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
  ...

30 files changed, 310 insertions, 443 deletions

diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c
index 35d7b3096d6e..21f9ac101324 100644
--- a/arch/alpha/kernel/pci_iommu.c
+++ b/arch/alpha/kernel/pci_iommu.c
@@ -649,7 +649,9 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg,
 		sg->dma_address
 		  = pci_map_single_1(pdev, SG_ENT_VIRT_ADDRESS(sg),
 				     sg->length, dac_allowed);
-		return sg->dma_address != DMA_MAPPING_ERROR;
+		if (sg->dma_address == DMA_MAPPING_ERROR)
+			return -EIO;
+		return 1;
 	}
 
 	start = sg;
@@ -685,8 +687,10 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg,
 	if (out < end)
 		out->dma_length = 0;
 
-	if (out - start == 0)
+	if (out - start == 0) {
 		printk(KERN_WARNING "pci_map_sg failed: no entries?\n");
+		return -ENOMEM;
+	}
 	DBGA("pci_map_sg: %ld entries\n", out - start);
 
 	return out - start;
@@ -699,7 +703,7 @@ static int alpha_pci_map_sg(struct device *dev, struct scatterlist *sg,
 	   entries.  Unmap them now.  */
 	if (out > start)
 		pci_unmap_sg(pdev, start, out - start, dir);
-	return 0;
+	return -ENOMEM;
 }
 
 /* Unmap a set of streaming mode DMA translations.  Again, cpu read
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;
 }
 
 /**
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index e5a852080730..aab1a40eb653 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -7,6 +7,7 @@ config HEXAGON
 	select ARCH_32BIT_OFF_T
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_NO_PREEMPT
+	select DMA_GLOBAL_POOL
 	# Other pending projects/to-do items.
 	# select HAVE_REGS_AND_STACK_ACCESS_API
 	# select HAVE_HW_BREAKPOINT if PERF_EVENTS
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index 00b9a81075dd..882680e81a30 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -7,54 +7,8 @@
 
 #include <linux/dma-map-ops.h>
 #include <linux/memblock.h>
-#include <linux/genalloc.h>
-#include <linux/module.h>
 #include <asm/page.h>
 
-static struct gen_pool *coherent_pool;
-
-
-/* Allocates from a pool of uncached memory that was reserved at boot time */
-
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_addr,
-		gfp_t flag, unsigned long attrs)
-{
-	void *ret;
-
-	/*
-	 * Our max_low_pfn should have been backed off by 16MB in
-	 * mm/init.c to create DMA coherent space.  Use that as the VA
-	 * for the pool.
-	 */
-
-	if (coherent_pool == NULL) {
-		coherent_pool = gen_pool_create(PAGE_SHIFT, -1);
-
-		if (coherent_pool == NULL)
-			panic("Can't create %s() memory pool!", __func__);
-		else
-			gen_pool_add(coherent_pool,
-				(unsigned long)pfn_to_virt(max_low_pfn),
-				hexagon_coherent_pool_size, -1);
-	}
-
-	ret = (void *) gen_pool_alloc(coherent_pool, size);
-
-	if (ret) {
-		memset(ret, 0, size);
-		*dma_addr = (dma_addr_t) virt_to_phys(ret);
-	} else
-		*dma_addr = ~0;
-
-	return ret;
-}
-
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_addr, unsigned long attrs)
-{
-	gen_pool_free(coherent_pool, (unsigned long) vaddr, size);
-}
-
 void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		enum dma_data_direction dir)
 {
@@ -77,3 +31,14 @@ void arch_sync_dma_for_device(phys_addr_t paddr, size_t size,
 		BUG();
 	}
 }
+
+/*
+ * Our max_low_pfn should have been backed off by 16MB in mm/init.c to create
+ * DMA coherent space.  Use that for the pool.
+ */
+static int __init hexagon_dma_init(void)
+{
+	return dma_init_global_coherent(PFN_PHYS(max_low_pfn),
+					hexagon_coherent_pool_size);
+}
+core_initcall(hexagon_dma_init);
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 9148ddbf02e5..8ad6946521d8 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1459,7 +1459,7 @@ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist,
 		sglist->dma_address = sba_map_page(dev, sg_page(sglist),
 				sglist->offset, sglist->length, dir, attrs);
 		if (dma_mapping_error(dev, sglist->dma_address))
-			return 0;
+			return -EIO;
 		return 1;
 	}
 
@@ -1486,7 +1486,7 @@ static int sba_map_sg_attrs(struct device *dev, struct scatterlist *sglist,
 	coalesced = sba_coalesce_chunks(ioc, dev, sglist, nents);
 	if (coalesced < 0) {
 		sba_unmap_sg_attrs(dev, sglist, nents, dir, attrs);
-		return 0;
+		return -ENOMEM;
 	}
 
 	/*
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index 461457b28982..eabddb89d221 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -552,7 +552,7 @@ static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 				dir);
 		sg->dma_address = vdma_alloc(sg_phys(sg), sg->length);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
-			return 0;
+			return -EIO;
 		sg_dma_len(sg) = sg->length;
 	}
 
