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, 37 insertions, 70 deletions

diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index a82f10054aec..61a6889f4dee 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -151,7 +151,7 @@ config OF_IOMMU
 # IOMMU-agnostic DMA-mapping layer
 config IOMMU_DMA
 	def_bool ARM64 || X86 || S390
-	select DMA_OPS
+	select DMA_OPS_HELPERS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select IRQ_MSI_IOMMU
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 7b1dfa0665df..3672d619bcb6 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -17,6 +17,7 @@
 #include <linux/gfp.h>
 #include <linux/huge_mm.h>
 #include <linux/iommu.h>
+#include <linux/iommu-dma.h>
 #include <linux/iova.h>
 #include <linux/irq.h>
 #include <linux/list_sort.h>
@@ -1037,9 +1038,8 @@ out_unmap:
 	return NULL;
 }
 
-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 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;
 
@@ -1055,7 +1055,7 @@ static struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev,
 	return &sh->sgt;
 }
 
-static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
+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);
@@ -1066,8 +1066,8 @@ static void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
 	kfree(sh);
 }
 
-static 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_cpu(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir)
 {
 	phys_addr_t phys;
 
@@ -1081,8 +1081,8 @@ static void iommu_dma_sync_single_for_cpu(struct device *dev,
 	swiotlb_sync_single_for_cpu(dev, phys, size, dir);
 }
 
-static 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_single_for_device(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir)
 {
 	phys_addr_t phys;
 
@@ -1096,9 +1096,8 @@ static void iommu_dma_sync_single_for_device(struct device *dev,
 		arch_sync_dma_for_device(phys, size, dir);
 }
 
-static 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_cpu(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
@@ -1112,9 +1111,8 @@ static void iommu_dma_sync_sg_for_cpu(struct device *dev,
 			arch_sync_dma_for_cpu(sg_phys(sg), sg->length, dir);
 }
 
-static void iommu_dma_sync_sg_for_device(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)
 {
 	struct scatterlist *sg;
 	int i;
@@ -1129,9 +1127,9 @@ static void iommu_dma_sync_sg_for_device(struct device *dev,
 			arch_sync_dma_for_device(sg_phys(sg), sg->length, dir);
 }
 
-static 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)
+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)
 {
 	phys_addr_t phys = page_to_phys(page) + offset;
 	bool coherent = dev_is_dma_coherent(dev);
@@ -1189,7 +1187,7 @@ static dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page,
 	return iova;
 }
 
-static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
@@ -1342,8 +1340,8 @@ out_unmap:
  * impedance-matching, to be able to hand off a suitably-aligned list,
  * but still preserve the original offsets and sizes for the caller.
  */
-static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, 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)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
@@ -1462,8 +1460,8 @@ out:
 	return ret;
 }
 
-static void iommu_dma_unmap_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)
 {
 	dma_addr_t end = 0, start;
 	struct scatterlist *tmp;
@@ -1512,7 +1510,7 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		__iommu_dma_unmap(dev, start, end - start);
 }
 
-static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
+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 __iommu_dma_map(dev, phys, size,
@@ -1520,7 +1518,7 @@ static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
 			dma_get_mask(dev));
 }
 
-static void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
+void iommu_dma_unmap_resource(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	__iommu_dma_unmap(dev, handle, size);
@@ -1557,7 +1555,7 @@ static void __iommu_dma_free(struct device *dev, size_t size, void *cpu_addr)
 		dma_free_contiguous(dev, page, alloc_size);
 }
 
-static void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
+void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t handle, unsigned long attrs)
 {
 	__iommu_dma_unmap(dev, handle, size);
@@ -1601,8 +1599,8 @@ out_free_pages:
 	return NULL;
 }
 
-static void *iommu_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *handle, gfp_t gfp, unsigned long attrs)
+void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	bool coherent = dev_is_dma_coherent(dev);
 	int ioprot = dma_info_to_prot(DMA_BIDIRECTIONAL, coherent, attrs);
@@ -1635,7 +1633,7 @@ static void *iommu_dma_alloc(struct device *dev, size_t size,
 	return cpu_addr;
 }
 
