ARM: dma-mapping: remove custom consistent dma region

This patch changes dma-mapping subsystem to use generic vmalloc areas
for all consistent dma allocations. This increases the total size limit
of the consistent allocations and removes platform hacks and a lot of
duplicated code.

Atomic allocations are served from special pool preallocated on boot,
because vmalloc areas cannot be reliably created in atomic context.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Reviewed-by: Kyungmin Park <kyungmin.park@samsung.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>

6 files changed, 181 insertions, 323 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index a92c5eb..4ee28f3 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -526,7 +526,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	coherent_pool=nn[KMG]	[ARM,KNL]
 			Sets the size of memory pool for coherent, atomic dma
-			allocations if Contiguous Memory Allocator (CMA) is used.
+			allocations, by default set to 256K.
 
 	code_bytes	[X86] How many bytes of object code to print
 			in an oops report.
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index bbef15d..80777d87 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -226,7 +226,7 @@ static inline int dma_mmap_writecombine(struct device *dev, struct vm_area_struc
  * DMA region above it's default value of 2MB. It must be called before the
  * memory allocator is initialised, i.e. before any core_initcall.
  */
-extern void __init init_consistent_dma_size(unsigned long size);
+static inline void init_consistent_dma_size(unsigned long size) { }
 
 /*
  * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 655878b..f906d5f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -22,6 +22,7 @@
 #include <linux/memblock.h>
 #include <linux/slab.h>
 #include <linux/iommu.h>
+#include <linux/io.h>
 #include <linux/vmalloc.h>
 
 #include <asm/memory.h>
@@ -217,115 +218,70 @@ static void __dma_free_buffer(struct page *page, size_t size)
 }
 
 #ifdef CONFIG_MMU
+#ifdef CONFIG_HUGETLB_PAGE
+#error ARM Coherent DMA allocator does not (yet) support huge TLB
+#endif
 
-#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - consistent_base) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - consistent_base) >> PMD_SHIFT)
-
-/*
- * These are the page tables (2MB each) covering uncached, DMA consistent allocations
- */
-static pte_t **consistent_pte;
-
-#define DEFAULT_CONSISTENT_DMA_SIZE SZ_2M
+static void *__alloc_from_contiguous(struct device *dev, size_t size,
+				     pgprot_t prot, struct page **ret_page);
 
-static unsigned long consistent_base = CONSISTENT_END - DEFAULT_CONSISTENT_DMA_SIZE;
+static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
+				 pgprot_t prot, struct page **ret_page,
+				 const void *caller);
 
-void __init init_consistent_dma_size(unsigned long size)
+static void *
+__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
+	const void *caller)
 {
-	unsigned long base = CONSISTENT_END - ALIGN(size, SZ_2M);
+	struct vm_struct *area;
+	unsigned long addr;
 
-	BUG_ON(consistent_pte); /* Check we're called before DMA region init */
-	BUG_ON(base < VMALLOC_END);
+	/*
+	 * 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));
 
-	/* Grow region to accommodate specified size  */
-	if (base < consistent_base)
-		consistent_base = base;
+	if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
+		vunmap((void *)addr);
+		return NULL;
+	}
+	return (void *)addr;
 }
 
-#include "vmregion.h"
-
-static struct arm_vmregion_head consistent_head = {
-	.vm_lock	= __SPIN_LOCK_UNLOCKED(&consistent_head.vm_lock),
-	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
-	.vm_end		= CONSISTENT_END,
-};
-
-#ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
-#endif
-
-/*
- * Initialise the consistent memory allocation.
- */
-static int __init consistent_init(void)
+static void __dma_free_remap(void *cpu_addr, size_t size)
 {
-	int ret = 0;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	int i = 0;
-	unsigned long base = consistent_base;
-	unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
-
-	if (IS_ENABLED(CONFIG_CMA) && !IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
-		return 0;
-
-	consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
-	if (!consistent_pte) {
-		pr_err("%s: no memory\n", __func__);
-		return -ENOMEM;
+	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;
 	}
-
-	pr_debug("DMA memory: 0x%08lx - 0x%08lx:\n", base, CONSISTENT_END);
-	consistent_head.vm_start = base;
-
-	do {
-		pgd = pgd_offset(&init_mm, base);
-
-		pud = pud_alloc(&init_mm, pgd, base);
-		if (!pud) {
-			pr_err("%s: no pud tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
-
-		pmd = pmd_alloc(&init_mm, pud, base);
-		if (!pmd) {
-			pr_err("%s: no pmd tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
-		WARN_ON(!pmd_none(*pmd));
-
-		pte = pte_alloc_kernel(pmd, base);
-		if (!pte) {
-			pr_err("%s: no pte tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
-
-		consistent_pte[i++] = pte;
-		base += PMD_SIZE;
-	} while (base < CONSISTENT_END);
-
-	return ret;
+	unmap_kernel_range((unsigned long)cpu_addr, size);
+	vunmap(cpu_addr);
 }
-core_initcall(consistent_init);
-
-static void *__alloc_from_contiguous(struct device *dev, size_t size,
-				     pgprot_t prot, struct page **ret_page);
 
