/*
 *  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
#endif

static 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_256K

struct 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)