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 2af89a5e379f..30b7736f0896 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -473,7 +473,7 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 	BUG_ON(direction == DMA_NONE);
 
 	if ((nelems == 0) || !tbl)
-		return 0;
+		return -EINVAL;
 
 	outs = s = segstart = &sglist[0];
 	outcount = 1;
@@ -575,7 +575,6 @@ int ppc_iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 	 */
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = DMA_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
@@ -593,13 +592,12 @@ 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 = DMA_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
 			break;
 	}
-	return 0;
+	return -EIO;
 }
 
 
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index cc5774c64fae..c8b50fec56bf 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -662,7 +662,7 @@ static int ps3_ioc0_map_sg(struct device *_dev, struct scatterlist *sg,
 			   unsigned long attrs)
 {
 	BUG();
-	return 0;
+	return -EINVAL;
 }
 
 static void ps3_sb_unmap_sg(struct device *_dev, struct scatterlist *sg,
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index 58283cecbd52..feafcb582e1b 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -560,7 +560,8 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 	for_each_sg(sglist, sgl, nelems, count)
 		alloc_size += roundup(sgl->length, IOMMU_PAGE_SIZE(tbl));
 
-	if (vio_cmo_alloc(viodev, alloc_size))
+	ret = vio_cmo_alloc(viodev, alloc_size);
+	if (ret)
 		goto out_fail;
 	ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, dma_get_mask(dev),
 			direction, attrs);
@@ -577,7 +578,7 @@ out_deallocate:
 	vio_cmo_dealloc(viodev, alloc_size);
 out_fail:
 	atomic_inc(&viodev->cmo.allocs_failed);
-	return 0;
+	return ret;
 }
 
 static void vio_dma_iommu_unmap_sg(struct device *dev,
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 58f2f7abea96..93223bd110c3 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -487,18 +487,18 @@ static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned int max = dma_get_max_seg_size(dev);
 	unsigned int size = s->offset + s->length;
 	unsigned int offset = s->offset;
-	int count = 0, i;
+	int count = 0, i, ret;
 
 	for (i = 1; i < nr_elements; 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 (__s390_dma_map_sg(dev, start, size,
-					      &dma->dma_address, dir))
+			ret = __s390_dma_map_sg(dev, start, size,
+						&dma->dma_address, dir);
+			if (ret)
 				goto unmap;
 
 			dma->dma_address += offset;
@@ -511,7 +511,8 @@ static int s390_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		}
 		size += s->length;
 	}
-	if (__s390_dma_map_sg(dev, start, size, &dma->dma_address, dir))
+	ret = __s390_dma_map_sg(dev, start, size, &dma->dma_address, dir);
+	if (ret)
 		goto unmap;
 
 	dma->dma_address += offset;
@@ -523,7 +524,7 @@ unmap:
 		s390_dma_unmap_pages(dev, sg_dma_address(s), sg_dma_len(s),
 				     dir, attrs);
 
-	return 0;
+	return ret;
 }
 
 static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index a034f571d869..da0363692528 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -448,7 +448,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	iommu = dev->archdata.iommu;
 	strbuf = dev->archdata.stc;
 	if (nelems == 0 || !iommu)
-		return 0;
+		return -EINVAL;
 
 	spin_lock_irqsave(&iommu->lock, flags);
 
@@ -546,7 +546,6 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = DMA_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
@@ -572,7 +571,6 @@ iommu_map_failed:
 			iommu_tbl_range_free(&iommu->tbl, vaddr, npages,
 					     IOMMU_ERROR_CODE);
 
-			s->dma_address = DMA_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
@@ -580,7 +578,7 @@ iommu_map_failed:
 	}
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
-	return 0;
+	return -EINVAL;
 }
 
 /* If contexts are being used, they are the same in all of the mappings
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 9de57e88f7a1..384480971805 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -486,7 +486,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	iommu = dev->archdata.iommu;
 	if (nelems == 0 || !iommu)
-		return 0;
+		return -EINVAL;
 	atu = iommu->atu;
 
 	prot = HV_PCI_MAP_ATTR_READ;
@@ -594,7 +594,6 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	if (outcount < incount) {
 		outs = sg_next(outs);
-		outs->dma_address = DMA_MAPPING_ERROR;
 		outs->dma_length = 0;
 	}
 
@@ -611,7 +610,6 @@ iommu_map_failed:
 			iommu_tbl_range_free(tbl, vaddr, npages,
 					     IOMMU_ERROR_CODE);
 			/* XXX demap? XXX */
-			s->dma_address = DMA_MAPPING_ERROR;
 			s->dma_length = 0;
 		}
 		if (s == outs)
@@ -619,7 +617,7 @@ iommu_map_failed:
 	}
 	local_irq_restore(flags);
 
