Merge tag 'dma-mapping-5.15' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping updates from Christoph Hellwig:

 - fix debugfs initialization order (Anthony Iliopoulos)

 - use memory_intersects() directly (Kefeng Wang)

 - allow to return specific errors from ->map_sg (Logan Gunthorpe,
   Martin Oliveira)

 - turn the dma_map_sg return value into an unsigned int (me)

 - provide a common global coherent pool іmplementation (me)

* tag 'dma-mapping-5.15' of git://git.infradead.org/users/hch/dma-mapping: (31 commits)
  hexagon: use the generic global coherent pool
  dma-mapping: make the global coherent pool conditional
  dma-mapping: add a dma_init_global_coherent helper
  dma-mapping: simplify dma_init_coherent_memory
  dma-mapping: allow using the global coherent pool for !ARM
  ARM/nommu: use the generic dma-direct code for non-coherent devices
  dma-direct: add support for dma_coherent_default_memory
  dma-mapping: return an unsigned int from dma_map_sg{,_attrs}
  dma-mapping: disallow .map_sg operations from returning zero on error
  dma-mapping: return error code from dma_dummy_map_sg()
  x86/amd_gart: don't set failed sg dma_address to DMA_MAPPING_ERROR
  x86/amd_gart: return error code from gart_map_sg()
  xen: swiotlb: return error code from xen_swiotlb_map_sg()
  parisc: return error code from .map_sg() ops
  sparc/iommu: don't set failed sg dma_address to DMA_MAPPING_ERROR
  sparc/iommu: return error codes from .map_sg() ops
  s390/pci: don't set failed sg dma_address to DMA_MAPPING_ERROR
  s390/pci: return error code from s390_dma_map_sg()
  powerpc/iommu: don't set failed sg dma_address to DMA_MAPPING_ERROR
  powerpc/iommu: return error code from .map_sg() ops
  ...

3 files changed, 25 insertions, 179 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 1a48c17a5909..f1d6531b5ce5 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -18,8 +18,8 @@ config ARM
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_STRICT_KERNEL_RWX if MMU && !XIP_KERNEL
 	select ARCH_HAS_STRICT_MODULE_RWX if MMU
-	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if SWIOTLB
-	select ARCH_HAS_SYNC_DMA_FOR_CPU if SWIOTLB
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if SWIOTLB || !MMU
+	select ARCH_HAS_SYNC_DMA_FOR_CPU if SWIOTLB || !MMU
 	select ARCH_HAS_TEARDOWN_DMA_OPS if MMU
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
@@ -44,6 +44,7 @@ config ARM
 	select CPU_PM if SUSPEND || CPU_IDLE
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select DMA_DECLARE_COHERENT
+	select DMA_GLOBAL_POOL if !MMU
 	select DMA_OPS
 	select DMA_REMAP if MMU
 	select EDAC_SUPPORT
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index 6bfd2b884505..cfd9c933d2f0 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -5,12 +5,7 @@
  *  Copyright (C) 2000-2004 Russell King
  */
 
-#include <linux/export.h>
-#include <linux/mm.h>
-#include <linux/dma-direct.h>
 #include <linux/dma-map-ops.h>
-#include <linux/scatterlist.h>
-
 #include <asm/cachetype.h>
 #include <asm/cacheflush.h>
 #include <asm/outercache.h>
@@ -18,65 +13,8 @@
 
 #include "dma.h"
 
