	pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);	gfp_t gfp = GFP_KERNEL | GFP_DMA;	unsigned long nr_pages = pool->size >> PAGE_SHIFT;	unsigned long *bitmap;	struct page *page;	struct page **pages;	void *ptr;	int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);	bitmap = kzalloc(bitmap_size, GFP_KERNEL);	if (!bitmap)		goto no_bitmap;	pages = kzalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);	if (!pages)		goto no_pages;	if (IS_ENABLED(CONFIG_CMA))		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page);	else		ptr = __alloc_remap_buffer(NULL, pool->size, gfp, prot, &page,					   NULL);	if (ptr) {		int i;		for (i = 0; i < nr_pages; i++)			pages[i] = page + i;		spin_lock_init(&pool->lock);		pool->vaddr = ptr;		pool->pages = pages;		pool->bitmap = bitmap;		pool->nr_pages = nr_pages;		pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",		       (unsigned)pool->size / 1024);		return 0;	}	kfree(pages);no_pages:	kfree(bitmap);no_bitmap:	pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",	       (unsigned)pool->size / 1024);	return -ENOMEM;}/* * CMA is activated by core_initcall, so we must be called after it. */postcore_initcall(atomic_pool_init);struct dma_contig_early_reserve {	phys_addr_t base;	unsigned long size;};static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata;static int dma_mmu_remap_num __initdata;void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size){	dma_mmu_remap[dma_mmu_remap_num].base = base;	dma_mmu_remap[dma_mmu_remap_num].size = size;	dma_mmu_remap_num++;}void __init dma_contiguous_remap(void){	int i;	for (i = 0; i < dma_mmu_remap_num; i++) {		phys_addr_t start = dma_mmu_remap[i].base;		phys_addr_t end = start + dma_mmu_remap[i].size;		struct map_desc map;		unsigned long addr;		if (end > arm_lowmem_limit)			end = arm_lowmem_limit;		if (start >= end)
 |