-	return 0;
+	return -EINVAL;
 }
 
 static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 0c0342e5b10d..9e3f6933ca13 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -256,7 +256,7 @@ static int __sbus_iommu_map_sg(struct device *dev, struct scatterlist *sgl,
 		sg->dma_address =__sbus_iommu_map_page(dev, sg_page(sg),
 				sg->offset, sg->length, per_page_flush);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
-			return 0;
+			return -EIO;
 		sg->dma_length = sg->length;
 	}
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index 9ac696487b13..ed837383de5c 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -331,7 +331,7 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start,
 	int i;
 
 	if (iommu_start == -1)
-		return -1;
+		return -ENOMEM;
 
 	for_each_sg(start, s, nelems, i) {
 		unsigned long pages, addr;
@@ -380,13 +380,13 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		       enum dma_data_direction dir, unsigned long attrs)
 {
 	struct scatterlist *s, *ps, *start_sg, *sgmap;
-	int need = 0, nextneed, i, out, start;
+	int need = 0, nextneed, i, out, start, ret;
 	unsigned long pages = 0;
 	unsigned int seg_size;
 	unsigned int max_seg_size;
 
 	if (nents == 0)
-		return 0;
+		return -EINVAL;
 
 	out		= 0;
 	start		= 0;
@@ -414,8 +414,9 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 			if (!iommu_merge || !nextneed || !need || s->offset ||
 			    (s->length + seg_size > max_seg_size) ||
 			    (ps->offset + ps->length) % PAGE_SIZE) {
-				if (dma_map_cont(dev, start_sg, i - start,
-						 sgmap, pages, need) < 0)
+				ret = dma_map_cont(dev, start_sg, i - start,
+						   sgmap, pages, need);
+				if (ret < 0)
 					goto error;
 				out++;
 
@@ -432,7 +433,8 @@ static int gart_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		pages += iommu_num_pages(s->offset, s->length, PAGE_SIZE);
 		ps = s;
 	}
-	if (dma_map_cont(dev, start_sg, i - start, sgmap, pages, need) < 0)
+	ret = dma_map_cont(dev, start_sg, i - start, sgmap, pages, need);
+	if (ret < 0)
 		goto error;
 	out++;
 	flush_gart();
@@ -456,9 +458,7 @@ error:
 		panic("dma_map_sg: overflow on %lu pages\n", pages);
 
 	iommu_full(dev, pages << PAGE_SHIFT, dir);
-	for_each_sg(sg, s, nents, i)
-		s->dma_address = DMA_MAPPING_ERROR;
-	return 0;
+	return ret;
 }
 
 /* allocate and map a coherent mapping */
diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 6f0df629353f..9b4c025b8871 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -973,7 +973,7 @@ static int iommu_dma_map_sg_swiotlb(struct device *dev, struct scatterlist *sg,
 
 out_unmap:
 	iommu_dma_unmap_sg_swiotlb(dev, sg, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	return 0;
+	return -EIO;
 }
 
 /*
@@ -994,11 +994,13 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	dma_addr_t iova;
 	size_t iova_len = 0;
 	unsigned long mask = dma_get_seg_boundary(dev);
+	ssize_t ret;
 	int i;
 
-	if (static_branch_unlikely(&iommu_deferred_attach_enabled) &&
-	    iommu_deferred_attach(dev, domain))
-		return 0;
+	if (static_branch_unlikely(&iommu_deferred_attach_enabled)) {
+		ret = iommu_deferred_attach(dev, domain);
+		goto out;
+	}
 
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		iommu_dma_sync_sg_for_device(dev, sg, nents, dir);
@@ -1046,14 +1048,17 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	}
 
 	iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
-	if (!iova)
+	if (!iova) {
+		ret = -ENOMEM;
 		goto out_restore_sg;
+	}
 
 	/*
 	 * We'll leave any physical concatenation to the IOMMU driver's
 	 * implementation - it knows better than we do.
 	 */
-	if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len)
+	ret = iommu_map_sg_atomic(domain, iova, sg, nents, prot);
+	if (ret < iova_len)
 		goto out_free_iova;
 
 	return __finalise_sg(dev, sg, nents, iova);
@@ -1062,7 +1067,10 @@ out_free_iova:
 	iommu_dma_free_iova(cookie, iova, iova_len, NULL);
 out_restore_sg:
 	__invalidate_sg(sg, nents);
-	return 0;
+out:
+	if (ret != -ENOMEM)
+		return -EINVAL;
+	return ret;
 }
 
 static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 63f0af10c403..5a570d495f8d 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2570,9 +2570,9 @@ size_t iommu_unmap_fast(struct iommu_domain *domain,
 }
 EXPORT_SYMBOL_GPL(iommu_unmap_fast);
 
-static size_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-			     struct scatterlist *sg, unsigned int nents, int prot,
-			     gfp_t gfp)
+static ssize_t __iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		struct scatterlist *sg, unsigned int nents, int prot,
+		gfp_t gfp)
 {
 	const struct iommu_ops *ops = domain->ops;
 	size_t len = 0, mapped = 0;
@@ -2613,19 +2613,18 @@ out_err:
 	/* undo mappings already done */
 	iommu_unmap(domain, iova, mapped);
 
