[PATCH v4 0/6] Preparation to .map_page and .unmap_page removal

[PATCH v4 0/6] Preparation to .map_page and .unmap_page removal

[Leon Romanovsky]

Changelog:
v4:
 * Added Jason's ROB tags
 * Added "xen: swiotlb ..." patch to the list of patches which had .map_resource
 * Added extra patch "ARM: dma-mapping: Reduce ..." to remove struct
   page as much as possible.
 * Added call to .map_phys/.unmap_phys to dma_common_*_pages() functions.
v3: https://lore.kernel.org/all/cover.1758006942.git.leon@kernel.org
 * Rewrote the series to allow combination of .map_resource and
 * .map_page
   to one flow.
 * Added two new patches to convert and remove .map_resource.
v2: https://lore.kernel.org/all/cover.1752734252.git.leon@kernel.org/
 * Added default "else" section without map_phys and map_page
   callbacks (impossible).
v1: https://lore.kernel.org/all/cover.1753003879.git.leon@kernel.org
 * Changed "else if" instead of "if".
v0: https://lore.kernel.org/all/cover.1752734252.git.leon@kernel.org
---------------------------------------------------------------------

This is followup to "dma-mapping: migrate to physical address-based API" series
https://lore.kernel.org/all/cover.1757423202.git.leonro@nvidia.com

Thanks

Leon Romanovsky (6):
  dma-mapping: prepare dma_map_ops to conversion to physical address
  dma-mapping: convert dummy ops to physical address mapping
  ARM: dma-mapping: Reduce struct page exposure in arch_sync_dma*()
  ARM: dma-mapping: Switch to physical address mapping callbacks
  xen: swiotlb: Switch to physical address mapping callbacks
  dma-mapping: remove unused mapping resource callbacks

 arch/arm/mm/dma-mapping.c   | 180 +++++++++++-------------------------
 drivers/xen/swiotlb-xen.c   |  63 ++++++-------
 include/linux/dma-map-ops.h |  13 +--
 kernel/dma/dummy.c          |  13 ++-
 kernel/dma/mapping.c        |  20 ++--
 kernel/dma/ops_helpers.c    |  12 ++-
 6 files changed, 113 insertions(+), 188 deletions(-)

-- 
2.51.0

[PATCH v4 1/6] dma-mapping: prepare dma_map_ops to conversion to physical address

[Leon Romanovsky]

From: Leon Romanovsky <leonro@nvidia.com>

Add new .map_phys() and .unmap_phys() callbacks to dma_map_ops as a
preparation to replace .map_page() and .unmap_page() respectively.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 include/linux/dma-map-ops.h |  7 +++++++
 kernel/dma/mapping.c        |  4 ++++
 kernel/dma/ops_helpers.c    | 12 ++++++++++--
 3 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 71f5b30254159..25603cb273769 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -37,6 +37,13 @@ struct dma_map_ops {
 	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
 			size_t size, enum dma_data_direction dir,
 			unsigned long attrs);
+
+	dma_addr_t (*map_phys)(struct device *dev, phys_addr_t phys,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*unmap_phys)(struct device *dev, dma_addr_t dma_handle,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
 	/*
 	 * map_sg should return a negative error code on error. See
 	 * dma_map_sgtable() for a list of appropriate error codes
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index fe7472f13b106..4080aebe5debb 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -169,6 +169,8 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 		addr = dma_direct_map_phys(dev, phys, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
+	else if (ops->map_phys)
+		addr = ops->map_phys(dev, phys, size, dir, attrs);
 	else if (is_mmio) {
 		if (!ops->map_resource)
 			return DMA_MAPPING_ERROR;
@@ -223,6 +225,8 @@ void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
 		dma_direct_unmap_phys(dev, addr, size, dir, attrs);
 	else if (use_dma_iommu(dev))
 		iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
+	else if (ops->unmap_phys)
+		ops->unmap_phys(dev, addr, size, dir, attrs);
 	else if (is_mmio) {
 		if (ops->unmap_resource)
 			ops->unmap_resource(dev, addr, size, dir, attrs);
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 6f9d604d9d406..1eccbdbc99c1e 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -64,6 +64,7 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	struct page *page;
+	phys_addr_t phys;
 
 	page = dma_alloc_contiguous(dev, size, gfp);
 	if (!page)
@@ -71,9 +72,13 @@ struct page *dma_common_alloc_pages(struct device *dev, size_t size,
 	if (!page)
 		return NULL;
 
