Merge branch 'stable/for-linus-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb

Pull swiotlb updates from Konrad Rzeszutek Wilk:

 - minor fixes (rate limiting), remove certain functions

 - support for DMA_ATTR_SKIP_CPU_SYNC which is an optimization
   in the DMA API

* 'stable/for-linus-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb:
  swiotlb: Minor fix-ups for DMA_ATTR_SKIP_CPU_SYNC support
  swiotlb: Add support for DMA_ATTR_SKIP_CPU_SYNC
  swiotlb-xen: Enforce return of DMA_ERROR_CODE in mapping function
  swiotlb: Drop unused functions swiotlb_map_sg and swiotlb_unmap_sg
  swiotlb: Rate-limit printing when running out of SW-IOMMU space

arch/arm/xen/mm.c

@@ -186,7 +186,6 @@ struct dma_map_ops *xen_dma_ops;
 EXPORT_SYMBOL(xen_dma_ops);
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
-	.mapping_error = xen_swiotlb_dma_mapping_error,
 	.alloc = xen_swiotlb_alloc_coherent,
 	.free = xen_swiotlb_free_coherent,
 	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,

arch/x86/xen/pci-swiotlb-xen.c

@@ -19,7 +19,6 @@
 int xen_swiotlb __read_mostly;
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
-	.mapping_error = xen_swiotlb_dma_mapping_error,
 	.alloc = xen_swiotlb_alloc_coherent,
 	.free = xen_swiotlb_free_coherent,
 	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,

drivers/xen/swiotlb-xen.c

@@ -405,7 +405,8 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	 */
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
 
-	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir);
+	map = swiotlb_tbl_map_single(dev, start_dma_addr, phys, size, dir,
+				     attrs);
 	if (map == SWIOTLB_MAP_ERROR)
 		return DMA_ERROR_CODE;
 
@@ -416,11 +417,13 @@ dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 	/*
 	 * Ensure that the address returned is DMA'ble
 	 */
-	if (!dma_capable(dev, dev_addr, size)) {
-		swiotlb_tbl_unmap_single(dev, map, size, dir);
-		dev_addr = 0;
-	}
-	return dev_addr;
+	if (dma_capable(dev, dev_addr, size))
+		return dev_addr;
+
+	attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+	swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
+
+	return DMA_ERROR_CODE;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_map_page);
 
@@ -444,7 +447,7 @@ static void xen_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 
 	/* NOTE: We use dev_addr here, not paddr! */
 	if (is_xen_swiotlb_buffer(dev_addr)) {
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
+		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
 		return;
 	}
 
@@ -557,11 +560,12 @@ xen_swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 								 start_dma_addr,
 								 sg_phys(sg),
 								 sg->length,
-								 dir);
+								 dir, attrs);
 			if (map == SWIOTLB_MAP_ERROR) {
 				dev_warn(hwdev, "swiotlb buffer is full\n");
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
+				attrs |= DMA_ATTR_SKIP_CPU_SYNC;
 				xen_swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
 							   attrs);
 				sg_dma_len(sgl) = 0;
@@ -648,13 +652,6 @@ xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_sync_sg_for_device);
 
-int
-xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
-{
-	return !dma_addr;
-}
-EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mapping_error);
-
 /*
  * Return whether the given device DMA address mask can be supported
  * properly.  For example, if your device can only drive the low 24-bits

include/linux/swiotlb.h

@@ -44,11 +44,13 @@ enum dma_sync_target {
 extern phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 					  dma_addr_t tbl_dma_addr,
 					  phys_addr_t phys, size_t size,
-					  enum dma_data_direction dir);
+					  enum dma_data_direction dir,
+					  unsigned long attrs);
 
 extern void swiotlb_tbl_unmap_single(struct device *hwdev,
 				     phys_addr_t tlb_addr,
-				     size_t size, enum dma_data_direction dir);
+				     size_t size, enum dma_data_direction dir,
+				     unsigned long attrs);
 
 extern void swiotlb_tbl_sync_single(struct device *hwdev,
 				    phys_addr_t tlb_addr,
@@ -72,14 +74,6 @@ extern void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 			       size_t size, enum dma_data_direction dir,
 			       unsigned long attrs);
 
-extern int
-swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nents,
-	       enum dma_data_direction dir);
-
-extern void
-swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
-		 enum dma_data_direction dir);
-
 extern int
 swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 		     enum dma_data_direction dir,

include/xen/swiotlb-xen.h

@@ -50,9 +50,6 @@ extern void
 xen_swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
 			       int nelems, enum dma_data_direction dir);
 
-extern int
-xen_swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
-
 extern int
 xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
 

lib/swiotlb.c

@@ -425,7 +425,8 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 				   dma_addr_t tbl_dma_addr,
 				   phys_addr_t orig_addr, size_t size,
-				   enum dma_data_direction dir)
+				   enum dma_data_direction dir,
+				   unsigned long attrs)
 {
 	unsigned long flags;
 	phys_addr_t tlb_addr;
@@ -526,7 +527,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	 */
 	for (i = 0; i < nslots; i++)
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
-	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
 
 	return tlb_addr;
@@ -539,18 +541,20 @@ EXPORT_SYMBOL_GPL(swiotlb_tbl_map_single);
 
 static phys_addr_t
 map_single(struct device *hwdev, phys_addr_t phys, size_t size,
-	   enum dma_data_direction dir)
+	   enum dma_data_direction dir, unsigned long attrs)
 {
 	dma_addr_t start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
 
-	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size, dir);
+	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
+				      dir, attrs);
 }
 
