Merge branch 'akpm/master'

123 files changed, 2544 insertions, 3596 deletions

diff --git a/Documentation/ABI/testing/configfs-iio b/Documentation/ABI/testing/configfs-iio
new file mode 100644
index 000000000000..2483756fccf5
--- /dev/null
+++ b/Documentation/ABI/testing/configfs-iio
@@ -0,0 +1,21 @@
+What:		/config/iio
+Date:		October 2015
+KernelVersion:	4.4
+Contact:	linux-iio@vger.kernel.org
+Description:
+		This represents Industrial IO configuration entry point
+		directory. It contains sub-groups corresponding to IIO
+		objects.
+
+What:		/config/iio/triggers
+Date:		October 2015
+KernelVersion:	4.4
+Description:
+		Industrial IO software triggers directory.
+
+What:		/config/iio/triggers/hrtimers
+Date:		October 2015
+KernelVersion:	4.4
+Description:
+		High resolution timers directory. Creating a directory here
+		will result in creating a hrtimer trigger in the IIO subsystem.
diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt
index d69b3fc64e14..781024ef9050 100644
--- a/Documentation/DMA-API-HOWTO.txt
+++ b/Documentation/DMA-API-HOWTO.txt
@@ -951,16 +951,6 @@ to "Closing".
    alignment constraints (e.g. the alignment constraints about 64-bit
    objects).
 
-3) Supporting multiple types of IOMMUs
-
-   If your architecture needs to support multiple types of IOMMUs, you
-   can use include/linux/asm-generic/dma-mapping-common.h. It's a
-   library to support the DMA API with multiple types of IOMMUs. Lots
-   of architectures (x86, powerpc, sh, alpha, ia64, microblaze and
-   sparc) use it. Choose one to see how it can be used. If you need to
-   support multiple types of IOMMUs in a single system, the example of
-   x86 or powerpc helps.
-
 			   Closing
 
 This document, and the API itself, would not be in its current
diff --git a/Documentation/cgroup.txt b/Documentation/cgroup.txt
index 31d1f7bf12a1..f441564023e1 100644
--- a/Documentation/cgroup.txt
+++ b/Documentation/cgroup.txt
@@ -819,6 +819,22 @@ PAGE_SIZE multiple when read back.
 		the cgroup.  This may not exactly match the number of
 		processes killed but should generally be close.
 
+  memory.swap.current
+
+	A read-only single value file which exists on non-root
+	cgroups.
+
+	The total amount of swap currently being used by the cgroup
+	and its descendants.
+
+  memory.swap.max
+
+	A read-write single value file which exists on non-root
+	cgroups.  The default is "max".
+
+	Swap usage hard limit.  If a cgroup's swap usage reaches this
+	limit, anonymous meomry of the cgroup will not be swapped out.
+
 
 5-2-2. General Usage
 
@@ -1291,3 +1307,20 @@ allocation from the slack available in other groups or the rest of the
 system than killing the group.  Otherwise, memory.max is there to
 limit this type of spillover and ultimately contain buggy or even
 malicious applications.
+
+The combined memory+swap accounting and limiting is replaced by real
+control over swap space.
+
+The main argument for a combined memory+swap facility in the original
+cgroup design was that global or parental pressure would always be
+able to swap all anonymous memory of a child group, regardless of the
+child's own (possibly untrusted) configuration.  However, untrusted
+groups can sabotage swapping by other means - such as referencing its
+anonymous memory in a tight loop - and an admin can not assume full
+swappability when overcommitting untrusted jobs.
+
+For trusted jobs, on the other hand, a combined counter is not an
+intuitive userspace interface, and it flies in the face of the idea
+that cgroup controllers should account and limit specific physical
+resources.  Swap space is a resource like all others in the system,
+and that's why unified hierarchy allows distributing it separately.
diff --git a/Documentation/features/io/dma_map_attrs/arch-support.txt b/Documentation/features/io/dma_map_attrs/arch-support.txt
deleted file mode 100644
index 51d0f1c02a3e..000000000000
--- a/Documentation/features/io/dma_map_attrs/arch-support.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-#
-# Feature name:          dma_map_attrs
-#         Kconfig:       HAVE_DMA_ATTRS
-#         description:   arch provides dma_*map*_attrs() APIs
-#
-    -----------------------
-    |         arch |status|
-    -----------------------
-    |       alpha: |  ok  |
-    |         arc: | TODO |
-    |         arm: |  ok  |
-    |       arm64: |  ok  |
-    |       avr32: | TODO |
-    |    blackfin: | TODO |
-    |         c6x: | TODO |
-    |        cris: | TODO |
-    |         frv: | TODO |
-    |       h8300: |  ok  |
-    |     hexagon: |  ok  |
-    |        ia64: |  ok  |
-    |        m32r: | TODO |
-    |        m68k: | TODO |
-    |       metag: | TODO |
-    |  microblaze: |  ok  |
-    |        mips: |  ok  |
-    |     mn10300: | TODO |
-    |       nios2: | TODO |
-    |    openrisc: |  ok  |
-    |      parisc: | TODO |
-    |     powerpc: |  ok  |
-    |        s390: |  ok  |
-    |       score: | TODO |
-    |          sh: |  ok  |
-    |       sparc: |  ok  |
-    |        tile: |  ok  |
-    |          um: | TODO |
-    |   unicore32: |  ok  |
-    |         x86: |  ok  |
-    |      xtensa: | TODO |
-    -----------------------
diff --git a/Documentation/iio/iio_configfs.txt b/Documentation/iio/iio_configfs.txt
new file mode 100644
index 000000000000..f0add35cd52e
--- /dev/null
+++ b/Documentation/iio/iio_configfs.txt
@@ -0,0 +1,93 @@
+Industrial IIO configfs support
+
+1. Overview
+
+Configfs is a filesystem-based manager of kernel objects. IIO uses some
+objects that could be easily configured using configfs (e.g.: devices,
+triggers).
+
+See Documentation/filesystems/configfs/configfs.txt for more information
+about how configfs works.
+
+2. Usage
+
+In order to use configfs support in IIO we need to select it at compile
+time via CONFIG_IIO_CONFIGFS config option.
+
+Then, mount the configfs filesystem (usually under /config directory):
+
+$ mkdir /config
+$ mount -t configfs none /config
+
+At this point, all default IIO groups will be created and can be accessed
+under /config/iio. Next chapters will describe available IIO configuration
+objects.
+
+3. Software triggers
+
+One of the IIO default configfs groups is the "triggers" group. It is
+automagically accessible when the configfs is mounted and can be found
+under /config/iio/triggers.
+
+IIO software triggers implementation offers support for creating multiple
+trigger types. A new trigger type is usually implemented as a separate
+kernel module following the interface in include/linux/iio/sw_trigger.h:
+
+/*
+ * drivers/iio/trigger/iio-trig-sample.c
+ * sample kernel module implementing a new trigger type
+ */
+#include <linux/iio/sw_trigger.h>
+
+
+static struct iio_sw_trigger *iio_trig_sample_probe(const char *name)
+{
+	/*
+	 * This allocates and registers an IIO trigger plus other
+	 * trigger type specific initialization.
+	 */
+}
+
+static int iio_trig_hrtimer_remove(struct iio_sw_trigger *swt)
+{
+	/*
+	 * This undoes the actions in iio_trig_sample_probe
+	 */
+}
+
+static const struct iio_sw_trigger_ops iio_trig_sample_ops = {
+	.probe		= iio_trig_sample_probe,
+	.remove		= iio_trig_sample_remove,
+};
+
+static struct iio_sw_trigger_type iio_trig_sample = {
+	.name = "trig-sample",
+	.owner = THIS_MODULE,
+	.ops = &iio_trig_sample_ops,
+};
+
+module_iio_sw_trigger_driver(iio_trig_sample);
+
+Each trigger type has its own directory under /config/iio/triggers. Loading
+iio-trig-sample module will create 'trig-sample' trigger type directory
+/config/iio/triggers/trig-sample.
+
+We support the following interrupt sources (trigger types):
+	* hrtimer, uses high resolution timers as interrupt source
+
+3.1 Hrtimer triggers creation and destruction
+
+Loading iio-trig-hrtimer module will register hrtimer trigger types allowing
+users to create hrtimer triggers under /config/iio/triggers/hrtimer.
+
+e.g:
+
+$ mkdir /config/triggers/hrtimer/instance1
+$ rmdir /config/triggers/hrtimer/instance1
+
+Each trigger can have one or more attributes specific to the trigger type.
+
+3.2 "hrtimer" trigger types attributes
+
+"hrtimer" trigger type doesn't have any configurable attribute from /config dir.
+It does introduce the sampling_frequency attribute to trigger directory.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 38ded23556a7..7665f7f50eee 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -611,6 +611,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	cgroup.memory=	[KNL] Pass options to the cgroup memory controller.
 			Format: <string>
 			nosocket -- Disable socket memory accounting.
+			nokmem -- Disable kernel memory accounting.
 
 	checkreqprot	[SELINUX] Set initial checkreqprot flag value.
 			Format: { "0" | "1" }
diff --git a/arch/Kconfig b/arch/Kconfig
index 30fc02aa5a32..dc5e0f2e981a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -212,9 +212,6 @@ config HAVE_NMI_WATCHDOG
 config HAVE_ARCH_TRACEHOOK
 	bool
 
-config HAVE_DMA_ATTRS
-	bool
-
 config HAVE_DMA_CONTIGUOUS
 	bool
 
@@ -639,4 +636,7 @@ config OLD_SIGACTION
 config COMPAT_OLD_SIGACTION
 	bool
 
+config ARCH_NO_COHERENT_DMA_MMAP
+	bool
+
 source "kernel/gcov/Kconfig"
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index f515a4dbf7a0..9d8a85801ed1 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -9,7 +9,6 @@ config ALPHA
 	select HAVE_OPROFILE
 	select HAVE_PCSPKR_PLATFORM
 	select HAVE_PERF_EVENTS
-	select HAVE_DMA_ATTRS
 	select VIRT_TO_BUS
 	select GENERIC_IRQ_PROBE
 	select AUTO_IRQ_AFFINITY if SMP
diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h
index 72a8ca7796d9..3c3451f58ff4 100644
--- a/arch/alpha/include/asm/dma-mapping.h
+++ b/arch/alpha/include/asm/dma-mapping.h
@@ -10,8 +10,6 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 	return dma_ops;
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 #define dma_cache_sync(dev, va, size, dir)		  ((void)0)
 
 #endif	/* _ALPHA_DMA_MAPPING_H */
diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h
index 2d28ba939d8e..660205414f1d 100644
--- a/arch/arc/include/asm/dma-mapping.h
+++ b/arch/arc/include/asm/dma-mapping.h
@@ -11,192 +11,11 @@
 #ifndef ASM_ARC_DMA_MAPPING_H
 #define ASM_ARC_DMA_MAPPING_H
 
-#include <asm-generic/dma-coherent.h>
-#include <asm/cacheflush.h>
+extern struct dma_map_ops arc_dma_ops;
 
-void *dma_alloc_noncoherent(struct device *dev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t gfp);
-
-void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
-			  dma_addr_t dma_handle);
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t gfp);
-
-void dma_free_coherent(struct device *dev, size_t size, void *kvaddr,
-		       dma_addr_t dma_handle);
-
-/* drivers/base/dma-mapping.c */
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
-extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size);
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
-#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
-
-/*
- * streaming DMA Mapping API...
- * CPU accesses page via normal paddr, thus needs to explicitly made
- * consistent before each use
- */
-
-static inline void __inline_dma_cache_sync(unsigned long paddr, size_t size,
-					   enum dma_data_direction dir)
-{
-	switch (dir) {
-	case DMA_FROM_DEVICE:
-		dma_cache_inv(paddr, size);
-		break;
-	case DMA_TO_DEVICE:
-		dma_cache_wback(paddr, size);
-		break;
-	case DMA_BIDIRECTIONAL:
-		dma_cache_wback_inv(paddr, size);
-		break;
-	default:
-		pr_err("Invalid DMA dir [%d] for OP @ %lx\n", dir, paddr);
-	}
-}
-
-void __arc_dma_cache_sync(unsigned long paddr, size_t size,
-			  enum dma_data_direction dir);
-
-#define _dma_cache_sync(addr, sz, dir)			\
-do {							\
-	if (__builtin_constant_p(dir))			\
-		__inline_dma_cache_sync(addr, sz, dir);	\
-	else						\
-		__arc_dma_cache_sync(addr, sz, dir);	\
-}							\
-while (0);
-
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *cpu_addr, size_t size,
-	       enum dma_data_direction dir)
-{
-	_dma_cache_sync((unsigned long)cpu_addr, size, dir);
-	return (dma_addr_t)cpu_addr;
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-		 size_t size, enum dma_data_direction dir)
-{
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size,
-	     enum dma_data_direction dir)
-{
-	unsigned long paddr = page_to_phys(page) + offset;
-	return dma_map_single(dev, (void *)paddr, size, dir);
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
-	       size_t size, enum dma_data_direction dir)
-{
-}
-
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg,
-	   int nents, enum dma_data_direction dir)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
-					       s->length, dir);
-
-	return nents;
-}
-
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-	     int nents, enum dma_data_direction dir)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nents, i)
-		dma_unmap_page(dev, sg_dma_address(s), sg_dma_len(s), dir);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			size_t size, enum dma_data_direction dir)
-{
-	_dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE);
-}
-
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir)
-{
-	_dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction direction)
-{
-	_dma_cache_sync(dma_handle + offset, size, DMA_FROM_DEVICE);
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction direction)
-{
-	_dma_cache_sync(dma_handle + offset, size, DMA_TO_DEVICE);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
-		    enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
-		       int nelems, enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
-}
-
-static inline int dma_supported(struct device *dev, u64 dma_mask)
-{
-	/* Support 32 bit DMA mask exclusively */
-	return dma_mask == DMA_BIT_MASK(32);
-}
-
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-
-	return 0;
+	return &arc_dma_ops;
 }
 
 #endif
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 29a46bb198cc..695029f41a48 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -17,18 +17,14 @@
  */
 
 #include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
-#include <linux/export.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
 
-/*
- * Helpers for Coherent DMA API.
- */
-void *dma_alloc_noncoherent(struct device *dev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t gfp)
+
+static void *arc_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
-	void *paddr;
+	void *paddr, *kvaddr;
 
 	/* This is linear addr (0x8000_0000 based) */
 	paddr = alloc_pages_exact(size, gfp);
@@ -38,22 +34,6 @@ void *dma_alloc_noncoherent(struct device *dev, size_t size,
 	/* This is bus address, platform dependent */
 	*dma_handle = (dma_addr_t)paddr;
 
-	return paddr;
-}
-EXPORT_SYMBOL(dma_alloc_noncoherent);
-
-void dma_free_noncoherent(struct device *dev, size_t size, void *vaddr,
-			  dma_addr_t dma_handle)
-{
-	free_pages_exact((void *)dma_handle, size);
-}
-EXPORT_SYMBOL(dma_free_noncoherent);
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t gfp)
-{
-	void *paddr, *kvaddr;
-
 	/*
 	 * IOC relies on all data (even coherent DMA data) being in cache
 	 * Thus allocate normal cached memory
@@ -65,22 +45,15 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 	 *   -For coherent data, Read/Write to buffers terminate early in cache
 	 *   (vs. always going to memory - thus are faster)
 	 */
-	if (is_isa_arcv2() && ioc_exists)
-		return dma_alloc_noncoherent(dev, size, dma_handle, gfp);
-
-	/* This is linear addr (0x8000_0000 based) */
-	paddr = alloc_pages_exact(size, gfp);
-	if (!paddr)
-		return NULL;
+	if ((is_isa_arcv2() && ioc_exists) ||
+	    dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs))
+		return paddr;
 
 	/* This is kernel Virtual address (0x7000_0000 based) */
 	kvaddr = ioremap_nocache((unsigned long)paddr, size);
 	if (kvaddr == NULL)
 		return NULL;
 
-	/* This is bus address, platform dependent */
-	*dma_handle = (dma_addr_t)paddr;
-
 	/*
 	 * Evict any existing L1 and/or L2 lines for the backing page
 	 * in case it was used earlier as a normal "cached" page.
@@ -95,26 +68,110 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 
 	return kvaddr;
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *dev, size_t size, void *kvaddr,
-		       dma_addr_t dma_handle)
+static void arc_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
-	if (is_isa_arcv2() && ioc_exists)
-		return dma_free_noncoherent(dev, size, kvaddr, dma_handle);
-
-	iounmap((void __force __iomem *)kvaddr);
+	if (!(is_isa_arcv2() && ioc_exists) ||
+	    dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs))
+		iounmap((void __force __iomem *)vaddr);
 
 	free_pages_exact((void *)dma_handle, size);
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
 /*
- * Helper for streaming DMA...
+ * streaming DMA Mapping API...
+ * CPU accesses page via normal paddr, thus needs to explicitly made
+ * consistent before each use
  */
-void __arc_dma_cache_sync(unsigned long paddr, size_t size,
-			  enum dma_data_direction dir)
+static void _dma_cache_sync(unsigned long paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_FROM_DEVICE:
+		dma_cache_inv(paddr, size);
+		break;
+	case DMA_TO_DEVICE:
+		dma_cache_wback(paddr, size);
+		break;
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv(paddr, size);
+		break;
+	default:
+		pr_err("Invalid DMA dir [%d] for OP @ %lx\n", dir, paddr);
+	}
+}
+
+static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	unsigned long paddr = page_to_phys(page) + offset;
+	return dma_map_single(dev, (void *)paddr, size, dir);
+}
+
+static int arc_dma_map_sg(struct device *dev, struct scatterlist *sg,
+	   int nents, enum dma_data_direction dir, struct dma_attrs *attrs)
+{
+	struct scatterlist *s;
+	int i;
+
+	for_each_sg(sg, s, nents, i)
+		s->dma_address = dma_map_page(dev, sg_page(s), s->offset,
+					       s->length, dir);
+
+	return nents;
+}
+
+static void arc_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+{
+	_dma_cache_sync(dma_handle, size, DMA_FROM_DEVICE);
+}
+
+static void arc_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
 {
-	__inline_dma_cache_sync(paddr, size, dir);
+	_dma_cache_sync(dma_handle, size, DMA_TO_DEVICE);
 }
-EXPORT_SYMBOL(__arc_dma_cache_sync);
+
+static void arc_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sglist, int nelems,
+		enum dma_data_direction dir)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
+		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
+}
+
+static void arc_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sglist, int nelems,
+		enum dma_data_direction dir)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
+		_dma_cache_sync((unsigned int)sg_virt(sg), sg->length, dir);
+}
+
+static int arc_dma_supported(struct device *dev, u64 dma_mask)
+{
+	/* Support 32 bit DMA mask exclusively */
+	return dma_mask == DMA_BIT_MASK(32);
+}
+
+struct dma_map_ops arc_dma_ops = {
+	.alloc			= arc_dma_alloc,
+	.free			= arc_dma_free,
+	.map_page		= arc_dma_map_page,
+	.map_sg			= arc_dma_map_sg,
+	.sync_single_for_device	= arc_dma_sync_single_for_device,
+	.sync_single_for_cpu	= arc_dma_sync_single_for_cpu,
+	.sync_sg_for_cpu	= arc_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= arc_dma_sync_sg_for_device,
+	.dma_supported		= arc_dma_supported,
+};
+EXPORT_SYMBOL(arc_dma_ops);
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3f0334a87319..c829b0dee806 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -44,7 +44,6 @@ config ARM
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
-	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS if MMU
 	select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 && MMU
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index ccb3aa64640d..6ad1ceda62a5 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -41,13 +41,6 @@ static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
 #define HAVE_ARCH_DMA_SUPPORTED 1
 extern int dma_supported(struct device *dev, u64 mask);
 