+	phys = page_to_phys(page);
 	if (use_dma_iommu(dev))
-		*dma_handle = iommu_dma_map_phys(dev, page_to_phys(page), size,
-						 dir, DMA_ATTR_SKIP_CPU_SYNC);
+		*dma_handle = iommu_dma_map_phys(dev, phys, size, dir,
+						 DMA_ATTR_SKIP_CPU_SYNC);
+	else if (ops->map_phys)
+		*dma_handle = ops->map_phys(dev, phys, size, dir,
+					    DMA_ATTR_SKIP_CPU_SYNC);
 	else
 		*dma_handle = ops->map_page(dev, page, 0, size, dir,
 					    DMA_ATTR_SKIP_CPU_SYNC);
@@ -94,6 +99,9 @@ void dma_common_free_pages(struct device *dev, size_t size, struct page *page,
 	if (use_dma_iommu(dev))
 		iommu_dma_unmap_phys(dev, dma_handle, size, dir,
 				     DMA_ATTR_SKIP_CPU_SYNC);
+	else if (ops->unmap_phys)
+		ops->unmap_phys(dev, dma_handle, size, dir,
+				DMA_ATTR_SKIP_CPU_SYNC);
 	else if (ops->unmap_page)
 		ops->unmap_page(dev, dma_handle, size, dir,
 				DMA_ATTR_SKIP_CPU_SYNC);
-- 
2.51.0

[PATCH v4 2/6] dma-mapping: convert dummy ops to physical address mapping

[Leon Romanovsky]

From: Leon Romanovsky <leonro@nvidia.com>

Change dma_dummy_map_page and dma_dummy_unmap_page routines
to accept physical address and rename them.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 kernel/dma/dummy.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c
index 92de80e5b057e..16a51736a2a39 100644
--- a/kernel/dma/dummy.c
+++ b/kernel/dma/dummy.c
@@ -11,17 +11,16 @@ static int dma_dummy_mmap(struct device *dev, struct vm_area_struct *vma,
 	return -ENXIO;
 }
 
-static dma_addr_t dma_dummy_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
+static dma_addr_t dma_dummy_map_phys(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	return DMA_MAPPING_ERROR;
 }
-static void dma_dummy_unmap_page(struct device *dev, dma_addr_t dma_handle,
+static void dma_dummy_unmap_phys(struct device *dev, dma_addr_t dma_handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	/*
-	 * Dummy ops doesn't support map_page, so unmap_page should never be
+	 * Dummy ops doesn't support map_phys, so unmap_page should never be
 	 * called.
 	 */
 	WARN_ON_ONCE(true);
@@ -51,8 +50,8 @@ static int dma_dummy_supported(struct device *hwdev, u64 mask)
 
 const struct dma_map_ops dma_dummy_ops = {
 	.mmap                   = dma_dummy_mmap,
-	.map_page               = dma_dummy_map_page,
-	.unmap_page             = dma_dummy_unmap_page,
+	.map_phys               = dma_dummy_map_phys,
+	.unmap_phys             = dma_dummy_unmap_phys,
 	.map_sg                 = dma_dummy_map_sg,
 	.unmap_sg               = dma_dummy_unmap_sg,
 	.dma_supported          = dma_dummy_supported,
-- 
2.51.0

[PATCH v4 3/6] ARM: dma-mapping: Reduce struct page exposure in arch_sync_dma*()

[Leon Romanovsky]