-static struct arm_vmregion_head coherent_head = {
-	.vm_lock	= __SPIN_LOCK_UNLOCKED(&coherent_head.vm_lock),
-	.vm_list	= LIST_HEAD_INIT(coherent_head.vm_list),
+struct dma_pool {
+	size_t size;
+	spinlock_t lock;
+	unsigned long *bitmap;
+	unsigned long nr_pages;
+	void *vaddr;
+	struct page *page;
 };
 
-static size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8;
+static struct dma_pool atomic_pool = {
+	.size = SZ_256K,
+};
 
 static int __init early_coherent_pool(char *p)
 {
-	coherent_pool_size = memparse(p, &p);
+	atomic_pool.size = memparse(p, &p);
 	return 0;
 }
 early_param("coherent_pool", early_coherent_pool);
@@ -333,32 +289,45 @@ early_param("coherent_pool", early_coherent_pool);
 /*
  * Initialise the coherent pool for atomic allocations.
  */
-static int __init coherent_init(void)
+static int __init atomic_pool_init(void)
 {
+	struct dma_pool *pool = &atomic_pool;
 	pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);
-	size_t size = coherent_pool_size;
+	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
+	unsigned long *bitmap;
 	struct page *page;
 	void *ptr;
+	int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
 
-	if (!IS_ENABLED(CONFIG_CMA))
-		return 0;
+	bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!bitmap)
+		goto no_bitmap;
 
-	ptr = __alloc_from_contiguous(NULL, size, prot, &page);
+	if (IS_ENABLED(CONFIG_CMA))
+		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page);
+	else
+		ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
+					   &page, NULL);
 	if (ptr) {
-		coherent_head.vm_start = (unsigned long) ptr;
-		coherent_head.vm_end = (unsigned long) ptr + size;
-		printk(KERN_INFO "DMA: preallocated %u KiB pool for atomic coherent allocations\n",
-		       (unsigned)size / 1024);
+		spin_lock_init(&pool->lock);
+		pool->vaddr = ptr;
+		pool->page = page;
+		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;
 	}
-	printk(KERN_ERR "DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
-	       (unsigned)size / 1024);
+	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(coherent_init);
+postcore_initcall(atomic_pool_init);
 
 struct dma_contig_early_reserve {
 	phys_addr_t base;
@@ -406,112 +375,6 @@ void __init dma_contiguous_remap(void)
 	}
 }
 
