Merge branch 'topic/iommu' into for-linus

Documentation/DMA-API.txt

@@ -277,14 +277,26 @@ and <size> parameters are provided to do partial page mapping, it is
 recommended that you never use these unless you really know what the
 cache width is.
 
+dma_addr_t
+dma_map_resource(struct device *dev, phys_addr_t phys_addr, size_t size,
+		 enum dma_data_direction dir, unsigned long attrs)
+
+void
+dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
+		   enum dma_data_direction dir, unsigned long attrs)
+
+API for mapping and unmapping for MMIO resources. All the notes and
+warnings for the other mapping APIs apply here. The API should only be
+used to map device MMIO resources, mapping of RAM is not permitted.
+
 int
 dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 
-In some circumstances dma_map_single() and dma_map_page() will fail to create
-a mapping. A driver can check for these errors by testing the returned
-DMA address with dma_mapping_error(). A non-zero return value means the mapping
-could not be created and the driver should take appropriate action (e.g.
-reduce current DMA mapping usage or delay and try again later).
+In some circumstances dma_map_single(), dma_map_page() and dma_map_resource()
+will fail to create a mapping. A driver can check for these errors by testing
+the returned DMA address with dma_mapping_error(). A non-zero return value
+means the mapping could not be created and the driver should take appropriate
+action (e.g. reduce current DMA mapping usage or delay and try again later).
 
 	int
 	dma_map_sg(struct device *dev, struct scatterlist *sg,

arch/arm/mm/dma-mapping.c

@@ -2014,6 +2014,63 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 	__free_iova(mapping, iova, len);
 }
 
+/**
+ * arm_iommu_map_resource - map a device resource for DMA
+ * @dev: valid struct device pointer
+ * @phys_addr: physical address of resource
+ * @size: size of resource to map
+ * @dir: DMA transfer direction
+ */
+static dma_addr_t arm_iommu_map_resource(struct device *dev,
+		phys_addr_t phys_addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
+	dma_addr_t dma_addr;
+	int ret, prot;
+	phys_addr_t addr = phys_addr & PAGE_MASK;
+	unsigned int offset = phys_addr & ~PAGE_MASK;
+	size_t len = PAGE_ALIGN(size + offset);
+
+	dma_addr = __alloc_iova(mapping, len);
+	if (dma_addr == DMA_ERROR_CODE)
+		return dma_addr;
+
+	prot = __dma_direction_to_prot(dir) | IOMMU_MMIO;
+
+	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot);
+	if (ret < 0)
+		goto fail;
+
+	return dma_addr + offset;
+fail:
+	__free_iova(mapping, dma_addr, len);
+	return DMA_ERROR_CODE;
+}
+
+/**
+ * arm_iommu_unmap_resource - unmap a device DMA resource
+ * @dev: valid struct device pointer
+ * @dma_handle: DMA address to resource
+ * @size: size of resource to map
+ * @dir: DMA transfer direction
+ */
+static void arm_iommu_unmap_resource(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
+	dma_addr_t iova = dma_handle & PAGE_MASK;
+	unsigned int offset = dma_handle & ~PAGE_MASK;
+	size_t len = PAGE_ALIGN(size + offset);
+
+	if (!iova)
+		return;
+
+	iommu_unmap(mapping->domain, iova, len);
+	__free_iova(mapping, iova, len);
+}
+
 static void arm_iommu_sync_single_for_cpu(struct device *dev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
@@ -2057,6 +2114,9 @@ struct dma_map_ops iommu_ops = {
 	.unmap_sg		= arm_iommu_unmap_sg,
 	.sync_sg_for_cpu	= arm_iommu_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_iommu_sync_sg_for_device,
+
+	.map_resource		= arm_iommu_map_resource,
+	.unmap_resource		= arm_iommu_unmap_resource,
 };
 
 struct dma_map_ops iommu_coherent_ops = {
@@ -2070,6 +2130,9 @@ struct dma_map_ops iommu_coherent_ops = {
 
 	.map_sg		= arm_coherent_iommu_map_sg,
 	.unmap_sg	= arm_coherent_iommu_unmap_sg,
+
+	.map_resource	= arm_iommu_map_resource,
+	.unmap_resource	= arm_iommu_unmap_resource,
 };
 