-	return 0;
-
+	return ret;
 }
 
-size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-		    struct scatterlist *sg, unsigned int nents, int prot)
+ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		     struct scatterlist *sg, unsigned int nents, int prot)
 {
 	might_sleep();
 	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(iommu_map_sg);
 
-size_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
+ssize_t iommu_map_sg_atomic(struct iommu_domain *domain, unsigned long iova,
 		    struct scatterlist *sg, unsigned int nents, int prot)
 {
 	return __iommu_map_sg(domain, iova, sg, nents, prot, GFP_ATOMIC);
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index b5f9ee81a46c..452e72b7bd01 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -918,7 +918,7 @@ ccio_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	BUG_ON(!dev);
 	ioc = GET_IOC(dev);
 	if (!ioc)
-		return 0;
+		return -EINVAL;
 	
 	DBG_RUN_SG("%s() START %d entries\n", __func__, nents);
 
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index dce4cdf786cd..e60690d38d67 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -947,7 +947,7 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 
 	ioc = GET_IOC(dev);
 	if (!ioc)
-		return 0;
+		return -EINVAL;
 
 	/* Fast path single entry scatterlists. */
 	if (nents == 1) {
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index 24d11861ac7d..85d58b720a24 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -509,7 +509,7 @@ xen_swiotlb_map_sg(struct device *dev, struct scatterlist *sgl, int nelems,
 out_unmap:
 	xen_swiotlb_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
 	sg_dma_len(sgl) = 0;
-	return 0;
+	return -EIO;
 }
 
 static void
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 0d53a96a3d64..0d5b06b3a4a6 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -41,8 +41,9 @@ struct dma_map_ops {
 			size_t size, enum dma_data_direction dir,
 			unsigned long attrs);
 	/*
-	 * map_sg returns 0 on error and a value > 0 on success.
-	 * It should never return a value < 0.
+	 * map_sg should return a negative error code on error. See
+	 * dma_map_sgtable() for a list of appropriate error codes
+	 * and their meanings.
 	 */
 	int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents,
 			enum dma_data_direction dir, unsigned long attrs);
@@ -170,13 +171,6 @@ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
 int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr);
 int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
 		void *cpu_addr, size_t size, int *ret);
-
-void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
-		dma_addr_t *dma_handle);
-int dma_release_from_global_coherent(int order, void *vaddr);
-int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
-		size_t size, int *ret);
-
 #else
 static inline int dma_declare_coherent_memory(struct device *dev,
 		phys_addr_t phys_addr, dma_addr_t device_addr, size_t size)
@@ -186,7 +180,16 @@ static inline int dma_declare_coherent_memory(struct device *dev,
 #define dma_alloc_from_dev_coherent(dev, size, handle, ret) (0)
 #define dma_release_from_dev_coherent(dev, order, vaddr) (0)
 #define dma_mmap_from_dev_coherent(dev, vma, vaddr, order, ret) (0)
+#endif /* CONFIG_DMA_DECLARE_COHERENT */
 
+#ifdef CONFIG_DMA_GLOBAL_POOL
+void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
+		dma_addr_t *dma_handle);
+int dma_release_from_global_coherent(int order, void *vaddr);
+int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *cpu_addr,
+		size_t size, int *ret);
+int dma_init_global_coherent(phys_addr_t phys_addr, size_t size);
+#else
 static inline void *dma_alloc_from_global_coherent(struct device *dev,
 		ssize_t size, dma_addr_t *dma_handle)
 {
@@ -201,7 +204,7 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 {
 	return 0;
 }
-#endif /* CONFIG_DMA_DECLARE_COHERENT */
+#endif /* CONFIG_DMA_GLOBAL_POOL */
 
 /*
  * This is the actual return value from the ->alloc_noncontiguous method.
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 183e7103a66d..dca2b1355bb1 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -105,11 +105,13 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		unsigned long attrs);
 void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs);
-int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir, unsigned long attrs);
+unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs);
 void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
 				      int nents, enum dma_data_direction dir,
 				      unsigned long attrs);
+int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
+		enum dma_data_direction dir, unsigned long attrs);
 dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
@@ -164,8 +166,9 @@ static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 }
-static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
+static inline unsigned int dma_map_sg_attrs(struct device *dev,
+		struct scatterlist *sg, int nents, enum dma_data_direction dir,
+		unsigned long attrs)
 {
 	return 0;
 }
@@ -174,6 +177,11 @@ static inline void dma_unmap_sg_attrs(struct device *dev,
 		unsigned long attrs)
 {
 }
+static inline int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	return -EOPNOTSUPP;
+}
 static inline dma_addr_t dma_map_resource(struct device *dev,
 		phys_addr_t phys_addr, size_t size, enum dma_data_direction dir,
 		unsigned long attrs)
@@ -344,34 +352,6 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
 }
 
