xen/arm: use dma-noncoherent.h calls for xen-swiotlb cache maintainance

Copy the arm64 code that uses the dma-direct/swiotlb helpers for DMA
on-coherent devices.

Signed-off-by: Christoph Hellwig <[e-mail]>
Reviewed-by: Stefano Stabellini <[e-mail]>

arch/arm/include/asm/device.h

···
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 	struct dma_iommu_mapping	*mapping;
 #endif
-#ifdef CONFIG_XEN
-	const struct dma_map_ops *dev_dma_ops;
-#endif
 	unsigned int dma_coherent:1;
 	unsigned int dma_ops_setup:1;
 };

arch/arm/include/asm/xen/page-coherent.h

···
 #include <asm/page.h>
 #include <xen/arm/page-coherent.h>
 
-static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
-{
-	if (dev && dev->archdata.dev_dma_ops)
-		return dev->archdata.dev_dma_ops;
-	return get_arch_dma_ops(NULL);
-}
-
 static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
 		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
 {
-	return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+	return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
 }
 
 static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
 		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
 {
-	xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+	dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+
+	if (pfn_valid(pfn))
+		dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
+	else
+		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn))
+		dma_direct_sync_single_for_device(hwdev, handle, size, dir);
+	else
+		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
 }
 
 static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
···
 	bool local = (page_pfn <= dev_pfn) &&
 		(dev_pfn - page_pfn < compound_pages);
 
-	/*
-	 * Dom0 is mapped 1:1, while the Linux page can span across
-	 * multiple Xen pages, it's not possible for it to contain a
-	 * mix of local and foreign Xen pages. So if the first xen_pfn
-	 * == mfn the page is local otherwise it's a foreign page
-	 * grant-mapped in dom0. If the page is local we can safely
-	 * call the native dma_ops function, otherwise we call the xen
-	 * specific function.
-	 */
 	if (local)
-		xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
 	else
 		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
 }
···
 	 * safely call the native dma_ops function, otherwise we call the xen
 	 * specific function.
 	 */
-	if (pfn_valid(pfn)) {
-		if (xen_get_dma_ops(hwdev)->unmap_page)
-			xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
-	} else
+	if (pfn_valid(pfn))
+		dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
+	else
 		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
-}
-
-static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-	if (pfn_valid(pfn)) {
-		if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
-			xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
-	} else
-		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
-}
-
-static inline void xen_dma_sync_single_for_device(struct device *hwdev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	unsigned long pfn = PFN_DOWN(handle);
-	if (pfn_valid(pfn)) {
-		if (xen_get_dma_ops(hwdev)->sync_single_for_device)
-			xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
-	} else
-		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
 }
 
 #endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */

arch/arm/mm/dma-mapping.c

···
 	 * 32-bit DMA.
 	 * Use the generic dma-direct / swiotlb ops code in that case, as that
 	 * handles bounce buffering for us.
-	 *
-	 * Note: this checks CONFIG_ARM_LPAE instead of CONFIG_SWIOTLB as the
-	 * latter is also selected by the Xen code, but that code for now relies
-	 * on non-NULL dev_dma_ops.  To be cleaned up later.
 	 */
 	if (IS_ENABLED(CONFIG_ARM_LPAE))
 		return NULL;
···
 	set_dma_ops(dev, dma_ops);
 
 #ifdef CONFIG_XEN
-	if (xen_initial_domain()) {
-		dev->archdata.dev_dma_ops = dev->dma_ops;
+	if (xen_initial_domain())
 		dev->dma_ops = xen_dma_ops;
-	}
 #endif
 	dev->archdata.dma_ops_setup = true;
 }

drivers/xen/swiotlb-xen.c

···
 		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		     unsigned long attrs)
 {
-#ifdef CONFIG_ARM
-	if (xen_get_dma_ops(dev)->mmap)
-		return xen_get_dma_ops(dev)->mmap(dev, vma, cpu_addr,
-						    dma_addr, size, attrs);
-#endif
 	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
 }
 
···
 			void *cpu_addr, dma_addr_t handle, size_t size,
 			unsigned long attrs)
 {
-#ifdef CONFIG_ARM
-	if (xen_get_dma_ops(dev)->get_sgtable) {
-#if 0
-	/*
-	 * This check verifies that the page belongs to the current domain and
-	 * is not one mapped from another domain.
-	 * This check is for debug only, and should not go to production build
-	 */
-		unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle));
-		BUG_ON (!page_is_ram(bfn));
-#endif
-		return xen_get_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
-							   handle, size, attrs);
-	}
-#endif
 	return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size, attrs);
 }