-static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
-	const void *caller)
-{
-	struct arm_vmregion *c;
-	size_t align;
-	int bit;
-
-	if (!consistent_pte) {
-		pr_err("%s: not initialised\n", __func__);
-		dump_stack();
-		return NULL;
-	}
-
-	/*
-	 * Align the virtual region allocation - maximum alignment is
-	 * a section size, minimum is a page size.  This helps reduce
-	 * fragmentation of the DMA space, and also prevents allocations
-	 * smaller than a section from crossing a section boundary.
-	 */
-	bit = fls(size - 1);
-	if (bit > SECTION_SHIFT)
-		bit = SECTION_SHIFT;
-	align = 1 << bit;
-
-	/*
-	 * Allocate a virtual address in the consistent mapping region.
-	 */
-	c = arm_vmregion_alloc(&consistent_head, align, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM), caller);
-	if (c) {
-		pte_t *pte;
-		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
-		u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
-
-		pte = consistent_pte[idx] + off;
-		c->priv = page;
-
-		do {
-			BUG_ON(!pte_none(*pte));
-
-			set_pte_ext(pte, mk_pte(page, prot), 0);
-			page++;
-			pte++;
-			off++;
-			if (off >= PTRS_PER_PTE) {
-				off = 0;
-				pte = consistent_pte[++idx];
-			}
-		} while (size -= PAGE_SIZE);
-
-		dsb();
-
-		return (void *)c->vm_start;
-	}
-	return NULL;
-}
-
-static void __dma_free_remap(void *cpu_addr, size_t size)
-{
-	struct arm_vmregion *c;
-	unsigned long addr;
-	pte_t *ptep;
-	int idx;
-	u32 off;
-
-	c = arm_vmregion_find_remove(&consistent_head, (unsigned long)cpu_addr);
-	if (!c) {
-		pr_err("%s: trying to free invalid coherent area: %p\n",
-		       __func__, cpu_addr);
-		dump_stack();
-		return;
-	}
-
-	if ((c->vm_end - c->vm_start) != size) {
-		pr_err("%s: freeing wrong coherent size (%ld != %d)\n",
-		       __func__, c->vm_end - c->vm_start, size);
-		dump_stack();
-		size = c->vm_end - c->vm_start;
-	}
-
-	idx = CONSISTENT_PTE_INDEX(c->vm_start);
-	off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
-	ptep = consistent_pte[idx] + off;
-	addr = c->vm_start;
-	do {
-		pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
-
-		ptep++;
-		addr += PAGE_SIZE;
-		off++;
-		if (off >= PTRS_PER_PTE) {
-			off = 0;
-			ptep = consistent_pte[++idx];
-		}
-
-		if (pte_none(pte) || !pte_present(pte))
-			pr_crit("%s: bad page in kernel page table\n",
-				__func__);
-	} while (size -= PAGE_SIZE);
-
-	flush_tlb_kernel_range(c->vm_start, c->vm_end);
-
-	arm_vmregion_free(&consistent_head, c);
-}
-
 static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
 			    void *data)
 {
@@ -552,16 +415,17 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 	return ptr;
 }
 
-static void *__alloc_from_pool(struct device *dev, size_t size,
-			       struct page **ret_page, const void *caller)
+static void *__alloc_from_pool(size_t size, struct page **ret_page)
 {
-	struct arm_vmregion *c;
+	struct dma_pool *pool = &atomic_pool;
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned int pageno;
+	unsigned long flags;
+	void *ptr = NULL;
 	size_t align;
 
-	if (!coherent_head.vm_start) {
-		printk(KERN_ERR "%s: coherent pool not initialised!\n",
-		       __func__);
-		dump_stack();
+	if (!pool->vaddr) {
+		WARN(1, "coherent pool not initialised!\n");
 		return NULL;
 	}
 
@@ -571,35 +435,41 @@ static void *__alloc_from_pool(struct device *dev, size_t size,
 	 * size. This helps reduce fragmentation of the DMA space.
 	 */
 	align = PAGE_SIZE << get_order(size);
-	c = arm_vmregion_alloc(&coherent_head, align, size, 0, caller);
-	if (c) {
-		void *ptr = (void *)c->vm_start;
-		struct page *page = virt_to_page(ptr);
-		*ret_page = page;
-		return ptr;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	pageno = bitmap_find_next_zero_area(pool->bitmap, pool->nr_pages,
+					    0, count, (1 << align) - 1);
+	if (pageno < pool->nr_pages) {
+		bitmap_set(pool->bitmap, pageno, count);
+		ptr = pool->vaddr + PAGE_SIZE * pageno;
+		*ret_page = pool->page + pageno;
 	}
-	return NULL;
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	return ptr;
 }
 
-static int __free_from_pool(void *cpu_addr, size_t size)
+static int __free_from_pool(void *start, size_t size)
 {
-	unsigned long start = (unsigned long)cpu_addr;
-	unsigned long end = start + size;
-	struct arm_vmregion *c;
+	struct dma_pool *pool = &atomic_pool;
+	unsigned long pageno, count;
+	unsigned long flags;
 
-	if (start < coherent_head.vm_start || end > coherent_head.vm_end)
+	if (start < pool->vaddr || start > pool->vaddr + pool->size)
 		return 0;
 
