Merge tag 'dma-mapping-5.13' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - add a new dma_alloc_noncontiguous API (me, Ricardo Ribalda)

 - fix a copyright notice (Hao Fang)

 - add an unlikely annotation to dma_mapping_error (Heiner Kallweit)

 - remove a pointless empty line (Wang Qing)

 - add support for multi-pages map/unmap bencharking (Xiang Chen)

* tag 'dma-mapping-5.13' of git://git.infradead.org/users/hch/dma-mapping:
  dma-mapping: add unlikely hint to error path in dma_mapping_error
  dma-mapping: benchmark: Add support for multi-pages map/unmap
  dma-mapping: benchmark: use the correct HiSilicon copyright
  dma-mapping: remove a pointless empty line in dma_alloc_coherent
  media: uvcvideo: Use dma_alloc_noncontiguous API
  dma-iommu: implement ->alloc_noncontiguous
  dma-iommu: refactor iommu_dma_alloc_remap
  dma-mapping: add a dma_alloc_noncontiguous API
  dma-mapping: refactor dma_{alloc,free}_pages
  dma-mapping: add a dma_mmap_pages helper

Documentation/core-api/dma-api.rst

@@ -563,6 +563,16 @@ Free a region of memory previously allocated using dma_alloc_pages().
 dev, size, dma_handle and dir must all be the same as those passed into
 dma_alloc_pages().  page must be the pointer returned by dma_alloc_pages().
 
+::
+
+	int
+	dma_mmap_pages(struct device *dev, struct vm_area_struct *vma,
+		       size_t size, struct page *page)
+
+Map an allocation returned from dma_alloc_pages() into a user address space.
+dev and size must be the same as those passed into dma_alloc_pages().
+page must be the pointer returned by dma_alloc_pages().
+
 ::
 
 	void *
@@ -584,6 +594,84 @@ dev, size, dma_handle and dir must all be the same as those passed into
 dma_alloc_noncoherent().  cpu_addr must be the virtual address returned by
 dma_alloc_noncoherent().
 
+::
+
+	struct sg_table *
+	dma_alloc_noncontiguous(struct device *dev, size_t size,
+				enum dma_data_direction dir, gfp_t gfp,
+				unsigned long attrs);
+
+This routine allocates  <size> bytes of non-coherent and possibly non-contiguous
+memory.  It returns a pointer to struct sg_table that describes the allocated
+and DMA mapped memory, or NULL if the allocation failed. The resulting memory
+can be used for struct page mapped into a scatterlist are suitable for.
+
+The return sg_table is guaranteed to have 1 single DMA mapped segment as
+indicated by sgt->nents, but it might have multiple CPU side segments as
+indicated by sgt->orig_nents.
+
+The dir parameter specified if data is read and/or written by the device,
+see dma_map_single() for details.
+
+The gfp parameter allows the caller to specify the ``GFP_`` flags (see
+kmalloc()) for the allocation, but rejects flags used to specify a memory
+zone such as GFP_DMA or GFP_HIGHMEM.
+
+The attrs argument must be either 0 or DMA_ATTR_ALLOC_SINGLE_PAGES.
+
+Before giving the memory to the device, dma_sync_sgtable_for_device() needs
+to be called, and before reading memory written by the device,
+dma_sync_sgtable_for_cpu(), just like for streaming DMA mappings that are
+reused.
+
+::
+
+	void
+	dma_free_noncontiguous(struct device *dev, size_t size,
+			       struct sg_table *sgt,
+			       enum dma_data_direction dir)
+
+Free memory previously allocated using dma_alloc_noncontiguous().  dev, size,
+and dir must all be the same as those passed into dma_alloc_noncontiguous().
+sgt must be the pointer returned by dma_alloc_noncontiguous().
+
+::
+
+	void *
+	dma_vmap_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt)
+
+Return a contiguous kernel mapping for an allocation returned from
+dma_alloc_noncontiguous().  dev and size must be the same as those passed into
+dma_alloc_noncontiguous().  sgt must be the pointer returned by
+dma_alloc_noncontiguous().
+
+Once a non-contiguous allocation is mapped using this function, the
+flush_kernel_vmap_range() and invalidate_kernel_vmap_range() APIs must be used
+to manage the coherency between the kernel mapping, the device and user space
+mappings (if any).
+
+::
+
+	void
+	dma_vunmap_noncontiguous(struct device *dev, void *vaddr)
+
+Unmap a kernel mapping returned by dma_vmap_noncontiguous().  dev must be the
+same the one passed into dma_alloc_noncontiguous().  vaddr must be the pointer
+returned by dma_vmap_noncontiguous().
+
+
+::
+
+	int
+	dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
+			       size_t size, struct sg_table *sgt)
+
+Map an allocation returned from dma_alloc_noncontiguous() into a user address
+space.  dev and size must be the same as those passed into
+dma_alloc_noncontiguous().  sgt must be the pointer returned by
+dma_alloc_noncontiguous().
+
 ::
 