-static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+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)
 {
@@ -1666,7 +1664,7 @@ static int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 			       vma->vm_page_prot);
 }
 
-static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+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)
 {
@@ -1693,19 +1691,19 @@ static int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 	return ret;
 }
 
-static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
+unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_dma_domain(dev);
 
 	return (1UL << __ffs(domain->pgsize_bitmap)) - 1;
 }
 
-static size_t iommu_dma_opt_mapping_size(void)
+size_t iommu_dma_opt_mapping_size(void)
 {
 	return iova_rcache_range();
 }
 
-static size_t iommu_dma_max_mapping_size(struct device *dev)
+size_t iommu_dma_max_mapping_size(struct device *dev)
 {
 	if (dev_is_untrusted(dev))
 		return swiotlb_max_mapping_size(dev);
@@ -1713,32 +1711,6 @@ static size_t iommu_dma_max_mapping_size(struct device *dev)
 	return SIZE_MAX;
 }
 
-static const struct dma_map_ops iommu_dma_ops = {
-	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED |
-				  DMA_F_CAN_SKIP_SYNC,
-	.alloc			= iommu_dma_alloc,
-	.free			= iommu_dma_free,
-	.alloc_pages_op		= dma_common_alloc_pages,
-	.free_pages		= dma_common_free_pages,
-	.alloc_noncontiguous	= iommu_dma_alloc_noncontiguous,
-	.free_noncontiguous	= iommu_dma_free_noncontiguous,
-	.mmap			= iommu_dma_mmap,
-	.get_sgtable		= iommu_dma_get_sgtable,
-	.map_page		= iommu_dma_map_page,
-	.unmap_page		= iommu_dma_unmap_page,
-	.map_sg			= iommu_dma_map_sg,
-	.unmap_sg		= iommu_dma_unmap_sg,
-	.sync_single_for_cpu	= iommu_dma_sync_single_for_cpu,
-	.sync_single_for_device	= iommu_dma_sync_single_for_device,
-	.sync_sg_for_cpu	= iommu_dma_sync_sg_for_cpu,
-	.sync_sg_for_device	= iommu_dma_sync_sg_for_device,
-	.map_resource		= iommu_dma_map_resource,
-	.unmap_resource		= iommu_dma_unmap_resource,
-	.get_merge_boundary	= iommu_dma_get_merge_boundary,
-	.opt_mapping_size	= iommu_dma_opt_mapping_size,
-	.max_mapping_size       = iommu_dma_max_mapping_size,
-};
-
 void iommu_setup_dma_ops(struct device *dev)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
@@ -1746,19 +1718,15 @@ void iommu_setup_dma_ops(struct device *dev)
 	if (dev_is_pci(dev))
 		dev->iommu->pci_32bit_workaround = !iommu_dma_forcedac;
 
-	if (iommu_is_dma_domain(domain)) {
-		if (iommu_dma_init_domain(domain, dev))
-			goto out_err;
-		dev->dma_ops = &iommu_dma_ops;
-	} else if (dev->dma_ops == &iommu_dma_ops) {
-		/* Clean up if we've switched *from* a DMA domain */
-		dev->dma_ops = NULL;
-	}
+	dev->dma_iommu = iommu_is_dma_domain(domain);
+	if (dev->dma_iommu && iommu_dma_init_domain(domain, dev))
+		goto out_err;
 
 	return;
 out_err:
-	 pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
-		 dev_name(dev));
+	pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n",
+		dev_name(dev));
+	dev->dma_iommu = false;
 }
 
 static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
diff --git a/drivers/iommu/intel/Kconfig b/drivers/iommu/intel/Kconfig
index f52fb39c968e..88fd32a9323c 100644
--- a/drivers/iommu/intel/Kconfig
+++ b/drivers/iommu/intel/Kconfig
@@ -12,7 +12,6 @@ config DMAR_DEBUG
 config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && X86
-	select DMA_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select IOMMUFD_DRIVER if IOMMUFD