Merge branch 'for-v3.16' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping into next

Pull CMA and DMA-mapping fixes from Marek Szyprowski:
 "A few fixes for dma-mapping and CMA subsystems"

* 'for-v3.16' of git://git.linaro.org/people/mszyprowski/linux-dma-mapping:
  CMA: correct unlock target
  drivers/base/dma-contiguous.c: erratum of dev_get_cma_area
  arm: dma-mapping: add checking cma area initialized
  arm: dma-iommu: Clean up redundant variable
  cma: Remove potential deadlock situation

arch/arm/include/asm/dma-iommu.h

@@ -18,7 +18,6 @@ struct dma_iommu_mapping {
 	unsigned int		extensions;
 	size_t			bitmap_size;	/* size of a single bitmap */
 	size_t			bits;		/* per bitmap */
-	unsigned int		size;		/* per bitmap */
 	dma_addr_t		base;
 
 	spinlock_t		lock;

arch/arm/mm/dma-mapping.c

@@ -390,7 +390,7 @@ static int __init atomic_pool_init(void)
 	if (!pages)
 		goto no_pages;
 
-	if (IS_ENABLED(CONFIG_DMA_CMA))
+	if (dev_get_cma_area(NULL))
 		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page,
 					      atomic_pool_init);
 	else
@@ -701,7 +701,7 @@ 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_DMA_CMA))
+	else if (!dev_get_cma_area(dev))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
 	else
 		addr = __alloc_from_contiguous(dev, size, prot, &page, caller);
@@ -790,7 +790,7 @@ 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_DMA_CMA)) {
+	} else if (!dev_get_cma_area(dev)) {
 		__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {
@@ -1074,6 +1074,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 	unsigned int order = get_order(size);
 	unsigned int align = 0;
 	unsigned int count, start;
+	size_t mapping_size = mapping->bits << PAGE_SHIFT;
 	unsigned long flags;
 	dma_addr_t iova;
 	int i;
@@ -1119,7 +1120,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 	}
 	spin_unlock_irqrestore(&mapping->lock, flags);
 
-	iova = mapping->base + (mapping->size * i);
+	iova = mapping->base + (mapping_size * i);
 	iova += start << PAGE_SHIFT;
 
 	return iova;
@@ -1129,6 +1130,7 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
 			       dma_addr_t addr, size_t size)
 {
 	unsigned int start, count;
+	size_t mapping_size = mapping->bits << PAGE_SHIFT;
 	unsigned long flags;
 	dma_addr_t bitmap_base;
 	u32 bitmap_index;
@@ -1136,14 +1138,14 @@ static inline void __free_iova(struct dma_iommu_mapping *mapping,
 	if (!size)
 		return;
 
-	bitmap_index = (u32) (addr - mapping->base) / (u32) mapping->size;
+	bitmap_index = (u32) (addr - mapping->base) / (u32) mapping_size;
 	BUG_ON(addr < mapping->base || bitmap_index > mapping->extensions);
 
-	bitmap_base = mapping->base + mapping->size * bitmap_index;
+	bitmap_base = mapping->base + mapping_size * bitmap_index;
 
 	start = (addr - bitmap_base) >>	PAGE_SHIFT;
 
-	if (addr + size > bitmap_base + mapping->size) {
+	if (addr + size > bitmap_base + mapping_size) {
 		/*
 		 * The address range to be freed reaches into the iova
 		 * range of the next bitmap. This should not happen as
@@ -1964,7 +1966,6 @@ arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size)
 	mapping->extensions = extensions;
 	mapping->base = base;
 	mapping->bits = BITS_PER_BYTE * bitmap_size;
-	mapping->size = mapping->bits << PAGE_SHIFT;
 
 	spin_lock_init(&mapping->lock);
 

drivers/base/dma-contiguous.c

@@ -37,6 +37,7 @@ struct cma {
 	unsigned long	base_pfn;
 	unsigned long	count;
 	unsigned long	*bitmap;
+	struct mutex	lock;
 };
 
 struct cma *dma_contiguous_default_area;
@@ -161,6 +162,7 @@ static int __init cma_activate_area(struct cma *cma)
 		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
 	} while (--i);
 
+	mutex_init(&cma->lock);
 	return 0;
 }
 
@@ -261,6 +263,13 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
 	return ret;
 }
 
+static void clear_cma_bitmap(struct cma *cma, unsigned long pfn, int count)
+{
+	mutex_lock(&cma->lock);
+	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
+	mutex_unlock(&cma->lock);
+}
+
 /**
  * dma_alloc_from_contiguous() - allocate pages from contiguous area
  * @dev:   Pointer to device for which the allocation is performed.
@@ -269,7 +278,7 @@ int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
  *
  * This function allocates memory buffer for specified device. It uses
  * device specific contiguous memory area if available or the default
- * global one. Requires architecture specific get_dev_cma_area() helper
+ * global one. Requires architecture specific dev_get_cma_area() helper
  * function.
  */
 struct page *dma_alloc_from_contiguous(struct device *dev, int count,
@@ -294,30 +303,41 @@ struct page *dma_alloc_from_contiguous(struct device *dev, int count,
 
 	mask = (1 << align) - 1;
 
-	mutex_lock(&cma_mutex);
 
 	for (;;) {
+		mutex_lock(&cma->lock);
 		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
 						    start, count, mask);
-		if (pageno >= cma->count)
+		if (pageno >= cma->count) {
+			mutex_unlock(&cma->lock);
 			break;
+		}
+		bitmap_set(cma->bitmap, pageno, count);
+		/*
+		 * It's safe to drop the lock here. We've marked this region for
+		 * our exclusive use. If the migration fails we will take the
+		 * lock again and unmark it.
+		 */
+		mutex_unlock(&cma->lock);
 
 		pfn = cma->base_pfn + pageno;
+		mutex_lock(&cma_mutex);
 		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
+		mutex_unlock(&cma_mutex);
 		if (ret == 0) {
-			bitmap_set(cma->bitmap, pageno, count);
 			page = pfn_to_page(pfn);
 			break;
 		} else if (ret != -EBUSY) {
+			clear_cma_bitmap(cma, pfn, count);
 			break;
 		}
+		clear_cma_bitmap(cma, pfn, count);
 		pr_debug("%s(): memory range at %p is busy, retrying\n",
 			 __func__, pfn_to_page(pfn));
 		/* try again with a bit different memory target */
 		start = pageno + mask + 1;
 	}
 
-	mutex_unlock(&cma_mutex);
 	pr_debug("%s(): returned %p\n", __func__, page);
 	return page;
 }
@@ -350,10 +370,8 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages,
 
 	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);
 
-	mutex_lock(&cma_mutex);
-	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count);
 	free_contig_range(pfn, count);
-	mutex_unlock(&cma_mutex);
+	clear_cma_bitmap(cma, pfn, count);
 
 	return true;
 }