 /**
- * dma_map_sgtable - Map the given buffer for DMA
- * @dev:	The device for which to perform the DMA operation
- * @sgt:	The sg_table object describing the buffer
- * @dir:	DMA direction
- * @attrs:	Optional DMA attributes for the map operation
- *
- * Maps a buffer described by a scatterlist stored in the given sg_table
- * object for the @dir DMA operation by the @dev device. After success the
- * ownership for the buffer is transferred to the DMA domain.  One has to
- * call dma_sync_sgtable_for_cpu() or dma_unmap_sgtable() to move the
- * ownership of the buffer back to the CPU domain before touching the
- * buffer by the CPU.
- *
- * Returns 0 on success or -EINVAL on error during mapping the buffer.
- */
-static inline int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	int nents;
-
-	nents = dma_map_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs);
-	if (nents <= 0)
-		return -EINVAL;
-	sgt->nents = nents;
-	return 0;
-}
-
-/**
  * dma_unmap_sgtable - Unmap the given buffer for DMA
  * @dev:	The device for which to perform the DMA operation
  * @sgt:	The sg_table object describing the buffer
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 32d448050bf7..9369458ba1bd 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -414,11 +414,11 @@ extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 extern size_t iommu_unmap_fast(struct iommu_domain *domain,
 			       unsigned long iova, size_t size,
 			       struct iommu_iotlb_gather *iotlb_gather);
-extern size_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
-			   struct scatterlist *sg,unsigned int nents, int prot);
-extern size_t iommu_map_sg_atomic(struct iommu_domain *domain,
-				  unsigned long iova, struct scatterlist *sg,
-				  unsigned int nents, int prot);
+extern ssize_t iommu_map_sg(struct iommu_domain *domain, unsigned long iova,
+		struct scatterlist *sg, unsigned int nents, int prot);
+extern ssize_t iommu_map_sg_atomic(struct iommu_domain *domain,
+				   unsigned long iova, struct scatterlist *sg,
+				   unsigned int nents, int prot);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova);
 extern void iommu_set_fault_handler(struct iommu_domain *domain,
 			iommu_fault_handler_t handler, void *token);
@@ -679,18 +679,18 @@ static inline size_t iommu_unmap_fast(struct iommu_domain *domain,
 	return 0;
 }
 
-static inline size_t iommu_map_sg(struct iommu_domain *domain,
-				  unsigned long iova, struct scatterlist *sg,
-				  unsigned int nents, int prot)
+static inline ssize_t iommu_map_sg(struct iommu_domain *domain,
+				   unsigned long iova, struct scatterlist *sg,
+				   unsigned int nents, int prot)
 {
-	return 0;
+	return -ENODEV;
 }
 
-static inline size_t iommu_map_sg_atomic(struct iommu_domain *domain,
+static inline ssize_t iommu_map_sg_atomic(struct iommu_domain *domain,
 				  unsigned long iova, struct scatterlist *sg,
 				  unsigned int nents, int prot)
 {
-	return 0;
+	return -ENODEV;
 }
 
 static inline void iommu_flush_iotlb_all(struct iommu_domain *domain)
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
index 77b405508743..725cfd51762b 100644
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@ -93,6 +93,10 @@ config DMA_COHERENT_POOL
 	select GENERIC_ALLOCATOR
 	bool
 
+config DMA_GLOBAL_POOL
+	select DMA_DECLARE_COHERENT
+	bool
+
 config DMA_REMAP
 	bool
 	depends on MMU
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
index 794e76b03b34..25fc85a7aebe 100644
--- a/kernel/dma/coherent.c
+++ b/kernel/dma/coherent.c
@@ -20,8 +20,6 @@ struct dma_coherent_mem {
 	bool		use_dev_dma_pfn_offset;
 };
 
-static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
-
 static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev)
 {
 	if (dev && dev->dma_mem)
@@ -37,51 +35,44 @@ static inline dma_addr_t dma_get_device_base(struct device *dev,
 	return mem->device_base;
 }
 
-static int dma_init_coherent_memory(phys_addr_t phys_addr,
-		dma_addr_t device_addr, size_t size,
-		struct dma_coherent_mem **mem)
+static struct dma_coherent_mem *dma_init_coherent_memory(phys_addr_t phys_addr,
+		dma_addr_t device_addr, size_t size, bool use_dma_pfn_offset)
 {
-	struct dma_coherent_mem *dma_mem = NULL;
-	void *mem_base = NULL;
+	struct dma_coherent_mem *dma_mem;
 	int pages = size >> PAGE_SHIFT;
 	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
-	int ret;
+	void *mem_base;
 