-/*
- * Note that while the generic code provides dummy dma_{alloc,free}_noncoherent
- * implementations, we don't provide a dma_cache_sync function so drivers using
- * this API are highlighted with build warnings.
- */
-#include <asm-generic/dma-mapping-common.h>
-
 #ifdef __arch_page_to_dma
 #error Please update to __arch_pfn_to_dma
 #endif
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 21e8c9c7e7af..9d6c9eae6e23 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -63,7 +63,6 @@ config ARM64
 	select HAVE_DEBUG_BUGVERBOSE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
-	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 61e08f360e31..ba437f090a74 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -64,8 +64,6 @@ static inline bool is_device_dma_coherent(struct device *dev)
 	return dev->archdata.dma_coherent;
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return (dma_addr_t)paddr;
diff --git a/arch/avr32/include/asm/dma-mapping.h b/arch/avr32/include/asm/dma-mapping.h
index ae7ac9205d20..1115f2a645d1 100644
--- a/arch/avr32/include/asm/dma-mapping.h
+++ b/arch/avr32/include/asm/dma-mapping.h
@@ -1,350 +1,14 @@
 #ifndef __ASM_AVR32_DMA_MAPPING_H
 #define __ASM_AVR32_DMA_MAPPING_H
 
-#include <linux/mm.h>
-#include <linux/device.h>
-#include <linux/scatterlist.h>
-#include <asm/processor.h>
-#include <asm/cacheflush.h>
-#include <asm/io.h>
-
 extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	int direction);
 
-/*
- * Return whether the given device DMA address mask can be supported
- * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask
- * to this function.
- */
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	/* Fix when needed. I really don't know of any limitations */
-	return 1;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-	return 0;
-}
+extern struct dma_map_ops avr32_dma_ops;
 
-/*
- * dma_map_single can't fail as it is implemented now.
- */
-static inline int dma_mapping_error(struct device *dev, dma_addr_t addr)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	return 0;
+	return &avr32_dma_ops;
 }
 
-/**
- * dma_alloc_coherent - allocate consistent memory for DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: required memory size
- * @handle: bus-specific DMA address
- *
- * Allocate some uncached, unbuffered memory for a device for
- * performing DMA.  This function allocates pages, and will
- * return the CPU-viewed address, and sets @handle to be the
- * device-viewed address.
- */
-extern void *dma_alloc_coherent(struct device *dev, size_t size,
-				dma_addr_t *handle, gfp_t gfp);
-
-/**
- * dma_free_coherent - free memory allocated by dma_alloc_coherent
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: size of memory originally requested in dma_alloc_coherent
- * @cpu_addr: CPU-view address returned from dma_alloc_coherent
- * @handle: device-view address returned from dma_alloc_coherent
- *
- * Free (and unmap) a DMA buffer previously allocated by
- * dma_alloc_coherent().
- *
- * References to memory and mappings associated with cpu_addr/handle
- * during and after this call executing are illegal.
- */
-extern void dma_free_coherent(struct device *dev, size_t size,
-			      void *cpu_addr, dma_addr_t handle);
-
-/**
- * dma_alloc_writecombine - allocate write-combining memory for DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: required memory size
- * @handle: bus-specific DMA address
- *
- * Allocate some uncached, buffered memory for a device for
- * performing DMA.  This function allocates pages, and will
- * return the CPU-viewed address, and sets @handle to be the
- * device-viewed address.
- */
-extern void *dma_alloc_writecombine(struct device *dev, size_t size,
-				    dma_addr_t *handle, gfp_t gfp);
-
-/**
- * dma_free_coherent - free memory allocated by dma_alloc_writecombine
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @size: size of memory originally requested in dma_alloc_writecombine
- * @cpu_addr: CPU-view address returned from dma_alloc_writecombine
- * @handle: device-view address returned from dma_alloc_writecombine
- *
- * Free (and unmap) a DMA buffer previously allocated by
- * dma_alloc_writecombine().
- *
- * References to memory and mappings associated with cpu_addr/handle
- * during and after this call executing are illegal.
- */
-extern void dma_free_writecombine(struct device *dev, size_t size,
-				  void *cpu_addr, dma_addr_t handle);
-
-/**
- * dma_map_single - map a single buffer for streaming DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @cpu_addr: CPU direct mapped address of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_single() or dma_sync_single().
- */
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *cpu_addr, size_t size,
-	       enum dma_data_direction direction)
-{
-	dma_cache_sync(dev, cpu_addr, size, direction);
-	return virt_to_bus(cpu_addr);
-}
-
-/**
- * dma_unmap_single - unmap a single buffer previously mapped
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Unmap a single streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_map_single() call.
- * All other usages are undefined.
- *
- * After this call, reads by the CPU to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
-{
-
-}
-
-/**
- * dma_map_page - map a portion of a page for streaming DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @page: page that buffer resides in
- * @offset: offset into page for start of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Ensure that any data held in the cache is appropriately discarded
- * or written back.
- *
- * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_page() or dma_sync_single().
- */
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size,
-	     enum dma_data_direction direction)
-{
-	return dma_map_single(dev, page_address(page) + offset,
-			      size, direction);
-}
-
-/**
- * dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Unmap a single streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_map_single() call.
- * All other usages are undefined.
- *
- * After this call, reads by the CPU to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
-{
-	dma_unmap_single(dev, dma_address, size, direction);
-}
-
-/**
- * dma_map_sg - map a set of SG buffers for streaming mode DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Map a set of buffers described by scatterlist in streaming
- * mode for DMA.  This is the scatter-gather version of the
- * above pci_map_single interface.  Here the scatter gather list
- * elements are each tagged with the appropriate dma address
- * and length.  They are obtained via sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- *       DMA address/length pairs than there are SG table elements.
- *       (for example via virtual mapping capabilities)
- *       The routine returns the number of addr/length pairs actually
- *       used, at most nents.
- *
- * Device ownership issues as mentioned above for pci_map_single are
- * the same here.
- */
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	   enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		char *virt;
-
-		sg->dma_address = page_to_bus(sg_page(sg)) + sg->offset;
-		virt = sg_virt(sg);
-		dma_cache_sync(dev, virt, sg->length, direction);
-	}
-
-	return nents;
-}
-
-/**
- * dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Unmap a set of streaming mode DMA translations.
- * Again, CPU read rules concerning calls here are the same as for
- * pci_unmap_single() above.
- */
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction)
-{
-
-}
-
-/**
- * dma_sync_single_for_cpu
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @handle: DMA address of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
- *
- * Make physical memory consistent for a single streaming mode DMA
- * translation after a transfer.
- *
- * If you perform a dma_map_single() but wish to interrogate the
- * buffer using the cpu, yet do not wish to teardown the DMA mapping,
- * you must call this function before doing so.  At the next point you
- * give the DMA address back to the card, you must first perform a
- * dma_sync_single_for_device, and then the device again owns the
- * buffer.
- */
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			size_t size, enum dma_data_direction direction)
-{
-	/*
-	 * No need to do anything since the CPU isn't supposed to
-	 * touch this memory after we flushed it at mapping- or
-	 * sync-for-device time.
-	 */
-}
-
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction direction)
-{
-	dma_cache_sync(dev, bus_to_virt(dma_handle), size, direction);
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction direction)
-{
-	/* just sync everything, that's all the pci API can do */
-	dma_sync_single_for_cpu(dev, dma_handle, offset+size, direction);
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction direction)
-{
-	/* just sync everything, that's all the pci API can do */
-	dma_sync_single_for_device(dev, dma_handle, offset+size, direction);
-}
-
-/**
- * dma_sync_sg_for_cpu
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Make physical memory consistent for a set of streaming
- * mode DMA translations after a transfer.
- *
- * The same as dma_sync_single_for_* but for a scatter-gather list,
- * same rules and usage.
- */
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-		    int nents, enum dma_data_direction direction)
-{
-	/*
-	 * No need to do anything since the CPU isn't supposed to
-	 * touch this memory after we flushed it at mapping- or
-	 * sync-for-device time.
-	 */
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
-		       int nents, enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i)
-		dma_cache_sync(dev, sg_virt(sg), sg->length, direction);
-}
-
-/* Now for the API extensions over the pci_ one */
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-/* drivers/base/dma-mapping.c */
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
-extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size);
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
-#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
-
 #endif /* __ASM_AVR32_DMA_MAPPING_H */
diff --git a/arch/avr32/mm/dma-coherent.c b/arch/avr32/mm/dma-coherent.c
index 50cdb5b10f0f..92cf1fb2b3e6 100644
--- a/arch/avr32/mm/dma-coherent.c
+++ b/arch/avr32/mm/dma-coherent.c
@@ -9,9 +9,14 @@
 #include <linux/dma-mapping.h>
 #include <linux/gfp.h>
 #include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/device.h>
+#include <linux/scatterlist.h>
 
-#include <asm/addrspace.h>
+#include <asm/processor.h>
 #include <asm/cacheflush.h>
+#include <asm/io.h>
+#include <asm/addrspace.h>
 
 void dma_cache_sync(struct device *dev, void *vaddr, size_t size, int direction)
 {
@@ -93,60 +98,100 @@ static void __dma_free(struct device *dev, size_t size,
 		__free_page(page++);
 }
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *handle, gfp_t gfp)
+static void *avr32_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	struct page *page;
-	void *ret = NULL;
+	dma_addr_t phys;
 
 	page = __dma_alloc(dev, size, handle, gfp);
-	if (page)
-		ret = phys_to_uncached(page_to_phys(page));
+	if (!page)
+		return NULL;
+	phys = page_to_phys(page);
 
-	return ret;
+	if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs)) {
+		/* Now, map the page into P3 with write-combining turned on */
+		*handle = phys;
+		return __ioremap(phys, size, _PAGE_BUFFER);
+	} else {
+		return phys_to_uncached(phys);
+	}
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *dev, size_t size,
-		       void *cpu_addr, dma_addr_t handle)
+static void avr32_dma_free(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t handle, struct dma_attrs *attrs)
 {
-	void *addr = phys_to_cached(uncached_to_phys(cpu_addr));
 	struct page *page;
 
-	pr_debug("dma_free_coherent addr %p (phys %08lx) size %u\n",
-		 cpu_addr, (unsigned long)handle, (unsigned)size);
-	BUG_ON(!virt_addr_valid(addr));
-	page = virt_to_page(addr);
+	if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs)) {
+		iounmap(cpu_addr);
+
+		page = phys_to_page(handle);
+	} else {
+		void *addr = phys_to_cached(uncached_to_phys(cpu_addr));
+
+		pr_debug("avr32_dma_free addr %p (phys %08lx) size %u\n",
+			 cpu_addr, (unsigned long)handle, (unsigned)size);
+
+		BUG_ON(!virt_addr_valid(addr));
+		page = virt_to_page(addr);
+	}
+
 	__dma_free(dev, size, page, handle);
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
-void *dma_alloc_writecombine(struct device *dev, size_t size,
-			     dma_addr_t *handle, gfp_t gfp)
+static dma_addr_t avr32_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size,
+		enum dma_data_direction direction, struct dma_attrs *attrs)
 {
-	struct page *page;
-	dma_addr_t phys;
+	void *cpu_addr = page_address(page) + offset;
 
-	page = __dma_alloc(dev, size, handle, gfp);
-	if (!page)
-		return NULL;
+	dma_cache_sync(dev, cpu_addr, size, direction);
+	return virt_to_bus(cpu_addr);
+}
 
-	phys = page_to_phys(page);
-	*handle = phys;
+static int avr32_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nents, i) {
+		char *virt;
 
-	/* Now, map the page into P3 with write-combining turned on */
-	return __ioremap(phys, size, _PAGE_BUFFER);
+		sg->dma_address = page_to_bus(sg_page(sg)) + sg->offset;
+		virt = sg_virt(sg);
+		dma_cache_sync(dev, virt, sg->length, direction);
+	}
+
+	return nents;
 }
-EXPORT_SYMBOL(dma_alloc_writecombine);
 
-void dma_free_writecombine(struct device *dev, size_t size,
-			   void *cpu_addr, dma_addr_t handle)
+static void avr32_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
 {
-	struct page *page;
+	dma_cache_sync(dev, bus_to_virt(dma_handle), size, direction);
+}
 
-	iounmap(cpu_addr);
+static void avr32_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sglist, int nents,
+		enum dma_data_direction direction)
+{
+	int i;
+	struct scatterlist *sg;
 
-	page = phys_to_page(handle);
-	__dma_free(dev, size, page, handle);
+	for_each_sg(sglist, sg, nents, i)
+		dma_cache_sync(dev, sg_virt(sg), sg->length, direction);
 }
-EXPORT_SYMBOL(dma_free_writecombine);
+
+struct dma_map_ops avr32_dma_ops = {
+	.alloc			= avr32_dma_alloc,
+	.free			= avr32_dma_free,
+	.map_page		= avr32_dma_map_page,
+	.map_sg			= avr32_dma_map_sg,
+	.sync_single_for_device	= avr32_dma_sync_single_for_device,
+	.sync_sg_for_device	= avr32_dma_sync_sg_for_device,
+};
+EXPORT_SYMBOL(avr32_dma_ops);
diff --git a/arch/blackfin/include/asm/dma-mapping.h b/arch/blackfin/include/asm/dma-mapping.h
index 054d9ec57d9d..3490570aaa82 100644
--- a/arch/blackfin/include/asm/dma-mapping.h
+++ b/arch/blackfin/include/asm/dma-mapping.h
@@ -8,36 +8,6 @@
 #define _BLACKFIN_DMA_MAPPING_H
 
 #include <asm/cacheflush.h>
-struct scatterlist;
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t gfp);
-void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-		       dma_addr_t dma_handle);
-
-/*
- * Now for the API extensions over the pci_ one
- */
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-#define dma_supported(d, m)         (1)
-
-static inline int
-dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-
-	return 0;
-}
-
-static inline int
-dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
 
 extern void
 __dma_sync(dma_addr_t addr, size_t size, enum dma_data_direction dir);
@@ -66,102 +36,11 @@ _dma_sync(dma_addr_t addr, size_t size, enum dma_data_direction dir)
 		__dma_sync(addr, size, dir);
 }
 
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction dir)
-{
-	_dma_sync((dma_addr_t)ptr, size, dir);
-	return (dma_addr_t) ptr;
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size,
-	     enum dma_data_direction dir)
-{
-	return dma_map_single(dev, page_address(page) + offset, size, dir);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
-	       enum dma_data_direction dir)
-{
-	dma_unmap_single(dev, dma_addr, size, dir);
-}
+extern struct dma_map_ops bfin_dma_ops;
 
-extern int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		      enum dma_data_direction dir);
-
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-	     int nhwentries, enum dma_data_direction dir)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	BUG_ON(!valid_dma_direction(dir));
+	return &bfin_dma_ops;
 }
 
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir)
-{
-	_dma_sync(handle + offset, size, dir);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle, size_t size,
-			enum dma_data_direction dir)
-{
-	dma_sync_single_range_for_cpu(dev, handle, 0, size, dir);
-}
-
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t handle, size_t size,
-			   enum dma_data_direction dir)
-{
-	dma_sync_single_range_for_device(dev, handle, 0, size, dir);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents,
-		    enum dma_data_direction dir)
-{
-	BUG_ON(!valid_dma_direction(dir));
-}
-
-extern void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-		       int nents, enum dma_data_direction dir);
-
-static inline void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction dir)
-{
-	_dma_sync((dma_addr_t)vaddr, size, dir);
-}
-
-/* drivers/base/dma-mapping.c */
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
-extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size);
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
-#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
-
 #endif				/* _BLACKFIN_DMA_MAPPING_H */
diff --git a/arch/blackfin/kernel/dma-mapping.c b/arch/blackfin/kernel/dma-mapping.c
index df437e52d9df..771afe6e4264 100644
--- a/arch/blackfin/kernel/dma-mapping.c
+++ b/arch/blackfin/kernel/dma-mapping.c
@@ -78,8 +78,8 @@ static void __free_dma_pages(unsigned long addr, unsigned int pages)
 	spin_unlock_irqrestore(&dma_page_lock, flags);
 }
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t gfp)
+static void *bfin_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	void *ret;
 
@@ -92,15 +92,12 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 
 	return ret;
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void
-dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-		  dma_addr_t dma_handle)
+static void bfin_dma_free(struct device *dev, size_t size, void *vaddr,
+		  dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	__free_dma_pages((unsigned long)vaddr, get_pages(size));
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
 /*
  * Streaming DMA mappings
@@ -112,9 +109,9 @@ void __dma_sync(dma_addr_t addr, size_t size,
 }
 EXPORT_SYMBOL(__dma_sync);
 
-int
-dma_map_sg(struct device *dev, struct scatterlist *sg_list, int nents,
-	   enum dma_data_direction direction)
+static int bfin_dma_map_sg(struct device *dev, struct scatterlist *sg_list,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int i;
@@ -126,10 +123,10 @@ dma_map_sg(struct device *dev, struct scatterlist *sg_list, int nents,
 
 	return nents;
 }
-EXPORT_SYMBOL(dma_map_sg);
 
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg_list,
-			    int nelems, enum dma_data_direction direction)
+static void bfin_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sg_list, int nelems,
+		enum dma_data_direction direction)
 {
 	struct scatterlist *sg;
 	int i;
@@ -139,4 +136,31 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg_list,
 		__dma_sync(sg_dma_address(sg), sg_dma_len(sg), direction);
 	}
 }
-EXPORT_SYMBOL(dma_sync_sg_for_device);
+
+static dma_addr_t bfin_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
+{
+	dma_addr_t handle = (dma_addr_t)(page_address(page) + offset);
+
+	_dma_sync(handle, size, dir);
+	return handle;
+}
+
+static inline void bfin_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	_dma_sync(handle, size, dir);
+}
+
+struct dma_map_ops bfin_dma_ops = {
+	.alloc			= bfin_dma_alloc,
+	.free			= bfin_dma_free,
+
+	.map_page		= bfin_dma_map_page,
+	.map_sg			= bfin_dma_map_sg,
+
+	.sync_single_for_device	= bfin_dma_sync_single_for_device,
+	.sync_sg_for_device	= bfin_dma_sync_sg_for_device,
+};
+EXPORT_SYMBOL(bfin_dma_ops);
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 77ea09b8bce1..79049d432d3c 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -17,6 +17,7 @@ config C6X
 	select OF_EARLY_FLATTREE
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
+	select ARCH_NO_COHERENT_DMA_MMAP
 
 config MMU
 	def_bool n
diff --git a/arch/c6x/include/asm/dma-mapping.h b/arch/c6x/include/asm/dma-mapping.h
index bbd7774e4d4e..6b5cd7b0cf32 100644
--- a/arch/c6x/include/asm/dma-mapping.h
+++ b/arch/c6x/include/asm/dma-mapping.h
@@ -12,104 +12,22 @@
 #ifndef _ASM_C6X_DMA_MAPPING_H
 #define _ASM_C6X_DMA_MAPPING_H
 