From: Leon Romanovsky <leonro@nvidia.com>

As a preparation to changing from .map_page to use .map_phys DMA
callbacks, convert arch_sync_dma*() functions to use physical addresses
instead of struct page.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 arch/arm/mm/dma-mapping.c | 82 +++++++++++++++------------------------
 1 file changed, 31 insertions(+), 51 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 88c2d68a69c9e..449fe6bf525e5 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -624,16 +624,14 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 	kfree(buf);
 }
 
-static void dma_cache_maint_page(struct page *page, unsigned long offset,
-	size_t size, enum dma_data_direction dir,
+static void dma_cache_maint_page(phys_addr_t phys, size_t size,
+	enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
 {
-	unsigned long pfn;
+	unsigned long offset = offset_in_page(phys);
+	unsigned long pfn = __phys_to_pfn(phys);
 	size_t left = size;
 
-	pfn = page_to_pfn(page) + offset / PAGE_SIZE;
-	offset %= PAGE_SIZE;
-
 	/*
 	 * A single sg entry may refer to multiple physically contiguous
 	 * pages.  But we still need to process highmem pages individually.
@@ -644,17 +642,18 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 		size_t len = left;
 		void *vaddr;
 
-		page = pfn_to_page(pfn);
-
-		if (PageHighMem(page)) {
+		phys = __pfn_to_phys(pfn);
+		if (PhysHighMem(phys)) {
 			if (len + offset > PAGE_SIZE)
 				len = PAGE_SIZE - offset;
 
 			if (cache_is_vipt_nonaliasing()) {
-				vaddr = kmap_atomic(page);
+				vaddr = kmap_atomic_pfn(pfn);
 				op(vaddr + offset, len, dir);
 				kunmap_atomic(vaddr);
 			} else {
+				struct page *page = phys_to_page(phys);
+
 				vaddr = kmap_high_get(page);
 				if (vaddr) {
 					op(vaddr + offset, len, dir);
@@ -662,7 +661,8 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
 				}
 			}
 		} else {
-			vaddr = page_address(page) + offset;
+			phys += offset;
+			vaddr = phys_to_virt(phys);
 			op(vaddr, len, dir);
 		}
 		offset = 0;
@@ -676,14 +676,11 @@ static void dma_cache_maint_page(struct page *page, unsigned long offset,
  * Note: Drivers should NOT use this function directly.
  * Use the driver DMA support - see dma-mapping.h (dma_sync_*)
  */
-static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
-	size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
+			      enum dma_data_direction dir)
 {
-	phys_addr_t paddr;
-
-	dma_cache_maint_page(page, off, size, dir, dmac_map_area);
+	dma_cache_maint_page(paddr, size, dir, dmac_map_area);
 
-	paddr = page_to_phys(page) + off;
 	if (dir == DMA_FROM_DEVICE) {
 		outer_inv_range(paddr, paddr + size);
 	} else {
@@ -692,17 +689,15 @@ static void __dma_page_cpu_to_dev(struct page *page, unsigned long off,
 	/* FIXME: non-speculating: flush on bidirectional mappings? */
 }
 
-static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
-	size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
+			   enum dma_data_direction dir)
 {
-	phys_addr_t paddr = page_to_phys(page) + off;
-
 	/* FIXME: non-speculating: not required */
 	/* in any case, don't bother invalidating if DMA to device */
 	if (dir != DMA_TO_DEVICE) {
 		outer_inv_range(paddr, paddr + size);
 
-		dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+		dma_cache_maint_page(paddr, size, dir, dmac_unmap_area);
 	}
 
 	/*
@@ -1205,7 +1200,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
 		if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
+			arch_sync_dma_for_device(sg_phys(s), s->length, dir);
 
 		prot = __dma_info_to_prot(dir, attrs);
 
@@ -1307,8 +1302,7 @@ static void arm_iommu_unmap_sg(struct device *dev,
 			__iommu_remove_mapping(dev, sg_dma_address(s),
 					       sg_dma_len(s));
 		if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			__dma_page_dev_to_cpu(sg_page(s), s->offset,
-					      s->length, dir);
+			arch_sync_dma_for_cpu(sg_phys(s), s->length, dir);
 	}
 }
 