-	if (!size) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!size)
+		return ERR_PTR(-EINVAL);
 
 	mem_base = memremap(phys_addr, size, MEMREMAP_WC);
-	if (!mem_base) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!mem_base)
+		return ERR_PTR(-EINVAL);
+
 	dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
-	if (!dma_mem) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!dma_mem)
+		goto out_unmap_membase;
 	dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!dma_mem->bitmap) {
-		ret = -ENOMEM;
-		goto out;
-	}
+	if (!dma_mem->bitmap)
+		goto out_free_dma_mem;
 
 	dma_mem->virt_base = mem_base;
 	dma_mem->device_base = device_addr;
 	dma_mem->pfn_base = PFN_DOWN(phys_addr);
 	dma_mem->size = pages;
+	dma_mem->use_dev_dma_pfn_offset = use_dma_pfn_offset;
 	spin_lock_init(&dma_mem->spinlock);
 
-	*mem = dma_mem;
-	return 0;
+	return dma_mem;
 
-out:
+out_free_dma_mem:
 	kfree(dma_mem);
-	if (mem_base)
-		memunmap(mem_base);
-	return ret;
+out_unmap_membase:
+	memunmap(mem_base);
+	pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %zd MiB\n",
+		&phys_addr, size / SZ_1M);
+	return ERR_PTR(-ENOMEM);
 }
 
 static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
@@ -130,9 +121,9 @@ int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 	struct dma_coherent_mem *mem;
 	int ret;
 
-	ret = dma_init_coherent_memory(phys_addr, device_addr, size, &mem);
-	if (ret)
-		return ret;
+	mem = dma_init_coherent_memory(phys_addr, device_addr, size, false);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
 
 	ret = dma_assign_coherent_memory(dev, mem);
 	if (ret)
@@ -198,16 +189,6 @@ int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
 	return 1;
 }
 
-void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
-				     dma_addr_t *dma_handle)
-{
-	if (!dma_coherent_default_memory)
-		return NULL;
-
-	return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size,
-					 dma_handle);
-}
-
 static int __dma_release_from_coherent(struct dma_coherent_mem *mem,
 				       int order, void *vaddr)
 {
@@ -243,15 +224,6 @@ int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr)
 	return __dma_release_from_coherent(mem, order, vaddr);
 }
 
-int dma_release_from_global_coherent(int order, void *vaddr)
-{
-	if (!dma_coherent_default_memory)
-		return 0;
-
-	return __dma_release_from_coherent(dma_coherent_default_memory, order,
-			vaddr);
-}
-
 static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
 		struct vm_area_struct *vma, void *vaddr, size_t size, int *ret)
 {
@@ -297,6 +269,28 @@ int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
 	return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret);
 }
 
+#ifdef CONFIG_DMA_GLOBAL_POOL
+static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
+
+void *dma_alloc_from_global_coherent(struct device *dev, ssize_t size,
+				     dma_addr_t *dma_handle)
+{
+	if (!dma_coherent_default_memory)
+		return NULL;
+
+	return __dma_alloc_from_coherent(dev, dma_coherent_default_memory, size,
+					 dma_handle);
+}
+
+int dma_release_from_global_coherent(int order, void *vaddr)
+{
+	if (!dma_coherent_default_memory)
+		return 0;
+
+	return __dma_release_from_coherent(dma_coherent_default_memory, order,
+			vaddr);
+}
+
 int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr,
 				   size_t size, int *ret)
 {
@@ -307,6 +301,19 @@ int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr,
 					vaddr, size, ret);
 }
 
+int dma_init_global_coherent(phys_addr_t phys_addr, size_t size)
+{
+	struct dma_coherent_mem *mem;
+
+	mem = dma_init_coherent_memory(phys_addr, phys_addr, size, true);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+	dma_coherent_default_memory = mem;
+	pr_info("DMA: default coherent area is set\n");
+	return 0;
+}
+#endif /* CONFIG_DMA_GLOBAL_POOL */
+
 /*
  * Support for reserved memory regions defined in device tree
  */
@@ -315,25 +322,22 @@ int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr,
 #include <linux/of_fdt.h>
 #include <linux/of_reserved_mem.h>
 
+#ifdef CONFIG_DMA_GLOBAL_POOL
 static struct reserved_mem *dma_reserved_default_memory __initdata;
+#endif
 
 static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
 {
-	struct dma_coherent_mem *mem = rmem->priv;
-	int ret;
-
-	if (!mem) {
-		ret = dma_init_coherent_memory(rmem->base, rmem->base,
-					       rmem->size, &mem);
-		if (ret) {
-			pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
-				&rmem->base, (unsigned long)rmem->size / SZ_1M);
-			return ret;
-		}
+	if (!rmem->priv) {
+		struct dma_coherent_mem *mem;
+
+		mem = dma_init_coherent_memory(rmem->base, rmem->base,
+					       rmem->size, true);
+		if (IS_ERR(mem))
+			return PTR_ERR(mem);
+		rmem->priv = mem;
 	}
-	mem->use_dev_dma_pfn_offset = true;
-	rmem->priv = mem;
-	dma_assign_coherent_memory(dev, mem);
+	dma_assign_coherent_memory(dev, rmem->priv);
 	return 0;
 }
 