-	c = arm_vmregion_find_remove(&coherent_head, (unsigned long)start);
-
-	if ((c->vm_end - c->vm_start) != size) {
-		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
-		       __func__, c->vm_end - c->vm_start, size);
-		dump_stack();
-		size = c->vm_end - c->vm_start;
+	if (start + size > pool->vaddr + pool->size) {
+		WARN(1, "freeing wrong coherent size from pool\n");
+		return 0;
 	}
 
-	arm_vmregion_free(&coherent_head, c);
+	pageno = (start - pool->vaddr) >> PAGE_SHIFT;
+	count = size >> PAGE_SHIFT;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	bitmap_clear(pool->bitmap, pageno, count);
+	spin_unlock_irqrestore(&pool->lock, flags);
+
 	return 1;
 }
 
@@ -644,7 +514,7 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
 
 #define __get_dma_pgprot(attrs, prot)	__pgprot(0)
 #define __alloc_remap_buffer(dev, size, gfp, prot, ret, c)	NULL
-#define __alloc_from_pool(dev, size, ret_page, c)		NULL
+#define __alloc_from_pool(size, ret_page)			NULL
 #define __alloc_from_contiguous(dev, size, prot, ret)		NULL
 #define __free_from_pool(cpu_addr, size)			0
 #define __free_from_contiguous(dev, page, size)			do { } while (0)
@@ -702,10 +572,10 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 
 	if (arch_is_coherent() || nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else if (gfp & GFP_ATOMIC)
+		addr = __alloc_from_pool(size, &page);
 	else if (!IS_ENABLED(CONFIG_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
-	else if (gfp & GFP_ATOMIC)
-		addr = __alloc_from_pool(dev, size, &page, caller);
 	else
 		addr = __alloc_from_contiguous(dev, size, prot, &page);
 
@@ -998,9 +868,6 @@ static int arm_dma_set_mask(struct device *dev, u64 dma_mask)
 
 static int __init dma_debug_do_init(void)
 {
-#ifdef CONFIG_MMU
-	arm_vmregion_create_proc("dma-mappings", &consistent_head);
-#endif
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 	return 0;
 }
@@ -1117,61 +984,32 @@ static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t s
  * Create a CPU mapping for a specified pages
  */
 static void *
-__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot)
+__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
+		    const void *caller)
 {
-	struct arm_vmregion *c;
-	size_t align;
-	size_t count = size >> PAGE_SHIFT;
-	int bit;
+	unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct vm_struct *area;
+	unsigned long p;
 
-	if (!consistent_pte[0]) {
-		pr_err("%s: not initialised\n", __func__);
-		dump_stack();
+	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+				  caller);
+	if (!area)
 		return NULL;
-	}
 
-	/*
-	 * Align the virtual region allocation - maximum alignment is
-	 * a section size, minimum is a page size.  This helps reduce
-	 * fragmentation of the DMA space, and also prevents allocations
-	 * smaller than a section from crossing a section boundary.
-	 */
-	bit = fls(size - 1);
-	if (bit > SECTION_SHIFT)
-		bit = SECTION_SHIFT;
-	align = 1 << bit;
-
-	/*
-	 * Allocate a virtual address in the consistent mapping region.
-	 */
-	c = arm_vmregion_alloc(&consistent_head, align, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM), NULL);
-	if (c) {
-		pte_t *pte;
-		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
-		int i = 0;
-		u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
-
-		pte = consistent_pte[idx] + off;
-		c->priv = pages;
-
-		do {
-			BUG_ON(!pte_none(*pte));
-
-			set_pte_ext(pte, mk_pte(pages[i], prot), 0);
-			pte++;
-			off++;
-			i++;
-			if (off >= PTRS_PER_PTE) {
-				off = 0;
-				pte = consistent_pte[++idx];
-			}
-		} while (i < count);
-
-		dsb();
+	area->pages = pages;
+	area->nr_pages = nr_pages;
+	p = (unsigned long)area->addr;
 
-		return (void *)c->vm_start;
+	for (i = 0; i < nr_pages; i++) {
+		phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
+		if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
+			goto err;
+		p += PAGE_SIZE;
 	}
+	return area->addr;
+err:
+	unmap_kernel_range((unsigned long)area->addr, size);
+	vunmap(area->addr);
 	return NULL;
 }
 
