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

3 files changed, 144 insertions, 58 deletions

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index efaf5eab40a1..4dadac3135b0 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/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,
diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index f2f565281e63..a777b389a66e 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/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",
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index 97df5ecd66c9..cce5e38133cd 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/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];