 	int

drivers/iommu/dma-iommu.c

@@ -647,23 +647,12 @@ static struct page **__iommu_dma_alloc_pages(struct device *dev,
 	return pages;
 }
 
-/**
- * iommu_dma_alloc_remap - Allocate and map a buffer contiguous in IOVA space
- * @dev: Device to allocate memory for. Must be a real device
- *	 attached to an iommu_dma_domain
- * @size: Size of buffer in bytes
- * @dma_handle: Out argument for allocated DMA handle
- * @gfp: Allocation flags
- * @prot: pgprot_t to use for the remapped mapping
- * @attrs: DMA attributes for this allocation
- *
- * If @size is less than PAGE_SIZE, then a full CPU page will be allocated,
+/*
+ * If size is less than PAGE_SIZE, then a full CPU page will be allocated,
  * but an IOMMU which supports smaller pages might not map the whole thing.
- *
- * Return: Mapped virtual address, or NULL on failure.
  */
-static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, pgprot_t prot,
+static struct page **__iommu_dma_alloc_noncontiguous(struct device *dev,
+		size_t size, struct sg_table *sgt, gfp_t gfp, pgprot_t prot,
 		unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
@@ -673,11 +662,7 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
 	unsigned int count, min_size, alloc_sizes = domain->pgsize_bitmap;
 	struct page **pages;
-	struct sg_table sgt;
 	dma_addr_t iova;
-	void *vaddr;
-
-	*dma_handle = DMA_MAPPING_ERROR;
 
 	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
 	    iommu_deferred_attach(dev, domain))
@@ -704,41 +689,91 @@ static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
 	if (!iova)
 		goto out_free_pages;
 
-	if (sg_alloc_table_from_pages(&sgt, pages, count, 0, size, GFP_KERNEL))
+	if (sg_alloc_table_from_pages(sgt, pages, count, 0, size, GFP_KERNEL))
 		goto out_free_iova;
 
 	if (!(ioprot & IOMMU_CACHE)) {
 		struct scatterlist *sg;
 		int i;
 
-		for_each_sg(sgt.sgl, sg, sgt.orig_nents, i)
+		for_each_sg(sgt->sgl, sg, sgt->orig_nents, i)
 			arch_dma_prep_coherent(sg_page(sg), sg->length);
 	}
 
-	if (iommu_map_sg_atomic(domain, iova, sgt.sgl, sgt.orig_nents, ioprot)
+	if (iommu_map_sg_atomic(domain, iova, sgt->sgl, sgt->orig_nents, ioprot)
 			< size)
 		goto out_free_sg;
 
+	sgt->sgl->dma_address = iova;
+	sgt->sgl->dma_length = size;
+	return pages;
+
+out_free_sg:
+	sg_free_table(sgt);
+out_free_iova:
+	iommu_dma_free_iova(cookie, iova, size, NULL);
+out_free_pages:
+	__iommu_dma_free_pages(pages, count);
+	return NULL;
+}
+
+static void *iommu_dma_alloc_remap(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, pgprot_t prot,
+		unsigned long attrs)
+{
+	struct page **pages;
+	struct sg_table sgt;
+	void *vaddr;
+
+	pages = __iommu_dma_alloc_noncontiguous(dev, size, &sgt, gfp, prot,
+						attrs);
+	if (!pages)
+		return NULL;
+	*dma_handle = sgt.sgl->dma_address;
+	sg_free_table(&sgt);
 	vaddr = dma_common_pages_remap(pages, size, prot,
 			__builtin_return_address(0));
 	if (!vaddr)
 		goto out_unmap;
-
-	*dma_handle = iova;
-	sg_free_table(&sgt);
 	return vaddr;
 
 out_unmap:
-	__iommu_dma_unmap(dev, iova, size);
-out_free_sg:
-	sg_free_table(&sgt);
-out_free_iova:
-	iommu_dma_free_iova(cookie, iova, size, NULL);
-out_free_pages:
-	__iommu_dma_free_pages(pages, count);
+	__iommu_dma_unmap(dev, *dma_handle, size);
+	__iommu_dma_free_pages(pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
 	return NULL;
 }
 