@@ -1330,7 +1324,7 @@ static void arm_iommu_sync_sg_for_cpu(struct device *dev,
 		return;
 
 	for_each_sg(sg, s, nents, i)
-		__dma_page_dev_to_cpu(sg_page(s), s->offset, s->length, dir);
+		arch_sync_dma_for_cpu(sg_phys(s), s->length, dir);
 
 }
 
@@ -1352,7 +1346,7 @@ static void arm_iommu_sync_sg_for_device(struct device *dev,
 		return;
 
 	for_each_sg(sg, s, nents, i)
-		__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
+		arch_sync_dma_for_device(sg_phys(s), s->length, dir);
 }
 
 /**
@@ -1374,7 +1368,7 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
 	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_page_cpu_to_dev(page, offset, size, dir);
+		arch_sync_dma_for_device(page_to_phys(page), offset, size, dir);
 
 	dma_addr = __alloc_iova(mapping, len);
 	if (dma_addr == DMA_MAPPING_ERROR)
@@ -1407,7 +1401,6 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page;
 	int offset = handle & ~PAGE_MASK;
 	int len = PAGE_ALIGN(size + offset);
 
@@ -1415,8 +1408,9 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 		return;
 
 	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
-		page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
-		__dma_page_dev_to_cpu(page, offset, size, dir);
+		phys_addr_t phys = iommu_iova_to_phys(mapping->domain, iova);
+
+		arch_sync_dma_for_cpu(phys + offset, size, dir);
 	}
 
 	iommu_unmap(mapping->domain, iova, len);
@@ -1485,14 +1479,14 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page;
 	unsigned int offset = handle & ~PAGE_MASK;
+	phys_addr_t phys;
 
 	if (dev->dma_coherent || !iova)
 		return;
 
-	page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
-	__dma_page_dev_to_cpu(page, offset, size, dir);
+	phys = iommu_iova_to_phys(mapping->domain, iova);
+	arch_sync_dma_for_cpu(phys + offset, size, dir);
 }
 
 static void arm_iommu_sync_single_for_device(struct device *dev,
@@ -1500,14 +1494,14 @@ static void arm_iommu_sync_single_for_device(struct device *dev,
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page;
 	unsigned int offset = handle & ~PAGE_MASK;
+	phys_addr_t phys;
 
 	if (dev->dma_coherent || !iova)
 		return;
 
-	page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
-	__dma_page_cpu_to_dev(page, offset, size, dir);
+	phys = iommu_iova_to_phys(mapping->domain, iova);
+	arch_sync_dma_for_device(phys + offset, size, dir);
 }
 
 static const struct dma_map_ops iommu_ops = {
@@ -1794,20 +1788,6 @@ void arch_teardown_dma_ops(struct device *dev)
 	set_dma_ops(dev, NULL);
 }
 
-void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-	__dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
-			      size, dir);
-}
-
-void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size,
-		enum dma_data_direction dir)
-{
-	__dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
-			      size, dir);
-}
-
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs)
 {
-- 
2.51.0

[PATCH v4 4/6] ARM: dma-mapping: Switch to physical address mapping callbacks

[Leon Romanovsky]

From: Leon Romanovsky <leonro@nvidia.com>

Combine resource and page mappings routines to one function, which
handles both these flows at the same manner. This conversion allows
us to remove .map_resource/.unmap_resource callbacks completely.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 arch/arm/mm/dma-mapping.c | 100 +++++++++-----------------------------
 1 file changed, 23 insertions(+), 77 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 449fe6bf525e5..a6606ba0584f4 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -732,6 +732,9 @@ static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
 	if (attrs & DMA_ATTR_PRIVILEGED)
 		prot |= IOMMU_PRIV;
 
+	if (attrs & DMA_ATTR_MMIO)
+		prot |= IOMMU_MMIO;
+
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
 		return prot | IOMMU_READ | IOMMU_WRITE;
@@ -1350,25 +1353,27 @@ static void arm_iommu_sync_sg_for_device(struct device *dev,
 }
 
