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
  ...

8 files changed, 23 insertions, 38 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index a1e858e42ada..50f27a656051 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -139,7 +139,6 @@ config PPC
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_MEMBARRIER_CALLBACKS
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC64
-	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !RELOCATABLE && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if PPC64
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index dacd0f93f2b2..ebf66809f2d3 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -103,7 +103,6 @@ static inline void set_dma_offset(struct device *dev, dma_addr_t off)
 }
 
 #define HAVE_ARCH_DMA_SET_MASK 1
-extern int dma_set_mask(struct device *dev, u64 dma_mask);
 
 extern u64 __dma_get_required_mask(struct device *dev);
 
diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h
index e847ff69cb2b..17524d222a7b 100644
--- a/arch/powerpc/include/asm/iommu.h
+++ b/arch/powerpc/include/asm/iommu.h
@@ -143,8 +143,6 @@ struct scatterlist;
 
 #ifdef CONFIG_PPC64
 
-#define IOMMU_MAPPING_ERROR		(~(dma_addr_t)0x0)
-
 static inline void set_iommu_table_base(struct device *dev,
 					struct iommu_table *base)
 {
@@ -239,8 +237,6 @@ static inline void iommu_del_device(struct device *dev)
 }
 #endif /* !CONFIG_IOMMU_API */
 
-int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr);
-
 #else
 
 static inline void *get_iommu_table_base(struct device *dev)
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index 2ca6cfaebf65..9c9bcaae2f75 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -105,11 +105,6 @@ static u64 dma_iommu_get_required_mask(struct device *dev)
 	return mask;
 }
 
-int dma_iommu_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == IOMMU_MAPPING_ERROR;
-}
-
 struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
@@ -120,5 +115,4 @@ struct dma_map_ops dma_iommu_ops = {
 	.map_page		= dma_iommu_map_page,
 	.unmap_page		= dma_iommu_unmap_page,
 	.get_required_mask	= dma_iommu_get_required_mask,
-	.mapping_error		= dma_iommu_mapping_error,
 };
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 678811abccfc..7d5fc9751622 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -50,16 +50,15 @@ const struct dma_map_ops powerpc_swiotlb_dma_ops = {
 	.alloc = __dma_nommu_alloc_coherent,
 	.free = __dma_nommu_free_coherent,
 	.mmap = dma_nommu_mmap_coherent,
-	.map_sg = swiotlb_map_sg_attrs,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
+	.map_sg = dma_direct_map_sg,
+	.unmap_sg = dma_direct_unmap_sg,
 	.dma_supported = swiotlb_dma_supported,
-	.map_page = swiotlb_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = swiotlb_sync_sg_for_device,
-	.mapping_error = dma_direct_mapping_error,
+	.map_page = dma_direct_map_page,
+	.unmap_page = dma_direct_unmap_page,
+	.sync_single_for_cpu = dma_direct_sync_single_for_cpu,
+	.sync_single_for_device = dma_direct_sync_single_for_device,
+	.sync_sg_for_cpu = dma_direct_sync_sg_for_cpu,
+	.sync_sg_for_device = dma_direct_sync_sg_for_device,
 	.get_required_mask = swiotlb_powerpc_get_required,
 };
 
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 9d5d109f15c0..d0625480b59e 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -198,11 +198,11 @@ static unsigned long iommu_range_alloc(struct device *dev,
 	if (unlikely(npages == 0)) {
 		if (printk_ratelimit())
 			WARN_ON(1);
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	if (should_fail_iommu(dev))
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 
 	/*
 	 * We don't need to disable preemption here because any CPU can
@@ -278,7 +278,7 @@ again:
 		} else {
 			/* Give up */
 			spin_unlock_irqrestore(&(pool->lock), flags);
-			return IOMMU_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 	}
 
@@ -310,13 +310,13 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 			      unsigned long attrs)
 {
 	unsigned long entry;
-	dma_addr_t ret = IOMMU_MAPPING_ERROR;
+	dma_addr_t ret = DMA_MAPPING_ERROR;
 	int build_fail;
 
 	entry = iommu_range_alloc(dev, tbl, npages, NULL, mask, align_order);
 
