Merge tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping

Pull DMA mapping updates from Christoph Hellwig:
 "A huge update this time, but a lot of that is just consolidating or
  removing code:

   - provide a common DMA_MAPPING_ERROR definition and avoid indirect
     calls for dma_map_* error checking

   - use direct calls for the DMA direct mapping case, avoiding huge
     retpoline overhead for high performance workloads

   - merge the swiotlb dma_map_ops into dma-direct

   - provide a generic remapping DMA consistent allocator for
     architectures that have devices that perform DMA that is not cache
     coherent. Based on the existing arm64 implementation and also used
     for csky now.

   - improve the dma-debug infrastructure, including dynamic allocation
     of entries (Robin Murphy)

   - default to providing chaining scatterlist everywhere, with opt-outs
     for the few architectures (alpha, parisc, most arm32 variants) that
     can't cope with it

   - misc sparc32 dma-related cleanups

   - remove the dma_mark_clean arch hook used by swiotlb on ia64 and
     replace it with the generic noncoherent infrastructure

   - fix the return type of dma_set_max_seg_size (Niklas Söderlund)

   - move the dummy dma ops for not DMA capable devices from arm64 to
     common code (Robin Murphy)

   - ensure dma_alloc_coherent returns zeroed memory to avoid kernel
     data leaks through userspace. We already did this for most common
     architectures, but this ensures we do it everywhere.
     dma_zalloc_coherent has been deprecated and can hopefully be
     removed after -rc1 with a coccinelle script"

* tag 'dma-mapping-4.21' of git://git.infradead.org/users/hch/dma-mapping: (73 commits)
  dma-mapping: fix inverted logic in dma_supported
  dma-mapping: deprecate dma_zalloc_coherent
  dma-mapping: zero memory returned from dma_alloc_*
  sparc/iommu: fix ->map_sg return value
  sparc/io-unit: fix ->map_sg return value
  arm64: default to the direct mapping in get_arch_dma_ops
  PCI: Remove unused attr variable in pci_dma_configure
  ia64: only select ARCH_HAS_DMA_COHERENT_TO_PFN if swiotlb is enabled
  dma-mapping: bypass indirect calls for dma-direct
  vmd: use the proper dma_* APIs instead of direct methods calls
  dma-direct: merge swiotlb_dma_ops into the dma_direct code
  dma-direct: use dma_direct_map_page to implement dma_direct_map_sg
  dma-direct: improve addressability error reporting
  swiotlb: remove dma_mark_clean
  swiotlb: remove SWIOTLB_MAP_ERROR
  ACPI / scan: Refactor _CCA enforcement
  dma-mapping: factor out dummy DMA ops
  dma-mapping: always build the direct mapping code
  dma-mapping: move dma_cache_sync out of line
  dma-mapping: move various slow path functions out of line
  ...

6 files changed, 24 insertions, 49 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 5c0305585a0a..2196aac0e45c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -19,6 +19,7 @@ config ARM
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
+	select ARCH_NO_SG_CHAIN if !ARM_HAS_SG_CHAIN
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
 	select ARCH_SUPPORTS_ATOMIC_RMW
@@ -29,7 +30,7 @@ config ARM
 	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select DMA_DIRECT_OPS if !MMU
+	select DMA_REMAP if MMU
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
 	select GENERIC_ALLOCATOR
@@ -118,7 +119,6 @@ config ARM
 	  <http://www.arm.linux.org.uk/>.
 
 config ARM_HAS_SG_CHAIN
-	select ARCH_HAS_SG_CHAIN
 	bool
 
 config ARM_DMA_USE_IOMMU
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index 9a92de63426f..5ba4622030ca 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -257,7 +257,7 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
 	if (buf == NULL) {
 		dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
 		       __func__, ptr);
-		return ARM_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
@@ -327,7 +327,7 @@ static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page,
 
 	ret = needs_bounce(dev, dma_addr, size);
 	if (ret < 0)
-		return ARM_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	if (ret == 0) {
 		arm_dma_ops.sync_single_for_device(dev, dma_addr, size, dir);
@@ -336,7 +336,7 @@ static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page,
 
 	if (PageHighMem(page)) {
 		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
-		return ARM_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	return map_single(dev, page_address(page) + offset, size, dir, attrs);
@@ -453,11 +453,6 @@ static int dmabounce_dma_supported(struct device *dev, u64 dma_mask)
 	return arm_dma_ops.dma_supported(dev, dma_mask);
 }
 
-static int dmabounce_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return arm_dma_ops.mapping_error(dev, dma_addr);
-}
-
 static const struct dma_map_ops dmabounce_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
@@ -472,7 +467,6 @@ static const struct dma_map_ops dmabounce_ops = {
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
 	.dma_supported		= dmabounce_dma_supported,
-	.mapping_error		= dmabounce_mapping_error,
 };
 
 static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h
index 6821f1249300..772f48ef84b7 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -9,8 +9,6 @@
 #include <linux/dma-debug.h>
 #include <linux/kref.h>
 