@@ -361,7 +365,9 @@ static int __init rmem_dma_setup(struct reserved_mem *rmem)
 		pr_err("Reserved memory: regions without no-map are not yet supported\n");
 		return -EINVAL;
 	}
+#endif
 
+#ifdef CONFIG_DMA_GLOBAL_POOL
 	if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) {
 		WARN(dma_reserved_default_memory,
 		     "Reserved memory: region for default DMA coherent area is redefined\n");
@@ -375,31 +381,16 @@ static int __init rmem_dma_setup(struct reserved_mem *rmem)
 	return 0;
 }
 
+#ifdef CONFIG_DMA_GLOBAL_POOL
 static int __init dma_init_reserved_memory(void)
 {
-	const struct reserved_mem_ops *ops;
-	int ret;
-
 	if (!dma_reserved_default_memory)
 		return -ENOMEM;
-
-	ops = dma_reserved_default_memory->ops;
-
-	/*
-	 * We rely on rmem_dma_device_init() does not propagate error of
-	 * dma_assign_coherent_memory() for "NULL" device.
-	 */
-	ret = ops->device_init(dma_reserved_default_memory, NULL);
-
-	if (!ret) {
-		dma_coherent_default_memory = dma_reserved_default_memory->priv;
-		pr_info("DMA: default coherent area is set\n");
-	}
-
-	return ret;
+	return dma_init_global_coherent(dma_reserved_default_memory->base,
+					dma_reserved_default_memory->size);
 }
-
 core_initcall(dma_init_reserved_memory);
+#endif /* CONFIG_DMA_GLOBAL_POOL */
 
 RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
 #endif
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index dadae6255d05..6c90c69e5311 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -792,7 +792,7 @@ static int dump_show(struct seq_file *seq, void *v)
 }
 DEFINE_SHOW_ATTRIBUTE(dump);
 
-static void dma_debug_fs_init(void)
+static int __init dma_debug_fs_init(void)
 {
 	struct dentry *dentry = debugfs_create_dir("dma-api", NULL);
 
@@ -805,7 +805,10 @@ static void dma_debug_fs_init(void)
 	debugfs_create_u32("nr_total_entries", 0444, dentry, &nr_total_entries);
 	debugfs_create_file("driver_filter", 0644, dentry, NULL, &filter_fops);
 	debugfs_create_file("dump", 0444, dentry, NULL, &dump_fops);
+
+	return 0;
 }
+core_initcall_sync(dma_debug_fs_init);
 
 static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry)
 {
@@ -890,8 +893,6 @@ static int dma_debug_init(void)
 		spin_lock_init(&dma_entry_hash[i].lock);
 	}
 
-	dma_debug_fs_init();
-
 	nr_pages = DIV_ROUND_UP(nr_prealloc_entries, DMA_DEBUG_DYNAMIC_ENTRIES);
 	for (i = 0; i < nr_pages; ++i)
 		dma_debug_create_entries(GFP_KERNEL);
@@ -1064,20 +1065,10 @@ static void check_for_stack(struct device *dev,
 	}
 }
 
-static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
-{
-	unsigned long a1 = (unsigned long)addr;
-	unsigned long b1 = a1 + len;
-	unsigned long a2 = (unsigned long)start;
-	unsigned long b2 = (unsigned long)end;
-
-	return !(b1 <= a2 || a1 >= b2);
-}
-
 static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
 {
-	if (overlap(addr, len, _stext, _etext) ||
-	    overlap(addr, len, __start_rodata, __end_rodata))
+	if (memory_intersects(_stext, _etext, addr, len) ||
+	    memory_intersects(__start_rodata, __end_rodata, addr, len))
 		err_printk(dev, NULL, "device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
 }
 
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index f737e3347059..8dca4f97d12d 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -156,9 +156,14 @@ void *dma_direct_alloc(struct device *dev, size_t size,
 
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
 	    !dev_is_dma_coherent(dev))
 		return arch_dma_alloc(dev, size, dma_handle, gfp, attrs);
 
+	if (IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
+	    !dev_is_dma_coherent(dev))
+		return dma_alloc_from_global_coherent(dev, size, dma_handle);
+
 	/*
 	 * Remapping or decrypting memory may block. If either is required and
 	 * we can't block, allocate the memory from the atomic pools.
@@ -255,11 +260,19 @@ void dma_direct_free(struct device *dev, size_t size,
 
 	if (!IS_ENABLED(CONFIG_ARCH_HAS_DMA_SET_UNCACHED) &&
 	    !IS_ENABLED(CONFIG_DMA_DIRECT_REMAP) &&
+	    !IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
 	    !dev_is_dma_coherent(dev)) {
 		arch_dma_free(dev, size, cpu_addr, dma_addr, attrs);
 		return;
 	}
 