-	if (unlikely(entry == IOMMU_MAPPING_ERROR))
-		return IOMMU_MAPPING_ERROR;
+	if (unlikely(entry == DMA_MAPPING_ERROR))
+		return DMA_MAPPING_ERROR;
 
 	entry += tbl->it_offset;	/* Offset into real TCE table */
 	ret = entry << tbl->it_page_shift;	/* Set the return dma address */
@@ -328,12 +328,12 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 
 	/* tbl->it_ops->set() only returns non-zero for transient errors.
 	 * Clean up the table bitmap in this case and return
-	 * IOMMU_MAPPING_ERROR. For all other errors the functionality is
+	 * DMA_MAPPING_ERROR. For all other errors the functionality is
 	 * not altered.
 	 */
 	if (unlikely(build_fail)) {
 		__iommu_free(tbl, ret, npages);
-		return IOMMU_MAPPING_ERROR;
+		return DMA_MAPPING_ERROR;
 	}
 
 	/* Flush/invalidate TLB caches if necessary */
@@ -478,7 +478,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 		DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
 		/* Handle failure */
-		if (unlikely(entry == IOMMU_MAPPING_ERROR)) {
+		if (unlikely(entry == DMA_MAPPING_ERROR)) {
 			if (!(attrs & DMA_ATTR_NO_WARN) &&
 			    printk_ratelimit())
 				dev_info(dev, "iommu_alloc failed, tbl %p "
@@ -545,7 +545,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 	 */
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = IOMMU_MAPPING_ERROR;
+		outs->dma_address = DMA_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
@@ -563,7 +563,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
 						 IOMMU_PAGE_SIZE(tbl));
 			__iommu_free(tbl, vaddr, npages);
-			s->dma_address = IOMMU_MAPPING_ERROR;
+			s->dma_address = DMA_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
@@ -777,7 +777,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 			  unsigned long mask, enum dma_data_direction direction,
 			  unsigned long attrs)
 {
-	dma_addr_t dma_handle = IOMMU_MAPPING_ERROR;
+	dma_addr_t dma_handle = DMA_MAPPING_ERROR;
 	void *vaddr;
 	unsigned long uaddr;
 	unsigned int npages, align;
@@ -797,7 +797,7 @@ dma_addr_t iommu_map_page(struct device *dev, struct iommu_table *tbl,
 		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction,
 					 mask >> tbl->it_page_shift, align,
 					 attrs);
-		if (dma_handle == IOMMU_MAPPING_ERROR) {
+		if (dma_handle == DMA_MAPPING_ERROR) {
 			if (!(attrs & DMA_ATTR_NO_WARN) &&
 			    printk_ratelimit())  {
 				dev_info(dev, "iommu_alloc failed, tbl %p "
@@ -869,7 +869,7 @@ void *iommu_alloc_coherent(struct device *dev, struct iommu_table *tbl,
 	io_order = get_iommu_order(size, tbl);
 	mapping = iommu_alloc(dev, tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
 			      mask >> tbl->it_page_shift, io_order, 0);
-	if (mapping == IOMMU_MAPPING_ERROR) {
+	if (mapping == DMA_MAPPING_ERROR) {
 		free_pages((unsigned long)ret, order);
 		return NULL;
 	}
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 12352a58072a..af2a3c15e0ec 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -654,7 +654,6 @@ static const struct dma_map_ops dma_iommu_fixed_ops = {
 	.dma_supported  = dma_suported_and_switch,
 	.map_page       = dma_fixed_map_page,
 	.unmap_page     = dma_fixed_unmap_page,
-	.mapping_error	= dma_iommu_mapping_error,
 };
 
 static void cell_dma_dev_setup(struct device *dev)
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 93cc9eec6601..1fad4649735b 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -519,7 +519,7 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
 {
 	struct vio_dev *viodev = to_vio_dev(dev);
 	struct iommu_table *tbl;
-	dma_addr_t ret = IOMMU_MAPPING_ERROR;
+	dma_addr_t ret = DMA_MAPPING_ERROR;
 
 	tbl = get_iommu_table_base(dev);
 	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl)))) {
@@ -625,7 +625,6 @@ static const struct dma_map_ops vio_dma_mapping_ops = {
 	.unmap_page        = vio_dma_iommu_unmap_page,
 	.dma_supported     = vio_dma_iommu_dma_supported,
 	.get_required_mask = vio_dma_get_required_mask,
-	.mapping_error	   = dma_iommu_mapping_error,
 };
 
 /**