dma-mapping: bypass indirect calls for dma-direct

Avoid expensive indirect calls in the fast path DMA mapping
operations by directly calling the dma_direct_* ops if we are using
the directly mapped DMA operations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Tested-by: Tony Luck <tony.luck@intel.com>

4 files changed, 102 insertions, 33 deletions

diff --git a/include/asm-generic/dma-mapping.h b/include/asm-generic/dma-mapping.h
index 880a292d792f..c13f46109e88 100644
--- a/include/asm-generic/dma-mapping.h
+++ b/include/asm-generic/dma-mapping.h
@@ -4,7 +4,7 @@
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return &dma_direct_ops;
+	return NULL;
 }
 
 #endif /* _ASM_GENERIC_DMA_MAPPING_H */
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 3b0a3ea3876d..b7338702592a 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -60,22 +60,5 @@ void dma_direct_free_pages(struct device *dev, size_t size, void *cpu_addr,
 struct page *__dma_direct_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs);
 void __dma_direct_free_pages(struct device *dev, size_t size, struct page *page);
-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);
-void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
-		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);
-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_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);
-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);
 int dma_direct_supported(struct device *dev, u64 mask);
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 269ee27fc3d9..f422aec0f53c 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -134,7 +134,6 @@ struct dma_map_ops {
 
 #define DMA_MAPPING_ERROR		(~(dma_addr_t)0)
 
-extern const struct dma_map_ops dma_direct_ops;
 extern const struct dma_map_ops dma_virt_ops;
 extern const struct dma_map_ops dma_dummy_ops;
 
@@ -222,6 +221,69 @@ static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 }
 #endif
 
+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);
+
+#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
+
 static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 					      size_t size,
 					      enum dma_data_direction dir,
@@ -232,9 +294,12 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
 
 	BUG_ON(!valid_dma_direction(dir));
 	debug_dma_map_single(dev, ptr, size);
-	addr = ops->map_page(dev, virt_to_page(ptr),
-			     offset_in_page(ptr), size,
-			     dir, attrs);
+	if (dma_is_direct(ops))
+		addr = dma_direct_map_page(dev, virt_to_page(ptr),
+				offset_in_page(ptr), size, dir, attrs);
+	else
+		addr = ops->map_page(dev, virt_to_page(ptr),
+				offset_in_page(ptr), size, dir, attrs);
 	debug_dma_map_page(dev, virt_to_page(ptr),
 			   offset_in_page(ptr), size,
 			   dir, addr, true);
@@ -249,7 +314,9 @@ static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
+	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, true);
 }
@@ -272,7 +339,10 @@ static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 	int ents;
 
 	BUG_ON(!valid_dma_direction(dir));
-	ents = ops->map_sg(dev, sg, nents, dir, attrs);
+	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);
 
@@ -287,7 +357,9 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg
 
 	BUG_ON(!valid_dma_direction(dir));
 	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (ops->unmap_sg)
+	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);
 }
 
@@ -301,7 +373,10 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 	dma_addr_t addr;
 
 	BUG_ON(!valid_dma_direction(dir));
-	addr = ops->map_page(dev, page, offset, size, dir, attrs);
+	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, false);
 
 	return addr;
@@ -322,7 +397,7 @@ static inline dma_addr_t dma_map_resource(struct device *dev,
 	BUG_ON(pfn_valid(PHYS_PFN(phys_addr)));
 
 	addr = phys_addr;
-	if (ops->map_resource)
+	if (ops && ops->map_resource)
 		addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
 
 	debug_dma_map_resource(dev, phys_addr, size, dir, addr);
@@ -337,7 +412,7 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_resource)
+	if (ops && ops->unmap_resource)
 		ops->unmap_resource(dev, addr, size, dir, attrs);
 	debug_dma_unmap_resource(dev, addr, size, dir);
 }
@@ -349,7 +424,9 @@ static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
+	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);
 }
@@ -368,7 +445,9 @@ static inline void dma_sync_single_for_device(struct device *dev,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
+	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);
 }
@@ -387,7 +466,9 @@ dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_cpu)
+	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);
 }
@@ -399,7 +480,9 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_device)
+	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);
 
diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 306557331d7d..69b36ed31a99 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -38,7 +38,10 @@ pgprot_t arch_dma_mmap_pgprot(struct device *dev, pgprot_t prot,
 void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		enum dma_data_direction direction);
 #else
-#define arch_dma_cache_sync NULL
+static inline void arch_dma_cache_sync(struct device *dev, void *vaddr,
+		size_t size, enum dma_data_direction direction)
+{
+}
 #endif /* CONFIG_DMA_NONCOHERENT_CACHE_SYNC */
 
 #ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_DEVICE