-#include <linux/dma-debug.h>
-#include <asm-generic/dma-coherent.h>
-
-#define dma_supported(d, m)	1
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-						    dma_addr_t addr,
-						    unsigned long offset,
-						    size_t size,
-						    enum dma_data_direction dir)
-{
-}
-
-static inline int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
-		return -EIO;
-
-	*dev->dma_mask = dma_mask;
-
-	return 0;
-}
-
 /*
  * DMA errors are defined by all-bits-set in the DMA address.
  */
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	debug_dma_mapping_error(dev, dma_addr);
-	return dma_addr == ~0;
-}
-
-extern dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-				 size_t size, enum dma_data_direction dir);
+#define DMA_ERROR_CODE ~0
 
-extern void dma_unmap_single(struct device *dev, dma_addr_t handle,
-			     size_t size, enum dma_data_direction dir);
+extern struct dma_map_ops c6x_dma_ops;
 
-extern int dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		      int nents, enum dma_data_direction direction);
-
-extern void dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-			 int nents, enum dma_data_direction direction);
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction dir)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	dma_addr_t handle;
-
-	handle = dma_map_single(dev, page_address(page) + offset, size, dir);
-
-	debug_dma_map_page(dev, page, offset, size, dir, handle, false);
-
-	return handle;
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t handle,
-		size_t size, enum dma_data_direction dir)
-{
-	dma_unmap_single(dev, handle, size, dir);
-
-	debug_dma_unmap_page(dev, handle, size, dir, false);
+	return &c6x_dma_ops;
 }
 
-extern void dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
-				    size_t size, enum dma_data_direction dir);
-
-extern void dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
-				       size_t size,
-				       enum dma_data_direction dir);
-
-extern void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction dir);
-
-extern void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction dir);
-
 extern void coherent_mem_init(u32 start, u32 size);
-extern void *dma_alloc_coherent(struct device *, size_t, dma_addr_t *, gfp_t);
-extern void dma_free_coherent(struct device *, size_t, void *, dma_addr_t);
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent((d), (s), (h), (f))
-#define dma_free_noncoherent(d, s, v, h)  dma_free_coherent((d), (s), (v), (h))
-
-/* Not supported for now */
-static inline int dma_mmap_coherent(struct device *dev,
-				    struct vm_area_struct *vma, void *cpu_addr,
-				    dma_addr_t dma_addr, size_t size)
-{
-	return -EINVAL;
-}
-
-static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size)
-{
-	return -EINVAL;
-}
+void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp, struct dma_attrs *attrs);
+void c6x_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs);
 
 #endif	/* _ASM_C6X_DMA_MAPPING_H */
diff --git a/arch/c6x/kernel/dma.c b/arch/c6x/kernel/dma.c
index ab7b12de144d..8a80f3a250c0 100644
--- a/arch/c6x/kernel/dma.c
+++ b/arch/c6x/kernel/dma.c
@@ -36,110 +36,101 @@ static void c6x_dma_sync(dma_addr_t handle, size_t size,
 	}
 }
 
-dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
-			  enum dma_data_direction dir)
+static dma_addr_t c6x_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
 {
-	dma_addr_t addr = virt_to_phys(ptr);
+	dma_addr_t handle = virt_to_phys(page_address(page) + offset);
 
-	c6x_dma_sync(addr, size, dir);
-
-	debug_dma_map_page(dev, virt_to_page(ptr),
-			   (unsigned long)ptr & ~PAGE_MASK, size,
-			   dir, addr, true);
-	return addr;
+	c6x_dma_sync(handle, size, dir);
+	return handle;
 }
-EXPORT_SYMBOL(dma_map_single);
-
 
-void dma_unmap_single(struct device *dev, dma_addr_t handle,
-		      size_t size, enum dma_data_direction dir)
+static void c6x_dma_unmap_page(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	c6x_dma_sync(handle, size, dir);
-
-	debug_dma_unmap_page(dev, handle, size, dir, true);
 }
-EXPORT_SYMBOL(dma_unmap_single);
-
 
-int dma_map_sg(struct device *dev, struct scatterlist *sglist,
-	       int nents, enum dma_data_direction dir)
+static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int i;
 
-	for_each_sg(sglist, sg, nents, i)
-		sg->dma_address = dma_map_single(dev, sg_virt(sg), sg->length,
-						 dir);
-
-	debug_dma_map_sg(dev, sglist, nents, nents, dir);
+	for_each_sg(sglist, sg, nents, i) {
+		sg->dma_address = sg_phys(sg);
+		c6x_dma_sync(sg->dma_address, sg->length, dir);
+	}
 
 	return nents;
 }
-EXPORT_SYMBOL(dma_map_sg);
-
 
-void dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-		  int nents, enum dma_data_direction dir)
+static void c6x_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+		  int nents, enum dma_data_direction dir,
+		  struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
 	int i;
 
 	for_each_sg(sglist, sg, nents, i)
-		dma_unmap_single(dev, sg_dma_address(sg), sg->length, dir);
+		c6x_dma_sync(sg_dma_address(sg), sg->length, dir);
 
-	debug_dma_unmap_sg(dev, sglist,	nents, dir);
 }
-EXPORT_SYMBOL(dma_unmap_sg);
 
-void dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
-			     size_t size, enum dma_data_direction dir)
+static void c6x_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
 {
 	c6x_dma_sync(handle, size, dir);
 
-	debug_dma_sync_single_for_cpu(dev, handle, size, dir);
 }
-EXPORT_SYMBOL(dma_sync_single_for_cpu);
 
-
-void dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
-				size_t size, enum dma_data_direction dir)
+static void c6x_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
 	c6x_dma_sync(handle, size, dir);
 
-	debug_dma_sync_single_for_device(dev, handle, size, dir);
 }
-EXPORT_SYMBOL(dma_sync_single_for_device);
-
 
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist,
-			 int nents, enum dma_data_direction dir)
+static void c6x_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sglist, int nents,
+		enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
 	for_each_sg(sglist, sg, nents, i)
-		dma_sync_single_for_cpu(dev, sg_dma_address(sg),
+		c6x_dma_sync_single_for_cpu(dev, sg_dma_address(sg),
 					sg->length, dir);
 
-	debug_dma_sync_sg_for_cpu(dev, sglist, nents, dir);
 }
-EXPORT_SYMBOL(dma_sync_sg_for_cpu);
-
 
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
-			    int nents, enum dma_data_direction dir)
+static void c6x_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sglist, int nents,
+		enum dma_data_direction dir)
 {
 	struct scatterlist *sg;
 	int i;
 
 	for_each_sg(sglist, sg, nents, i)
-		dma_sync_single_for_device(dev, sg_dma_address(sg),
+		c6x_dma_sync_single_for_device(dev, sg_dma_address(sg),
 					   sg->length, dir);
 
-	debug_dma_sync_sg_for_device(dev, sglist, nents, dir);
 }
-EXPORT_SYMBOL(dma_sync_sg_for_device);
 
+struct dma_map_ops c6x_dma_ops = {
+	.alloc			= c6x_dma_alloc,
+	.free			= c6x_dma_free,
+	.map_page		= c6x_dma_map_page,
+	.unmap_page		= c6x_dma_unmap_page,
+	.map_sg			= c6x_dma_map_sg,
+	.unmap_sg		= c6x_dma_unmap_sg,
+	.sync_single_for_device	= c6x_dma_sync_single_for_device,
+	.sync_single_for_cpu	= c6x_dma_sync_single_for_cpu,
+	.sync_sg_for_device	= c6x_dma_sync_sg_for_device,
+	.sync_sg_for_cpu	= c6x_dma_sync_sg_for_cpu,
+};
+EXPORT_SYMBOL(c6x_dma_ops);
 
 /* Number of entries preallocated for DMA-API debugging */
 #define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c
index 4187e5180373..f7ee63af2541 100644
--- a/arch/c6x/mm/dma-coherent.c
+++ b/arch/c6x/mm/dma-coherent.c
@@ -73,8 +73,8 @@ static void __free_dma_pages(u32 addr, int order)
  * Allocate DMA coherent memory space and return both the kernel
  * virtual and DMA address for that space.
  */
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *handle, gfp_t gfp)
+void *c6x_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp, struct dma_attrs *attrs)
 {
 	u32 paddr;
 	int order;
@@ -94,13 +94,12 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 
 	return phys_to_virt(paddr);
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
 /*
  * Free DMA coherent memory as defined by the above mapping.
  */
-void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-		       dma_addr_t dma_handle)
+void c6x_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	int order;
 
@@ -111,7 +110,6 @@ void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 
 	__free_dma_pages(virt_to_phys(vaddr), order);
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
 /*
  * Initialise the coherent DMA memory allocator using the given uncached region.
diff --git a/arch/cris/arch-v32/drivers/pci/dma.c b/arch/cris/arch-v32/drivers/pci/dma.c
index ee55578d9834..8d5efa58cce1 100644
--- a/arch/cris/arch-v32/drivers/pci/dma.c
+++ b/arch/cris/arch-v32/drivers/pci/dma.c
@@ -16,21 +16,18 @@
 #include <linux/gfp.h>
 #include <asm/io.h>
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t gfp)
+static void *v32_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp,  struct dma_attrs *attrs)
 {
 	void *ret;
-	int order = get_order(size);
+
 	/* ignore region specifiers */
 	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM);
 
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &ret))
-		return ret;
-
 	if (dev == NULL || (dev->coherent_dma_mask < 0xffffffff))
 		gfp |= GFP_DMA;
 
-	ret = (void *)__get_free_pages(gfp, order);
+	ret = (void *)__get_free_pages(gfp,  get_order(size));
 
 	if (ret != NULL) {
 		memset(ret, 0, size);
@@ -39,12 +36,45 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 	return ret;
 }
 
-void dma_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle)
+static void v32_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
+{
+	free_pages((unsigned long)vaddr, get_order(size));
+}
+
+static inline dma_addr_t v32_dma_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
-	int order = get_order(size);
+	return page_to_phys(page) + offset;
+}
 
-	if (!dma_release_from_coherent(dev, order, vaddr))
-		free_pages((unsigned long)vaddr, order);
+static inline int v32_dma_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	printk("Map sg\n");
+	return nents;
+}
+
+static inline int v32_dma_supported(struct device *dev, u64 mask)
+{
+        /*
+         * we fall back to GFP_DMA when the mask isn't all 1s,
+         * so we can't guarantee allocations that must be
+         * within a tighter range than GFP_DMA..
+         */
+        if (mask < 0x00ffffff)
+                return 0;
+	return 1;
 }
 
+struct dma_map_ops v32_dma_ops = {
+	.alloc			= v32_dma_alloc,
+	.free			= v32_dma_free,
+	.map_page		= v32_dma_map_page,
+	.map_sg                 = v32_dma_map_sg,
+	.dma_supported		= v32_dma_supported,
+};
+EXPORT_SYMBOL(v32_dma_ops);
diff --git a/arch/cris/include/asm/dma-mapping.h b/arch/cris/include/asm/dma-mapping.h
index 57f794ee6039..5a370178a0e9 100644
--- a/arch/cris/include/asm/dma-mapping.h
+++ b/arch/cris/include/asm/dma-mapping.h
@@ -1,156 +1,20 @@
-/* DMA mapping. Nothing tricky here, just virt_to_phys */
-
 #ifndef _ASM_CRIS_DMA_MAPPING_H
 #define _ASM_CRIS_DMA_MAPPING_H
 
-#include <linux/mm.h>
-#include <linux/kernel.h>
-#include <linux/scatterlist.h>
-
-#include <asm/cache.h>
-#include <asm/io.h>
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
 #ifdef CONFIG_PCI
-#include <asm-generic/dma-coherent.h>
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag);
+extern struct dma_map_ops v32_dma_ops;
 
-void dma_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle);
-#else
-static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-                   gfp_t flag)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-        BUG();
-        return NULL;
+	return &v32_dma_ops;
 }
-
-static inline void
-dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-                    dma_addr_t dma_handle)
+#else
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-        BUG();
+	BUG();
+	return NULL;
 }
 #endif
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-	return virt_to_phys(ptr);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	   enum dma_data_direction direction)
-{
-	printk("Map sg\n");
-	return nents;
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-	     size_t size, enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-	return page_to_phys(page) + offset;
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-			enum dma_data_direction direction)
-{
-}
-
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
-			enum dma_data_direction direction)
-{
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction direction)
-{
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction direction)
-{
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
-		    enum dma_data_direction direction)
-{
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		    enum dma_data_direction direction)
-{
-}
-
-static inline int
-dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static inline int
-dma_supported(struct device *dev, u64 mask)
-{
-        /*
-         * we fall back to GFP_DMA when the mask isn't all 1s,
-         * so we can't guarantee allocations that must be
-         * within a tighter range than GFP_DMA..
-         */
-        if(mask < 0x00ffffff)
-                return 0;
-
-	return 1;
-}
-
-static inline int
-dma_set_mask(struct device *dev, u64 mask)
-{
-	if(!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-
-	return 0;
-}
 
 static inline void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
@@ -158,15 +22,4 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 {
 }
 
-/* drivers/base/dma-mapping.c */
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
-extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size);
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
-#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
-
-
 #endif
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index 34aa19352dc1..4211be88e082 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -14,6 +14,7 @@ config FRV
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select HAVE_DEBUG_STACKOVERFLOW
+	select ARCH_NO_COHERENT_DMA_MMAP
 
 config ZONE_DMA
 	bool
diff --git a/arch/frv/include/asm/dma-mapping.h b/arch/frv/include/asm/dma-mapping.h
index 2840adcd6d92..9a82bfa4303b 100644
--- a/arch/frv/include/asm/dma-mapping.h
+++ b/arch/frv/include/asm/dma-mapping.h
@@ -1,128 +1,17 @@
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
 
-#include <linux/device.h>
-#include <linux/scatterlist.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
-#include <asm/io.h>
-
-/*
- * See Documentation/DMA-API.txt for the description of how the
- * following DMA API should work.
- */
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
 extern unsigned long __nongprelbss dma_coherent_mem_start;
 extern unsigned long __nongprelbss dma_coherent_mem_end;
 
-void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp);
-void dma_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle);
-
-extern dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
-				 enum dma_data_direction direction);
-
-static inline
-void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		      enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-extern int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		      enum dma_data_direction direction);
-
-static inline
-void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-extern
-dma_addr_t dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-			size_t size, enum dma_data_direction direction);
-
-static inline
-void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-		    enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-
-static inline
-void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-			     enum dma_data_direction direction)
-{
-}
-
-static inline
-void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
-				enum dma_data_direction direction)
-{
-	flush_write_buffers();
-}
-
-static inline
-void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction direction)
-{
-}
-
-static inline
-void dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction direction)
-{
-	flush_write_buffers();
-}
-
-static inline
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
-			 enum dma_data_direction direction)
-{
-}
-
-static inline
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-			    enum dma_data_direction direction)
-{
-	flush_write_buffers();
-}
-
-static inline
-int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static inline
-int dma_supported(struct device *dev, u64 mask)
-{
-        /*
-         * we fall back to GFP_DMA when the mask isn't all 1s,
-         * so we can't guarantee allocations that must be
-         * within a tighter range than GFP_DMA..
-         */
-        if (mask < 0x00ffffff)
-                return 0;
-
-	return 1;
-}
+extern struct dma_map_ops frv_dma_ops;
 
-static inline
-int dma_set_mask(struct device *dev, u64 mask)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-
-	return 0;
+	return &frv_dma_ops;
 }
 
 static inline
@@ -132,19 +21,4 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	flush_write_buffers();
 }
 
-/* Not supported for now */
-static inline int dma_mmap_coherent(struct device *dev,
-				    struct vm_area_struct *vma, void *cpu_addr,
-				    dma_addr_t dma_addr, size_t size)
-{
-	return -EINVAL;
-}
-
-static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size)
-{
-	return -EINVAL;
-}
-
 #endif  /* _ASM_DMA_MAPPING_H */
diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c
index 8eeea0d77aad..082be49b5df0 100644
--- a/arch/frv/mb93090-mb00/pci-dma-nommu.c
+++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c
@@ -34,7 +34,8 @@ struct dma_alloc_record {
 static DEFINE_SPINLOCK(dma_alloc_lock);
 static LIST_HEAD(dma_alloc_list);
 
-void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t gfp)
+static void *frv_dma_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, struct dma_attrs *attrs)
 {
 	struct dma_alloc_record *new;
 	struct list_head *this = &dma_alloc_list;
@@ -84,9 +85,8 @@ void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_hand
 	return NULL;
 }
 
-EXPORT_SYMBOL(dma_alloc_coherent);
-
-void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle)
+static void frv_dma_free(struct device *hwdev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	struct dma_alloc_record *rec;
 	unsigned long flags;
@@ -105,22 +105,9 @@ void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_
 	BUG();
 }
 
-EXPORT_SYMBOL(dma_free_coherent);
-
-dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
-			  enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size);
-
-	return virt_to_bus(ptr);
-}
-
-EXPORT_SYMBOL(dma_map_single);
-
-int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	       enum dma_data_direction direction)
+static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	int i;
 	struct scatterlist *sg;
@@ -135,14 +122,49 @@ int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	return nents;
 }
 
-EXPORT_SYMBOL(dma_map_sg);
-
-dma_addr_t dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-			size_t size, enum dma_data_direction direction)
+static dma_addr_t frv_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size,
+		enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	BUG_ON(direction == DMA_NONE);
 	flush_dcache_page(page);
 	return (dma_addr_t) page_to_phys(page) + offset;
 }
 
-EXPORT_SYMBOL(dma_map_page);
+static void frv_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+	flush_write_buffers();
+}
+
+static void frv_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sg, int nelems,
+		enum dma_data_direction direction)
+{
+	flush_write_buffers();
+}
+
+
+static int frv_dma_supported(struct device *dev, u64 mask)
+{
+        /*
+         * we fall back to GFP_DMA when the mask isn't all 1s,
+         * so we can't guarantee allocations that must be
+         * within a tighter range than GFP_DMA..
+         */
+        if (mask < 0x00ffffff)
+                return 0;
+	return 1;
+}
+
+struct dma_map_ops frv_dma_ops = {
+	.alloc			= frv_dma_alloc,
+	.free			= frv_dma_free,
+	.map_page		= frv_dma_map_page,
+	.map_sg			= frv_dma_map_sg,
+	.sync_single_for_device	= frv_dma_sync_single_for_device,
+	.sync_sg_for_device	= frv_dma_sync_sg_for_device,
+	.dma_supported		= frv_dma_supported,
+};
+EXPORT_SYMBOL(frv_dma_ops);
diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c
index 4d1f01dc46e5..316b7b65348d 100644
--- a/arch/frv/mb93090-mb00/pci-dma.c
+++ b/arch/frv/mb93090-mb00/pci-dma.c
@@ -18,7 +18,9 @@
 #include <linux/scatterlist.h>
 #include <asm/io.h>
 