@@ -1230,6 +1068,16 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
 	return 0;
 }
 
+static struct page **__iommu_get_pages(void *cpu_addr)
+{
+	struct vm_struct *area;
+
+	area = find_vm_area(cpu_addr);
+	if (area && (area->flags & VM_ARM_DMA_CONSISTENT))
+		return area->pages;
+	return NULL;
+}
+
 static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
@@ -1248,7 +1096,8 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (*handle == DMA_ERROR_CODE)
 		goto err_buffer;
 
-	addr = __iommu_alloc_remap(pages, size, gfp, prot);
+	addr = __iommu_alloc_remap(pages, size, gfp, prot,
+				   __builtin_return_address(0));
 	if (!addr)
 		goto err_mapping;
 
@@ -1265,31 +1114,25 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		    struct dma_attrs *attrs)
 {
-	struct arm_vmregion *c;
+	unsigned long uaddr = vma->vm_start;
+	unsigned long usize = vma->vm_end - vma->vm_start;
+	struct page **pages = __iommu_get_pages(cpu_addr);
 
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
 
-	if (c) {
-		struct page **pages = c->priv;
-
-		unsigned long uaddr = vma->vm_start;
-		unsigned long usize = vma->vm_end - vma->vm_start;
-		int i = 0;
-
-		do {
-			int ret;
+	if (!pages)
+		return -ENXIO;
 
-			ret = vm_insert_page(vma, uaddr, pages[i++]);
-			if (ret) {
-				pr_err("Remapping memory, error: %d\n", ret);
-				return ret;
-			}
+	do {
+		int ret = vm_insert_page(vma, uaddr, *pages++);
+		if (ret) {
+			pr_err("Remapping memory failed: %d\n", ret);
+			return ret;
+		}
+		uaddr += PAGE_SIZE;
+		usize -= PAGE_SIZE;
+	} while (usize > 0);
 
-			uaddr += PAGE_SIZE;
-			usize -= PAGE_SIZE;
-		} while (usize > 0);
-	}
 	return 0;
 }
 
@@ -1300,16 +1143,19 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 			  dma_addr_t handle, struct dma_attrs *attrs)
 {
-	struct arm_vmregion *c;
+	struct page **pages = __iommu_get_pages(cpu_addr);
 	size = PAGE_ALIGN(size);
 
-	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
-	if (c) {
-		struct page **pages = c->priv;
-		__dma_free_remap(cpu_addr, size);
-		__iommu_remove_mapping(dev, handle, size);
-		__iommu_free_buffer(dev, pages, size);
+	if (!pages) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
 	}
+
+	unmap_kernel_range((unsigned long)cpu_addr, size);
+	vunmap(cpu_addr);
+
+	__iommu_remove_mapping(dev, handle, size);
+	__iommu_free_buffer(dev, pages, size);
 }
 
 /*
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 2e8a1ef..6776160 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -59,6 +59,9 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 #define VM_ARM_MTYPE(mt)		((mt) << 20)
 #define VM_ARM_MTYPE_MASK	(0x1f << 20)
 
+/* consistent regions used by dma_alloc_attrs() */
+#define VM_ARM_DMA_CONSISTENT	0x20000000
+
 #endif
 
 #ifdef CONFIG_ZONE_DMA
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 2e28f4d..6071e91 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -93,6 +93,7 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size,
 					unsigned long start, unsigned long end,
 					const void *caller);
 extern struct vm_struct *remove_vm_area(const void *addr);
+extern struct vm_struct *find_vm_area(const void *addr);
 
 extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
 			struct page ***pages);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 11308f0..65fc4dc 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1403,7 +1403,15 @@ struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
 						-1, GFP_KERNEL, caller);
 }
 
-static struct vm_struct *find_vm_area(const void *addr)
+/**
+ *	find_vm_area  -  find a continuous kernel virtual area
+ *	@addr:		base address
+ *
+ *	Search for the kernel VM area starting at @addr, and return it.
+ *	It is up to the caller to do all required locking to keep the returned
+ *	pointer valid.
+ */
+struct vm_struct *find_vm_area(const void *addr)
 {
 	struct vmap_area *va;