Merge branch 'fixes-for-3.6' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping

Pull DMA-mapping fixes from Marek Szyprowski:
 "Another set of fixes for ARM dma-mapping subsystem.

  Commit e9da6e9905e6 replaced custom consistent buffer remapping code
  with generic vmalloc areas.  It however introduced some regressions
  caused by limited support for allocations in atomic context.  This
  series contains fixes for those regressions.

  For some subplatforms the default, pre-allocated pool for atomic
  allocations turned out to be too small, so a function for setting its
  size has been added.

  Another set of patches adds support for atomic allocations to
  IOMMU-aware DMA-mapping implementation.

  The last part of this pull request contains two fixes for Contiguous
  Memory Allocator, which relax too strict requirements."

* 'fixes-for-3.6' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping:
  ARM: dma-mapping: IOMMU allocates pages from atomic_pool with GFP_ATOMIC
  ARM: dma-mapping: Introduce __atomic_get_pages() for __iommu_get_pages()
  ARM: dma-mapping: Refactor out to introduce __in_atomic_pool
  ARM: dma-mapping: atomic_pool with struct page **pages
  ARM: Kirkwood: increase atomic coherent pool size
  ARM: DMA-Mapping: print warning when atomic coherent allocation fails
  ARM: DMA-Mapping: add function for setting coherent pool size from platform code
  ARM: relax conditions required for enabling Contiguous Memory Allocator
  mm: cma: fix alignment requirements for contiguous regions

5 files changed, 120 insertions, 12 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index c5f9ae5dbd1..2f88d8d9770 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -6,7 +6,7 @@ config ARM
 	select HAVE_DMA_API_DEBUG
 	select HAVE_IDE if PCI || ISA || PCMCIA
 	select HAVE_DMA_ATTRS
-	select HAVE_DMA_CONTIGUOUS if (CPU_V6 || CPU_V6K || CPU_V7)
+	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 2ae842df455..5c44dcb0987 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -203,6 +203,13 @@ static inline void dma_free_writecombine(struct device *dev, size_t size,
 }
 
 /*
+ * This can be called during early boot to increase the size of the atomic
+ * coherent DMA pool above the default value of 256KiB. It must be called
+ * before postcore_initcall.
+ */
+extern void __init init_dma_coherent_pool_size(unsigned long size);
+
+/*
  * This can be called during boot to increase the size of the consistent
  * 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.
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index 3226077735b..1201191d7f1 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -517,6 +517,13 @@ void __init kirkwood_wdt_init(void)
 void __init kirkwood_init_early(void)
 {
 	orion_time_set_base(TIMER_VIRT_BASE);
+
+	/*
+	 * Some Kirkwood devices allocate their coherent buffers from atomic
+	 * context. Increase size of atomic coherent pool to make sure such
+	 * the allocations won't fail.
+	 */
+	init_dma_coherent_pool_size(SZ_1M);
 }
 
 int kirkwood_tclk;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4e7d1182e8a..051204fc461 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -267,17 +267,19 @@ static void __dma_free_remap(void *cpu_addr, size_t 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 *page;
+	struct page **pages;
 };
 
 static struct dma_pool atomic_pool = {
-	.size = SZ_256K,
+	.size = DEFAULT_DMA_COHERENT_POOL_SIZE,
 };
 
 static int __init early_coherent_pool(char *p)
@@ -287,6 +289,21 @@ static int __init early_coherent_pool(char *p)
 }
 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.
  */
@@ -297,6 +314,7 @@ static int __init atomic_pool_init(void)
 	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);
 