-/*
- *  The generic direct mapping code is used if
- *   - MMU/MPU is off
- *   - cpu is v7m w/o cache support
- *   - device is coherent
- *  otherwise arm_nommu_dma_ops is used.
- *
- *  arm_nommu_dma_ops rely on consistent DMA memory (please, refer to
- *  [1] on how to declare such memory).
- *
- *  [1] Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
- */
-
-static void *arm_nommu_dma_alloc(struct device *dev, size_t size,
-				 dma_addr_t *dma_handle, gfp_t gfp,
-				 unsigned long attrs)
-
-{
-	void *ret = dma_alloc_from_global_coherent(dev, size, dma_handle);
-
-	/*
-	 * dma_alloc_from_global_coherent() may fail because:
-	 *
-	 * - no consistent DMA region has been defined, so we can't
-	 *   continue.
-	 * - there is no space left in consistent DMA region, so we
-	 *   only can fallback to generic allocator if we are
-	 *   advertised that consistency is not required.
-	 */
-
-	WARN_ON_ONCE(ret == NULL);
-	return ret;
-}
-
-static void arm_nommu_dma_free(struct device *dev, size_t size,
-			       void *cpu_addr, dma_addr_t dma_addr,
-			       unsigned long attrs)
-{
-	int ret = dma_release_from_global_coherent(get_order(size), cpu_addr);
-
-	WARN_ON_ONCE(ret == 0);
-}
-
-static int arm_nommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-			      void *cpu_addr, dma_addr_t dma_addr, size_t size,
-			      unsigned long attrs)
-{
-	int ret;
-
-	if (dma_mmap_from_global_coherent(vma, cpu_addr, size, &ret))
-		return ret;
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-	return -ENXIO;
-}
-
-
-static void __dma_page_cpu_to_dev(phys_addr_t paddr, 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)
 {
 	dmac_map_area(__va(paddr), size, dir);
 
@@ -86,8 +24,8 @@ static void __dma_page_cpu_to_dev(phys_addr_t paddr, size_t size,
 		outer_clean_range(paddr, paddr + size);
 }
 
-static void __dma_page_dev_to_cpu(phys_addr_t paddr, 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)
 {
 	if (dir != DMA_TO_DEVICE) {
 		outer_inv_range(paddr, paddr + size);
@@ -95,102 +33,6 @@ static void __dma_page_dev_to_cpu(phys_addr_t paddr, size_t size,
 	}
 }
 
-static dma_addr_t arm_nommu_dma_map_page(struct device *dev, struct page *page,
-					 unsigned long offset, size_t size,
-					 enum dma_data_direction dir,
-					 unsigned long attrs)
-{
-	dma_addr_t handle = page_to_phys(page) + offset;
-
-	__dma_page_cpu_to_dev(handle, size, dir);
-
-	return handle;
-}
-
-static void arm_nommu_dma_unmap_page(struct device *dev, dma_addr_t handle,
-				     size_t size, enum dma_data_direction dir,
-				     unsigned long attrs)
-{
-	__dma_page_dev_to_cpu(handle, size, dir);
-}
-
-
-static int arm_nommu_dma_map_sg(struct device *dev, struct scatterlist *sgl,
-				int nents, enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sgl, sg, nents, i) {
-		sg_dma_address(sg) = sg_phys(sg);
-		sg_dma_len(sg) = sg->length;
-		__dma_page_cpu_to_dev(sg_dma_address(sg), sg_dma_len(sg), dir);
-	}
-
-	return nents;
-}
-
-static void arm_nommu_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
-				   int nents, enum dma_data_direction dir,
-				   unsigned long attrs)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_page_dev_to_cpu(sg_dma_address(sg), sg_dma_len(sg), dir);
-}
-
-static void arm_nommu_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	__dma_page_cpu_to_dev(handle, size, dir);
-}
-
-static void arm_nommu_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
-{
-	__dma_page_cpu_to_dev(handle, size, dir);
-}
-
-static void arm_nommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
-					     int nents, enum dma_data_direction dir)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_page_cpu_to_dev(sg_dma_address(sg), sg_dma_len(sg), dir);
-}
-
-static void arm_nommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
-					  int nents, enum dma_data_direction dir)
-{
-	struct scatterlist *sg;
-	int i;
-
-	for_each_sg(sgl, sg, nents, i)
-		__dma_page_dev_to_cpu(sg_dma_address(sg), sg_dma_len(sg), dir);
-}
-
-const struct dma_map_ops arm_nommu_dma_ops = {
-	.alloc			= arm_nommu_dma_alloc,
-	.free			= arm_nommu_dma_free,
-	.alloc_pages		= dma_direct_alloc_pages,
-	.free_pages		= dma_direct_free_pages,
-	.mmap			= arm_nommu_dma_mmap,
-	.map_page		= arm_nommu_dma_map_page,
-	.unmap_page		= arm_nommu_dma_unmap_page,
-	.map_sg			= arm_nommu_dma_map_sg,
-	.unmap_sg		= arm_nommu_dma_unmap_sg,
-	.sync_single_for_device	= arm_nommu_dma_sync_single_for_device,
-	.sync_single_for_cpu	= arm_nommu_dma_sync_single_for_cpu,
-	.sync_sg_for_device	= arm_nommu_dma_sync_sg_for_device,
-	.sync_sg_for_cpu	= arm_nommu_dma_sync_sg_for_cpu,
-};
-EXPORT_SYMBOL(arm_nommu_dma_ops);
-
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
@@ -201,14 +43,11 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 		 * enough to check if MPU is in use or not since in absense of
 		 * MPU system memory map is used.
 		 */
-		dev->archdata.dma_coherent = (cacheid) ? coherent : true;
+		dev->dma_coherent = cacheid ? coherent : true;
 	} else {
 		/*
 		 * Assume coherent DMA in case MMU/MPU has not been set up.
 		 */
-		dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true;
+		dev->dma_coherent = (get_cr() & CR_M) ? coherent : true;
 	}
-
-	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 c4b8df2ad328..4b61541853ea 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -980,7 +980,7 @@ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	struct scatterlist *s;
-	int i, j;
+	int i, j, ret;
 