+#ifdef CONFIG_DMA_REMAP
+static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev,
+		size_t size, enum dma_data_direction dir, gfp_t gfp,
+		unsigned long attrs)
+{
+	struct dma_sgt_handle *sh;
+
+	sh = kmalloc(sizeof(*sh), gfp);
+	if (!sh)
+		return NULL;
+
+	sh->pages = __iommu_dma_alloc_noncontiguous(dev, size, &sh->sgt, gfp,
+						    PAGE_KERNEL, attrs);
+	if (!sh->pages) {
+		kfree(sh);
+		return NULL;
+	}
+	return &sh->sgt;
+}
+
+static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+	struct dma_sgt_handle *sh = sgt_handle(sgt);
+
+	__iommu_dma_unmap(dev, sgt->sgl->dma_address, size);
+	__iommu_dma_free_pages(sh->pages, PAGE_ALIGN(size) >> PAGE_SHIFT);
+	sg_free_table(&sh->sgt);
+}
+#endif /* CONFIG_DMA_REMAP */
+
 static void iommu_dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
 {
@@ -1255,6 +1290,10 @@ static const struct dma_map_ops iommu_dma_ops = {
 	.free			= iommu_dma_free,
 	.alloc_pages		= dma_common_alloc_pages,
 	.free_pages		= dma_common_free_pages,
+#ifdef CONFIG_DMA_REMAP
+	.alloc_noncontiguous	= iommu_dma_alloc_noncontiguous,
+	.free_noncontiguous	= iommu_dma_free_noncontiguous,
+#endif
 	.mmap			= iommu_dma_mmap,
 	.get_sgtable		= iommu_dma_get_sgtable,
 	.map_page		= iommu_dma_map_page,

drivers/media/usb/uvc/uvc_video.c

@@ -6,11 +6,14 @@
  *          Laurent Pinchart (laurent.pinchart@ideasonboard.com)
  */
 
+#include <linux/dma-mapping.h>
+#include <linux/highmem.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/usb.h>
+#include <linux/usb/hcd.h>
 #include <linux/videodev2.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
@@ -1096,6 +1099,29 @@ static int uvc_video_decode_start(struct uvc_streaming *stream,
 	return data[0];
 }
 
+static inline enum dma_data_direction uvc_stream_dir(
+				struct uvc_streaming *stream)
+{
+	if (stream->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
+		return DMA_FROM_DEVICE;
+	else
+		return DMA_TO_DEVICE;
+}
+
+static inline struct device *uvc_stream_to_dmadev(struct uvc_streaming *stream)
+{
+	return bus_to_hcd(stream->dev->udev->bus)->self.sysdev;
+}
+
+static int uvc_submit_urb(struct uvc_urb *uvc_urb, gfp_t mem_flags)
+{
+	/* Sync DMA. */
+	dma_sync_sgtable_for_device(uvc_stream_to_dmadev(uvc_urb->stream),
+				    uvc_urb->sgt,
+				    uvc_stream_dir(uvc_urb->stream));
+	return usb_submit_urb(uvc_urb->urb, mem_flags);
+}
+
 /*
  * uvc_video_decode_data_work: Asynchronous memcpy processing
  *
@@ -1117,7 +1143,7 @@ static void uvc_video_copy_data_work(struct work_struct *work)
 		uvc_queue_buffer_release(op->buf);
 	}
 
-	ret = usb_submit_urb(uvc_urb->urb, GFP_KERNEL);
+	ret = uvc_submit_urb(uvc_urb, GFP_KERNEL);
 	if (ret < 0)
 		dev_err(&uvc_urb->stream->intf->dev,
 			"Failed to resubmit video URB (%d).\n", ret);
@@ -1537,6 +1563,12 @@ static void uvc_video_complete(struct urb *urb)
 	/* Re-initialise the URB async work. */
 	uvc_urb->async_operations = 0;
 
