Merge tag 'dma-mapping-4.13' of git://git.infradead.org/users/hch/dma-mapping

Pull dma-mapping infrastructure from Christoph Hellwig:
 "This is the first pull request for the new dma-mapping subsystem

  In this new subsystem we'll try to properly maintain all the generic
  code related to dma-mapping, and will further consolidate arch code
  into common helpers.

  This pull request contains:

   - removal of the DMA_ERROR_CODE macro, replacing it with calls to
     ->mapping_error so that the dma_map_ops instances are more self
     contained and can be shared across architectures (me)

   - removal of the ->set_dma_mask method, which duplicates the
     ->dma_capable one in terms of functionality, but requires more
     duplicate code.

   - various updates for the coherent dma pool and related arm code
     (Vladimir)

   - various smaller cleanups (me)"

* tag 'dma-mapping-4.13' of git://git.infradead.org/users/hch/dma-mapping: (56 commits)
  ARM: dma-mapping: Remove traces of NOMMU code
  ARM: NOMMU: Set ARM_DMA_MEM_BUFFERABLE for M-class cpus
  ARM: NOMMU: Introduce dma operations for noMMU
  drivers: dma-mapping: allow dma_common_mmap() for NOMMU
  drivers: dma-coherent: Introduce default DMA pool
  drivers: dma-coherent: Account dma_pfn_offset when used with device tree
  dma: Take into account dma_pfn_offset
  dma-mapping: replace dmam_alloc_noncoherent with dmam_alloc_attrs
  dma-mapping: remove dmam_free_noncoherent
  crypto: qat - avoid an uninitialized variable warning
  au1100fb: remove a bogus dma_free_nonconsistent call
  MAINTAINERS: add entry for dma mapping helpers
  powerpc: merge __dma_set_mask into dma_set_mask
  dma-mapping: remove the set_dma_mask method
  powerpc/cell: use the dma_supported method for ops switching
  powerpc/cell: clean up fixed mapping dma_ops initialization
  tile: remove dma_supported and mapping_error methods
  xen-swiotlb: remove xen_swiotlb_set_dma_mask
  arm: implement ->dma_supported instead of ->set_dma_mask
  mips/loongson64: implement ->dma_supported instead of ->set_dma_mask
  ...

75 files changed, 778 insertions, 725 deletions

diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index 979228bc9035..4ed388356898 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -550,32 +550,11 @@ and to unmap it:
 	dma_unmap_single(dev, dma_handle, size, direction);
 
 You should call dma_mapping_error() as dma_map_single() could fail and return
-error. Not all DMA implementations support the dma_mapping_error() interface.
-However, it is a good practice to call dma_mapping_error() interface, which
-will invoke the generic mapping error check interface. Doing so will ensure
-that the mapping code will work correctly on all DMA implementations without
-any dependency on the specifics of the underlying implementation. Using the
-returned address without checking for errors could result in failures ranging
-from panics to silent data corruption. A couple of examples of incorrect ways
-to check for errors that make assumptions about the underlying DMA
-implementation are as follows and these are applicable to dma_map_page() as
-well.
-
-Incorrect example 1:
-	dma_addr_t dma_handle;
-
-	dma_handle = dma_map_single(dev, addr, size, direction);
-	if ((dma_handle & 0xffff != 0) || (dma_handle >= 0x1000000)) {
-		goto map_error;
-	}
-
-Incorrect example 2:
-	dma_addr_t dma_handle;
-
-	dma_handle = dma_map_single(dev, addr, size, direction);
-	if (dma_handle == DMA_ERROR_CODE) {
-		goto map_error;
-	}
+error.  Doing so will ensure that the mapping code will work correctly on all
+DMA implementations without any dependency on the specifics of the underlying
+implementation. Using the returned address without checking for errors could
+result in failures ranging from panics to silent data corruption.  The same
+applies to dma_map_page() as well.
 
 You should call dma_unmap_single() when the DMA activity is finished, e.g.,
 from the interrupt which told you that the DMA transfer is done.
diff --git a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
index 3da0ebdba8d9..16291f2a4688 100644
--- a/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
+++ b/Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
@@ -68,6 +68,9 @@ Linux implementation note:
 - If a "linux,cma-default" property is present, then Linux will use the
   region for the default pool of the contiguous memory allocator.
 