 /*
  * dma_addr is the kernel virtual address of the bounce buffer to unmap.
  */
 void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
-			      size_t size, enum dma_data_direction dir)
+			      size_t size, enum dma_data_direction dir,
+			      unsigned long attrs)
 {
 	unsigned long flags;
 	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
@@ -561,6 +565,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	 * First, sync the memory before unmapping the entry
 	 */
 	if (orig_addr != INVALID_PHYS_ADDR &&
+	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
 		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
 
@@ -654,7 +659,8 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 * GFP_DMA memory; fall back on map_single(), which
 		 * will grab memory from the lowest available address range.
 		 */
-		phys_addr_t paddr = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
+		phys_addr_t paddr = map_single(hwdev, 0, size,
+					       DMA_FROM_DEVICE, 0);
 		if (paddr == SWIOTLB_MAP_ERROR)
 			goto err_warn;
 
@@ -667,9 +673,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 			       (unsigned long long)dma_mask,
 			       (unsigned long long)dev_addr);
 
-			/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
+			/*
+			 * DMA_TO_DEVICE to avoid memcpy in unmap_single.
+			 * The DMA_ATTR_SKIP_CPU_SYNC is optional.
+			 */
 			swiotlb_tbl_unmap_single(hwdev, paddr,
-						 size, DMA_TO_DEVICE);
+						 size, DMA_TO_DEVICE,
+						 DMA_ATTR_SKIP_CPU_SYNC);
 			goto err_warn;
 		}
 	}
@@ -698,8 +708,12 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	if (!is_swiotlb_buffer(paddr))
 		free_pages((unsigned long)vaddr, get_order(size));
 	else
-		/* DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single */
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, DMA_TO_DEVICE);
+		/*
+		 * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single.
+		 * DMA_ATTR_SKIP_CPU_SYNC is optional.
+		 */
+		swiotlb_tbl_unmap_single(hwdev, paddr, size, DMA_TO_DEVICE,
+					 DMA_ATTR_SKIP_CPU_SYNC);
 }
 EXPORT_SYMBOL(swiotlb_free_coherent);
 
@@ -714,8 +728,8 @@ swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
 	 * When the mapping is small enough return a static buffer to limit
 	 * the damage, or panic when the transfer is too big.
 	 */
-	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
-	       "device %s\n", size, dev ? dev_name(dev) : "?");
+	dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n",
+			    size);
 
 	if (size <= io_tlb_overflow || !do_panic)
 		return;
@@ -755,7 +769,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
 
 	/* Oh well, have to allocate and map a bounce buffer. */
-	map = map_single(dev, phys, size, dir);
+	map = map_single(dev, phys, size, dir, attrs);
 	if (map == SWIOTLB_MAP_ERROR) {
 		swiotlb_full(dev, size, dir, 1);
 		return phys_to_dma(dev, io_tlb_overflow_buffer);
@@ -764,12 +778,13 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	dev_addr = phys_to_dma(dev, map);
 
 	/* Ensure that the address returned is DMA'ble */
-	if (!dma_capable(dev, dev_addr, size)) {
-		swiotlb_tbl_unmap_single(dev, map, size, dir);
-		return phys_to_dma(dev, io_tlb_overflow_buffer);
-	}
+	if (dma_capable(dev, dev_addr, size))
+		return dev_addr;
 
-	return dev_addr;
+	attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+	swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
+
+	return phys_to_dma(dev, io_tlb_overflow_buffer);
 }
 EXPORT_SYMBOL_GPL(swiotlb_map_page);
 
@@ -782,14 +797,15 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
  * whatever the device wrote there.
  */
 static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
-			 size_t size, enum dma_data_direction dir)
+			 size_t size, enum dma_data_direction dir,
+			 unsigned long attrs)
 {
 	phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 
 	if (is_swiotlb_buffer(paddr)) {
-		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir);
+		swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
 		return;
 	}
 
@@ -809,7 +825,7 @@ void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
 			size_t size, enum dma_data_direction dir,
 			unsigned long attrs)
 {
-	unmap_single(hwdev, dev_addr, size, dir);
+	unmap_single(hwdev, dev_addr, size, dir, attrs);
 }
 EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
 
@@ -891,11 +907,12 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 		if (swiotlb_force ||
 		    !dma_capable(hwdev, dev_addr, sg->length)) {
 			phys_addr_t map = map_single(hwdev, sg_phys(sg),
-						     sg->length, dir);
+						     sg->length, dir, attrs);
 			if (map == SWIOTLB_MAP_ERROR) {
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
 				swiotlb_full(hwdev, sg->length, dir, 0);
+				attrs |= DMA_ATTR_SKIP_CPU_SYNC;
 				swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
 						       attrs);
 				sg_dma_len(sgl) = 0;
@@ -910,14 +927,6 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 }
 EXPORT_SYMBOL(swiotlb_map_sg_attrs);
 
-int
-swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
-	       enum dma_data_direction dir)
-{
-	return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, 0);
-}
-EXPORT_SYMBOL(swiotlb_map_sg);
-
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
  * concerning calls here are the same as for swiotlb_unmap_page() above.
@@ -933,19 +942,11 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i)
-		unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir);
-
+		unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir,
+			     attrs);
 }
 EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
 
-void
-swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
-		 enum dma_data_direction dir)
-{
-	return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, 0);
-}
-EXPORT_SYMBOL(swiotlb_unmap_sg);
-
 /*
  * Make physical memory consistent for a set of streaming mode DMA translations
  * after a transfer.