+	/* Sync DMA and invalidate vmap range. */
+	dma_sync_sgtable_for_cpu(uvc_stream_to_dmadev(uvc_urb->stream),
+				 uvc_urb->sgt, uvc_stream_dir(stream));
+	invalidate_kernel_vmap_range(uvc_urb->buffer,
+				     uvc_urb->stream->urb_size);
+
 	/*
 	 * Process the URB headers, and optionally queue expensive memcpy tasks
 	 * to be deferred to a work queue.
@@ -1545,7 +1577,7 @@ static void uvc_video_complete(struct urb *urb)
 
 	/* If no async work is needed, resubmit the URB immediately. */
 	if (!uvc_urb->async_operations) {
-		ret = usb_submit_urb(uvc_urb->urb, GFP_ATOMIC);
+		ret = uvc_submit_urb(uvc_urb, GFP_ATOMIC);
 		if (ret < 0)
 			dev_err(&stream->intf->dev,
 				"Failed to resubmit video URB (%d).\n", ret);
@@ -1560,24 +1592,49 @@ static void uvc_video_complete(struct urb *urb)
  */
 static void uvc_free_urb_buffers(struct uvc_streaming *stream)
 {
+	struct device *dma_dev = uvc_stream_to_dmadev(stream);
 	struct uvc_urb *uvc_urb;
 
 	for_each_uvc_urb(uvc_urb, stream) {
 		if (!uvc_urb->buffer)
 			continue;
 
-#ifndef CONFIG_DMA_NONCOHERENT
-		usb_free_coherent(stream->dev->udev, stream->urb_size,
-				  uvc_urb->buffer, uvc_urb->dma);
-#else
-		kfree(uvc_urb->buffer);
-#endif
+		dma_vunmap_noncontiguous(dma_dev, uvc_urb->buffer);
+		dma_free_noncontiguous(dma_dev, stream->urb_size, uvc_urb->sgt,
+				       uvc_stream_dir(stream));
+
 		uvc_urb->buffer = NULL;
+		uvc_urb->sgt = NULL;
 	}
 
 	stream->urb_size = 0;
 }
 
+static bool uvc_alloc_urb_buffer(struct uvc_streaming *stream,
+				 struct uvc_urb *uvc_urb, gfp_t gfp_flags)
+{
+	struct device *dma_dev = uvc_stream_to_dmadev(stream);
+
+	uvc_urb->sgt = dma_alloc_noncontiguous(dma_dev, stream->urb_size,
+					       uvc_stream_dir(stream),
+					       gfp_flags, 0);
+	if (!uvc_urb->sgt)
+		return false;
+	uvc_urb->dma = uvc_urb->sgt->sgl->dma_address;
+
+	uvc_urb->buffer = dma_vmap_noncontiguous(dma_dev, stream->urb_size,
+						 uvc_urb->sgt);
+	if (!uvc_urb->buffer) {
+		dma_free_noncontiguous(dma_dev, stream->urb_size,
+				       uvc_urb->sgt,
+				       uvc_stream_dir(stream));
+		uvc_urb->sgt = NULL;
+		return false;
+	}
+
+	return true;
+}
+
 /*
  * Allocate transfer buffers. This function can be called with buffers
  * already allocated when resuming from suspend, in which case it will
@@ -1608,19 +1665,12 @@ static int uvc_alloc_urb_buffers(struct uvc_streaming *stream,
 
 	/* Retry allocations until one succeed. */
 	for (; npackets > 1; npackets /= 2) {
+		stream->urb_size = psize * npackets;
+
 		for (i = 0; i < UVC_URBS; ++i) {
 			struct uvc_urb *uvc_urb = &stream->uvc_urb[i];
 
-			stream->urb_size = psize * npackets;
-#ifndef CONFIG_DMA_NONCOHERENT
-			uvc_urb->buffer = usb_alloc_coherent(
-				stream->dev->udev, stream->urb_size,
-				gfp_flags | __GFP_NOWARN, &uvc_urb->dma);
-#else
-			uvc_urb->buffer =
-			    kmalloc(stream->urb_size, gfp_flags | __GFP_NOWARN);
-#endif
-			if (!uvc_urb->buffer) {
+			if (!uvc_alloc_urb_buffer(stream, uvc_urb, gfp_flags)) {
 				uvc_free_urb_buffers(stream);
 				break;
 			}
@@ -1730,12 +1780,8 @@ static int uvc_init_video_isoc(struct uvc_streaming *stream,
 		urb->context = uvc_urb;
 		urb->pipe = usb_rcvisocpipe(stream->dev->udev,
 				ep->desc.bEndpointAddress);
-#ifndef CONFIG_DMA_NONCOHERENT
 		urb->transfer_flags = URB_ISO_ASAP | URB_NO_TRANSFER_DMA_MAP;
 		urb->transfer_dma = uvc_urb->dma;
-#else
-		urb->transfer_flags = URB_ISO_ASAP;
-#endif
 		urb->interval = ep->desc.bInterval;
 		urb->transfer_buffer = uvc_urb->buffer;
 		urb->complete = uvc_video_complete;
@@ -1795,10 +1841,8 @@ static int uvc_init_video_bulk(struct uvc_streaming *stream,
 