-#define ARM_MAPPING_ERROR		(~(dma_addr_t)0x0)
-
 struct dma_iommu_mapping {
 	/* iommu specific data */
 	struct iommu_domain	*domain;
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 965b7c846ecb..31d3b96f0f4b 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -18,7 +18,7 @@ extern const struct dma_map_ops arm_coherent_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_direct_ops;
+	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : NULL;
 }
 
 #ifdef __arch_page_to_dma
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 712416ecd8e6..f304b10e23a4 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -22,7 +22,7 @@
 #include "dma.h"
 
 /*
- *  dma_direct_ops is used if
+ *  The generic direct mapping code is used if
  *   - MMU/MPU is off
  *   - cpu is v7m w/o cache support
  *   - device is coherent
@@ -209,16 +209,9 @@ const struct dma_map_ops arm_nommu_dma_ops = {
 };
 EXPORT_SYMBOL(arm_nommu_dma_ops);
 
-static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
-{
-	return coherent ? &dma_direct_ops : &arm_nommu_dma_ops;
-}
-
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
-	const struct dma_map_ops *dma_ops;
-
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*
 		 * Cache support for v7m is optional, so can be treated as
@@ -234,7 +227,6 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true;
 	}
 
-	dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent);
-
-	set_dma_ops(dev, dma_ops);
+	if (!dev->archdata.dma_coherent)
+		set_dma_ops(dev, &arm_nommu_dma_ops);
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 78de138aa66d..f1e2922e447c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -179,11 +179,6 @@ static void arm_dma_sync_single_for_device(struct device *dev,
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
-static int arm_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == ARM_MAPPING_ERROR;
-}
-
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
@@ -197,7 +192,6 @@ const struct dma_map_ops arm_dma_ops = {
 	.sync_single_for_device	= arm_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 EXPORT_SYMBOL(arm_dma_ops);
@@ -217,7 +211,6 @@ const struct dma_map_ops arm_coherent_dma_ops = {
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
 	.map_sg			= arm_dma_map_sg,
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
@@ -774,7 +767,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	gfp &= ~(__GFP_COMP);
 	args.gfp = gfp;
 
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 	allowblock = gfpflags_allow_blocking(gfp);
 	cma = allowblock ? dev_get_cma_area(dev) : false;
 
@@ -1217,7 +1210,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 	if (i == mapping->nr_bitmaps) {
 		if (extend_iommu_mapping(mapping)) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return ARM_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 
 		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
@@ -1225,7 +1218,7 @@ static inline dma_addr_t __alloc_iova(struct dma_iommu_mapping *mapping,
 
 		if (start > mapping->bits) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return ARM_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 
 		bitmap_set(mapping->bitmaps[i], start, count);
@@ -1409,7 +1402,7 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
 	int i;
 
 	dma_addr = __alloc_iova(mapping, size);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	iova = dma_addr;
@@ -1436,7 +1429,7 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size,
 fail:
 	iommu_unmap(mapping->domain, dma_addr, iova-dma_addr);
 	__free_iova(mapping, dma_addr, size);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
@@ -1497,7 +1490,7 @@ static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, &page, size, attrs);
-	if (*handle == ARM_MAPPING_ERROR)
+	if (*handle == DMA_MAPPING_ERROR)
 		goto err_mapping;
 
 	return addr;
@@ -1525,7 +1518,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	struct page **pages;
 	void *addr = NULL;
 
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 	size = PAGE_ALIGN(size);
 
 	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
@@ -1546,7 +1539,7 @@ static void *__arm_iommu_alloc_attrs(struct device *dev, size_t size,
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, pages, size, attrs);
-	if (*handle == ARM_MAPPING_ERROR)
+	if (*handle == DMA_MAPPING_ERROR)
 		goto err_buffer;
 
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
@@ -1696,10 +1689,10 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 	int prot;
 
 	size = PAGE_ALIGN(size);
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 
 	iova_base = iova = __alloc_iova(mapping, size);
-	if (iova == ARM_MAPPING_ERROR)
+	if (iova == DMA_MAPPING_ERROR)
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
@@ -1739,7 +1732,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	for (i = 1; i < nents; i++) {
 		s = sg_next(s);
 
-		s->dma_address = ARM_MAPPING_ERROR;
+		s->dma_address = DMA_MAPPING_ERROR;
 		s->dma_length = 0;
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
@@ -1914,7 +1907,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs);
@@ -1926,7 +1919,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 /**
@@ -2020,7 +2013,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 	size_t len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
@@ -2032,7 +2025,7 @@ static dma_addr_t arm_iommu_map_resource(struct device *dev,
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 /**
@@ -2105,7 +2098,6 @@ const struct dma_map_ops iommu_ops = {
 	.map_resource		= arm_iommu_map_resource,
 	.unmap_resource		= arm_iommu_unmap_resource,
 
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 
@@ -2124,7 +2116,6 @@ const struct dma_map_ops iommu_coherent_ops = {
 	.map_resource	= arm_iommu_map_resource,
 	.unmap_resource	= arm_iommu_unmap_resource,
 
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };