dma-mapping: direct calls for dma-iommu

Directly call into dma-iommu just like we have been doing for dma-direct
for a while.  This avoids the indirect call overhead for IOMMU ops and
removes the need to have DMA ops entirely for many common configurations.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

3 files changed, 152 insertions, 13 deletions

diff --git a/include/linux/device.h b/include/linux/device.h
index 34eb20f5966f..1c5280d28bc3 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -707,6 +707,8 @@ struct device_physical_location {
  *		for dma allocations.  This flag is managed by the dma ops
  *		instance from ->dma_supported.
  * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers.
+ * @dma_iommu: Device is using default IOMMU implementation for DMA and
+ *		doesn't rely on dma_ops structure.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -822,6 +824,9 @@ struct device {
 #ifdef CONFIG_DMA_NEED_SYNC
 	bool			dma_skip_sync:1;
 #endif
+#ifdef CONFIG_IOMMU_DMA
+	bool			dma_iommu:1;
+#endif
 };
 
 /**
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 02a1c825896b..077b15c93bb8 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -13,20 +13,7 @@
 struct cma;
 struct iommu_ops;
 
-/*
- * Values for struct dma_map_ops.flags:
- *
- * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can
- * handle PCI P2PDMA pages in the map_sg/unmap_sg operation.
- * DMA_F_CAN_SKIP_SYNC: DMA sync operations can be skipped if the device is
- * coherent and it's not an SWIOTLB buffer.
- */
-#define DMA_F_PCI_P2PDMA_SUPPORTED     (1 << 0)
-#define DMA_F_CAN_SKIP_SYNC            (1 << 1)
-
 struct dma_map_ops {
-	unsigned int flags;
-
 	void *(*alloc)(struct device *dev, size_t size,
 			dma_addr_t *dma_handle, gfp_t gfp,
 			unsigned long attrs);
diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h
new file mode 100644
index 000000000000..d30a58bf00fd
--- /dev/null
+++ b/include/linux/iommu-dma.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ *
+ * DMA operations that map physical memory through IOMMU.
+ */
+#ifndef _LINUX_IOMMU_DMA_H
+#define _LINUX_IOMMU_DMA_H
+
+#include <linux/dma-direction.h>
+
+#ifdef CONFIG_IOMMU_DMA
+dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp, unsigned long attrs);
+int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+unsigned long iommu_dma_get_merge_boundary(struct device *dev);
+size_t iommu_dma_opt_mapping_size(void);
+size_t iommu_dma_max_mapping_size(struct device *dev);
+void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t handle, unsigned long attrs);
+dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size,
+		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs);
+void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir);
+void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir);
+void iommu_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir);
+void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir);
+void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir);
+#else
+static inline dma_addr_t iommu_dma_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	return DMA_MAPPING_ERROR;
+}
+static inline void iommu_dma_unmap_page(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	return -EINVAL;
+}
+static inline void iommu_dma_unmap_sg(struct device *dev,
+		struct scatterlist *sg, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline void *iommu_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
+{
+	return NULL;
+}
+static inline int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	return -EINVAL;
+}
+static inline int iommu_dma_get_sgtable(struct device *dev,
+		struct sg_table *sgt, void *cpu_addr, dma_addr_t dma_addr,
+		size_t size, unsigned long attrs)
+{
+	return -EINVAL;
+}
+static inline unsigned long iommu_dma_get_merge_boundary(struct device *dev)
+{
+	return 0;
+}
+static inline size_t iommu_dma_opt_mapping_size(void)
+{
+	return 0;
+}
+static inline size_t iommu_dma_max_mapping_size(struct device *dev)
+{
+	return 0;
+}
+static inline void iommu_dma_free(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t handle, unsigned long attrs)
+{
+}
+static inline dma_addr_t iommu_dma_map_resource(struct device *dev,
+		phys_addr_t phys, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	return DMA_MAPPING_ERROR;
+}
+static inline void iommu_dma_unmap_resource(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+}
+static inline struct sg_table *
+iommu_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 iommu_dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir)
+{
+}
+static inline void iommu_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction dir)
+{
+}
+static inline void iommu_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+{
+}
+static inline void iommu_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nelems,
+		enum dma_data_direction dir)
+{
+}
+static inline void iommu_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nelems,
+		enum dma_data_direction dir)
+{
+}
+#endif /* CONFIG_IOMMU_DMA */
+#endif /* _LINUX_IOMMU_DMA_H */