 		usb_fill_bulk_urb(urb, stream->dev->udev, pipe,	uvc_urb->buffer,
 				  size, uvc_video_complete, uvc_urb);
-#ifndef CONFIG_DMA_NONCOHERENT
 		urb->transfer_flags = URB_NO_TRANSFER_DMA_MAP;
 		urb->transfer_dma = uvc_urb->dma;
-#endif
 
 		uvc_urb->urb = urb;
 	}
@@ -1895,7 +1939,7 @@ static int uvc_video_start_transfer(struct uvc_streaming *stream,
 
 	/* Submit the URBs. */
 	for_each_uvc_urb(uvc_urb, stream) {
-		ret = usb_submit_urb(uvc_urb->urb, gfp_flags);
+		ret = uvc_submit_urb(uvc_urb, gfp_flags);
 		if (ret < 0) {
 			dev_err(&stream->intf->dev,
 				"Failed to submit URB %u (%d).\n",

drivers/media/usb/uvc/uvcvideo.h

@@ -219,6 +219,7 @@
  */
 
 struct gpio_desc;
+struct sg_table;
 struct uvc_device;
 
 /* TODO: Put the most frequently accessed fields at the beginning of
@@ -545,7 +546,8 @@ struct uvc_copy_op {
  * @urb: the URB described by this context structure
  * @stream: UVC streaming context
  * @buffer: memory storage for the URB
- * @dma: DMA coherent addressing for the urb_buffer
+ * @dma: Allocated DMA handle
+ * @sgt: sgt_table with the urb locations in memory
  * @async_operations: counter to indicate the number of copy operations
  * @copy_operations: work descriptors for asynchronous copy operations
  * @work: work queue entry for asynchronous decode
@@ -556,6 +558,7 @@ struct uvc_urb {
 
 	char *buffer;
 	dma_addr_t dma;
+	struct sg_table *sgt;
 
 	unsigned int async_operations;
 	struct uvc_copy_op copy_operations[UVC_MAX_PACKETS];

include/linux/dma-map-ops.h

@@ -22,6 +22,11 @@ struct dma_map_ops {
 			gfp_t gfp);
 	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
 			dma_addr_t dma_handle, enum dma_data_direction dir);
+	struct sg_table *(*alloc_noncontiguous)(struct device *dev, size_t size,
+			enum dma_data_direction dir, gfp_t gfp,
+			unsigned long attrs);
+	void (*free_noncontiguous)(struct device *dev, size_t size,
+			struct sg_table *sgt, enum dma_data_direction dir);
 	int (*mmap)(struct device *, struct vm_area_struct *,
 			void *, dma_addr_t, size_t, unsigned long attrs);
 
@@ -198,6 +203,20 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
+/*
+ * This is the actual return value from the ->alloc_noncontiguous method.
+ * The users of the DMA API should only care about the sg_table, but to make
+ * the DMA-API internal vmaping and freeing easier we stash away the page
+ * array as well (except for the fallback case).  This can go away any time,
+ * e.g. when a vmap-variant that takes a scatterlist comes along.
+ */
+struct dma_sgt_handle {
+	struct sg_table sgt;
+	struct page **pages;
+};
+#define sgt_handle(sgt) \
+	container_of((sgt), struct dma_sgt_handle, sgt)
+
 int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);

include/linux/dma-mapping.h

@@ -95,7 +95,7 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	debug_dma_mapping_error(dev, dma_addr);
 