+- If a "linux,dma-default" property is present, then Linux will use the
+  region for the default pool of the consistent DMA allocator.
+
 Device node references to reserved memory
 -----------------------------------------
 Regions in the /reserved-memory node may be referenced by other device
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index 2d132fcea0f8..4231b45b2f8f 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -240,10 +240,9 @@ CLOCK
 
 DMA
   dmam_alloc_coherent()
-  dmam_alloc_noncoherent()
+  dmam_alloc_attrs()
   dmam_declare_coherent_memory()
   dmam_free_coherent()
-  dmam_free_noncoherent()
   dmam_pool_create()
   dmam_pool_destroy()
 
diff --git a/MAINTAINERS b/MAINTAINERS
index c8f7952b8bbe..e23b07d2ce1d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2631,6 +2631,21 @@ S:	Maintained
 F:	net/bluetooth/
 F:	include/net/bluetooth/
 
+DMA MAPPING HELPERS
+M:	Christoph Hellwig <hch@lst.de>
+M:	Marek Szyprowski <m.szyprowski@samsung.com>
+R:	Robin Murphy <robin.murphy@arm.com>
+L:	linux-kernel@vger.kernel.org
+T:	git git://git.infradead.org/users/hch/dma-mapping.git
+W:	http://git.infradead.org/users/hch/dma-mapping.git
+S:	Supported
+F:	lib/dma-debug.c
+F:	lib/dma-noop.c
+F:	lib/dma-virt.c
+F:	drivers/base/dma-mapping.c
+F:	drivers/base/dma-coherent.c
+F:	include/linux/dma-mapping.h
+
 BONDING DRIVER
 M:	Jay Vosburgh <j.vosburgh@gmail.com>
 M:	Veaceslav Falico <vfalico@gmail.com>
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index abd59fad1a34..0b731e8ab17e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -22,6 +22,7 @@ config ARM
 	select CLONE_BACKWARDS
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS if HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select DMA_NOOP_OPS if !MMU
 	select EDAC_SUPPORT
 	select EDAC_ATOMIC_SCRUB
 	select GENERIC_ALLOCATOR
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index 9b1b7be2ec0e..9a92de63426f 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -33,6 +33,7 @@
 #include <linux/scatterlist.h>
 
 #include <asm/cacheflush.h>
+#include <asm/dma-iommu.h>
 
 #undef STATS
 
@@ -256,7 +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 DMA_ERROR_CODE;
+		return ARM_MAPPING_ERROR;
 	}
 
 	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
@@ -326,7 +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 DMA_ERROR_CODE;
+		return ARM_MAPPING_ERROR;
 
 	if (ret == 0) {
 		arm_dma_ops.sync_single_for_device(dev, dma_addr, size, dir);
@@ -335,7 +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 DMA_ERROR_CODE;
+		return ARM_MAPPING_ERROR;
 	}
 
 	return map_single(dev, page_address(page) + offset, size, dir, attrs);
@@ -444,12 +445,17 @@ static void dmabounce_sync_for_device(struct device *dev,
 	arm_dma_ops.sync_single_for_device(dev, handle, size, dir);
 }
 
-static int dmabounce_set_mask(struct device *dev, u64 dma_mask)
+static int dmabounce_dma_supported(struct device *dev, u64 dma_mask)
 {
 	if (dev->archdata.dmabounce)
 		return 0;
 
-	return arm_dma_ops.set_dma_mask(dev, 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 = {
@@ -465,7 +471,8 @@ static const struct dma_map_ops dmabounce_ops = {
 	.unmap_sg		= arm_dma_unmap_sg,
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
-	.set_dma_mask		= dmabounce_set_mask,
+	.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 2ef282f96651..c090ec675eac 100644
--- a/arch/arm/include/asm/dma-iommu.h
+++ b/arch/arm/include/asm/dma-iommu.h
@@ -9,6 +9,8 @@
 #include <linux/kmemcheck.h>
 #include <linux/kref.h>
 
+#define ARM_MAPPING_ERROR		(~(dma_addr_t)0x0)
+
 struct dma_iommu_mapping {
 	/* iommu specific data */
 	struct iommu_domain	*domain;
@@ -33,5 +35,7 @@ int arm_iommu_attach_device(struct device *dev,
 					struct dma_iommu_mapping *mapping);
 void arm_iommu_detach_device(struct device *dev);
 