 /**
- * arm_iommu_map_page
+ * arm_iommu_map_phys
  * @dev: valid struct device pointer
- * @page: page that buffer resides in
- * @offset: offset into page for start of buffer
+ * @phys: physical address that buffer resides in
  * @size: size of buffer to map
  * @dir: DMA transfer direction
+ * @attrs: DMA mapping attributes
  *
  * IOMMU aware version of arm_dma_map_page()
  */
-static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size, enum dma_data_direction dir,
-	     unsigned long attrs)
+static dma_addr_t arm_iommu_map_phys(struct device *dev, phys_addr_t phys,
+	     size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
+	int len = PAGE_ALIGN(size + offset_in_page(phys));
+	phys_addr_t addr = phys & PAGE_MASK;
 	dma_addr_t dma_addr;
-	int ret, prot, len = PAGE_ALIGN(size + offset);
+	int ret, prot;
 
-	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		arch_sync_dma_for_device(page_to_phys(page), offset, size, dir);
+	if (!dev->dma_coherent &&
+	    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO)))
+		arch_sync_dma_for_device(phys, size, dir);
 
 	dma_addr = __alloc_iova(mapping, len);
 	if (dma_addr == DMA_MAPPING_ERROR)
@@ -1376,12 +1381,11 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
 
 	prot = __dma_info_to_prot(dir, attrs);
 
-	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len,
-			prot, GFP_KERNEL);
+	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL);
 	if (ret < 0)
 		goto fail;
 
-	return dma_addr + offset;
+	return dma_addr + offset_in_page(phys);
 fail:
 	__free_iova(mapping, dma_addr, len);
 	return DMA_MAPPING_ERROR;
@@ -1393,10 +1397,11 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
  * @handle: DMA address of buffer
  * @size: size of buffer (same as passed to dma_map_page)
  * @dir: DMA transfer direction (same as passed to dma_map_page)
+ * @attrs: DMA mapping attributes
  *
- * IOMMU aware version of arm_dma_unmap_page()
+ * IOMMU aware version of arm_dma_unmap_phys()
  */
-static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
+static void arm_iommu_unmap_phys(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
@@ -1407,7 +1412,8 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 	if (!iova)
 		return;
 
-	if (!dev->dma_coherent && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
+	if (!dev->dma_coherent &&
+	    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))) {
 		phys_addr_t phys = iommu_iova_to_phys(mapping->domain, iova);
 
 		arch_sync_dma_for_cpu(phys + offset, size, dir);
@@ -1417,63 +1423,6 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 	__free_iova(mapping, iova, len);
 }
 
-/**
- * arm_iommu_map_resource - map a device resource for DMA
- * @dev: valid struct device pointer
- * @phys_addr: physical address of resource
- * @size: size of resource to map
- * @dir: DMA transfer direction
- */
-static dma_addr_t arm_iommu_map_resource(struct device *dev,
-		phys_addr_t phys_addr, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
-	dma_addr_t dma_addr;
-	int ret, prot;
-	phys_addr_t addr = phys_addr & PAGE_MASK;
-	unsigned int offset = phys_addr & ~PAGE_MASK;
-	size_t len = PAGE_ALIGN(size + offset);
-
-	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == DMA_MAPPING_ERROR)
-		return dma_addr;
-
-	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
-
-	ret = iommu_map(mapping->domain, dma_addr, addr, len, prot, GFP_KERNEL);
-	if (ret < 0)
-		goto fail;
-
-	return dma_addr + offset;
-fail:
-	__free_iova(mapping, dma_addr, len);
-	return DMA_MAPPING_ERROR;
-}
-
-/**
- * arm_iommu_unmap_resource - unmap a device DMA resource
- * @dev: valid struct device pointer
- * @dma_handle: DMA address to resource
- * @size: size of resource to map
- * @dir: DMA transfer direction
- */
-static void arm_iommu_unmap_resource(struct device *dev, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
-	dma_addr_t iova = dma_handle & PAGE_MASK;
-	unsigned int offset = dma_handle & ~PAGE_MASK;
-	size_t len = PAGE_ALIGN(size + offset);
-
-	if (!iova)
-		return;
-
-	iommu_unmap(mapping->domain, iova, len);
-	__free_iova(mapping, iova, len);
-}
-
 static void arm_iommu_sync_single_for_cpu(struct device *dev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
@@ -1510,8 +1459,8 @@ static const struct dma_map_ops iommu_ops = {
 	.mmap		= arm_iommu_mmap_attrs,
 	.get_sgtable	= arm_iommu_get_sgtable,
 