-	if (dma_addr == DMA_MAPPING_ERROR)
+	if (unlikely(dma_addr == DMA_MAPPING_ERROR))
 		return -ENOMEM;
 	return 0;
 }
@@ -144,6 +144,15 @@ u64 dma_get_required_mask(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
 bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
+struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
+		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs);
+void dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir);
+void *dma_vmap_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt);
+void dma_vunmap_noncontiguous(struct device *dev, void *vaddr);
+int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
+		size_t size, struct sg_table *sgt);
 #else /* CONFIG_HAS_DMA */
 static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 		struct page *page, size_t offset, size_t size,
@@ -257,12 +266,37 @@ static inline unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	return 0;
 }
+static inline struct sg_table *dma_alloc_noncontiguous(struct device *dev,
+		size_t size, enum dma_data_direction dir, gfp_t gfp,
+		unsigned long attrs)
+{
+	return NULL;
+}
+static inline void dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+}
+static inline void *dma_vmap_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt)
+{
+	return NULL;
+}
+static inline void dma_vunmap_noncontiguous(struct device *dev, void *vaddr)
+{
+}
+static inline int dma_mmap_noncontiguous(struct device *dev,
+		struct vm_area_struct *vma, size_t size, struct sg_table *sgt)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_HAS_DMA */
 
 struct page *dma_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
 void dma_free_pages(struct device *dev, size_t size, struct page *page,
 		dma_addr_t dma_handle, enum dma_data_direction dir);
+int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma,
+		size_t size, struct page *page);
 
 static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
@@ -401,7 +435,6 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
-
 	return dma_alloc_attrs(dev, size, dma_handle, gfp,
 			(gfp & __GFP_NOWARN) ? DMA_ATTR_NO_WARN : 0);
 }

kernel/dma/map_benchmark.c

 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020 Hisilicon Limited.
+ * Copyright (C) 2020 HiSilicon Limited.
  */
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
@@ -38,7 +38,8 @@ struct map_benchmark {
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
 	__u32 dma_trans_ns; /* time for DMA transmission in ns */
-	__u8 expansion[80];	/* For future use */
+	__u32 granule;	/* how many PAGE_SIZE will do map/unmap once a time */
+	__u8 expansion[76];	/* For future use */
 };
 
 struct map_benchmark_data {
@@ -58,9 +59,11 @@ static int map_benchmark_thread(void *data)
 	void *buf;
 	dma_addr_t dma_addr;
 	struct map_benchmark_data *map = data;
+	int npages = map->bparam.granule;
+	u64 size = npages * PAGE_SIZE;
 	int ret = 0;
 
-	buf = (void *)__get_free_page(GFP_KERNEL);
+	buf = alloc_pages_exact(size, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -76,10 +79,10 @@ static int map_benchmark_thread(void *data)
 		 * 66 means evertything goes well! 66 is lucky.
 		 */
 		if (map->dir != DMA_FROM_DEVICE)
-			memset(buf, 0x66, PAGE_SIZE);
+			memset(buf, 0x66, size);
 
 		map_stime = ktime_get();
-		dma_addr = dma_map_single(map->dev, buf, PAGE_SIZE, map->dir);
+		dma_addr = dma_map_single(map->dev, buf, size, map->dir);
 		if (unlikely(dma_mapping_error(map->dev, dma_addr))) {
 			pr_err("dma_map_single failed on %s\n",
 				dev_name(map->dev));
@@ -93,7 +96,7 @@ static int map_benchmark_thread(void *data)
 		ndelay(map->bparam.dma_trans_ns);
 
 		unmap_stime = ktime_get();
-		dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir);
+		dma_unmap_single(map->dev, dma_addr, size, map->dir);
 		unmap_etime = ktime_get();
 		unmap_delta = ktime_sub(unmap_etime, unmap_stime);
 
@@ -112,7 +115,7 @@ static int map_benchmark_thread(void *data)
 	}
 
 out:
-	free_page((unsigned long)buf);
+	free_pages_exact(buf, size);
 	return ret;
 }
 
@@ -203,7 +206,6 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 	struct map_benchmark_data *map = file->private_data;
 	void __user *argp = (void __user *)arg;
 	u64 old_dma_mask;
-
 	int ret;
 
 	if (copy_from_user(&map->bparam, argp, sizeof(map->bparam)))
@@ -234,6 +236,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 			return -EINVAL;
 		}
 
+		if (map->bparam.granule < 1 || map->bparam.granule > 1024) {
+			pr_err("invalid granule size\n");
+			return -EINVAL;
+		}
+
 		switch (map->bparam.dma_dir) {
 		case DMA_MAP_BIDIRECTIONAL:
 			map->dir = DMA_BIDIRECTIONAL;

kernel/dma/mapping.c

@@ -477,11 +477,10 @@ void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 }
 EXPORT_SYMBOL(dma_free_attrs);
 