@@ -304,21 +322,31 @@ static int __init atomic_pool_init(void)
 	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_KERNEL, 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->page = page;
+		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;
 	}
+no_pages:
 	kfree(bitmap);
 no_bitmap:
 	pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
@@ -443,27 +471,45 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page)
 	if (pageno < pool->nr_pages) {
 		bitmap_set(pool->bitmap, pageno, count);
 		ptr = pool->vaddr + PAGE_SIZE * pageno;
-		*ret_page = pool->page + pageno;
+		*ret_page = pool->pages[pageno];
+	} else {
+		pr_err_once("ERROR: %u KiB atomic DMA coherent pool is too small!\n"
+			    "Please increase it with coherent_pool= kernel parameter!\n",
+			    (unsigned)pool->size / 1024);
 	}
 	spin_unlock_irqrestore(&pool->lock, flags);
 
 	return ptr;
 }
 
+static bool __in_atomic_pool(void *start, size_t size)
+{
+	struct dma_pool *pool = &atomic_pool;
+	void *end = start + size;
+	void *pool_start = pool->vaddr;
+	void *pool_end = pool->vaddr + pool->size;
+
+	if (start < pool_start || start > pool_end)
+		return false;
+
+	if (end <= pool_end)
+		return true;
+
+	WARN(1, "Wrong coherent size(%p-%p) from atomic pool(%p-%p)\n",
+	     start, end - 1, pool_start, pool_end - 1);
+
+	return false;
+}
+
 static int __free_from_pool(void *start, size_t size)
 {
 	struct dma_pool *pool = &atomic_pool;
 	unsigned long pageno, count;
 	unsigned long flags;
 
-	if (start < pool->vaddr || start > pool->vaddr + pool->size)
+	if (!__in_atomic_pool(start, size))
 		return 0;
 
-	if (start + size > pool->vaddr + pool->size) {
-		WARN(1, "freeing wrong coherent size from pool\n");
-		return 0;
-	}
-
 	pageno = (start - pool->vaddr) >> PAGE_SHIFT;
 	count = size >> PAGE_SHIFT;
 
@@ -1090,10 +1136,22 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
 	return 0;
 }
 
+static struct page **__atomic_get_pages(void *addr)
+{
+	struct dma_pool *pool = &atomic_pool;
+	struct page **pages = pool->pages;
+	int offs = (addr - pool->vaddr) >> PAGE_SHIFT;
+
+	return pages + offs;
+}
+
 static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
 {
 	struct vm_struct *area;
 
+	if (__in_atomic_pool(cpu_addr, PAGE_SIZE))
+		return __atomic_get_pages(cpu_addr);
+
 	if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
 		return cpu_addr;
 
@@ -1103,6 +1161,34 @@ static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
 	return NULL;
 }
 
+static void *__iommu_alloc_atomic(struct device *dev, size_t size,
+				  dma_addr_t *handle)
+{
+	struct page *page;
+	void *addr;
+
+	addr = __alloc_from_pool(size, &page);
+	if (!addr)
+		return NULL;
+
+	*handle = __iommu_create_mapping(dev, &page, size);
+	if (*handle == DMA_ERROR_CODE)
+		goto err_mapping;
+
+	return addr;
+
+err_mapping:
+	__free_from_pool(addr, size);
+	return NULL;
+}
+
+static void __iommu_free_atomic(struct device *dev, struct page **pages,
+				dma_addr_t handle, size_t size)
+{
+	__iommu_remove_mapping(dev, handle, size);
+	__free_from_pool(page_address(pages[0]), size);
+}
+
 static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
@@ -1113,6 +1199,9 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
 
+	if (gfp & GFP_ATOMIC)
+		return __iommu_alloc_atomic(dev, size, handle);
+
 	pages = __iommu_alloc_buffer(dev, size, gfp);
 	if (!pages)
 		return NULL;
@@ -1179,6 +1268,11 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 		return;
 	}
 
+	if (__in_atomic_pool(cpu_addr, size)) {
+		__iommu_free_atomic(dev, pages, handle, size);
+		return;
+	}
+
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
 		unmap_kernel_range((unsigned long)cpu_addr, size);
 		vunmap(cpu_addr);
diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c
index 78efb0306a4..34d94c762a1 100644
--- a/drivers/base/dma-contiguous.c
+++ b/drivers/base/dma-contiguous.c
@@ -250,7 +250,7 @@ int __init dma_declare_contiguous(struct device *dev, unsigned long size,
 		return -EINVAL;
 
 	/* Sanitise input arguments */
-	alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order);
+	alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
 	base = ALIGN(base, alignment);
 	size = ALIGN(size, alignment);
 	limit &= ~(alignment - 1);