Merge tag 'dma-mapping-5.9' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - make support for dma_ops optional

 - move more code out of line

 - add generic support for a dma_ops bypass mode

 - misc cleanups

* tag 'dma-mapping-5.9' of git://git.infradead.org/users/hch/dma-mapping:
  dma-contiguous: cleanup dma_alloc_contiguous
  dma-debug: use named initializers for dir2name
  powerpc: use the generic dma_ops_bypass mode
  dma-mapping: add a dma_ops_bypass flag to struct device
  dma-mapping: make support for dma ops optional
  dma-mapping: inline the fast path dma-direct calls
  dma-mapping: move the remaining DMA API calls out of line

3 files changed, 143 insertions, 223 deletions

diff --git a/include/linux/device.h b/include/linux/device.h
index 4e2e9d3a2eda..06d3b7622082 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -525,6 +525,11 @@ struct dev_links_info {
  *		  sync_state() callback.
  * @dma_coherent: this particular device is dma coherent, even if the
  *		architecture supports non-coherent devices.
+ * @dma_ops_bypass: If set to %true then the dma_ops are bypassed for the
+ *		streaming DMA operations (->map_* / ->unmap_* / ->sync_*),
+ *		and optionall (if the coherent mask is large enough) also
+ *		for dma allocations.  This flag is managed by the dma ops
+ *		instance from ->dma_supported.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -574,8 +579,9 @@ struct device {
 #ifdef CONFIG_GENERIC_MSI_IRQ
 	struct list_head	msi_list;
 #endif
-
+#ifdef CONFIG_DMA_OPS
 	const struct dma_map_ops *dma_ops;
+#endif
 	u64		*dma_mask;	/* dma mask (if dma'able device) */
 	u64		coherent_dma_mask;/* Like dma_mask, but for
 					     alloc_coherent mappings as
@@ -628,6 +634,9 @@ struct device {
     defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 	bool			dma_coherent:1;
 #endif
+#ifdef CONFIG_DMA_OPS_BYPASS
+	bool			dma_ops_bypass : 1;
+#endif
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index ab2e20cba951..5a3ce2a24794 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -1,10 +1,16 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Internals of the DMA direct mapping implementation.  Only for use by the
+ * DMA mapping code and IOMMU drivers.
+ */
 #ifndef _LINUX_DMA_DIRECT_H
 #define _LINUX_DMA_DIRECT_H 1
 
 #include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/memblock.h> /* for min_low_pfn */
 #include <linux/mem_encrypt.h>
+#include <linux/swiotlb.h>
 
 extern unsigned int zone_dma_bits;
 
@@ -87,4 +93,102 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 		unsigned long attrs);
 int dma_direct_supported(struct device *dev, u64 mask);
 bool dma_direct_need_sync(struct device *dev, dma_addr_t dma_addr);
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+size_t dma_direct_max_mapping_size(struct device *dev);
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
+    defined(CONFIG_SWIOTLB)
+void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
+		int nents, enum dma_data_direction dir, unsigned long attrs);
+void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
+#else
+static inline void dma_direct_unmap_sg(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+}
+#endif
+
+static inline void dma_direct_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_DEVICE);
+
+	if (!dev_is_dma_coherent(dev))
+		arch_sync_dma_for_device(paddr, size, dir);
+}
+
+static inline void dma_direct_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	phys_addr_t paddr = dma_to_phys(dev, addr);
+
+	if (!dev_is_dma_coherent(dev)) {
+		arch_sync_dma_for_cpu(paddr, size, dir);
+		arch_sync_dma_for_cpu_all();
+	}
+
+	if (unlikely(is_swiotlb_buffer(paddr)))
+		swiotlb_tbl_sync_single(dev, paddr, size, dir, SYNC_FOR_CPU);
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+	dma_addr_t dma_addr = phys_to_dma(dev, phys);
+
+	if (unlikely(swiotlb_force == SWIOTLB_FORCE))
+		return swiotlb_map(dev, phys, size, dir, attrs);
+
+	if (unlikely(!dma_capable(dev, dma_addr, size, true))) {
+		if (swiotlb_force != SWIOTLB_NO_FORCE)
+			return swiotlb_map(dev, phys, size, dir, attrs);
+
+		dev_WARN_ONCE(dev, 1,
+			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
+		return DMA_MAPPING_ERROR;
+	}
+
+	if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(phys, size, dir);
+	return dma_addr;
+}
+
+static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	phys_addr_t phys = dma_to_phys(dev, addr);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
+
+	if (unlikely(is_swiotlb_buffer(phys)))
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
+}
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index a33ed3954ed4..39da883c8619 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -188,76 +188,10 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_DECLARE_COHERENT */
 