-struct page *dma_alloc_pages(struct device *dev, size_t size,
+static struct page *__dma_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
-	struct page *page;
 
 	if (WARN_ON_ONCE(!dev->coherent_dma_mask))
 		return NULL;
@@ -490,33 +489,162 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
 
 	size = PAGE_ALIGN(size);
 	if (dma_alloc_direct(dev, ops))
-		page = dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp);
-	else if (ops->alloc_pages)
-		page = ops->alloc_pages(dev, size, dma_handle, dir, gfp);
-	else
+		return dma_direct_alloc_pages(dev, size, dma_handle, dir, gfp);
+	if (!ops->alloc_pages)
 		return NULL;
+	return ops->alloc_pages(dev, size, dma_handle, dir, gfp);
+}
 
-	debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
+struct page *dma_alloc_pages(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp)
+{
+	struct page *page = __dma_alloc_pages(dev, size, dma_handle, dir, gfp);
 
+	if (page)
+		debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
 	return page;
 }
 EXPORT_SYMBOL_GPL(dma_alloc_pages);
 
-void dma_free_pages(struct device *dev, size_t size, struct page *page,
+static void __dma_free_pages(struct device *dev, size_t size, struct page *page,
 		dma_addr_t dma_handle, enum dma_data_direction dir)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	size = PAGE_ALIGN(size);
-	debug_dma_unmap_page(dev, dma_handle, size, dir);
-
 	if (dma_alloc_direct(dev, ops))
 		dma_direct_free_pages(dev, size, page, dma_handle, dir);
 	else if (ops->free_pages)
 		ops->free_pages(dev, size, page, dma_handle, dir);
 }
+
+void dma_free_pages(struct device *dev, size_t size, struct page *page,
+		dma_addr_t dma_handle, enum dma_data_direction dir)
+{
+	debug_dma_unmap_page(dev, dma_handle, size, dir);
+	__dma_free_pages(dev, size, page, dma_handle, dir);
+}
 EXPORT_SYMBOL_GPL(dma_free_pages);
 
+int dma_mmap_pages(struct device *dev, struct vm_area_struct *vma,
+		size_t size, struct page *page)
+{
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	if (vma->vm_pgoff >= count || vma_pages(vma) > count - vma->vm_pgoff)
+		return -ENXIO;
+	return remap_pfn_range(vma, vma->vm_start,
+			       page_to_pfn(page) + vma->vm_pgoff,
+			       vma_pages(vma) << PAGE_SHIFT, vma->vm_page_prot);
+}
+EXPORT_SYMBOL_GPL(dma_mmap_pages);
+
+static struct sg_table *alloc_single_sgt(struct device *dev, size_t size,
+		enum dma_data_direction dir, gfp_t gfp)
+{
+	struct sg_table *sgt;
+	struct page *page;
+
+	sgt = kmalloc(sizeof(*sgt), gfp);
+	if (!sgt)
+		return NULL;
+	if (sg_alloc_table(sgt, 1, gfp))
+		goto out_free_sgt;
+	page = __dma_alloc_pages(dev, size, &sgt->sgl->dma_address, dir, gfp);
+	if (!page)
+		goto out_free_table;
+	sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	sg_dma_len(sgt->sgl) = sgt->sgl->length;
+	return sgt;
+out_free_table:
+	sg_free_table(sgt);
+out_free_sgt:
+	kfree(sgt);
+	return NULL;
+}
+
+struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
+		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	struct sg_table *sgt;
+
+	if (WARN_ON_ONCE(attrs & ~DMA_ATTR_ALLOC_SINGLE_PAGES))
+		return NULL;
+
+	if (ops && ops->alloc_noncontiguous)
+		sgt = ops->alloc_noncontiguous(dev, size, dir, gfp, attrs);
+	else
+		sgt = alloc_single_sgt(dev, size, dir, gfp);
+
+	if (sgt) {
+		sgt->nents = 1;
+		debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir);
+	}
+	return sgt;
+}
+EXPORT_SYMBOL_GPL(dma_alloc_noncontiguous);
+
+static void free_single_sgt(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+	__dma_free_pages(dev, size, sg_page(sgt->sgl), sgt->sgl->dma_address,
+			 dir);
+	sg_free_table(sgt);
+	kfree(sgt);
+}
+
+void dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	debug_dma_unmap_sg(dev, sgt->sgl, sgt->orig_nents, dir);
+	if (ops && ops->free_noncontiguous)
+		ops->free_noncontiguous(dev, size, sgt, dir);
+	else
+		free_single_sgt(dev, size, sgt, dir);
+}
+EXPORT_SYMBOL_GPL(dma_free_noncontiguous);
+
+void *dma_vmap_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+	if (ops && ops->alloc_noncontiguous)
+		return vmap(sgt_handle(sgt)->pages, count, VM_MAP, PAGE_KERNEL);
+	return page_address(sg_page(sgt->sgl));
+}
+EXPORT_SYMBOL_GPL(dma_vmap_noncontiguous);
+
+void dma_vunmap_noncontiguous(struct device *dev, void *vaddr)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops && ops->alloc_noncontiguous)
+		vunmap(vaddr);
+}
+EXPORT_SYMBOL_GPL(dma_vunmap_noncontiguous);
+
+int dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
+		size_t size, struct sg_table *sgt)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops && ops->alloc_noncontiguous) {
+		unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+		if (vma->vm_pgoff >= count ||
+		    vma_pages(vma) > count - vma->vm_pgoff)
+			return -ENXIO;
+		return vm_map_pages(vma, sgt_handle(sgt)->pages, count);
+	}
+	return dma_mmap_pages(dev, vma, size, sg_page(sgt->sgl));
+}
+EXPORT_SYMBOL_GPL(dma_mmap_noncontiguous);
+
 int dma_supported(struct device *dev, u64 mask)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);