 	for_each_sg(sg, s, nents, i) {
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
@@ -988,15 +988,17 @@ int arm_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 #endif
 		s->dma_address = ops->map_page(dev, sg_page(s), s->offset,
 						s->length, dir, attrs);
-		if (dma_mapping_error(dev, s->dma_address))
+		if (dma_mapping_error(dev, s->dma_address)) {
+			ret = -EIO;
 			goto bad_mapping;
+		}
 	}
 	return nents;
 
  bad_mapping:
 	for_each_sg(sg, s, i, j)
 		ops->unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir, attrs);
-	return 0;
+	return ret;
 }
 
 /**
@@ -1622,7 +1624,7 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		     bool is_coherent)
 {
 	struct scatterlist *s = sg, *dma = sg, *start = sg;
-	int i, count = 0;
+	int i, count = 0, ret;
 	unsigned int offset = s->offset;
 	unsigned int size = s->offset + s->length;
 	unsigned int max = dma_get_max_seg_size(dev);
@@ -1630,12 +1632,13 @@ 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 = DMA_MAPPING_ERROR;
 		s->dma_length = 0;
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
-			if (__map_sg_chunk(dev, start, size, &dma->dma_address,
-			    dir, attrs, is_coherent) < 0)
+			ret = __map_sg_chunk(dev, start, size,
+					     &dma->dma_address, dir, attrs,
+					     is_coherent);
+			if (ret < 0)
 				goto bad_mapping;
 
 			dma->dma_address += offset;
@@ -1648,8 +1651,9 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		}
 		size += s->length;
 	}
-	if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs,
-		is_coherent) < 0)
+	ret = __map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs,
+			     is_coherent);
+	if (ret < 0)
 		goto bad_mapping;
 
 	dma->dma_address += offset;
@@ -1660,7 +1664,9 @@ static int __iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 bad_mapping:
 	for_each_sg(sg, s, count, i)
 		__iommu_remove_mapping(dev, sg_dma_address(s), sg_dma_len(s));
-	return 0;
+	if (ret == -ENOMEM)
+		return ret;
+	return -EINVAL;
 }
 
 /**