-	.map_page		= arm_iommu_map_page,
-	.unmap_page		= arm_iommu_unmap_page,
+	.map_phys		= arm_iommu_map_phys,
+	.unmap_phys		= arm_iommu_unmap_phys,
 	.sync_single_for_cpu	= arm_iommu_sync_single_for_cpu,
 	.sync_single_for_device	= arm_iommu_sync_single_for_device,
 
@@ -1519,9 +1468,6 @@ static const struct dma_map_ops iommu_ops = {
 	.unmap_sg		= arm_iommu_unmap_sg,
 	.sync_sg_for_cpu	= arm_iommu_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_iommu_sync_sg_for_device,
-
-	.map_resource		= arm_iommu_map_resource,
-	.unmap_resource		= arm_iommu_unmap_resource,
 };
 
 /**
-- 
2.51.0

[PATCH v4 5/6] xen: swiotlb: Switch to physical address mapping callbacks

[Leon Romanovsky]

From: Leon Romanovsky <leonro@nvidia.com>

Combine resource and page mappings routines to one function
and remove .map_resource/.unmap_resource callbacks completely.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/xen/swiotlb-xen.c | 63 ++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 34 deletions(-)

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index dd7747a2de879..48936179c940b 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -200,17 +200,32 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr,
  * physical address to use is returned.
  *
  * Once the device is given the dma address, the device owns this memory until
- * either xen_swiotlb_unmap_page or xen_swiotlb_dma_sync_single is performed.
+ * either xen_swiotlb_unmap_phys or xen_swiotlb_dma_sync_single is performed.
  */
-static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
-				unsigned long offset, size_t size,
-				enum dma_data_direction dir,
+static dma_addr_t xen_swiotlb_map_phys(struct device *dev, phys_addr_t phys,
+				size_t size, enum dma_data_direction dir,
 				unsigned long attrs)
 {
-	phys_addr_t map, phys = page_to_phys(page) + offset;
-	dma_addr_t dev_addr = xen_phys_to_dma(dev, phys);
+	dma_addr_t dev_addr;
+	phys_addr_t map;
 
 	BUG_ON(dir == DMA_NONE);
+
+	if (attrs & DMA_ATTR_MMIO) {
+		if (unlikely(!dma_capable(dev, phys, size, false))) {
+			dev_err_once(
+				dev,
+				"DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
+				&dma_addr, size, *dev->dma_mask,
+				dev->bus_dma_limit);
+			WARN_ON_ONCE(1);
+			return DMA_MAPPING_ERROR;
+		}
+		return phys;
+	}
+
+	dev_addr = xen_phys_to_dma(dev, phys);
+
 	/*
 	 * If the address happens to be in the device's DMA window,
 	 * we can safely return the device addr and not worry about bounce
@@ -257,13 +272,13 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page,
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
- * match what was provided for in a previous xen_swiotlb_map_page call.  All
+ * match what was provided for in a previous xen_swiotlb_map_phys call.  All
  * other usages are undefined.
  *
  * After this call, reads by the cpu to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
-static void xen_swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+static void xen_swiotlb_unmap_phys(struct device *hwdev, dma_addr_t dev_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 	phys_addr_t paddr = xen_dma_to_phys(hwdev, dev_addr);
@@ -325,7 +340,7 @@ xen_swiotlb_sync_single_for_device(struct device *dev, dma_addr_t dma_addr,
 
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_page() above.
+ * concerning calls here are the same as for swiotlb_unmap_phys() above.
  */
 static void
 xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
@@ -337,7 +352,7 @@ xen_swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i)
-		xen_swiotlb_unmap_page(hwdev, sg->dma_address, sg_dma_len(sg),
+		xen_swiotlb_unmap_phys(hwdev, sg->dma_address, sg_dma_len(sg),
 				dir, attrs);
 