 /**

drivers/dma/sh/rcar-dmac.c

@@ -117,15 +117,35 @@ struct rcar_dmac_desc_page {
 	((PAGE_SIZE - offsetof(struct rcar_dmac_desc_page, chunks)) /	\
 	sizeof(struct rcar_dmac_xfer_chunk))
 
+/*
+ * struct rcar_dmac_chan_slave - Slave configuration
+ * @slave_addr: slave memory address
+ * @xfer_size: size (in bytes) of hardware transfers
+ */
+struct rcar_dmac_chan_slave {
+	phys_addr_t slave_addr;
+	unsigned int xfer_size;
+};
+
+/*
+ * struct rcar_dmac_chan_map - Map of slave device phys to dma address
+ * @addr: slave dma address
+ * @dir: direction of mapping
+ * @slave: slave configuration that is mapped
+ */
+struct rcar_dmac_chan_map {
+	dma_addr_t addr;
+	enum dma_data_direction dir;
+	struct rcar_dmac_chan_slave slave;
+};
+
 /*
  * struct rcar_dmac_chan - R-Car Gen2 DMA Controller Channel
  * @chan: base DMA channel object
  * @iomem: channel I/O memory base
  * @index: index of this channel in the controller
- * @src_xfer_size: size (in bytes) of hardware transfers on the source side
- * @dst_xfer_size: size (in bytes) of hardware transfers on the destination side
- * @src_slave_addr: slave source memory address
- * @dst_slave_addr: slave destination memory address
+ * @src: slave memory address and size on the source side
+ * @dst: slave memory address and size on the destination side
  * @mid_rid: hardware MID/RID for the DMA client using this channel
  * @lock: protects the channel CHCR register and the desc members
  * @desc.free: list of free descriptors
@@ -142,10 +162,9 @@ struct rcar_dmac_chan {
 	void __iomem *iomem;
 	unsigned int index;
 
-	unsigned int src_xfer_size;
-	unsigned int dst_xfer_size;
-	dma_addr_t src_slave_addr;
-	dma_addr_t dst_slave_addr;
+	struct rcar_dmac_chan_slave src;
+	struct rcar_dmac_chan_slave dst;
+	struct rcar_dmac_chan_map map;
 	int mid_rid;
 
 	spinlock_t lock;
@@ -793,13 +812,13 @@ static void rcar_dmac_chan_configure_desc(struct rcar_dmac_chan *chan,
 	case DMA_DEV_TO_MEM:
 		chcr = RCAR_DMACHCR_DM_INC | RCAR_DMACHCR_SM_FIXED
 		     | RCAR_DMACHCR_RS_DMARS;
-		xfer_size = chan->src_xfer_size;
+		xfer_size = chan->src.xfer_size;
 		break;
 
 	case DMA_MEM_TO_DEV:
 		chcr = RCAR_DMACHCR_DM_FIXED | RCAR_DMACHCR_SM_INC
 		     | RCAR_DMACHCR_RS_DMARS;
-		xfer_size = chan->dst_xfer_size;
+		xfer_size = chan->dst.xfer_size;
 		break;
 
 	case DMA_MEM_TO_MEM:
@@ -1023,13 +1042,65 @@ rcar_dmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
 				      DMA_MEM_TO_MEM, flags, false);
 }
 