+int arm_dma_supported(struct device *dev, u64 mask);
+
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 680d3f3889e7..4e0285a66ef8 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -12,18 +12,14 @@
 #include <xen/xen.h>
 #include <asm/xen/hypervisor.h>
 
-#define DMA_ERROR_CODE	(~(dma_addr_t)0x0)
 extern const struct dma_map_ops arm_dma_ops;
 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 &arm_dma_ops;
+	return IS_ENABLED(CONFIG_MMU) ? &arm_dma_ops : &dma_noop_ops;
 }
 
-#define HAVE_ARCH_DMA_SUPPORTED 1
-extern int dma_supported(struct device *dev, u64 mask);
-
 #ifdef __arch_page_to_dma
 #error Please update to __arch_pfn_to_dma
 #endif
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index c6c4c9c8824b..877a0e3fd17d 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1045,8 +1045,8 @@ config ARM_L1_CACHE_SHIFT
 	default 5
 
 config ARM_DMA_MEM_BUFFERABLE
-	bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7
-	default y if CPU_V6 || CPU_V6K || CPU_V7
+	bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K || CPU_V7M) && !CPU_V7
+	default y if CPU_V6 || CPU_V6K || CPU_V7 || CPU_V7M
 	help
 	  Historically, the kernel has used strongly ordered mappings to
 	  provide DMA coherent memory.  With the advent of ARMv7, mapping
@@ -1061,6 +1061,10 @@ config ARM_DMA_MEM_BUFFERABLE
 	  and therefore turning this on may result in unpredictable driver
 	  behaviour.  Therefore, we offer this as an option.
 
+	  On some of the beefier ARMv7-M machines (with DMA and write
+	  buffers) you likely want this enabled, while those that
+	  didn't need it until now also won't need it in the future.
+
 	  You are recommended say 'Y' here and debug any affected drivers.
 
 config ARM_HEAVY_MB
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index b3dea80715b4..950d19babb5f 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -2,9 +2,8 @@
 # Makefile for the linux arm-specific parts of the memory manager.
 #
 
-obj-y				:= dma-mapping.o extable.o fault.o init.o \
-				   iomap.o
-
+obj-y				:= extable.o fault.o init.o iomap.o
+obj-y				+= dma-mapping$(MMUEXT).o
 obj-$(CONFIG_MMU)		+= fault-armv.o flush.o idmap.o ioremap.o \
 				   mmap.o pgd.o mmu.o pageattr.o
 
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
new file mode 100644
index 000000000000..90ee354d803e
--- /dev/null
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -0,0 +1,228 @@
+/*
+ *  Based on linux/arch/arm/mm/dma-mapping.c
+ *
+ *  Copyright (C) 2000-2004 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+
+#include <asm/cachetype.h>
+#include <asm/cacheflush.h>
+#include <asm/outercache.h>
+#include <asm/cp15.h>
+
+#include "dma.h"
+
+/*
+ *  dma_noop_ops 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)
+
+{
+	const struct dma_map_ops *ops = &dma_noop_ops;
+
+	/*
+	 * We are here 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.
+	 */
+
+	if (attrs & DMA_ATTR_NON_CONSISTENT)
+		return ops->alloc(dev, size, dma_handle, gfp, attrs);
+
+	WARN_ON_ONCE(1);
+	return NULL;
+}
+
+static void arm_nommu_dma_free(struct device *dev, size_t size,
+			       void *cpu_addr, dma_addr_t dma_addr,
+			       unsigned long attrs)
+{
+	const struct dma_map_ops *ops = &dma_noop_ops;
+
+	if (attrs & DMA_ATTR_NON_CONSISTENT)
+		ops->free(dev, size, cpu_addr, dma_addr, attrs);
+	else
+		WARN_ON_ONCE(1);
+
+	return;
+}
+
+static void __dma_page_cpu_to_dev(phys_addr_t paddr, size_t size,
+				  enum dma_data_direction dir)
+{
+	dmac_map_area(__va(paddr), size, dir);
+
+	if (dir == DMA_FROM_DEVICE)
+		outer_in