 }
@@ -352,8 +367,8 @@ xen_swiotlb_map_sg(struct device *dev, struct scatterlist *sgl, int nelems,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i) {
-		sg->dma_address = xen_swiotlb_map_page(dev, sg_page(sg),
-				sg->offset, sg->length, dir, attrs);
+		sg->dma_address = xen_swiotlb_map_phys(dev, sg_phys(sg),
+				sg->length, dir, attrs);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
 			goto out_unmap;
 		sg_dma_len(sg) = sg->length;
@@ -392,25 +407,6 @@ xen_swiotlb_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
 	}
 }
 
-static dma_addr_t xen_swiotlb_direct_map_resource(struct device *dev,
-						  phys_addr_t paddr,
-						  size_t size,
-						  enum dma_data_direction dir,
-						  unsigned long attrs)
-{
-	dma_addr_t dma_addr = paddr;
-
-	if (unlikely(!dma_capable(dev, dma_addr, size, false))) {
-		dev_err_once(dev,
-			     "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-			     &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit);
-		WARN_ON_ONCE(1);
-		return DMA_MAPPING_ERROR;
-	}
-
-	return dma_addr;
-}
-
 /*
  * Return whether the given device DMA address mask can be supported
  * properly.  For example, if your device can only drive the low 24-bits
@@ -437,13 +433,12 @@ const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.sync_sg_for_device = xen_swiotlb_sync_sg_for_device,
 	.map_sg = xen_swiotlb_map_sg,
 	.unmap_sg = xen_swiotlb_unmap_sg,
-	.map_page = xen_swiotlb_map_page,
-	.unmap_page = xen_swiotlb_unmap_page,
+	.map_phys = xen_swiotlb_map_phys,
+	.unmap_phys = xen_swiotlb_unmap_phys,
 	.dma_supported = xen_swiotlb_dma_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
 	.alloc_pages_op = dma_common_alloc_pages,
 	.free_pages = dma_common_free_pages,
 	.max_mapping_size = swiotlb_max_mapping_size,
-	.map_resource = xen_swiotlb_direct_map_resource,
 };
-- 
2.51.0

[PATCH v4 6/6] dma-mapping: remove unused mapping resource callbacks

[Leon Romanovsky]

From: Leon Romanovsky <leonro@nvidia.com>

After ARM and XEN conversions to use physical addresses for the mapping,
there are no in-kernel users for map_resource/unmap_resource callbacks,
so remove them.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 include/linux/dma-map-ops.h |  6 ------
 kernel/dma/mapping.c        | 16 ++++------------
 2 files changed, 4 insertions(+), 18 deletions(-)

diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 25603cb273769..a2ec1566aa270 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -53,12 +53,6 @@ struct dma_map_ops {
 			enum dma_data_direction dir, unsigned long attrs);
 	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents,
 			enum dma_data_direction dir, unsigned long attrs);
-	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
-			size_t size, enum dma_data_direction dir,
-			unsigned long attrs);
-	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
-			size_t size, enum dma_data_direction dir,
-			unsigned long attrs);
 	void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle,
 			size_t size, enum dma_data_direction dir);
 	void (*sync_single_for_device)(struct device *dev,
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 4080aebe5debb..32a85bfdf873a 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -157,7 +157,7 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	bool is_mmio = attrs & DMA_ATTR_MMIO;
-	dma_addr_t addr;
+	dma_addr_t addr = DMA_MAPPING_ERROR;
 
 	BUG_ON(!valid_dma_direction(dir));
 
@@ -171,18 +171,13 @@ dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
 		addr = iommu_dma_map_phys(dev, phys, size, dir, attrs);
 	else if (ops->map_phys)
 		addr = ops->map_phys(dev, phys, size, dir, attrs);
-	else if (is_mmio) {
-		if (!ops->map_resource)
-			return DMA_MAPPING_ERROR;
-
-		addr = ops->map_resource(dev, phys, size, dir, attrs);
-	} else {
+	else if (!is_mmio && ops->map_page) {
 		struct page *page = phys_to_page(phys);
 		size_t offset = offset_in_page(phys);
 