+	if (IS_ENABLED(CONFIG_DMA_GLOBAL_POOL) &&
+	    !dev_is_dma_coherent(dev)) {
+		if (!dma_release_from_global_coherent(page_order, cpu_addr))
+			WARN_ON_ONCE(1);
+		return;
+	}
+
 	/* If cpu_addr is not from an atomic pool, dma_free_from_pool() fails */
 	if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) &&
 	    dma_free_from_pool(dev, cpu_addr, PAGE_ALIGN(size)))
@@ -411,7 +424,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 
 out_unmap:
 	dma_direct_unmap_sg(dev, sgl, i, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC);
-	return 0;
+	return -EIO;
 }
 
 dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
@@ -462,6 +475,8 @@ int dma_direct_mmap(struct device *dev, struct vm_area_struct *vma,
 
 	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
+	if (dma_mmap_from_global_coherent(vma, cpu_addr, size, &ret))
+		return ret;
 
 	if (vma->vm_pgoff >= count || user_count > count - vma->vm_pgoff)
 		return -ENXIO;
diff --git a/kernel/dma/dummy.c b/kernel/dma/dummy.c
index eacd4c5b10bf..b492d59ac77e 100644
--- a/kernel/dma/dummy.c
+++ b/kernel/dma/dummy.c
@@ -22,7 +22,7 @@ static int dma_dummy_map_sg(struct device *dev, struct scatterlist *sgl,
 		int nelems, enum dma_data_direction dir,
 		unsigned long attrs)
 {
-	return 0;
+	return -EINVAL;
 }
 
 static int dma_dummy_supported(struct device *hwdev, u64 mask)
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 2b06a809d0b9..7ee5284bff58 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -177,12 +177,8 @@ void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 }
 EXPORT_SYMBOL(dma_unmap_page_attrs);
 
-/*
- * dma_maps_sg_attrs returns 0 on error and > 0 on success.
- * It should never return a value < 0.
- */
-int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir, unsigned long attrs)
+static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
+	 int nents, enum dma_data_direction dir, unsigned long attrs)
 {
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 	int ents;
@@ -197,13 +193,81 @@ int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg, int nents,
 		ents = dma_direct_map_sg(dev, sg, nents, dir, attrs);
 	else
 		ents = ops->map_sg(dev, sg, nents, dir, attrs);
-	BUG_ON(ents < 0);
-	debug_dma_map_sg(dev, sg, nents, ents, dir);
+
+	if (ents > 0)
+		debug_dma_map_sg(dev, sg, nents, ents, dir);
+	else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM &&
+			      ents != -EIO))
+		return -EIO;
 
 	return ents;
 }
+
+/**
+ * dma_map_sg_attrs - Map the given buffer for DMA
+ * @dev:	The device for which to perform the DMA operation
+ * @sg:	The sg_table object describing the buffer
+ * @dir:	DMA direction
+ * @attrs:	Optional DMA attributes for the map operation
+ *
+ * Maps a buffer described by a scatterlist passed in the sg argument with
+ * nents segments for the @dir DMA operation by the @dev device.
+ *
+ * Returns the number of mapped entries (which can be less than nents)
+ * on success. Zero is returned for any error.
+ *
+ * dma_unmap_sg_attrs() should be used to unmap the buffer with the
+ * original sg and original nents (not the value returned by this funciton).
+ */
+unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
+		    int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	int ret;
+
+	ret = __dma_map_sg_attrs(dev, sg, nents, dir, attrs);
+	if (ret < 0)
+		return 0;
+	return ret;
+}
 EXPORT_SYMBOL(dma_map_sg_attrs);
 
+/**
+ * dma_map_sgtable - Map the given buffer for DMA
+ * @dev:	The device for which to perform the DMA operation
+ * @sgt:	The sg_table object describing the buffer
+ * @dir:	DMA direction
+ * @attrs:	Optional DMA attributes for the map operation
+ *
+ * Maps a buffer described by a scatterlist stored in the given sg_table
+ * object for the @dir DMA operation by the @dev device. After success, the
+ * ownership for the buffer is transferred to the DMA domain.  One has to
+ * call dma_sync_sgtable_for_cpu() or dma_unmap_sgtable() to move the
+ * ownership of the buffer back to the CPU domain before touching the
+ * buffer by the CPU.
+ *
+ * Returns 0 on success or a negative error code on error. The following
+ * error codes are supported with the given meaning:
+ *
+ *   -EINVAL - An invalid argument, unaligned access or other error
+ *	       in usage. Will not succeed if retried.
+ *   -ENOMEM - Insufficient resources (like memory or IOVA space) to
+ *	       complete the mapping. Should succeed if retried later.
+ *   -EIO    - Legacy error code with an unknown meaning. eg. this is
+ *	       returned if a lower level call returned DMA_MAPPING_ERROR.
+ */
+int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
+		    enum dma_data_direction dir, unsigned long attrs)
+{
+	int nents;
+
+	nents = __dma_map_sg_attrs(dev, sgt->sgl, sgt->orig_nents, dir, attrs);
+	if (nents < 0)
+		return nents;
+	sgt->nents = nents;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dma_map_sgtable);
+
 void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
 				      int nents, enum dma_data_direction dir,
 				      unsigned long attrs)