-void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t gfp)
+static void *frv_dma_alloc(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp,
+		struct dma_attrs *attrs)
 {
 	void *ret;
 
@@ -29,29 +31,15 @@ void *dma_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_hand
 	return ret;
 }
 
-EXPORT_SYMBOL(dma_alloc_coherent);
-
-void dma_free_coherent(struct device *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle)
+static void frv_dma_free(struct device *hwdev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	consistent_free(vaddr);
 }
 
-EXPORT_SYMBOL(dma_free_coherent);
-
-dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
-			  enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	frv_cache_wback_inv((unsigned long) ptr, (unsigned long) ptr + size);
-
-	return virt_to_bus(ptr);
-}
-
-EXPORT_SYMBOL(dma_map_single);
-
-int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	       enum dma_data_direction direction)
+static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	unsigned long dampr2;
 	void *vaddr;
@@ -79,14 +67,48 @@ int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	return nents;
 }
 
-EXPORT_SYMBOL(dma_map_sg);
-
-dma_addr_t dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-			size_t size, enum dma_data_direction direction)
+static dma_addr_t frv_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size,
+		enum dma_data_direction direction, struct dma_attrs *attrs)
 {
-	BUG_ON(direction == DMA_NONE);
 	flush_dcache_page(page);
 	return (dma_addr_t) page_to_phys(page) + offset;
 }
 
-EXPORT_SYMBOL(dma_map_page);
+static void frv_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+	flush_write_buffers();
+}
+
+static void frv_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sg, int nelems,
+		enum dma_data_direction direction)
+{
+	flush_write_buffers();
+}
+
+
+static int frv_dma_supported(struct device *dev, u64 mask)
+{
+        /*
+         * we fall back to GFP_DMA when the mask isn't all 1s,
+         * so we can't guarantee allocations that must be
+         * within a tighter range than GFP_DMA..
+         */
+        if (mask < 0x00ffffff)
+                return 0;
+	return 1;
+}
+
+struct dma_map_ops frv_dma_ops = {
+	.alloc			= frv_dma_alloc,
+	.free			= frv_dma_free,
+	.map_page		= frv_dma_map_page,
+	.map_sg			= frv_dma_map_sg,
+	.sync_single_for_device	= frv_dma_sync_single_for_device,
+	.sync_sg_for_device	= frv_dma_sync_sg_for_device,
+	.dma_supported		= frv_dma_supported,
+};
+EXPORT_SYMBOL(frv_dma_ops);
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index 93811ac1bed6..45d4c8565b40 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -15,7 +15,6 @@ config H8300
 	select OF_IRQ
 	select OF_EARLY_FLATTREE
 	select HAVE_MEMBLOCK
-	select HAVE_DMA_ATTRS
 	select CLKSRC_OF
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
diff --git a/arch/h8300/include/asm/dma-mapping.h b/arch/h8300/include/asm/dma-mapping.h
index d9b5b806afe6..7ac7fadffed0 100644
--- a/arch/h8300/include/asm/dma-mapping.h
+++ b/arch/h8300/include/asm/dma-mapping.h
@@ -8,6 +8,4 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 	return &h8300_dma_map_ops;
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 #endif
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 4dc89d1f9c48..57298e7b4867 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -27,7 +27,6 @@ config HEXAGON
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select MODULES_USE_ELF_RELA
 	select GENERIC_CPU_DEVICES
-	select HAVE_DMA_ATTRS
 	---help---
 	  Qualcomm Hexagon is a processor architecture designed for high
 	  performance and low power across a wide variety of applications.
diff --git a/arch/hexagon/include/asm/dma-mapping.h b/arch/hexagon/include/asm/dma-mapping.h
index 268fde8a4575..aa6203464520 100644
--- a/arch/hexagon/include/asm/dma-mapping.h
+++ b/arch/hexagon/include/asm/dma-mapping.h
@@ -49,8 +49,6 @@ extern int dma_is_consistent(struct device *dev, dma_addr_t dma_handle);
 extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 			   enum dma_data_direction direction);
 
-#include <asm-generic/dma-mapping-common.h>
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
 	if (!dev->dma_mask)
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index eb0249e37981..fb0515eb639b 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -25,7 +25,6 @@ config IA64
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE if (!ITANIUM)
 	select HAVE_FUNCTION_TRACER
-	select HAVE_DMA_ATTRS
 	select TTY
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
diff --git a/arch/ia64/include/asm/dma-mapping.h b/arch/ia64/include/asm/dma-mapping.h
index 9beccf8010bd..d472805edfa9 100644
--- a/arch/ia64/include/asm/dma-mapping.h
+++ b/arch/ia64/include/asm/dma-mapping.h
@@ -25,8 +25,6 @@ extern void machvec_dma_sync_sg(struct device *, struct scatterlist *, int,
 
 #define get_dma_ops(dev) platform_dma_get_ops(dev)
 
-#include <asm-generic/dma-mapping-common.h>
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
 	if (!dev->dma_mask)
diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h
index 05aa53594d49..96c536194287 100644
--- a/arch/m68k/include/asm/dma-mapping.h
+++ b/arch/m68k/include/asm/dma-mapping.h
@@ -1,123 +1,17 @@
 #ifndef _M68K_DMA_MAPPING_H
 #define _M68K_DMA_MAPPING_H
 
-#include <asm/cache.h>
+extern struct dma_map_ops m68k_dma_ops;
 
-struct scatterlist;
-
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 mask)
-{
-	return 0;
-}
-
-extern void *dma_alloc_coherent(struct device *, size_t,
-				dma_addr_t *, gfp_t);
-extern void dma_free_coherent(struct device *, size_t,
-			      void *, dma_addr_t);
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t flag,
-				    struct dma_attrs *attrs)
-{
-	/* attrs is not supported and ignored */
-	return dma_alloc_coherent(dev, size, dma_handle, flag);
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				  void *cpu_addr, dma_addr_t dma_handle,
-				  struct dma_attrs *attrs)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	/* attrs is not supported and ignored */
-	dma_free_coherent(dev, size, cpu_addr, dma_handle);
+        return &m68k_dma_ops;
 }
 
-static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
-					  dma_addr_t *handle, gfp_t flag)
-{
-	return dma_alloc_coherent(dev, size, handle, flag);
-}
-static inline void dma_free_noncoherent(struct device *dev, size_t size,
-					void *addr, dma_addr_t handle)
-{
-	dma_free_coherent(dev, size, addr, handle);
-}
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 				  enum dma_data_direction dir)
 {
 	/* we use coherent allocation, so not much to do here. */
 }
 
-extern dma_addr_t dma_map_single(struct device *, void *, size_t,
-				 enum dma_data_direction);
-static inline void dma_unmap_single(struct device *dev, dma_addr_t addr,
-				    size_t size, enum dma_data_direction dir)
-{
-}
-
-extern dma_addr_t dma_map_page(struct device *, struct page *,
-			       unsigned long, size_t size,
-			       enum dma_data_direction);
-static inline void dma_unmap_page(struct device *dev, dma_addr_t address,
-				  size_t size, enum dma_data_direction dir)
-{
-}
-
-extern int dma_map_sg(struct device *, struct scatterlist *, int,
-		      enum dma_data_direction);
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nhwentries, enum dma_data_direction dir)
-{
-}
-
-extern void dma_sync_single_for_device(struct device *, dma_addr_t, size_t,
-				       enum dma_data_direction);
-extern void dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
-				   enum dma_data_direction);
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	/* just sync everything for now */
-	dma_sync_single_for_device(dev, dma_handle, offset + size, direction);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
-					   size_t size, enum dma_data_direction dir)
-{
-}
-
-static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-				       int nents, enum dma_data_direction dir)
-{
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	/* just sync everything for now */
-	dma_sync_single_for_cpu(dev, dma_handle, offset + size, direction);
-}
-
-static inline int dma_mapping_error(struct device *dev, dma_addr_t handle)
-{
-	return 0;
-}
-
-/* drivers/base/dma-mapping.c */
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
-extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size);
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
-#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
-
 #endif  /* _M68K_DMA_MAPPING_H */
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 564665f9af30..cbc78b4117b5 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -18,8 +18,8 @@
 
 #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE)
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *handle, gfp_t flag)
+static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t flag, struct dma_attrs *attrs)
 {
 	struct page *page, **map;
 	pgprot_t pgprot;
@@ -61,8 +61,8 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 	return addr;
 }
 
-void dma_free_coherent(struct device *dev, size_t size,
-		       void *addr, dma_addr_t handle)
+static void m68k_dma_free(struct device *dev, size_t size, void *addr,
+		dma_addr_t handle, struct dma_attrs *attrs)
 {
 	pr_debug("dma_free_coherent: %p, %x\n", addr, handle);
 	vfree(addr);
@@ -72,8 +72,8 @@ void dma_free_coherent(struct device *dev, size_t size,
 
 #include <asm/cacheflush.h>
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t gfp)
+static void *m68k_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	void *ret;
 	/* ignore region specifiers */
@@ -90,19 +90,16 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 	return ret;
 }
 
-void dma_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle)
+static void m68k_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
 #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */
 
-EXPORT_SYMBOL(dma_alloc_coherent);
-EXPORT_SYMBOL(dma_free_coherent);
-
-void dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
-				size_t size, enum dma_data_direction dir)
+static void m68k_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
@@ -118,10 +115,9 @@ void dma_sync_single_for_device(struct device *dev, dma_addr_t handle,
 		break;
 	}
 }
-EXPORT_SYMBOL(dma_sync_single_for_device);
 
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
-			    int nents, enum dma_data_direction dir)
+static void m68k_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sglist, int nents, enum dma_data_direction dir)
 {
 	int i;
 	struct scatterlist *sg;
@@ -131,31 +127,19 @@ void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
 					   dir);
 	}
 }
-EXPORT_SYMBOL(dma_sync_sg_for_device);
-
-dma_addr_t dma_map_single(struct device *dev, void *addr, size_t size,
-			  enum dma_data_direction dir)
-{
-	dma_addr_t handle = virt_to_bus(addr);
-
-	dma_sync_single_for_device(dev, handle, size, dir);
-	return handle;
-}
-EXPORT_SYMBOL(dma_map_single);
 
-dma_addr_t dma_map_page(struct device *dev, struct page *page,
-			unsigned long offset, size_t size,
-			enum dma_data_direction dir)
+static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs)
 {
 	dma_addr_t handle = page_to_phys(page) + offset;
 
 	dma_sync_single_for_device(dev, handle, size, dir);
 	return handle;
 }
-EXPORT_SYMBOL(dma_map_page);
 
-int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	       enum dma_data_direction dir)
+static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	int i;
 	struct scatterlist *sg;
@@ -167,4 +151,13 @@ int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	}
 	return nents;
 }
-EXPORT_SYMBOL(dma_map_sg);
+
+struct dma_map_ops m68k_dma_ops = {
+	.alloc			= m68k_dma_alloc,
+	.free			= m68k_dma_free,
+	.map_page		= m68k_dma_map_page,
+	.map_sg			= m68k_dma_map_sg,
+	.sync_single_for_device	= m68k_dma_sync_single_for_device,
+	.sync_sg_for_device	= m68k_dma_sync_sg_for_device,
+};
+EXPORT_SYMBOL(m68k_dma_ops);
diff --git a/arch/metag/include/asm/dma-mapping.h b/arch/metag/include/asm/dma-mapping.h
index eb5cdec94be0..27af5d479ce6 100644
--- a/arch/metag/include/asm/dma-mapping.h
+++ b/arch/metag/include/asm/dma-mapping.h
@@ -1,177 +1,11 @@
 #ifndef _ASM_METAG_DMA_MAPPING_H
 #define _ASM_METAG_DMA_MAPPING_H
 
-#include <linux/mm.h>
+extern struct dma_map_ops metag_dma_ops;
 
-#include <asm/cache.h>
-#include <asm/io.h>
-#include <linux/scatterlist.h>
-#include <asm/bug.h>
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, gfp_t flag);
-
-void dma_free_coherent(struct device *dev, size_t size,
-		       void *vaddr, dma_addr_t dma_handle);
-
-void dma_sync_for_device(void *vaddr, size_t size, int dma_direction);
-void dma_sync_for_cpu(void *vaddr, size_t size, int dma_direction);
-
-int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
-		      void *cpu_addr, dma_addr_t dma_addr, size_t size);
-
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
-			  void *cpu_addr, dma_addr_t dma_addr, size_t size);
-
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-	WARN_ON(size == 0);
-	dma_sync_for_device(ptr, size, direction);
-	return virt_to_phys(ptr);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-	dma_sync_for_cpu(phys_to_virt(dma_addr), size, direction);
-}
-
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	   enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	int i;
-
-	BUG_ON(!valid_dma_direction(direction));
-	WARN_ON(nents == 0 || sglist[0].length == 0);
-
-	for_each_sg(sglist, sg, nents, i) {
-		BUG_ON(!sg_page(sg));
-
-		sg->dma_address = sg_phys(sg);
-		dma_sync_for_device(sg_virt(sg), sg->length, direction);
-	}
-
-	return nents;
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-	     size_t size, enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-	dma_sync_for_device((void *)(page_to_phys(page) + offset), size,
-			    direction);
-	return page_to_phys(page) + offset;
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-	dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
-}
-
-
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nhwentries,
-	     enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	int i;
-
-	BUG_ON(!valid_dma_direction(direction));
-	WARN_ON(nhwentries == 0 || sglist[0].length == 0);
-
-	for_each_sg(sglist, sg, nhwentries, i) {
-		BUG_ON(!sg_page(sg));
-
-		sg->dma_address = sg_phys(sg);
-		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
-	}
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-			enum dma_data_direction direction)
-{
-	dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction);
-}
-
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction direction)
-{
-	dma_sync_for_device(phys_to_virt(dma_handle), size, direction);
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction direction)
-{
-	dma_sync_for_cpu(phys_to_virt(dma_handle)+offset, size,
-			 direction);
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction direction)
-{
-	dma_sync_for_device(phys_to_virt(dma_handle)+offset, size,
-			    direction);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nelems,
-		    enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist,
-		       int nelems, enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nelems, i)
-		dma_sync_for_device(sg_virt(sg), sg->length, direction);
-}
-
-static inline int
-dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	return 0;
-}
-
-#define dma_supported(dev, mask)        (1)
-
-static inline int
-dma_set_mask(struct device *dev, u64 mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-
-	return 0;
+	return &metag_dma_ops;
 }
 
 /*
@@ -184,11 +18,4 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 {
 }
 
-/* drivers/base/dma-mapping.c */
-extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size);
-
-#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
-
 #endif
diff --git a/arch/metag/kernel/dma.c b/arch/metag/kernel/dma.c
index c700d625067a..e12368d02155 100644
--- a/arch/metag/kernel/dma.c
+++ b/arch/metag/kernel/dma.c
@@ -171,8 +171,8 @@ out:
  * Allocate DMA-coherent memory space and return both the kernel remapped
  * virtual and bus address for that space.
  */
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *handle, gfp_t gfp)
+static void *metag_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	struct page *page;
 	struct metag_vm_region *c;
@@ -263,13 +263,12 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 no_page:
 	return NULL;
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
 /*
  * free a page as defined by the above mapping.
  */
-void dma_free_coherent(struct device *dev, size_t size,
-		       void *vaddr, dma_addr_t dma_handle)
+static void metag_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	struct metag_vm_region *c;
 	unsigned long flags, addr;
@@ -329,16 +328,19 @@ no_area:
 	       __func__, vaddr);
 	dump_stack();
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
-
-static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
-		    void *cpu_addr, dma_addr_t dma_addr, size_t size)
+static int metag_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs)
 {
-	int ret = -ENXIO;
-
 	unsigned long flags, user_size, kern_size;
 	struct metag_vm_region *c;
+	int ret = -ENXIO;
+
+	if (dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 	user_size = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 
@@ -364,25 +366,6 @@ static int dma_mmap(struct device *dev, struct vm_area_struct *vma,
 	return ret;
 }
 
-int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
-		      void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
-}
-EXPORT_SYMBOL(dma_mmap_coherent);
-
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
-			  void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
-	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-	return dma_mmap(dev, vma, cpu_addr, dma_addr, size);
-}
-EXPORT_SYMBOL(dma_mmap_writecombine);
-
-
-
-
 /*
  * Initialise the consistent memory allocation.
  */
@@ -423,7 +406,7 @@ early_initcall(dma_alloc_init);
 /*
  * make an area consistent to devices.
  */
-void dma_sync_for_device(void *vaddr, size_t size, int dma_direction)
+static void dma_sync_for_device(void *vaddr, size_t size, int dma_direction)
 {
 	/*
 	 * Ensure any writes get through the write combiner. This is necessary
@@ -465,12 +448,11 @@ void dma_sync_for_device(void *vaddr, size_t size, int dma_direction)
 
 	wmb();
 }
-EXPORT_SYMBOL(dma_sync_for_device);
 
 /*
  * make an area consistent to the core.
  */
-void dma_sync_for_cpu(void *vaddr, size_t size, int dma_direction)
+static void dma_sync_for_cpu(void *vaddr, size_t size, int dma_direction)
 {
 	/*
 	 * Hardware L2 cache prefetch doesn't occur across 4K physical
@@ -497,4 +479,100 @@ void dma_sync_for_cpu(void *vaddr, size_t size, int dma_direction)
 
 	rmb();
 }
-EXPORT_SYMBOL(dma_sync_for_cpu);
+
+static dma_addr_t metag_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size,
+		enum dma_data_direction direction, struct dma_attrs *attrs)
+{
+	dma_sync_for_device((void *)(page_to_phys(page) + offset), size,
+			    direction);
+	return page_to_phys(page) + offset;
+}
+
+static void metag_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
+		size_t size, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
+}
+
+static int metag_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sglist, sg, nents, i) {
+		BUG_ON(!sg_page(sg));
+
+		sg->dma_address = sg_phys(sg);
+		dma_sync_for_device(sg_virt(sg), sg->length, direction);
+	}
+
+	return nents;
+}
+
+
+static void metag_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+		int nhwentries, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sglist, sg, nhwentries, i) {
+		BUG_ON(!sg_page(sg));
+
+		sg->dma_address = sg_phys(sg);
+		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
+	}
+}
+
+static void metag_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+	dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction);
+}
+
+static void metag_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+	dma_sync_for_device(phys_to_virt(dma_handle), size, direction);
+}
+
+static void metag_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sglist, int nelems,
+		enum dma_data_direction direction)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
+		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
+}
+
+static void metag_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sglist, int nelems,
+		enum dma_data_direction direction)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nelems, i)
+		dma_sync_for_device(sg_virt(sg), sg->length, direction);
+}
+
+struct dma_map_ops metag_dma_ops = {
+	.alloc			= metag_dma_alloc,
+	.free			= metag_dma_free,
+	.map_page		= metag_dma_map_page,
+	.map_sg			= metag_dma_map_sg,
+	.sync_single_for_device	= metag_dma_sync_single_for_device,
+	.sync_single_for_cpu	= metag_dma_sync_single_for_cpu,
+	.sync_sg_for_cpu	= metag_dma_sync_sg_for_cpu,
+	.mmap			= metag_dma_mmap,
+};
+EXPORT_SYMBOL(metag_dma_ops);
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 5ecd0287a874..53b69deceb99 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -19,7 +19,6 @@ config MICROBLAZE
 	select HAVE_ARCH_KGDB
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_API_DEBUG
-	select HAVE_DMA_ATTRS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h
index 24b12970c9cf..1884783d15c0 100644
--- a/arch/microblaze/include/asm/dma-mapping.h
+++ b/arch/microblaze/include/asm/dma-mapping.h
@@ -44,8 +44,6 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 	return &dma_direct_ops;
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 static inline void __dma_sync(unsigned long paddr,
 			      size_t size, enum dma_data_direction direction)
 {
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 35ae01fe980a..78105d981f46 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -31,7 +31,6 @@ config MIPS
 	select RTC_LIB if !MACH_LOONGSON64
 	select GENERIC_ATOMIC64 if !64BIT
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
-	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DMA_API_DEBUG
 	select GENERIC_IRQ_PROBE
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index e604f760c4a0..12fa79e2f1b4 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -29,8 +29,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
-#include <asm-generic/dma-mapping-common.h>
-
 extern void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction);
 