 		/*
 		 * The dma_ops API contract for ops->map_page() requires
-		 * kmappable memory, while ops->map_resource() does not.
+		 * kmappable memory.
 		 */
 		addr = ops->map_page(dev, page, offset, size, dir, attrs);
 	}
@@ -227,10 +222,7 @@ void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
 		iommu_dma_unmap_phys(dev, addr, size, dir, attrs);
 	else if (ops->unmap_phys)
 		ops->unmap_phys(dev, addr, size, dir, attrs);
-	else if (is_mmio) {
-		if (ops->unmap_resource)
-			ops->unmap_resource(dev, addr, size, dir, attrs);
-	} else
+	else
 		ops->unmap_page(dev, addr, size, dir, attrs);
 	trace_dma_unmap_phys(dev, addr, size, dir, attrs);
 	debug_dma_unmap_phys(dev, addr, size, dir);
-- 
2.51.0

Re: [PATCH v4 5/6] xen: swiotlb: Switch to physical address mapping callbacks

[Leon Romanovsky]

On Thu, Sep 18, 2025 at 05:09:28PM +0300, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@nvidia.com>
> 
> Combine resource and page mappings routines to one function
> and remove .map_resource/.unmap_resource callbacks completely.
> 
> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
> ---
>  drivers/xen/swiotlb-xen.c | 63 ++++++++++++++++++---------------------
>  1 file changed, 29 insertions(+), 34 deletions(-)

<...>

> +	if (attrs & DMA_ATTR_MMIO) {
> +		if (unlikely(!dma_capable(dev, phys, size, false))) {
> +			dev_err_once(
> +				dev,
> +				"DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
> +				&dma_addr, size, *dev->dma_mask,
> +				dev->bus_dma_limit);
> +			WARN_ON_ONCE(1);
> +			return DMA_MAPPING_ERROR;
> +		}
> +		return phys;
> +	}

This need to be fixed by the following change (dma_addr->phys):

diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 48936179c940b..ccf25027bec19 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -215,8 +215,8 @@ static dma_addr_t xen_swiotlb_map_phys(struct device *dev, phys_addr_t phys,
                if (unlikely(!dma_capable(dev, phys, size, false))) {
                        dev_err_once(
                                dev,
-                               "DMA addr %pad+%zu overflow (mask %llx, bus limit %llx).\n",
-                               &dma_addr, size, *dev->dma_mask,
+                               "DMA addr %pa+%zu overflow (mask %llx, bus limit %llx).\n",
+                               &phys, size, *dev->dma_mask,
                                dev->bus_dma_limit);
                        WARN_ON_ONCE(1);
                        return DMA_MAPPING_ERROR;

Thanks

Re: [PATCH v4 3/6] ARM: dma-mapping: Reduce struct page exposure in arch_sync_dma*()

[Jason Gunthorpe]

On Thu, Sep 18, 2025 at 05:09:26PM +0300, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@nvidia.com>
> 
> As a preparation to changing from .map_page to use .map_phys DMA
> callbacks, convert arch_sync_dma*() functions to use physical addresses
> instead of struct page.
> 
> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
> ---
>  arch/arm/mm/dma-mapping.c | 82 +++++++++++++++------------------------
>  1 file changed, 31 insertions(+), 51 deletions(-)

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>

Jason

Re: [PATCH v4 5/6] xen: swiotlb: Switch to physical address mapping callbacks

[Jason Gunthorpe]

On Thu, Sep 18, 2025 at 05:09:28PM +0300, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@nvidia.com>
> 
> Combine resource and page mappings routines to one function
> and remove .map_resource/.unmap_resource callbacks completely.
> 
> Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
> ---
>  drivers/xen/swiotlb-xen.c | 63 ++++++++++++++++++---------------------
>  1 file changed, 29 insertions(+), 34 deletions(-)

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>

Jason