-static inline bool dma_is_direct(const struct dma_map_ops *ops)
-{
-	return likely(!ops);
-}
-
-/*
- * All the dma_direct_* declarations are here just for the indirect call bypass,
- * and must not be used directly drivers!
- */
-dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs);
-int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
-dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir);
-void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_direct_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
-    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL) || \
-    defined(CONFIG_SWIOTLB)
-void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sgl,
-		int nents, enum dma_data_direction dir, unsigned long attrs);
-void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir);
-void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir);
-#else
-static inline void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-}
-static inline void dma_direct_unmap_sg(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-}
-static inline void dma_direct_sync_single_for_cpu(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_direct_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
-{
-}
-#endif
-
-size_t dma_direct_max_mapping_size(struct device *dev);
-
 #ifdef CONFIG_HAS_DMA
 #include <asm/dma-mapping.h>
 
+#ifdef CONFIG_DMA_OPS
 static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 {
 	if (dev->dma_ops)
@@ -270,165 +204,16 @@ static inline void set_dma_ops(struct device *dev,
 {
 	dev->dma_ops = dma_ops;
 }
-
-static inline dma_addr_t dma_map_page_attrs(struct device *dev,
-		struct page *page, size_t offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
-	else
-		addr = ops->map_page(dev, page, offset, size, dir, attrs);
-	debug_dma_map_page(dev, page, offset, size, dir, addr);
-
-	return addr;
-}
-
-static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_unmap_page(dev, addr, size, dir, attrs);
-	else if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, attrs);
-	debug_dma_unmap_page(dev, addr, size, dir);
-}
-
-/*
- * dma_maps_sg_attrs returns 0 on error and > 0 on success.
- * It should never return a value < 0.
- */
-static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	int ents;
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
-	else
-		ents = ops->map_sg(dev, sg, nents, dir, attrs);
-	BUG_ON(ents < 0);
-	debug_dma_map_sg(dev, sg, nents, ents, dir);
-
-	return ents;
-}
-
-static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-				      int nents, enum dma_data_direction dir,
-				      unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (dma_is_direct(ops))
-		dma_direct_unmap_sg(dev, sg, nents, dir, attrs);
-	else if (ops->unmap_sg)
-		ops->unmap_sg(dev, sg, nents, dir, attrs);
-}
-
-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)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr = DMA_MAPPING_ERROR;
-
-	BUG_ON(!valid_dma_direction(dir));
-
-	/* Don't allow RAM to be mapped */
-	if (WARN_ON_ONCE(pfn_valid(PHYS_PFN(phys_addr))))
-		return DMA_MAPPING_ERROR;
-
-	if (dma_is_direct(ops))
-		addr = dma_direct_map_resource(dev, phys_addr, size, dir, attrs);
-	else 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)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (!dma_is_direct(ops) && 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)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
-	else if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(dev, addr, size, dir);
-	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-					      dma_addr_t addr, size_t size,
-					      enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_single_for_device(dev, addr, size, dir);
-	else if (ops->sync_single_for_device)
-		ops->sync_single_for_device(dev, addr, size, dir);
-	debug_dma_sync_single_for_device(dev, addr, size, dir);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-		    int nelems, enum dma_data_direction dir)
+#else /* CONFIG_DMA_OPS */
+static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_sg_for_cpu(dev, sg, nelems, dir);
-	else if (ops->sync_sg_for_cpu)
-		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+	return NULL;
 }
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-		       int nelems, enum dma_data_direction dir)
+static inline void set_dma_ops(struct device *dev,
+			       const struct dma_map_ops *dma_ops)
 {
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (dma_is_direct(ops))
-		dma_direct_sync_sg_for_device(dev, sg, nelems, dir);
-	else if (ops->sync_sg_for_device)
-		ops->sync_sg_for_device(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
-
 }
+#endif /* CONFIG_DMA_OPS */
 
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
@@ -439,6 +224,28 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 	return 0;
 }
 
+dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir,
+				      unsigned long attrs);
+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);
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir);
+void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir);
+void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir);
+void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir);
 void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t flag, unsigned long attrs);
 void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,