tools/testing/selftests/dma/dma_map_benchmark.c

 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Copyright (C) 2020 Hisilicon Limited.
+ * Copyright (C) 2020 HiSilicon Limited.
  */
 
 #include <fcntl.h>
@@ -40,7 +40,8 @@ struct map_benchmark {
 	__u32 dma_bits; /* DMA addressing capability */
 	__u32 dma_dir; /* DMA data direction */
 	__u32 dma_trans_ns; /* time for DMA transmission in ns */
-	__u8 expansion[80];	/* For future use */
+	__u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */
+	__u8 expansion[76];	/* For future use */
 };
 
 int main(int argc, char **argv)
@@ -51,11 +52,13 @@ int main(int argc, char **argv)
 	int threads = 1, seconds = 20, node = -1;
 	/* default dma mask 32bit, bidirectional DMA */
 	int bits = 32, xdelay = 0, dir = DMA_MAP_BIDIRECTIONAL;
+	/* default granule 1 PAGESIZE */
+	int granule = 1;
 
 	int cmd = DMA_MAP_BENCHMARK;
 	char *p;
 
-	while ((opt = getopt(argc, argv, "t:s:n:b:d:x:")) != -1) {
+	while ((opt = getopt(argc, argv, "t:s:n:b:d:x:g:")) != -1) {
 		switch (opt) {
 		case 't':
 			threads = atoi(optarg);
@@ -75,6 +78,9 @@ int main(int argc, char **argv)
 		case 'x':
 			xdelay = atoi(optarg);
 			break;
+		case 'g':
+			granule = atoi(optarg);
+			break;
 		default:
 			return -1;
 		}
@@ -110,6 +116,11 @@ int main(int argc, char **argv)
 		exit(1);
 	}
 
+	if (granule < 1 || granule > 1024) {
+		fprintf(stderr, "invalid granule size\n");
+		exit(1);
+	}
+
 	fd = open("/sys/kernel/debug/dma_map_benchmark", O_RDWR);
 	if (fd == -1) {
 		perror("open");
@@ -123,14 +134,15 @@ int main(int argc, char **argv)
 	map.dma_bits = bits;
 	map.dma_dir = dir;
 	map.dma_trans_ns = xdelay;
+	map.granule = granule;
 
 	if (ioctl(fd, cmd, &map)) {
 		perror("ioctl");
 		exit(1);
 	}
 
-	printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s\n",
-			threads, seconds, node, dir[directions]);
+	printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granule: %d\n",
+			threads, seconds, node, dir[directions], granule);
 	printf("average map latency(us):%.1f standard deviation:%.1f\n",
 			map.avg_map_100ns/10.0, map.map_stddev/10.0);
 	printf("average unmap latency(us):%.1f standard deviation:%.1f\n",