+static int rcar_dmac_map_slave_addr(struct dma_chan *chan,
+				    enum dma_transfer_direction dir)
+{
+	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
+	struct rcar_dmac_chan_map *map = &rchan->map;
+	phys_addr_t dev_addr;
+	size_t dev_size;
+	enum dma_data_direction dev_dir;
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = rchan->src.slave_addr;
+		dev_size = rchan->src.xfer_size;
+		dev_dir = DMA_TO_DEVICE;
+	} else {
+		dev_addr = rchan->dst.slave_addr;
+		dev_size = rchan->dst.xfer_size;
+		dev_dir = DMA_FROM_DEVICE;
+	}
+
+	/* Reuse current map if possible. */
+	if (dev_addr == map->slave.slave_addr &&
+	    dev_size == map->slave.xfer_size &&
+	    dev_dir == map->dir)
+		return 0;
+
+	/* Remove old mapping if present. */
+	if (map->slave.xfer_size)
+		dma_unmap_resource(chan->device->dev, map->addr,
+				   map->slave.xfer_size, map->dir, 0);
+	map->slave.xfer_size = 0;
+
+	/* Create new slave address map. */
+	map->addr = dma_map_resource(chan->device->dev, dev_addr, dev_size,
+				     dev_dir, 0);
+
+	if (dma_mapping_error(chan->device->dev, map->addr)) {
+		dev_err(chan->device->dev,
+			"chan%u: failed to map %zx@%pap", rchan->index,
+			dev_size, &dev_addr);
+		return -EIO;
+	}
+
+	dev_dbg(chan->device->dev, "chan%u: map %zx@%pap to %pad dir: %s\n",
+		rchan->index, dev_size, &dev_addr, &map->addr,
+		dev_dir == DMA_TO_DEVICE ? "DMA_TO_DEVICE" : "DMA_FROM_DEVICE");
+
+	map->slave.slave_addr = dev_addr;
+	map->slave.xfer_size = dev_size;
+	map->dir = dev_dir;
+
+	return 0;
+}
+
 static struct dma_async_tx_descriptor *
 rcar_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			unsigned int sg_len, enum dma_transfer_direction dir,
 			unsigned long flags, void *context)
 {
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
-	dma_addr_t dev_addr;
 
 	/* Someone calling slave DMA on a generic channel? */
 	if (rchan->mid_rid < 0 || !sg_len) {
@@ -1039,9 +1110,10 @@ rcar_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		return NULL;
 	}
 
-	dev_addr = dir == DMA_DEV_TO_MEM
-		 ? rchan->src_slave_addr : rchan->dst_slave_addr;
-	return rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, dev_addr,
+	if (rcar_dmac_map_slave_addr(chan, dir))
+		return NULL;
+
+	return rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, rchan->map.addr,
 				      dir, flags, false);
 }
 
@@ -1055,7 +1127,6 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
 	struct dma_async_tx_descriptor *desc;
 	struct scatterlist *sgl;
-	dma_addr_t dev_addr;
 	unsigned int sg_len;
 	unsigned int i;
 
@@ -1067,6 +1138,9 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		return NULL;
 	}
 
+	if (rcar_dmac_map_slave_addr(chan, dir))
+		return NULL;
+
 	sg_len = buf_len / period_len;
 	if (sg_len > RCAR_DMAC_MAX_SG_LEN) {
 		dev_err(chan->device->dev,
@@ -1094,9 +1168,7 @@ rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		sg_dma_len(&sgl[i]) = period_len;
 	}
 
-	dev_addr = dir == DMA_DEV_TO_MEM
-		 ? rchan->src_slave_addr : rchan->dst_slave_addr;
-	desc = rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, dev_addr,
+	desc = rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, rchan->map.addr,
 				      dir, flags, true);
 
 	kfree(sgl);
@@ -1112,10 +1184,10 @@ static int rcar_dmac_device_config(struct dma_chan *chan,
 	 * We could lock this, but you shouldn't be configuring the
 	 * channel, while using it...
 	 */
-	rchan->src_slave_addr = cfg->src_addr;
-	rchan->dst_slave_addr = cfg->dst_addr;
-	rchan->src_xfer_size = cfg->src_addr_width;
-	rchan->dst_xfer_size = cfg->dst_addr_width;
+	rchan->src.slave_addr = cfg->src_addr;
+	rchan->dst.slave_addr = cfg->dst_addr;
+	rchan->src.xfer_size = cfg->src_addr_width;
+	rchan->dst.xfer_size = cfg->dst_addr_width;
 
 	return 0;
 }

include/linux/dma-debug.h

@@ -56,6 +56,13 @@ extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
 extern void debug_dma_free_coherent(struct device *dev, size_t size,
 				    void *virt, dma_addr_t addr);
 
+extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
+				   size_t size, int direction,
+				   dma_addr_t dma_addr);
+
+extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
+				     size_t size, int direction);
+
 extern void debug_dma_sync_single_for_cpu(struct device *dev,
 					  dma_addr_t dma_handle, size_t size,
 					  int direction);
@@ -141,6 +148,18 @@ static inline void debug_dma_free_coherent(struct device *dev, size_t size,
 {
 }
 
