1 files changed, 89 insertions, 158 deletions

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index b4a33358d2e9..a4c765d24692 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -25,7 +25,7 @@
 #include <linux/sizes.h>
 #include <linux/cma.h>
 
-#include <asm/memory.h>
+#include <asm/page.h>
 #include <asm/highmem.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
@@ -258,12 +258,14 @@ static struct dma_contig_early_reserve dma_mmu_remap[MAX_CMA_AREAS] __initdata;
 
 static int dma_mmu_remap_num __initdata;
 
+#ifdef CONFIG_DMA_CMA
 void __init dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
 {
 	dma_mmu_remap[dma_mmu_remap_num].base = base;
 	dma_mmu_remap[dma_mmu_remap_num].size = size;
 	dma_mmu_remap_num++;
 }
+#endif
 
 void __init dma_contiguous_remap(void)
 {
@@ -622,16 +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.
@@ -642,17 +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);
@@ -660,7 +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;
@@ -674,14 +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(paddr, size, dir, dmac_map_area);
 
-	dma_cache_maint_page(page, off, size, dir, dmac_map_area);
-
-	paddr = page_to_phys(page) + off;
 	if (dir == DMA_FROM_DEVICE) {
 		outer_inv_range(paddr, paddr + size);
 	} else {
@@ -690,36 +689,36 @@ 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);
 	}
 
 	/*
 	 * Mark the D-cache clean for these pages to avoid extra flushing.
 	 */
 	if (dir != DMA_TO_DEVICE && size >= PAGE_SIZE) {
-		unsigned long pfn;
-		size_t left = size;
-
-		pfn = page_to_pfn(page) + off / PAGE_SIZE;
-		off %= PAGE_SIZE;
-		if (off) {
-			pfn++;
-			left -= PAGE_SIZE - off;
-		}
-		while (left >= PAGE_SIZE) {
-			page = pfn_to_page(pfn++);
-			set_bit(PG_dcache_clean, &page->flags);
-			left -= PAGE_SIZE;
+		struct folio *folio = pfn_folio(paddr / PAGE_SIZE);
+		size_t offset = offset_in_folio(folio, paddr);
+
+		for (;;) {
+			size_t sz = folio_size(folio) - offset;
+
+			if (size < sz)
+				break;
+			if (!offset)
+				set_bit(PG_dcache_clean, &folio->flags.f);
+			offset = 0;
+			size -= sz;
+			if (!size)
+				break;
+			folio = folio_next(folio);
 		}
 	}
 }
@@ -733,6 +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;
@@ -855,10 +857,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 	int i = 0;
 	int order_idx = 0;
 
-	if (array_size <= PAGE_SIZE)
-		pages = kzalloc(array_size, GFP_KERNEL);
-	else
-		pages = vzalloc(array_size);
+	pages = kvzalloc(array_size, GFP_KERNEL);
 	if (!pages)
 		return NULL;
 
@@ -1204,7 +1203,7 @@ 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);
 
@@ -1306,8 +1305,7 @@ 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);
 	}
 }
 
@@ -1329,7 +1327,7 @@ 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);
 
 }
 
@@ -1351,29 +1349,31 @@ 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);
 }
 
 /**
- * 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))
-		__dma_page_cpu_to_dev(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)
@@ -1381,12 +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;
@@ -1398,82 +1397,27 @@ fail:
  * @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);
 	dma_addr_t iova = handle & PAGE_MASK;
-	struct page *page;
 	int offset = handle & ~PAGE_MASK;
 	int len = PAGE_ALIGN(size + offset);
 
 	if (!iova)
 		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);
-	}
-
-	iommu_unmap(mapping->domain, iova, len);
-	__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;
+	if (!dev->dma_coherent &&
+	    !(attrs & (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_MMIO))) {
+		phys_addr_t phys = iommu_iova_to_phys(mapping->domain, iova);
 
-	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;
+		arch_sync_dma_for_cpu(phys + offset, size, dir);
+	}
 
 	iommu_unmap(mapping->domain, iova, len);
 	__free_iova(mapping, iova, len);
@@ -1484,14 +1428,14 @@ 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,
@@ -1499,14 +1443,14 @@ 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 = {
@@ -1515,8 +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,
 
@@ -1524,14 +1468,11 @@ 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,
 };
 
 /**
  * arm_iommu_create_mapping
- * @bus: pointer to the bus holding the client device (for IOMMU calls)
+ * @dev: pointer to the client device (for IOMMU calls)
  * @base: start address of the valid IO address space
  * @size: maximum size of the valid IO address space
  *
@@ -1543,7 +1484,7 @@ static const struct dma_map_ops iommu_ops = {
  * arm_iommu_attach_device function.
  */
 struct dma_iommu_mapping *
-arm_iommu_create_mapping(const struct bus_type *bus, dma_addr_t base, u64 size)
+arm_iommu_create_mapping(struct device *dev, dma_addr_t base, u64 size)
 {
 	unsigned int bits = size >> PAGE_SHIFT;
 	unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long);
@@ -1584,9 +1525,11 @@ arm_iommu_create_mapping(const struct bus_type *bus, dma_addr_t base, u64 size)
 
 	spin_lock_init(&mapping->lock);
 
-	mapping->domain = iommu_domain_alloc(bus);
-	if (!mapping->domain)
+	mapping->domain = iommu_paging_domain_alloc(dev);
+	if (IS_ERR(mapping->domain)) {
+		err = PTR_ERR(mapping->domain);
 		goto err4;
+	}
 
 	kref_init(&mapping->kref);
 	return mapping;
@@ -1708,12 +1651,16 @@ void arm_iommu_detach_device(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
-static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+static void arm_setup_iommu_dma_ops(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping;
+	u64 dma_base = 0, size = 1ULL << 32;
 
-	mapping = arm_iommu_create_mapping(dev->bus, dma_base, size);
+	if (dev->dma_range_map) {
+		dma_base = dma_range_map_min(dev->dma_range_map);
+		size = dma_range_map_max(dev->dma_range_map) - dma_base;
+	}
+	mapping = arm_iommu_create_mapping(dev, dma_base, size);
 	if (IS_ERR(mapping)) {
 		pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n",
 				size, dev_name(dev));
@@ -1743,8 +1690,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev)
 
 #else
 
-static void arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
-				    const struct iommu_ops *iommu, bool coherent)
+static void arm_setup_iommu_dma_ops(struct device *dev)
 {
 }
 
@@ -1752,8 +1698,7 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-			const struct iommu_ops *iommu, bool coherent)
+void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 	/*
 	 * Due to legacy code that sets the ->dma_coherent flag from a bus
@@ -1772,8 +1717,8 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	if (dev->dma_ops)
 		return;
 
-	if (iommu)
-		arm_setup_iommu_dma_ops(dev, dma_base, size, iommu, coherent);
+	if (device_iommu_mapped(dev))
+		arm_setup_iommu_dma_ops(dev);
 
 	xen_setup_dma_ops(dev);
 	dev->archdata.dma_ops_setup = true;
@@ -1789,20 +1734,6 @@ 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)
 {