Merge remote-tracking branch 'lsk/v3.10/topic/dma-mapping' into lsk-v3.10-arm64-misc

arch/arm/mm/dma-mapping.c

@@ -265,37 +265,19 @@ 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;
+	return dma_common_contiguous_remap(page, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+			prot, caller);
 }
 
 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);
+	dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 }
 
 #define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
@@ -1167,29 +1149,8 @@ static void *
 __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
 		    const void *caller)
 {
-	unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct vm_struct *area;
-	unsigned long p;
-
-	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-				  caller);
-	if (!area)
-		return NULL;
-
-	area->pages = pages;
-	area->nr_pages = nr_pages;
-	p = (unsigned long)area->addr;
-
-	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 dma_common_pages_remap(pages, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
 	return NULL;
 }
 
@@ -1386,8 +1347,8 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	}
 
 	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
-		unmap_kernel_range((unsigned long)cpu_addr, size);
-		vunmap(cpu_addr);
+		dma_common_free_remap(cpu_addr, size,
+			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
 	}
 
 	__iommu_remove_mapping(dev, handle, size);

drivers/base/dma-mapping.c

@@ -10,6 +10,8 @@
 #include <linux/dma-mapping.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <asm-generic/dma-coherent.h>
 
 /*
@@ -267,3 +269,73 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 EXPORT_SYMBOL(dma_common_mmap);
+
+#ifdef CONFIG_MMU
+/*
+ * remaps an array of PAGE_SIZE pages into another vm_area
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller)
+{
+	struct vm_struct *area;
+
+	area = get_vm_area_caller(size, vm_flags, caller);
+	if (!area)
+		return NULL;
+
+	area->pages = pages;
+
+	if (map_vm_area(area, prot, pages)) {
+		vunmap(area->addr);
+		return NULL;
+	}
+
+	return area->addr;
+}
+
+/*
+ * remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller)
+{
+	int i;
+	struct page **pages;
+	void *ptr;
+	unsigned long pfn;
+
+	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+	if (!pages)
+		return NULL;
+
+	for (i = 0, pfn = page_to_pfn(page); i < (size >> PAGE_SHIFT); i++)
+		pages[i] = pfn_to_page(pfn + i);
+
+	ptr = dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+	kfree(pages);
+
+	return ptr;
+}
+
+/*
+ * unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+	struct vm_struct *area = find_vm_area(cpu_addr);
+
+	if (!area || (area->flags & vm_flags) != vm_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);
+}
+#endif

include/asm-generic/dma-mapping-common.h

@@ -179,6 +179,15 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
 
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller);
+
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
+
 /**
  * dma_mmap_attrs - map a coherent DMA allocation into user space
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices

include/linux/genalloc.h

@@ -106,6 +106,10 @@ extern void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo,
 extern unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data);
 
+extern unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+		unsigned long size, unsigned long start, unsigned int nr,
+		void *data);
+
 extern unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
 		unsigned long start, unsigned int nr, void *data);
 
@@ -113,6 +117,9 @@ extern struct gen_pool *devm_gen_pool_create(struct device *dev,
 		int min_alloc_order, int nid);
 extern struct gen_pool *dev_get_gen_pool(struct device *dev);
 
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+			size_t size);
+
 #ifdef CONFIG_OF
 extern struct gen_pool *of_get_named_gen_pool(struct device_node *np,
 	const char *propname, int index);

lib/genalloc.c

@@ -368,6 +368,35 @@ void gen_pool_for_each_chunk(struct gen_pool *pool,
 }
 EXPORT_SYMBOL(gen_pool_for_each_chunk);
 
+/**
+ * addr_in_gen_pool - checks if an address falls within the range of a pool
+ * @pool:	the generic memory pool
+ * @start:	start address
+ * @size:	size of the region
+ *
+ * Check if the range of addresses falls within the specified pool. Returns
+ * true if the entire range is contained in the pool and false otherwise.
+ */
+bool addr_in_gen_pool(struct gen_pool *pool, unsigned long start,
+			size_t size)
+{
+	bool found = false;
+	unsigned long end = start + size;
+	struct gen_pool_chunk *chunk;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk) {
+		if (start >= chunk->start_addr && start <= chunk->end_addr) {
+			if (end <= chunk->end_addr) {
+				found = true;
+				break;
+			}
+		}
+	}
+	rcu_read_unlock();
+	return found;
+}
+
 /**
  * gen_pool_avail - get available free space of the pool
  * @pool: pool to get available free space
@@ -446,6 +475,26 @@ unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
 }
 EXPORT_SYMBOL(gen_pool_first_fit);
 
+/**
+ * gen_pool_first_fit_order_align - find the first available region
+ * of memory matching the size requirement. The region will be aligned
+ * to the order of the size specified.
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @data: additional data - unused
+ */
+unsigned long gen_pool_first_fit_order_align(unsigned long *map,
+		unsigned long size, unsigned long start,
+		unsigned int nr, void *data)
+{
+	unsigned long align_mask = roundup_pow_of_two(nr) - 1;
+
+	return bitmap_find_next_zero_area(map, size, start, nr, align_mask);
+}
+EXPORT_SYMBOL(gen_pool_first_fit_order_align);
+
 /**
  * gen_pool_best_fit - find the best fitting region of memory
  * macthing the size requirement (no alignment constraint)