+static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
+					  size_t size, int direction,
+					  dma_addr_t dma_addr)
+{
+}
+
+static inline void debug_dma_unmap_resource(struct device *dev,
+					    dma_addr_t dma_addr, size_t size,
+					    int direction)
+{
+}
+
 static inline void debug_dma_sync_single_for_cpu(struct device *dev,
 						 dma_addr_t dma_handle,
 						 size_t size, int direction)

include/linux/dma-mapping.h

@@ -95,6 +95,12 @@ struct dma_map_ops {
 			 struct scatterlist *sg, int nents,
 			 enum dma_data_direction dir,
 			 unsigned long attrs);
+	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
+			       size_t size, enum dma_data_direction dir,
+			       unsigned long attrs);
+	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
+			   size_t size, enum dma_data_direction dir,
+			   unsigned long attrs);
 	void (*sync_single_for_cpu)(struct device *dev,
 				    dma_addr_t dma_handle, size_t size,
 				    enum dma_data_direction dir);
@@ -258,6 +264,41 @@ static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
 	debug_dma_unmap_page(dev, addr, size, dir, false);
 }
 
+static inline dma_addr_t dma_map_resource(struct device *dev,
+					  phys_addr_t phys_addr,
+					  size_t size,
+					  enum dma_data_direction dir,
+					  unsigned long attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	BUG_ON(!valid_dma_direction(dir));
+
+	/* Don't allow RAM to be mapped */
+	BUG_ON(pfn_valid(PHYS_PFN(phys_addr)));
+
+	addr = phys_addr;
+	if (ops->map_resource)
+		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
+
+	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
+
+	return addr;
+}
+
+static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr,
+				      size_t size, enum dma_data_direction dir,
+				      unsigned long attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->unmap_resource)
+		ops->unmap_resource(dev, addr, size, dir, attrs);
+	debug_dma_unmap_resource(dev, addr, size, dir);
+}
+
 static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 					   size_t size,
 					   enum dma_data_direction dir)

lib/dma-debug.c

@@ -43,6 +43,7 @@ enum {
 	dma_debug_page,
 	dma_debug_sg,
 	dma_debug_coherent,
+	dma_debug_resource,
 };
 
 enum map_err_types {
@@ -150,8 +151,9 @@ static const char *const maperr2str[] = {
 	[MAP_ERR_CHECKED] = "dma map error checked",
 };
 
-static const char *type2name[4] = { "single", "page",
-				    "scather-gather", "coherent" };
+static const char *type2name[5] = { "single", "page",
+				    "scather-gather", "coherent",
+				    "resource" };
 
 static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
 				   "DMA_FROM_DEVICE", "DMA_NONE" };
@@ -399,6 +401,9 @@ static void hash_bucket_del(struct dma_debug_entry *entry)
 
 static unsigned long long phys_addr(struct dma_debug_entry *entry)
 {
+	if (entry->type == dma_debug_resource)
+		return __pfn_to_phys(entry->pfn) + entry->offset;
+
 	return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset;
 }
 
@@ -1495,6 +1500,49 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
 }
 EXPORT_SYMBOL(debug_dma_free_coherent);
 
+void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
+			    int direction, dma_addr_t dma_addr)
+{
+	struct dma_debug_entry *entry;
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	entry = dma_entry_alloc();
+	if (!entry)
+		return;
+
+	entry->type		= dma_debug_resource;
+	entry->dev		= dev;
+	entry->pfn		= PHYS_PFN(addr);
+	entry->offset		= offset_in_page(addr);
+	entry->size		= size;
+	entry->dev_addr		= dma_addr;
+	entry->direction	= direction;
+	entry->map_err_type	= MAP_ERR_NOT_CHECKED;
+
+	add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_map_resource);
+
+void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
+			      size_t size, int direction)
+{
+	struct dma_debug_entry ref = {
+		.type           = dma_debug_resource,
+		.dev            = dev,
+		.dev_addr       = dma_addr,
+		.size           = size,
+		.direction      = direction,
+	};
+
+	if (unlikely(dma_debug_disabled()))
+		return;
+
+	check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_unmap_resource);
+
 void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
 				   size_t size, int direction)
 {