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 78ae5552fdb8..10607f0d2bcd 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -14,6 +14,7 @@ config MN10300
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select HAVE_DEBUG_STACKOVERFLOW
+	select ARCH_NO_COHERENT_DMA_MMAP
 
 config AM33_2
 	def_bool n
diff --git a/arch/mn10300/include/asm/dma-mapping.h b/arch/mn10300/include/asm/dma-mapping.h
index a18abfc558eb..1dcd44757f32 100644
--- a/arch/mn10300/include/asm/dma-mapping.h
+++ b/arch/mn10300/include/asm/dma-mapping.h
@@ -11,154 +11,14 @@
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
 
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
-
 #include <asm/cache.h>
 #include <asm/io.h>
 
-/*
- * See Documentation/DMA-API.txt for the description of how the
- * following DMA API should work.
- */
-
-extern void *dma_alloc_coherent(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, int flag);
-
-extern void dma_free_coherent(struct device *dev, size_t size,
-			      void *vaddr, dma_addr_t dma_handle);
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent((d), (s), (h), (f))
-#define dma_free_noncoherent(d, s, v, h)  dma_free_coherent((d), (s), (v), (h))
-
-static inline
-dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
-			  enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-	mn10300_dcache_flush_inv();
-	return virt_to_bus(ptr);
-}
-
-static inline
-void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		      enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-static inline
-int dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	       enum dma_data_direction direction)
-{
-	struct scatterlist *sg;
-	int i;
-
-	BUG_ON(!valid_dma_direction(direction));
-	WARN_ON(nents == 0 || sglist[0].length == 0);
-
-	for_each_sg(sglist, sg, nents, i) {
-		BUG_ON(!sg_page(sg));
-
-		sg->dma_address = sg_phys(sg);
-	}
+extern struct dma_map_ops mn10300_dma_ops;
 
-	mn10300_dcache_flush_inv();
-	return nents;
-}
-
-static inline
-void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-		  enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-}
-
-static inline
-dma_addr_t dma_map_page(struct device *dev, struct page *page,
-			unsigned long offset, size_t size,
-			enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-	return page_to_bus(page) + offset;
-}
-
-static inline
-void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-		    enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-}
-
-static inline
-void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			     size_t size, enum dma_data_direction direction)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-}
-
-static inline
-void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
-				size_t size, enum dma_data_direction direction)
-{
-	mn10300_dcache_flush_inv();
-}
-
-static inline
-void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction direction)
-{
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction direction)
-{
-	mn10300_dcache_flush_inv();
-}
-
-
-static inline
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-			 int nelems, enum dma_data_direction direction)
-{
-}
-
-static inline
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-			    int nelems, enum dma_data_direction direction)
-{
-	mn10300_dcache_flush_inv();
-}
-
-static inline
-int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-static inline
-int dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s, so we can't
-	 * guarantee allocations that must be within a tighter range than
-	 * GFP_DMA
-	 */
-	if (mask < 0x00ffffff)
-		return 0;
-	return 1;
-}
-
-static inline
-int dma_set_mask(struct device *dev, u64 mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-	return 0;
+	return &mn10300_dma_ops;
 }
 
 static inline
@@ -168,19 +28,4 @@ void dma_cache_sync(void *vaddr, size_t size,
 	mn10300_dcache_flush_inv();
 }
 
-/* Not supported for now */
-static inline int dma_mmap_coherent(struct device *dev,
-				    struct vm_area_struct *vma, void *cpu_addr,
-				    dma_addr_t dma_addr, size_t size)
-{
-	return -EINVAL;
-}
-
-static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size)
-{
-	return -EINVAL;
-}
-
 #endif
diff --git a/arch/mn10300/mm/dma-alloc.c b/arch/mn10300/mm/dma-alloc.c
index e244ebe637e1..8842394cb49a 100644
--- a/arch/mn10300/mm/dma-alloc.c
+++ b/arch/mn10300/mm/dma-alloc.c
@@ -20,8 +20,8 @@
 
 static unsigned long pci_sram_allocated = 0xbc000000;
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			 dma_addr_t *dma_handle, int gfp)
+static void *mn10300_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	unsigned long addr;
 	void *ret;
@@ -61,10 +61,9 @@ done:
 	printk("dma_alloc_coherent() = %p [%x]\n", ret, *dma_handle);
 	return ret;
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-		       dma_addr_t dma_handle)
+static void mn10300_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	unsigned long addr = (unsigned long) vaddr & ~0x20000000;
 
@@ -73,4 +72,60 @@ void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
 
 	free_pages(addr, get_order(size));
 }
-EXPORT_SYMBOL(dma_free_coherent);
+
+static int mn10300_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sglist, sg, nents, i) {
+		BUG_ON(!sg_page(sg));
+
+		sg->dma_address = sg_phys(sg);
+	}
+
+	mn10300_dcache_flush_inv();
+	return nents;
+}
+
+static dma_addr_t mn10300_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size,
+		enum dma_data_direction direction, struct dma_attrs *attrs)
+{
+	return page_to_bus(page) + offset;
+}
+
+static void mn10300_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
+				size_t size, enum dma_data_direction direction)
+{
+	mn10300_dcache_flush_inv();
+}
+
+static void mn10300_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+			    int nelems, enum dma_data_direction direction)
+{
+	mn10300_dcache_flush_inv();
+}
+
+static int mn10300_dma_supported(struct device *dev, u64 mask)
+{
+	/*
+	 * we fall back to GFP_DMA when the mask isn't all 1s, so we can't
+	 * guarantee allocations that must be within a tighter range than
+	 * GFP_DMA
+	 */
+	if (mask < 0x00ffffff)
+		return 0;
+	return 1;
+}
+
+struct dma_map_ops mn10300_dma_ops = {
+	.alloc			= mn10300_dma_alloc,
+	.free			= mn10300_dma_free,
+	.map_page		= mn10300_dma_map_page,
+	.map_sg			= mn10300_dma_map_sg,
+	.sync_single_for_device	= mn10300_dma_sync_single_for_device,
+	.sync_sg_for_device	= mn10300_dma_sync_sg_for_device,
+};
diff --git a/arch/nios2/include/asm/dma-mapping.h b/arch/nios2/include/asm/dma-mapping.h
index b5567233f7f1..bec8ac8e6ad2 100644
--- a/arch/nios2/include/asm/dma-mapping.h
+++ b/arch/nios2/include/asm/dma-mapping.h
@@ -10,131 +10,20 @@
 #ifndef _ASM_NIOS2_DMA_MAPPING_H
 #define _ASM_NIOS2_DMA_MAPPING_H
 
-#include <linux/scatterlist.h>
-#include <linux/cache.h>
-#include <asm/cacheflush.h>
+extern struct dma_map_ops nios2_dma_ops;
 
-static inline void __dma_sync_for_device(void *vaddr, size_t size,
-			      enum dma_data_direction direction)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	switch (direction) {
-	case DMA_FROM_DEVICE:
-		invalidate_dcache_range((unsigned long)vaddr,
-			(unsigned long)(vaddr + size));
-		break;
-	case DMA_TO_DEVICE:
-		/*
-		 * We just need to flush the caches here , but Nios2 flush
-		 * instruction will do both writeback and invalidate.
-		 */
-	case DMA_BIDIRECTIONAL: /* flush and invalidate */
-		flush_dcache_range((unsigned long)vaddr,
-			(unsigned long)(vaddr + size));
-		break;
-	default:
-		BUG();
-	}
-}
-
-static inline void __dma_sync_for_cpu(void *vaddr, size_t size,
-			      enum dma_data_direction direction)
-{
-	switch (direction) {
-	case DMA_BIDIRECTIONAL:
-	case DMA_FROM_DEVICE:
-		invalidate_dcache_range((unsigned long)vaddr,
-			(unsigned long)(vaddr + size));
-		break;
-	case DMA_TO_DEVICE:
-		break;
-	default:
-		BUG();
-	}
-}
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, gfp_t flag);
-
-void dma_free_coherent(struct device *dev, size_t size,
-			 void *vaddr, dma_addr_t dma_handle);
-
-static inline dma_addr_t dma_map_single(struct device *dev, void *ptr,
-					size_t size,
-					enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-	__dma_sync_for_device(ptr, size, direction);
-	return virt_to_phys(ptr);
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-				size_t size, enum dma_data_direction direction)
-{
-}
-
-extern int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	enum dma_data_direction direction);
-extern dma_addr_t dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction);
-extern void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-	size_t size, enum dma_data_direction direction);
-extern void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-	int nhwentries, enum dma_data_direction direction);
-extern void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-	size_t size, enum dma_data_direction direction);
-extern void dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction);
-extern void dma_sync_single_range_for_cpu(struct device *dev,
-	dma_addr_t dma_handle, unsigned long offset, size_t size,
-	enum dma_data_direction direction);
-extern void dma_sync_single_range_for_device(struct device *dev,
-	dma_addr_t dma_handle, unsigned long offset, size_t size,
-	enum dma_data_direction direction);
-extern void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-	int nelems, enum dma_data_direction direction);
-extern void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-	int nelems, enum dma_data_direction direction);
-
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 mask)
-{
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-
-	return 0;
-}
-
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
+	return &nios2_dma_ops;
 }
 
 /*
-* dma_alloc_noncoherent() returns non-cacheable memory, so there's no need to
-* do any flushing here.
-*/
+ * dma_alloc_noncoherent() returns non-cacheable memory, so there's no need to
+ * do any flushing here.
+ */
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 				  enum dma_data_direction direction)
 {
 }
 
-/* drivers/base/dma-mapping.c */
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-		void *cpu_addr, dma_addr_t dma_addr, size_t size);
-extern int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-		void *cpu_addr, dma_addr_t dma_addr,
-		size_t size);
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_common_mmap(d, v, c, h, s)
-#define dma_get_sgtable(d, t, v, h, s) dma_common_get_sgtable(d, t, v, h, s)
-
 #endif /* _ASM_NIOS2_DMA_MAPPING_H */
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index ac5da7594f0b..90422c367ed3 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -20,9 +20,46 @@
 #include <linux/cache.h>
 #include <asm/cacheflush.h>
 
+static inline void __dma_sync_for_device(void *vaddr, size_t size,
+			      enum dma_data_direction direction)
+{
+	switch (direction) {
+	case DMA_FROM_DEVICE:
+		invalidate_dcache_range((unsigned long)vaddr,
+			(unsigned long)(vaddr + size));
+		break;
+	case DMA_TO_DEVICE:
+		/*
+		 * We just need to flush the caches here , but Nios2 flush
+		 * instruction will do both writeback and invalidate.
+		 */
+	case DMA_BIDIRECTIONAL: /* flush and invalidate */
+		flush_dcache_range((unsigned long)vaddr,
+			(unsigned long)(vaddr + size));
+		break;
+	default:
+		BUG();
+	}
+}
 
-void *dma_alloc_coherent(struct device *dev, size_t size,
-			    dma_addr_t *dma_handle, gfp_t gfp)
+static inline void __dma_sync_for_cpu(void *vaddr, size_t size,
+			      enum dma_data_direction direction)
+{
+	switch (direction) {
+	case DMA_BIDIRECTIONAL:
+	case DMA_FROM_DEVICE:
+		invalidate_dcache_range((unsigned long)vaddr,
+			(unsigned long)(vaddr + size));
+		break;
+	case DMA_TO_DEVICE:
+		break;
+	default:
+		BUG();
+	}
+}
+
+static void *nios2_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, struct dma_attrs *attrs)
 {
 	void *ret;
 
@@ -45,24 +82,21 @@ void *dma_alloc_coherent(struct device *dev, size_t size,
 
 	return ret;
 }
-EXPORT_SYMBOL(dma_alloc_coherent);
 
-void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-			dma_addr_t dma_handle)
+static void nios2_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	unsigned long addr = (unsigned long) CAC_ADDR((unsigned long) vaddr);
 
 	free_pages(addr, get_order(size));
 }
-EXPORT_SYMBOL(dma_free_coherent);
 
-int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction direction)
+static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	int i;
 
-	BUG_ON(!valid_dma_direction(direction));
-
 	for_each_sg(sg, sg, nents, i) {
 		void *addr;
 
@@ -75,40 +109,32 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 
 	return nents;
 }
-EXPORT_SYMBOL(dma_map_sg);
 
-dma_addr_t dma_map_page(struct device *dev, struct page *page,
+static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page,
 			unsigned long offset, size_t size,
-			enum dma_data_direction direction)
+			enum dma_data_direction direction,
+			struct dma_attrs *attrs)
 {
-	void *addr;
-
-	BUG_ON(!valid_dma_direction(direction));
+	void *addr = page_address(page) + offset;
 
-	addr = page_address(page) + offset;
 	__dma_sync_for_device(addr, size, direction);
-
 	return page_to_phys(page) + offset;
 }
-EXPORT_SYMBOL(dma_map_page);
 
-void dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-		    enum dma_data_direction direction)
+static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
+		size_t size, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
-	BUG_ON(!valid_dma_direction(direction));
-
 	__dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
 }
-EXPORT_SYMBOL(dma_unmap_page);
 
-void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-		  enum dma_data_direction direction)
+static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+		int nhwentries, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	void *addr;
 	int i;
 
-	BUG_ON(!valid_dma_direction(direction));
-
 	if (direction == DMA_TO_DEVICE)
 		return;
 
@@ -118,69 +144,54 @@ void dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
 			__dma_sync_for_cpu(addr, sg->length, direction);
 	}
 }
-EXPORT_SYMBOL(dma_unmap_sg);
-
-void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			     size_t size, enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
 
-	__dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction);
-}
-EXPORT_SYMBOL(dma_sync_single_for_cpu);
-
-void dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
-				size_t size, enum dma_data_direction direction)
-{
-	BUG_ON(!valid_dma_direction(direction));
-
-	__dma_sync_for_device(phys_to_virt(dma_handle), size, direction);
-}
-EXPORT_SYMBOL(dma_sync_single_for_device);
-
-void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-					unsigned long offset, size_t size,
-					enum dma_data_direction direction)
+static void nios2_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
 {
-	BUG_ON(!valid_dma_direction(direction));
-
 	__dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction);
 }
-EXPORT_SYMBOL(dma_sync_single_range_for_cpu);
 
-void dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-					unsigned long offset, size_t size,
-					enum dma_data_direction direction)
+static void nios2_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
 {
-	BUG_ON(!valid_dma_direction(direction));
-
 	__dma_sync_for_device(phys_to_virt(dma_handle), size, direction);
 }
-EXPORT_SYMBOL(dma_sync_single_range_for_device);
 
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
-			 enum dma_data_direction direction)
+static void nios2_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sg, int nelems,
+		enum dma_data_direction direction)
 {
 	int i;
 
-	BUG_ON(!valid_dma_direction(direction));
-
 	/* Make sure that gcc doesn't leave the empty loop body.  */
 	for_each_sg(sg, sg, nelems, i)
 		__dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
 }
-EXPORT_SYMBOL(dma_sync_sg_for_cpu);
 
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-				int nelems, enum dma_data_direction direction)
+static void nios2_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sg, int nelems,
+		enum dma_data_direction direction)
 {
 	int i;
 
-	BUG_ON(!valid_dma_direction(direction));
-
 	/* Make sure that gcc doesn't leave the empty loop body.  */
 	for_each_sg(sg, sg, nelems, i)
 		__dma_sync_for_device(sg_virt(sg), sg->length, direction);
 
 }
-EXPORT_SYMBOL(dma_sync_sg_for_device);
+
+struct dma_map_ops nios2_dma_ops = {
+	.alloc			= nios2_dma_alloc,
+	.free			= nios2_dma_free,
+	.map_page		= nios2_dma_map_page,
+	.unmap_page		= nios2_dma_unmap_page,
+	.map_sg			= nios2_dma_map_sg,
+	.unmap_sg		= nios2_dma_unmap_sg,
+	.sync_single_for_device	= nios2_dma_sync_single_for_device,
+	.sync_single_for_cpu	= nios2_dma_sync_single_for_cpu,
+	.sync_sg_for_cpu	= nios2_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= nios2_dma_sync_sg_for_device,
+};
+EXPORT_SYMBOL(nios2_dma_ops);
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 443f44de1020..e118c02cc79a 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -29,9 +29,6 @@ config OPENRISC
 config MMU
 	def_bool y
 
-config HAVE_DMA_ATTRS
-	def_bool y
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
diff --git a/arch/openrisc/include/asm/dma-mapping.h b/arch/openrisc/include/asm/dma-mapping.h
index 413bfcf86384..1f260bccb368 100644
--- a/arch/openrisc/include/asm/dma-mapping.h
+++ b/arch/openrisc/include/asm/dma-mapping.h
@@ -42,6 +42,4 @@ static inline int dma_supported(struct device *dev, u64 dma_mask)
 	return dma_mask == DMA_BIT_MASK(32);
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 #endif	/* __ASM_OPENRISC_DMA_MAPPING_H */
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 7c34cafdf301..14f655cf542e 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -29,6 +29,7 @@ config PARISC
 	select TTY # Needed for pdc_cons.c
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_ARCH_AUDITSYSCALL
+	select ARCH_NO_COHERENT_DMA_MMAP
 
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index d8d60a57183f..16e024602737 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -1,30 +1,11 @@
 #ifndef _PARISC_DMA_MAPPING_H
 #define _PARISC_DMA_MAPPING_H
 
-#include <linux/mm.h>
-#include <linux/scatterlist.h>
 #include <asm/cacheflush.h>
 
