cma: Remove potential deadlock situation

CMA locking is currently very coarse. The cma_mutex protects both
the bitmap and avoids concurrency with alloc_contig_range. There
are several situations which may result in a deadlock on the CMA
mutex currently, mostly involving AB/BA situations with alloc and
free. Fix this issue by protecting the bitmap with a mutex per CMA
region and use the existing mutex for protecting against concurrency
with alloc_contig_range.
Signed-off-by: Laura Abbott <lauraa@codeaurora.org>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>

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.
@@ -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_mutex);
 			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;
 }