-/* See Documentation/DMA-API-HOWTO.txt */
-struct hppa_dma_ops {
-	int  (*dma_supported)(struct device *dev, u64 mask);
-	void *(*alloc_consistent)(struct device *dev, size_t size, dma_addr_t *iova, gfp_t flag);
-	void *(*alloc_noncoherent)(struct device *dev, size_t size, dma_addr_t *iova, gfp_t flag);
-	void (*free_consistent)(struct device *dev, size_t size, void *vaddr, dma_addr_t iova);
-	dma_addr_t (*map_single)(struct device *dev, void *addr, size_t size, enum dma_data_direction direction);
-	void (*unmap_single)(struct device *dev, dma_addr_t iova, size_t size, enum dma_data_direction direction);
-	int  (*map_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction);
-	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nhwents, enum dma_data_direction direction);
-	void (*dma_sync_single_for_cpu)(struct device *dev, dma_addr_t iova, unsigned long offset, size_t size, enum dma_data_direction direction);
-	void (*dma_sync_single_for_device)(struct device *dev, dma_addr_t iova, unsigned long offset, size_t size, enum dma_data_direction direction);
-	void (*dma_sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction);
-	void (*dma_sync_sg_for_device)(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction);
-};
-
 /*
-** We could live without the hppa_dma_ops indirection if we didn't want
-** to support 4 different coherent dma models with one binary (they will
-** someday be loadable modules):
+** We need to support 4 different coherent dma models with one binary:
+**
 **     I/O MMU        consistent method           dma_sync behavior
 **  =============   ======================       =======================
 **  a) PA-7x00LC    uncachable host memory          flush/purge
@@ -40,158 +21,22 @@ struct hppa_dma_ops {
 */
 
 #ifdef CONFIG_PA11
-extern struct hppa_dma_ops pcxl_dma_ops;
-extern struct hppa_dma_ops pcx_dma_ops;
+extern struct dma_map_ops pcxl_dma_ops;
+extern struct dma_map_ops pcx_dma_ops;
 #endif
 
-extern struct hppa_dma_ops *hppa_dma_ops;
-
-#define dma_alloc_attrs(d, s, h, f, a) dma_alloc_coherent(d, s, h, f)
-#define dma_free_attrs(d, s, h, f, a) dma_free_coherent(d, s, h, f)
-
-static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		   gfp_t flag)
-{
-	return hppa_dma_ops->alloc_consistent(dev, size, dma_handle, flag);
-}
-
-static inline void *
-dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		      gfp_t flag)
-{
-	return hppa_dma_ops->alloc_noncoherent(dev, size, dma_handle, flag);
-}
-
-static inline void
-dma_free_coherent(struct device *dev, size_t size, 
-		    void *vaddr, dma_addr_t dma_handle)
-{
-	hppa_dma_ops->free_consistent(dev, size, vaddr, dma_handle);
-}
-
-static inline void
-dma_free_noncoherent(struct device *dev, size_t size, 
-		    void *vaddr, dma_addr_t dma_handle)
-{
-	hppa_dma_ops->free_consistent(dev, size, vaddr, dma_handle);
-}
-
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction direction)
-{
-	return hppa_dma_ops->map_single(dev, ptr, size, direction);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
-{
-	hppa_dma_ops->unmap_single(dev, dma_addr, size, direction);
-}
-
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	   enum dma_data_direction direction)
-{
-	return hppa_dma_ops->map_sg(dev, sg, nents, direction);
-}
+extern struct dma_map_ops *hppa_dma_ops;
 
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction)
-{
-	hppa_dma_ops->unmap_sg(dev, sg, nhwentries, direction);
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-	     size_t size, enum dma_data_direction direction)
-{
-	return dma_map_single(dev, (page_address(page) + (offset)), size, direction);
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-	dma_unmap_single(dev, dma_address, size, direction);
-}
-
-
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_cpu)
-		hppa_dma_ops->dma_sync_single_for_cpu(dev, dma_handle, 0, size, direction);
-}
-
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_device)
-		hppa_dma_ops->dma_sync_single_for_device(dev, dma_handle, 0, size, direction);
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_cpu)
-		hppa_dma_ops->dma_sync_single_for_cpu(dev, dma_handle, offset, size, direction);
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_device)
-		hppa_dma_ops->dma_sync_single_for_device(dev, dma_handle, offset, size, direction);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
-		 enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_sg_for_cpu)
-		hppa_dma_ops->dma_sync_sg_for_cpu(dev, sg, nelems, direction);
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		 enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_sg_for_device)
-		hppa_dma_ops->dma_sync_sg_for_device(dev, sg, nelems, direction);
-}
-
-static inline int
-dma_supported(struct device *dev, u64 mask)
-{
-	return hppa_dma_ops->dma_supported(dev, mask);
-}
-
-static inline int
-dma_set_mask(struct device *dev, u64 mask)
-{
-	if(!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-
-	return 0;
+	return hppa_dma_ops;
 }
 
 static inline void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction)
 {
-	if(hppa_dma_ops->dma_sync_single_for_cpu)
+	if (hppa_dma_ops->sync_single_for_cpu)
 		flush_kernel_dcache_range((unsigned long)vaddr, size);
 }
 
@@ -238,22 +83,4 @@ struct parisc_device;
 void * sba_get_iommu(struct parisc_device *dev);
 #endif
 
-/* At the moment, we panic on error for IOMMU resource exaustion */
-#define dma_mapping_error(dev, x)	0
-
-/* This API cannot be supported on PA-RISC */
-static inline int dma_mmap_coherent(struct device *dev,
-				    struct vm_area_struct *vma, void *cpu_addr,
-				    dma_addr_t dma_addr, size_t size)
-{
-	return -EINVAL;
-}
-
-static inline int dma_get_sgtable(struct device *dev, struct sg_table *sgt,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size)
-{
-	return -EINVAL;
-}
-
 #endif
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index dba508fe1683..f8150669b8c6 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -40,7 +40,7 @@
 #include <asm/parisc-device.h>
 
 /* See comments in include/asm-parisc/pci.h */
-struct hppa_dma_ops *hppa_dma_ops __read_mostly;
+struct dma_map_ops *hppa_dma_ops __read_mostly;
 EXPORT_SYMBOL(hppa_dma_ops);
 
 static struct device root = {
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index b9402c9b3454..a27e4928bf73 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -413,7 +413,8 @@ pcxl_dma_init(void)
 
 __initcall(pcxl_dma_init);
 
-static void * pa11_dma_alloc_consistent (struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag)
+static void *pa11_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs)
 {
 	unsigned long vaddr;
 	unsigned long paddr;
@@ -439,7 +440,8 @@ static void * pa11_dma_alloc_consistent (struct device *dev, size_t size, dma_ad
 	return (void *)vaddr;
 }
 
-static void pa11_dma_free_consistent (struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle)
+static void pa11_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
 	int order;
 
@@ -450,15 +452,20 @@ static void pa11_dma_free_consistent (struct device *dev, size_t size, void *vad
 	free_pages((unsigned long)__va(dma_handle), order);
 }
 
-static dma_addr_t pa11_dma_map_single(struct device *dev, void *addr, size_t size, enum dma_data_direction direction)
+static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size,
+		enum dma_data_direction direction, struct dma_attrs *attrs)
 {
+	void *addr = page_address(page) + offset;
 	BUG_ON(direction == DMA_NONE);
 
 	flush_kernel_dcache_range((unsigned long) addr, size);
 	return virt_to_phys(addr);
 }
 
-static void pa11_dma_unmap_single(struct device *dev, dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
+static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	BUG_ON(direction == DMA_NONE);
 
@@ -475,7 +482,9 @@ static void pa11_dma_unmap_single(struct device *dev, dma_addr_t dma_handle, siz
 	return;
 }
 
-static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
+static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	int i;
 	struct scatterlist *sg;
@@ -492,7 +501,9 @@ static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist, int n
 	return nents;
 }
 
-static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
+static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
 {
 	int i;
 	struct scatterlist *sg;
@@ -509,18 +520,24 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist, in
 	return;
 }
 
-static void pa11_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, unsigned long offset, size_t size, enum dma_data_direction direction)
+static void pa11_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
 {
 	BUG_ON(direction == DMA_NONE);
 
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle) + offset, size);
+	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
+			size);
 }
 
-static void pa11_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, unsigned long offset, size_t size, enum dma_data_direction direction)
+static void pa11_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
 {
 	BUG_ON(direction == DMA_NONE);
 
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle) + offset, size);
+	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
+			size);
 }
 
 static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
@@ -545,32 +562,28 @@ static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *
 		flush_kernel_vmap_range(sg_virt(sg), sg->length);
 }
 
-struct hppa_dma_ops pcxl_dma_ops = {
+struct dma_map_ops pcxl_dma_ops = {
 	.dma_supported =	pa11_dma_supported,
-	.alloc_consistent =	pa11_dma_alloc_consistent,
-	.alloc_noncoherent =	pa11_dma_alloc_consistent,
-	.free_consistent =	pa11_dma_free_consistent,
-	.map_single =		pa11_dma_map_single,
-	.unmap_single =		pa11_dma_unmap_single,
+	.alloc =		pa11_dma_alloc,
+	.free =			pa11_dma_free,
+	.map_page =		pa11_dma_map_page,
+	.unmap_page =		pa11_dma_unmap_page,
 	.map_sg =		pa11_dma_map_sg,
 	.unmap_sg =		pa11_dma_unmap_sg,
-	.dma_sync_single_for_cpu = pa11_dma_sync_single_for_cpu,
-	.dma_sync_single_for_device = pa11_dma_sync_single_for_device,
-	.dma_sync_sg_for_cpu = pa11_dma_sync_sg_for_cpu,
-	.dma_sync_sg_for_device = pa11_dma_sync_sg_for_device,
+	.sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
+	.sync_single_for_device = pa11_dma_sync_single_for_device,
+	.sync_sg_for_cpu =	pa11_dma_sync_sg_for_cpu,
+	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
 };
 
-static void *fail_alloc_consistent(struct device *dev, size_t size,
-				   dma_addr_t *dma_handle, gfp_t flag)
-{
-	return NULL;
-}
-
-static void *pa11_dma_alloc_noncoherent(struct device *dev, size_t size,
-					  dma_addr_t *dma_handle, gfp_t flag)
+static void *pcx_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs)
 {
 	void *addr;
 
+	if (!dma_get_attr(DMA_ATTR_NON_CONSISTENT, attrs))
+		return NULL;
+
 	addr = (void *)__get_free_pages(flag, get_order(size));
 	if (addr)
 		*dma_handle = (dma_addr_t)virt_to_phys(addr);
@@ -578,24 +591,23 @@ static void *pa11_dma_alloc_noncoherent(struct device *dev, size_t size,
 	return addr;
 }
 
-static void pa11_dma_free_noncoherent(struct device *dev, size_t size,
-					void *vaddr, dma_addr_t iova)
+static void pcx_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t iova, struct dma_attrs *attrs)
 {
 	free_pages((unsigned long)vaddr, get_order(size));
 	return;
 }
 
-struct hppa_dma_ops pcx_dma_ops = {
+struct dma_map_ops pcx_dma_ops = {
 	.dma_supported =	pa11_dma_supported,
-	.alloc_consistent =	fail_alloc_consistent,
-	.alloc_noncoherent =	pa11_dma_alloc_noncoherent,
-	.free_consistent =	pa11_dma_free_noncoherent,
-	.map_single =		pa11_dma_map_single,
-	.unmap_single =		pa11_dma_unmap_single,
+	.alloc =		pcx_dma_alloc,
+	.free =			pcx_dma_free,
+	.map_page =		pa11_dma_map_page,
+	.unmap_page =		pa11_dma_unmap_page,
 	.map_sg =		pa11_dma_map_sg,
 	.unmap_sg =		pa11_dma_unmap_sg,
-	.dma_sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
-	.dma_sync_single_for_device =	pa11_dma_sync_single_for_device,
-	.dma_sync_sg_for_cpu =		pa11_dma_sync_sg_for_cpu,
-	.dma_sync_sg_for_device =	pa11_dma_sync_sg_for_device,
+	.sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
+	.sync_single_for_device = pa11_dma_sync_single_for_device,
+	.sync_sg_for_cpu =	pa11_dma_sync_sg_for_cpu,
+	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
 };
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9164bcc14003..378f1127ca98 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -108,7 +108,6 @@ config PPC
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
-	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
 	select HAVE_OPROFILE
 	select HAVE_DEBUG_KMEMLEAK
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 7f522c021dc3..77816acd4fd9 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -125,8 +125,6 @@ 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);
 
-#include <asm-generic/dma-mapping-common.h>
-
 extern int __dma_set_mask(struct device *dev, u64 dma_mask);
 extern u64 __dma_get_required_mask(struct device *dev);
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 74e6ef0a2c6f..529da95ed2ad 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -123,7 +123,6 @@ config S390
 	select HAVE_CMPXCHG_DOUBLE
 	select HAVE_CMPXCHG_LOCAL
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
diff --git a/arch/s390/include/asm/dma-mapping.h b/arch/s390/include/asm/dma-mapping.h
index cb05f5c57ce1..3249b7464889 100644
--- a/arch/s390/include/asm/dma-mapping.h
+++ b/arch/s390/include/asm/dma-mapping.h
@@ -25,8 +25,6 @@ static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 {
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
 	if (!dev->dma_mask)
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index cf04cdbc9f52..be0c6de84fba 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -11,7 +11,6 @@ config SUPERH
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_DMA_API_DEBUG
-	select HAVE_DMA_ATTRS
 	select HAVE_PERF_EVENTS
 	select HAVE_DEBUG_BUGVERBOSE
 	select ARCH_HAVE_CUSTOM_GPIO_H
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
index a3745a3fe029..e11cf0c8206b 100644
--- a/arch/sh/include/asm/dma-mapping.h
+++ b/arch/sh/include/asm/dma-mapping.h
@@ -11,8 +11,6 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 
 #define DMA_ERROR_CODE 0
 
-#include <asm-generic/dma-mapping-common.h>
-
 void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		    enum dma_data_direction dir);
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 43bcff288a91..a900e7f35f6a 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -26,7 +26,6 @@ config SPARC
 	select RTC_CLASS
 	select RTC_DRV_M48T59
 	select RTC_SYSTOHC
-	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
 	select HAVE_ARCH_JUMP_LABEL if SPARC64
 	select GENERIC_IRQ_SHOW
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index a21da597b0b5..1180ae254154 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -37,21 +37,4 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 	return dma_ops;
 }
 
-#define HAVE_ARCH_DMA_SET_MASK 1
-
-static inline int dma_set_mask(struct device *dev, u64 mask)
-{
-#ifdef CONFIG_PCI
-	if (dev->bus == &pci_bus_type) {
-		if (!dev->dma_mask || !dma_supported(dev, mask))
-			return -EINVAL;
-		*dev->dma_mask = mask;
-		return 0;
-	}
-#endif
-	return -EINVAL;
-}
-
-#include <asm-generic/dma-mapping-common.h>
-
 #endif
diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig
index 3d75b13651dd..76333d8cc1d2 100644
--- a/arch/tile/Kconfig
+++ b/arch/tile/Kconfig
@@ -5,7 +5,6 @@ config TILE
 	def_bool y
 	select HAVE_PERF_EVENTS
 	select USE_PMC if PERF_EVENTS
-	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
 	select HAVE_KVM if !TILEGX
 	select GENERIC_FIND_FIRST_BIT
diff --git a/arch/tile/include/asm/dma-mapping.h b/arch/tile/include/asm/dma-mapping.h
index 96ac6cce4a32..01ceb4a895b0 100644
--- a/arch/tile/include/asm/dma-mapping.h
+++ b/arch/tile/include/asm/dma-mapping.h
@@ -73,37 +73,7 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 }
 
 #define HAVE_ARCH_DMA_SET_MASK 1
-
-#include <asm-generic/dma-mapping-common.h>
-
-static inline int
-dma_set_mask(struct device *dev, u64 mask)
-{
-	struct dma_map_ops *dma_ops = get_dma_ops(dev);
-
-	/*
-	 * For PCI devices with 64-bit DMA addressing capability, promote
-	 * the dma_ops to hybrid, with the consistent memory DMA space limited
-	 * to 32-bit. For 32-bit capable devices, limit the streaming DMA
-	 * address range to max_direct_dma_addr.
-	 */
-	if (dma_ops == gx_pci_dma_map_ops ||
-	    dma_ops == gx_hybrid_pci_dma_map_ops ||
-	    dma_ops == gx_legacy_pci_dma_map_ops) {
-		if (mask == DMA_BIT_MASK(64) &&
-		    dma_ops == gx_legacy_pci_dma_map_ops)
-			set_dma_ops(dev, gx_hybrid_pci_dma_map_ops);
-		else if (mask > dev->archdata.max_direct_dma_addr)
-			mask = dev->archdata.max_direct_dma_addr;
-	}
-
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-
-	return 0;
-}
+int dma_set_mask(struct device *dev, u64 mask);
 
 /*
  * dma_alloc_noncoherent() is #defined to return coherent memory,
diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c
index 09b58703ac26..b6bc0547a4f6 100644
--- a/arch/tile/kernel/pci-dma.c
+++ b/arch/tile/kernel/pci-dma.c
@@ -583,6 +583,35 @@ struct dma_map_ops *gx_hybrid_pci_dma_map_ops;
 EXPORT_SYMBOL(gx_legacy_pci_dma_map_ops);
 EXPORT_SYMBOL(gx_hybrid_pci_dma_map_ops);
 
+int dma_set_mask(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *dma_ops = get_dma_ops(dev);
+
+	/*
+	 * For PCI devices with 64-bit DMA addressing capability, promote
+	 * the dma_ops to hybrid, with the consistent memory DMA space limited
+	 * to 32-bit. For 32-bit capable devices, limit the streaming DMA
+	 * address range to max_direct_dma_addr.
+	 */
+	if (dma_ops == gx_pci_dma_map_ops ||
+	    dma_ops == gx_hybrid_pci_dma_map_ops ||
+	    dma_ops == gx_legacy_pci_dma_map_ops) {
+		if (mask == DMA_BIT_MASK(64) &&
+		    dma_ops == gx_legacy_pci_dma_map_ops)
+			set_dma_ops(dev, gx_hybrid_pci_dma_map_ops);
+		else if (mask > dev->archdata.max_direct_dma_addr)
+			mask = dev->archdata.max_direct_dma_addr;
+	}
+
+	if (!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+
+	*dev->dma_mask = mask;
+
+	return 0;
+}
+EXPORT_SYMBOL(dma_set_mask);
+
 #ifdef CONFIG_ARCH_HAS_DMA_SET_COHERENT_MASK
 int dma_set_coherent_mask(struct device *dev, u64 mask)
 {
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 910aaaaed969..cb01ea45c52c 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -4,7 +4,6 @@ config UNICORE32
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select HAVE_MEMBLOCK
 	select HAVE_GENERIC_DMA_COHERENT
-	select HAVE_DMA_ATTRS
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
 	select GENERIC_ATOMIC64
diff --git a/arch/unicore32/include/asm/dma-mapping.h b/arch/unicore32/include/asm/dma-mapping.h
index 8140e053ccd3..4749854afd03 100644
--- a/arch/unicore32/include/asm/dma-mapping.h
+++ b/arch/unicore32/include/asm/dma-mapping.h
@@ -28,8 +28,6 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 	return &swiotlb_dma_map_ops;
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
 	if (dev && dev->dma_mask)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5655223d3318..6ccc955c4838 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -99,7 +99,6 @@ config X86
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DMA_API_DEBUG
-	select HAVE_DMA_ATTRS
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 953b7263f844..3a27b93e6261 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -46,8 +46,6 @@ bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp);
 #define HAVE_ARCH_DMA_SUPPORTED 1
 extern int dma_supported(struct device *hwdev, u64 mask);
 
-#include <asm-generic/dma-mapping-common.h>
-
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_addr, gfp_t flag,
 					struct dma_attrs *attrs);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 82044f732323..e9df1567d778 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -15,7 +15,6 @@ config XTENSA
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
 	select HAVE_DMA_API_DEBUG
-	select HAVE_DMA_ATTRS
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if !MMU
 	select HAVE_IRQ_TIME_ACCOUNTING
diff --git a/arch/xtensa/include/asm/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 66c9ba261e30..3fc1170a6488 100644
--- a/arch/xtensa/include/asm/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
@@ -13,8 +13,6 @@
 #include <asm/cache.h>
 #include <asm/io.h>
 
-#include <asm-generic/dma-coherent.h>
-
 #include <linux/mm.h>
 #include <linux/scatterlist.h>
 
@@ -30,8 +28,6 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 		return &xtensa_dma_map_ops;
 }
 
-#include <asm-generic/dma-mapping-common.h>
-
 void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		    enum dma_data_direction direction);
 
diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c
index d95c5971c225..d799662f19eb 100644
--- a/drivers/base/dma-mapping.c
+++ b/drivers/base/dma-mapping.c
@@ -12,7 +12,6 @@
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-#include <asm-generic/dma-coherent.h>
 
 /*
  * Managed DMA API
@@ -167,7 +166,7 @@ void dmam_free_noncoherent(struct device *dev, size_t size, void *vaddr,
 }
 EXPORT_SYMBOL(dmam_free_noncoherent);
 
-#ifdef ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
 
 static void dmam_coherent_decl_release(struct device *dev, void *res)
 {
@@ -247,7 +246,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size)
 {
 	int ret = -ENXIO;
-#ifdef CONFIG_MMU
+#if defined(CONFIG_MMU) && !defined(CONFIG_ARCH_NO_COHERENT_DMA_MMAP)
 	unsigned long user_count = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long pfn = page_to_pfn(virt_to_page(cpu_addr));
@@ -264,7 +263,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 				      user_count << PAGE_SHIFT,
 				      vma->vm_page_prot);
 	}
-#endif	/* CONFIG_MMU */
+#endif	/* CONFIG_MMU && !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index b02ac62f5863..b7df8df94c1b 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -82,13 +82,13 @@ config DRM_TTM
 
 config DRM_GEM_CMA_HELPER
 	bool
-	depends on DRM && HAVE_DMA_ATTRS
+	depends on DRM
 	help
 	  Choose this if you need the GEM CMA helper functions
 
 config DRM_KMS_CMA_HELPER
 	bool
-	depends on DRM && HAVE_DMA_ATTRS
+	depends on DRM
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_FB_HELPER
 	select FB_SYS_FILLRECT
diff --git a/drivers/gpu/drm/imx/Kconfig b/drivers/gpu/drm/imx/Kconfig
index 35ca4f007839..a1844b50546c 100644
--- a/drivers/gpu/drm/imx/Kconfig
+++ b/drivers/gpu/drm/imx/Kconfig
@@ -5,7 +5,7 @@ config DRM_IMX
 	select VIDEOMODE_HELPERS
 	select DRM_GEM_CMA_HELPER
 	select DRM_KMS_CMA_HELPER
-	depends on DRM && (ARCH_MXC || ARCH_MULTIPLATFORM) && HAVE_DMA_ATTRS
+	depends on DRM && (ARCH_MXC || ARCH_MULTIPLATFORM)
 	depends on IMX_IPUV3_CORE
 	help
 	  enable i.MX graphics support
diff --git a/drivers/gpu/drm/rcar-du/Kconfig b/drivers/gpu/drm/rcar-du/Kconfig
index d4e0a39568f6..96dcd4a78951 100644
--- a/drivers/gpu/drm/rcar-du/Kconfig
+++ b/drivers/gpu/drm/rcar-du/Kconfig
@@ -1,6 +1,6 @@
 config DRM_RCAR_DU
 	tristate "DRM Support for R-Car Display Unit"
-	depends on DRM && ARM && HAVE_DMA_ATTRS && OF
+	depends on DRM && ARM && OF
 	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
diff --git a/drivers/gpu/drm/shmobile/Kconfig b/drivers/gpu/drm/shmobile/Kconfig
index b9202aa6f8ab..8d17d00ddb4b 100644
--- a/drivers/gpu/drm/shmobile/Kconfig
+++ b/drivers/gpu/drm/shmobile/Kconfig
@@ -1,6 +1,6 @@
 config DRM_SHMOBILE
 	tristate "DRM Support for SH Mobile"
-	depends on DRM && ARM && HAVE_DMA_ATTRS
+	depends on DRM && ARM
 	depends on ARCH_SHMOBILE || COMPILE_TEST
 	depends on FB_SH_MOBILE_MERAM || !FB_SH_MOBILE_MERAM
 	select BACKLIGHT_CLASS_DEVICE
diff --git a/drivers/gpu/drm/sti/Kconfig b/drivers/gpu/drm/sti/Kconfig
index 10c1b1926e6f..5ad43a1bb260 100644
--- a/drivers/gpu/drm/sti/Kconfig
+++ b/drivers/gpu/drm/sti/Kconfig
@@ -1,6 +1,6 @@
 config DRM_STI
 	tristate "DRM Support for STMicroelectronics SoC stiH41x Series"
-	depends on DRM && (SOC_STIH415 || SOC_STIH416 || ARCH_MULTIPLATFORM) && HAVE_DMA_ATTRS
+	depends on DRM && (SOC_STIH415 || SOC_STIH416 || ARCH_MULTIPLATFORM)
 	select RESET_CONTROLLER
 	select DRM_KMS_HELPER
 	select DRM_GEM_CMA_HELPER
diff --git a/drivers/gpu/drm/tilcdc/Kconfig b/drivers/gpu/drm/tilcdc/Kconfig
index 78beafb0742c..f60a1ec84fa4 100644
--- a/drivers/gpu/drm/tilcdc/Kconfig
+++ b/drivers/gpu/drm/tilcdc/Kconfig
@@ -1,6 +1,6 @@
 config DRM_TILCDC
 	tristate "DRM Support for TI LCDC Display Controller"
-	depends on DRM && OF && ARM && HAVE_DMA_ATTRS
+	depends on DRM && OF && ARM
 	select DRM_KMS_HELPER
 	select DRM_KMS_FB_HELPER
 	select DRM_KMS_CMA_HELPER
diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig
index 2d7d115ddf3f..584810474e5b 100644
--- a/drivers/gpu/drm/vc4/Kconfig
+++ b/drivers/gpu/drm/vc4/Kconfig
@@ -1,7 +1,7 @@
 config DRM_VC4
 	tristate "Broadcom VC4 Graphics"
 	depends on ARCH_BCM2835 || COMPILE_TEST
-	depends on DRM && HAVE_DMA_ATTRS
+	depends on DRM
 	select DRM_KMS_HELPER
 	select DRM_KMS_CMA_HELPER
 	select DRM_GEM_CMA_HELPER
diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig
index 6b8c77c97d40..ac8715e56ba1 100644
--- a/drivers/iio/Kconfig
+++ b/drivers/iio/Kconfig
@@ -22,6 +22,14 @@ if IIO_BUFFER
 	source "drivers/iio/buffer/Kconfig"
 endif # IIO_BUFFER
 
+config IIO_CONFIGFS
+	tristate "Enable IIO configuration via configfs"
+	select CONFIGFS_FS
+	help
+	  This allows configuring various IIO bits through configfs
+	  (e.g. software triggers). For more info see
+	  Documentation/iio/iio_configfs.txt.
+
 config IIO_TRIGGER
 	bool "Enable triggered sampling support"
 	help
@@ -38,6 +46,14 @@ config IIO_CONSUMERS_PER_TRIGGER
 	This value controls the maximum number of consumers that a
 	given trigger may handle. Default is 2.
 
+config IIO_SW_TRIGGER
+	tristate "Enable software triggers support"
+	select IIO_CONFIGFS
+	help
+	 Provides IIO core support for software triggers. A software
+	 trigger can be created via configfs or directly by a driver
+	 using the API provided.
+
 config IIO_TRIGGERED_EVENT
 	tristate
 	select IIO_TRIGGER
diff --git a/drivers/iio/Makefile b/drivers/iio/Makefile
index 6769f2f43e86..f670b82298aa 100644
--- a/drivers/iio/Makefile
+++ b/drivers/iio/Makefile
@@ -7,6 +7,8 @@ industrialio-y := industrialio-core.o industrialio-event.o inkern.o
 industrialio-$(CONFIG_IIO_BUFFER) += industrialio-buffer.o
 industrialio-$(CONFIG_IIO_TRIGGER) += industrialio-trigger.o
 
+obj-$(CONFIG_IIO_CONFIGFS) += industrialio-configfs.o
+obj-$(CONFIG_IIO_SW_TRIGGER) += industrialio-sw-trigger.o
 obj-$(CONFIG_IIO_TRIGGERED_EVENT) += industrialio-triggered-event.o
 
 obj-y += accel/
diff --git a/drivers/iio/industrialio-configfs.c b/drivers/iio/industrialio-configfs.c
new file mode 100644
index 000000000000..83563dd7fcf4
--- /dev/null
+++ b/drivers/iio/industrialio-configfs.c
@@ -0,0 +1,50 @@
+/*
+ * Industrial I/O configfs bits
+ *
+ * Copyright (c) 2015 Intel Corporation
+ *
+ * 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/configfs.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kmod.h>
+#include <linux/slab.h>
+
+#include <linux/iio/iio.h>
+
+static struct config_item_type iio_root_group_type = {
+	.ct_owner       = THIS_MODULE,
+};
+
+struct configfs_subsystem iio_configfs_subsys = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "iio",
+			.ci_type = &iio_root_group_type,
+		},
+	},
+	.su_mutex = __MUTEX_INITIALIZER(iio_configfs_subsys.su_mutex),
+};
+EXPORT_SYMBOL(iio_configfs_subsys);
+
+static int __init iio_configfs_init(void)
+{
+	config_group_init(&iio_configfs_subsys.su_group);
+
+	return configfs_register_subsystem(&iio_configfs_subsys);
+}
+module_init(iio_configfs_init);
+
+static void __exit iio_configfs_exit(void)
+{
+	configfs_unregister_subsystem(&iio_configfs_subsys);
+}
+module_exit(iio_configfs_exit);
+
+MODULE_AUTHOR("Daniel Baluta <daniel.baluta@intel.com>");
+MODULE_DESCRIPTION("Industrial I/O configfs support");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/industrialio-sw-trigger.c b/drivers/iio/industrialio-sw-trigger.c
new file mode 100644
index 000000000000..22262f68db6e
--- /dev/null
+++ b/drivers/iio/industrialio-sw-trigger.c
@@ -0,0 +1,181 @@
+/*
+ * The Industrial I/O core, software trigger functions
+ *
+ * Copyright (c) 2015 Intel Corporation
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/kmod.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+#include <linux/iio/sw_trigger.h>
+#include <linux/configfs.h>
+
+static struct config_group *iio_triggers_group;
+static struct config_item_type iio_trigger_type_group_type;
+
+static struct config_item_type iio_triggers_group_type = {
+	.ct_owner = THIS_MODULE,
+};
+
+static LIST_HEAD(iio_trigger_types_list);
+static DEFINE_MUTEX(iio_trigger_types_lock);
+
+static
+struct iio_sw_trigger_type *__iio_find_sw_trigger_type(const char *name,
+						       unsigned len)
+{
+	struct iio_sw_trigger_type *t = NULL, *iter;
+
+	list_for_each_entry(iter, &iio_trigger_types_list, list)
+		if (!strcmp(iter->name, name)) {
+			t = iter;
+			break;
+		}
+
+	return t;
+}
+
+int iio_register_sw_trigger_type(struct iio_sw_trigger_type *t)
+{
+	struct iio_sw_trigger_type *iter;
+	int ret = 0;
+
+	mutex_lock(&iio_trigger_types_lock);
+	iter = __iio_find_sw_trigger_type(t->name, strlen(t->name));
+	if (iter)
+		ret = -EBUSY;
+	else
+		list_add_tail(&t->list, &iio_trigger_types_list);
+	mutex_unlock(&iio_trigger_types_lock);
+
+	if (ret)
+		return ret;
+
+	t->group = configfs_register_default_group(iio_triggers_group, t->name,
+						&iio_trigger_type_group_type);
+	if (IS_ERR(t->group))
+		ret = PTR_ERR(t->group);
+
+	return ret;
+}
+EXPORT_SYMBOL(iio_register_sw_trigger_type);
+
+void iio_unregister_sw_trigger_type(struct iio_sw_trigger_type *t)
+{
+	struct iio_sw_trigger_type *iter;
+
+	mutex_lock(&iio_trigger_types_lock);
+	iter = __iio_find_sw_trigger_type(t->name, strlen(t->name));
+	if (iter)
+		list_del(&t->list);
+	mutex_unlock(&iio_trigger_types_lock);
+
+	configfs_unregister_default_group(t->group);
+}
+EXPORT_SYMBOL(iio_unregister_sw_trigger_type);
+
+static
+struct iio_sw_trigger_type *iio_get_sw_trigger_type(const char *name)
+{
+	struct iio_sw_trigger_type *t;
+
+	mutex_lock(&iio_trigger_types_lock);
+	t = __iio_find_sw_trigger_type(name, strlen(name));
+	if (t && !try_module_get(t->owner))
+		t = NULL;
+	mutex_unlock(&iio_trigger_types_lock);
+
+	return t;
+}
+
+struct iio_sw_trigger *iio_sw_trigger_create(const char *type, const char *name)
+{
+	struct iio_sw_trigger *t;
+	struct iio_sw_trigger_type *tt;
+
+	tt = iio_get_sw_trigger_type(type);
+	if (!tt) {
+		pr_err("Invalid trigger type: %s\n", type);
+		return ERR_PTR(-EINVAL);
+	}
+	t = tt->ops->probe(name);
+	if (IS_ERR(t))
+		goto out_module_put;
+
+	t->trigger_type = tt;
+
+	return t;
+out_module_put:
+	module_put(tt->owner);
+	return t;
+}
+EXPORT_SYMBOL(iio_sw_trigger_create);
+
+void iio_sw_trigger_destroy(struct iio_sw_trigger *t)
+{
+	struct iio_sw_trigger_type *tt = t->trigger_type;
+
+	tt->ops->remove(t);
+	module_put(tt->owner);
+}
+EXPORT_SYMBOL(iio_sw_trigger_destroy);
+
+static struct config_group *trigger_make_group(struct config_group *group,
+					       const char *name)
+{
+	struct iio_sw_trigger *t;
+
+	t = iio_sw_trigger_create(group->cg_item.ci_name, name);
+	if (IS_ERR(t))
+		return ERR_CAST(t);
+
+	config_item_set_name(&t->group.cg_item, "%s", name);
+
+	return &t->group;
+}
+
+static void trigger_drop_group(struct config_group *group,
+			       struct config_item *item)
+{
+	struct iio_sw_trigger *t = to_iio_sw_trigger(item);
+
+	iio_sw_trigger_destroy(t);
+	config_item_put(item);
+}
+
+static struct configfs_group_operations trigger_ops = {
+	.make_group	= &trigger_make_group,
+	.drop_item	= &trigger_drop_group,
+};
+
+static struct config_item_type iio_trigger_type_group_type = {
+	.ct_group_ops = &trigger_ops,
+	.ct_owner       = THIS_MODULE,
+};
+
+static int __init iio_sw_trigger_init(void)
+{
+	iio_triggers_group =
+		configfs_register_default_group(&iio_configfs_subsys.su_group,
+						"triggers",
+						&iio_triggers_group_type);
+	return PTR_ERR_OR_ZERO(iio_triggers_group);
+}
+module_init(iio_sw_trigger_init);
+
+static void __exit iio_sw_trigger_exit(void)
+{
+	configfs_unregister_default_group(iio_triggers_group);
+}
+module_exit(iio_sw_trigger_exit);
+
+MODULE_AUTHOR("Daniel Baluta <daniel.baluta@intel.com>");
+MODULE_DESCRIPTION("Industrial I/O software triggers support");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/trigger/Kconfig b/drivers/iio/trigger/Kconfig
index 79996123a71b..519e6772f6f5 100644
--- a/drivers/iio/trigger/Kconfig
+++ b/drivers/iio/trigger/Kconfig
@@ -5,6 +5,16 @@
 
 menu "Triggers - standalone"
 
+config IIO_HRTIMER_TRIGGER
+	tristate "High resolution timer trigger"
+	depends on IIO_SW_TRIGGER
+	help
+	  Provides a frequency based IIO trigger using high resolution
+	  timers as interrupt source.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called iio-trig-hrtimer.
+
 config IIO_INTERRUPT_TRIGGER
 	tristate "Generic interrupt trigger"
 	help
diff --git a/drivers/iio/trigger/Makefile b/drivers/iio/trigger/Makefile
index 0694daecaf22..fe06eb564367 100644
--- a/drivers/iio/trigger/Makefile
+++ b/drivers/iio/trigger/Makefile
@@ -3,5 +3,7 @@
 #
 
 # When adding new entries keep the list in alphabetical order
+
+obj-$(CONFIG_IIO_HRTIMER_TRIGGER) += iio-trig-hrtimer.o
 obj-$(CONFIG_IIO_INTERRUPT_TRIGGER) += iio-trig-interrupt.o
 obj-$(CONFIG_IIO_SYSFS_TRIGGER) += iio-trig-sysfs.o
diff --git a/drivers/iio/trigger/iio-trig-hrtimer.c b/drivers/iio/trigger/iio-trig-hrtimer.c
new file mode 100644
index 000000000000..5e6d451febeb
--- /dev/null
+++ b/drivers/iio/trigger/iio-trig-hrtimer.c
@@ -0,0 +1,193 @@
+/**
+ * The industrial I/O periodic hrtimer trigger driver
+ *
+ * Copyright (C) Intuitive Aerial AB
+ * Written by Marten Svanfeldt, marten@intuitiveaerial.com
+ * Copyright (C) 2012, Analog Device Inc.
+ *	Author: Lars-Peter Clausen <lars@metafoo.de>
+ * Copyright (C) 2015, Intel Corporation
+ *
+ * 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/kernel.h>
+#include <linux/slab.h>
+#include <linux/hrtimer.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/sw_trigger.h>
+
+/* default sampling frequency - 100Hz */
+#define HRTIMER_DEFAULT_SAMPLING_FREQUENCY 100
+
+struct iio_hrtimer_info {
+	struct iio_sw_trigger swt;
+	struct hrtimer timer;
+	unsigned long sampling_frequency;
+	ktime_t period;
+};
+
+static struct config_item_type iio_hrtimer_type = {
+	.ct_owner = THIS_MODULE,
+};
+
+static
+ssize_t iio_hrtimer_show_sampling_frequency(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct iio_trigger *trig = to_iio_trigger(dev);
+	struct iio_hrtimer_info *info = iio_trigger_get_drvdata(trig);
+
+	return snprintf(buf, PAGE_SIZE, "%lu\n", info->sampling_frequency);
+}
+
+static
+ssize_t iio_hrtimer_store_sampling_frequency(struct device *dev,
+					     struct device_attribute *attr,
+					     const char *buf, size_t len)
+{
+	struct iio_trigger *trig = to_iio_trigger(dev);
+	struct iio_hrtimer_info *info = iio_trigger_get_drvdata(trig);
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	if (!val || val > NSEC_PER_SEC)
+		return -EINVAL;
+
+	info->sampling_frequency = val;
+	info->period = ktime_set(0, NSEC_PER_SEC / val);
+
+	return len;
+}
+
+static DEVICE_ATTR(sampling_frequency, S_IRUGO | S_IWUSR,
+		   iio_hrtimer_show_sampling_frequency,
+		   iio_hrtimer_store_sampling_frequency);
+
+static struct attribute *iio_hrtimer_attrs[] = {
+	&dev_attr_sampling_frequency.attr,
+	NULL
+};
+
+static const struct attribute_group iio_hrtimer_attr_group = {
+	.attrs = iio_hrtimer_attrs,
+};
+
+static const struct attribute_group *iio_hrtimer_attr_groups[] = {
+	&iio_hrtimer_attr_group,
+	NULL
+};
+
+static enum hrtimer_restart iio_hrtimer_trig_handler(struct hrtimer *timer)
+{
+	struct iio_hrtimer_info *info;
+
+	info = container_of(timer, struct iio_hrtimer_info, timer);
+
+	hrtimer_forward_now(timer, info->period);
+	iio_trigger_poll(info->swt.trigger);
+
+	return HRTIMER_RESTART;
+}
+
+static int iio_trig_hrtimer_set_state(struct iio_trigger *trig, bool state)
+{
+	struct iio_hrtimer_info *trig_info;
+
+	trig_info = iio_trigger_get_drvdata(trig);
+
+	if (state)
+		hrtimer_start(&trig_info->timer, trig_info->period,
+			      HRTIMER_MODE_REL);
+	else
+		hrtimer_cancel(&trig_info->timer);
+
+	return 0;
+}
+
+static const struct iio_trigger_ops iio_hrtimer_trigger_ops = {
+	.owner = THIS_MODULE,
+	.set_trigger_state = iio_trig_hrtimer_set_state,
+};
+
+static struct iio_sw_trigger *iio_trig_hrtimer_probe(const char *name)
+{
+	struct iio_hrtimer_info *trig_info;
+	int ret;
+
+	trig_info = kzalloc(sizeof(*trig_info), GFP_KERNEL);
+	if (!trig_info)
+		return ERR_PTR(-ENOMEM);
+
+	trig_info->swt.trigger = iio_trigger_alloc("%s", name);
+	if (!trig_info->swt.trigger) {
+		ret = -ENOMEM;
+		goto err_free_trig_info;
+	}
+
+	iio_trigger_set_drvdata(trig_info->swt.trigger, trig_info);
+	trig_info->swt.trigger->ops = &iio_hrtimer_trigger_ops;
+	trig_info->swt.trigger->dev.groups = iio_hrtimer_attr_groups;
+
+	hrtimer_init(&trig_info->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	trig_info->timer.function = iio_hrtimer_trig_handler;
+
+	trig_info->sampling_frequency = HRTIMER_DEFAULT_SAMPLING_FREQUENCY;
+	trig_info->period = ktime_set(0, NSEC_PER_SEC /
+				      trig_info->sampling_frequency);
+
+	ret = iio_trigger_register(trig_info->swt.trigger);
+	if (ret)
+		goto err_free_trigger;
+
+	iio_swt_group_init_type_name(&trig_info->swt, name, &iio_hrtimer_type);
+	return &trig_info->swt;
+err_free_trigger:
+	iio_trigger_free(trig_info->swt.trigger);
+err_free_trig_info:
+	kfree(trig_info);
+
+	return ERR_PTR(ret);
+}
+
+static int iio_trig_hrtimer_remove(struct iio_sw_trigger *swt)
+{
+	struct iio_hrtimer_info *trig_info;
+
+	trig_info = iio_trigger_get_drvdata(swt->trigger);
+
+	iio_trigger_unregister(swt->trigger);
+
+	/* cancel the timer after unreg to make sure no one rearms it */
+	hrtimer_cancel(&trig_info->timer);
+	iio_trigger_free(swt->trigger);
+	kfree(trig_info);
+
+	return 0;
+}
+
+static const struct iio_sw_trigger_ops iio_trig_hrtimer_ops = {
+	.probe		= iio_trig_hrtimer_probe,
+	.remove		= iio_trig_hrtimer_remove,
+};
+
+static struct iio_sw_trigger_type iio_trig_hrtimer = {
+	.name = "hrtimer",
+	.owner = THIS_MODULE,
+	.ops = &iio_trig_hrtimer_ops,
+};
+
+module_iio_sw_trigger_driver(iio_trig_hrtimer);
+
+MODULE_AUTHOR("Marten Svanfeldt <marten@intuitiveaerial.com>");
+MODULE_AUTHOR("Daniel Baluta <daniel.baluta@intel.com>");
+MODULE_DESCRIPTION("Periodic hrtimer trigger for the IIO subsystem");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 0c53805dff0e..526359447ff9 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -216,7 +216,6 @@ config VIDEO_STI_BDISP
 	tristate "STMicroelectronics BDISP 2D blitter driver"
 	depends on VIDEO_DEV && VIDEO_V4L2
 	depends on ARCH_STI || COMPILE_TEST
-	depends on HAVE_DMA_ATTRS
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	help
diff --git a/drivers/memstick/core/ms_block.c b/drivers/memstick/core/ms_block.c
index 24f2f8473dee..84abf9d3c24e 100644
--- a/drivers/memstick/core/ms_block.c
+++ b/drivers/memstick/core/ms_block.c
@@ -1909,7 +1909,7 @@ static void msb_io_work(struct work_struct *work)
 		lba = blk_rq_pos(msb->req);
 
 		sector_div(lba, msb->page_size / 512);
-		page = do_div(lba, msb->pages_in_block);
+		page = sector_div(lba, msb->pages_in_block);
 
 		if (rq_data_dir(msb->req) == READ)
 			error = msb_do_read_request(msb, lba, page, sg,
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index 8e11fb2831cd..a153bc929173 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -786,18 +786,27 @@ ccio_map_single(struct device *dev, void *addr, size_t size,
 	return CCIO_IOVA(iovp, offset);
 }
 
+
+static dma_addr_t 
+ccio_map_page(struct device *dev, struct page *page, unsigned long offset,
+		size_t size, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	return ccio_map_single(dev, page_address(page) + offset, size,
+			direction);
+}
+
+
 /**
- * ccio_unmap_single - Unmap an address range from the IOMMU.
+ * ccio_unmap_page - Unmap an address range from the IOMMU.
  * @dev: The PCI device.
  * @addr: The start address of the DMA region.
  * @size: The length of the DMA region.
  * @direction: The direction of the DMA transaction (to/from device).
- *
- * This function implements the pci_unmap_single function.
  */
 static void 
-ccio_unmap_single(struct device *dev, dma_addr_t iova, size_t size, 
-		  enum dma_data_direction direction)
+ccio_unmap_page(struct device *dev, dma_addr_t iova, size_t size, 
+		enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 	unsigned long flags; 
@@ -826,7 +835,7 @@ ccio_unmap_single(struct device *dev, dma_addr_t iova, size_t size,
 }
 
 /**
- * ccio_alloc_consistent - Allocate a consistent DMA mapping.
+ * ccio_alloc - Allocate a consistent DMA mapping.
  * @dev: The PCI device.
  * @size: The length of the DMA region.
  * @dma_handle: The DMA address handed back to the device (not the cpu).
@@ -834,7 +843,8 @@ ccio_unmap_single(struct device *dev, dma_addr_t iova, size_t size,
  * This function implements the pci_alloc_consistent function.
  */
 static void * 
-ccio_alloc_consistent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag)
+ccio_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag,
+		struct dma_attrs *attrs)
 {
       void *ret;
 #if 0
@@ -858,7 +868,7 @@ ccio_alloc_consistent(struct device *dev, size_t size, dma_addr_t *dma_handle, g
 }
 
 /**
- * ccio_free_consistent - Free a consistent DMA mapping.
+ * ccio_free - Free a consistent DMA mapping.
  * @dev: The PCI device.
  * @size: The length of the DMA region.
  * @cpu_addr: The cpu address returned from the ccio_alloc_consistent.
@@ -867,10 +877,10 @@ ccio_alloc_consistent(struct device *dev, size_t size, dma_addr_t *dma_handle, g
  * This function implements the pci_free_consistent function.
  */
 static void 
-ccio_free_consistent(struct device *dev, size_t size, void *cpu_addr, 
-		     dma_addr_t dma_handle)
+ccio_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
-	ccio_unmap_single(dev, dma_handle, size, 0);
+	ccio_unmap_page(dev, dma_handle, size, 0, NULL);
 	free_pages((unsigned long)cpu_addr, get_order(size));
 }
 
@@ -897,7 +907,7 @@ ccio_free_consistent(struct device *dev, size_t size, void *cpu_addr,
  */
 static int
 ccio_map_sg(struct device *dev, struct scatterlist *sglist, int nents, 
-	    enum dma_data_direction direction)
+	    enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 	int coalesced, filled = 0;
@@ -974,7 +984,7 @@ ccio_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
  */
 static void 
 ccio_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, 
-	      enum dma_data_direction direction)
+	      enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 
@@ -993,27 +1003,22 @@ ccio_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
 #ifdef CCIO_COLLECT_STATS
 		ioc->usg_pages += sg_dma_len(sglist) >> PAGE_SHIFT;
 #endif
-		ccio_unmap_single(dev, sg_dma_address(sglist),
-				  sg_dma_len(sglist), direction);
+		ccio_unmap_page(dev, sg_dma_address(sglist),
+				  sg_dma_len(sglist), direction, NULL);
 		++sglist;
 	}
 
 	DBG_RUN_SG("%s() DONE (nents %d)\n", __func__, nents);
 }
 
-static struct hppa_dma_ops ccio_ops = {
+static struct dma_map_ops ccio_ops = {
 	.dma_supported =	ccio_dma_supported,
-	.alloc_consistent =	ccio_alloc_consistent,
-	.alloc_noncoherent =	ccio_alloc_consistent,
-	.free_consistent =	ccio_free_consistent,
-	.map_single =		ccio_map_single,
-	.unmap_single =		ccio_unmap_single,
+	.alloc =		ccio_alloc,
+	.free =			ccio_free,
+	.map_page =		ccio_map_page,
+	.unmap_page =		ccio_unmap_page,
 	.map_sg = 		ccio_map_sg,
 	.unmap_sg = 		ccio_unmap_sg,
-	.dma_sync_single_for_cpu =	NULL,	/* NOP for U2/Uturn */
-	.dma_sync_single_for_device =	NULL,	/* NOP for U2/Uturn */
-	.dma_sync_sg_for_cpu =		NULL,	/* ditto */
-	.dma_sync_sg_for_device =		NULL,	/* ditto */
 };
 
 #ifdef CONFIG_PROC_FS
@@ -1062,7 +1067,7 @@ static int ccio_proc_info(struct seq_file *m, void *p)
 			   ioc->msingle_calls, ioc->msingle_pages,
 			   (int)((ioc->msingle_pages * 1000)/ioc->msingle_calls));
 
-		/* KLUGE - unmap_sg calls unmap_single for each mapped page */
+		/* KLUGE - unmap_sg calls unmap_page for each mapped page */
 		min = ioc->usingle_calls - ioc->usg_calls;
 		max = ioc->usingle_pages - ioc->usg_pages;
 		seq_printf(m, "pci_unmap_single: %8ld calls  %8ld pages (avg %d/1000)\n",
diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c
index 225049b492e5..24ec9b8ea4b3 100644
--- a/drivers/parisc/sba_iommu.c
+++ b/drivers/parisc/sba_iommu.c
@@ -780,8 +780,18 @@ sba_map_single(struct device *dev, void *addr, size_t size,
 }
 
 
+static dma_addr_t 
+sba_map_page(struct device *dev, struct page *page, unsigned long offset,
+		size_t size, enum dma_data_direction direction,
+		struct dma_attrs *attrs)
+{
+	return sba_map_single(dev, page_address(page) + offset, size,
+			direction);
+}
+
+
 /**
- * sba_unmap_single - unmap one IOVA and free resources
+ * sba_unmap_page - unmap one IOVA and free resources
  * @dev: instance of PCI owned by the driver that's asking.
  * @iova:  IOVA of driver buffer previously mapped.
  * @size:  number of bytes mapped in driver buffer.
@@ -790,8 +800,8 @@ sba_map_single(struct device *dev, void *addr, size_t size,
  * See Documentation/DMA-API-HOWTO.txt
  */
 static void
-sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size,
-		 enum dma_data_direction direction)
+sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
+		enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 #if DELAYED_RESOURCE_CNT > 0
@@ -858,15 +868,15 @@ sba_unmap_single(struct device *dev, dma_addr_t iova, size_t size,
 
 
 /**
- * sba_alloc_consistent - allocate/map shared mem for DMA
+ * sba_alloc - allocate/map shared mem for DMA
  * @hwdev: instance of PCI owned by the driver that's asking.
  * @size:  number of bytes mapped in driver buffer.
  * @dma_handle:  IOVA of new buffer.
  *
  * See Documentation/DMA-API-HOWTO.txt
  */
-static void *sba_alloc_consistent(struct device *hwdev, size_t size,
-					dma_addr_t *dma_handle, gfp_t gfp)
+static void *sba_alloc(struct device *hwdev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, struct dma_attrs *attrs)
 {
 	void *ret;
 
@@ -888,7 +898,7 @@ static void *sba_alloc_consistent(struct device *hwdev, size_t size,
 
 
 /**
- * sba_free_consistent - free/unmap shared mem for DMA
+ * sba_free - free/unmap shared mem for DMA
  * @hwdev: instance of PCI owned by the driver that's asking.
  * @size:  number of bytes mapped in driver buffer.
  * @vaddr:  virtual address IOVA of "consistent" buffer.
@@ -897,10 +907,10 @@ static void *sba_alloc_consistent(struct device *hwdev, size_t size,
  * See Documentation/DMA-API-HOWTO.txt
  */
 static void
-sba_free_consistent(struct device *hwdev, size_t size, void *vaddr,
-		    dma_addr_t dma_handle)
+sba_free(struct device *hwdev, size_t size, void *vaddr,
+		    dma_addr_t dma_handle, struct dma_attrs *attrs)
 {
-	sba_unmap_single(hwdev, dma_handle, size, 0);
+	sba_unmap_page(hwdev, dma_handle, size, 0, NULL);
 	free_pages((unsigned long) vaddr, get_order(size));
 }
 
@@ -933,7 +943,7 @@ int dump_run_sg = 0;
  */
 static int
 sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	   enum dma_data_direction direction)
+	   enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 	int coalesced, filled = 0;
@@ -1016,7 +1026,7 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
  */
 static void 
 sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
-	     enum dma_data_direction direction)
+	     enum dma_data_direction direction, struct dma_attrs *attrs)
 {
 	struct ioc *ioc;
 #ifdef ASSERT_PDIR_SANITY
@@ -1040,7 +1050,8 @@ sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
 
 	while (sg_dma_len(sglist) && nents--) {
 
-		sba_unmap_single(dev, sg_dma_address(sglist), sg_dma_len(sglist), direction);
+		sba_unmap_page(dev, sg_dma_address(sglist), sg_dma_len(sglist),
+				direction, NULL);
 #ifdef SBA_COLLECT_STATS
 		ioc->usg_pages += ((sg_dma_address(sglist) & ~IOVP_MASK) + sg_dma_len(sglist) + IOVP_SIZE - 1) >> PAGE_SHIFT;
 		ioc->usingle_calls--;	/* kluge since call is unmap_sg() */
@@ -1058,19 +1069,14 @@ sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents,
 
 }
 
-static struct hppa_dma_ops sba_ops = {
+static struct dma_map_ops sba_ops = {
 	.dma_supported =	sba_dma_supported,
-	.alloc_consistent =	sba_alloc_consistent,
-	.alloc_noncoherent =	sba_alloc_consistent,
-	.free_consistent =	sba_free_consistent,
-	.map_single =		sba_map_single,
-	.unmap_single =		sba_unmap_single,
+	.alloc =		sba_alloc,
+	.free =			sba_free,
+	.map_page =		sba_map_page,
+	.unmap_page =		sba_unmap_page,
 	.map_sg =		sba_map_sg,
 	.unmap_sg =		sba_unmap_sg,
-	.dma_sync_single_for_cpu =	NULL,
-	.dma_sync_single_for_device =	NULL,
-	.dma_sync_sg_for_cpu =		NULL,
-	.dma_sync_sg_for_device =	NULL,
 };
 
 
diff --git a/fs/adfs/adfs.h b/fs/adfs/adfs.h
index ea4aba56f29d..fadf408bdd46 100644
--- a/fs/adfs/adfs.h
+++ b/fs/adfs/adfs.h
@@ -44,24 +44,24 @@ struct adfs_dir_ops;
  */
 struct adfs_sb_info {
 	union { struct {
-		struct adfs_discmap *s_map;	/* bh list containing map	 */
-		const struct adfs_dir_ops *s_dir; /* directory operations	 */
+		struct adfs_discmap *s_map;	/* bh list containing map */
+		const struct adfs_dir_ops *s_dir; /* directory operations */
 		};
-		struct rcu_head rcu;		/* used only at shutdown time	 */
+		struct rcu_head rcu;	/* used only at shutdown time	 */
 	};
-	kuid_t		s_uid;		/* owner uid				 */
-	kgid_t		s_gid;		/* owner gid				 */
-	umode_t		s_owner_mask;	/* ADFS owner perm -> unix perm		 */
-	umode_t		s_other_mask;	/* ADFS other perm -> unix perm		 */
+	kuid_t		s_uid;		/* owner uid */
+	kgid_t		s_gid;		/* owner gid */
+	umode_t		s_owner_mask;	/* ADFS owner perm -> unix perm */
+	umode_t		s_other_mask;	/* ADFS other perm -> unix perm	*/
 	int		s_ftsuffix;	/* ,xyz hex filetype suffix option */
 
-	__u32		s_ids_per_zone;	/* max. no ids in one zone		 */
-	__u32		s_idlen;	/* length of ID in map			 */
-	__u32		s_map_size;	/* sector size of a map			 */
-	unsigned long	s_size;		/* total size (in blocks) of this fs	 */
-	signed int	s_map2blk;	/* shift left by this for map->sector	 */
-	unsigned int	s_log2sharesize;/* log2 share size			 */
-	__le32		s_version;	/* disc format version			 */
+	__u32		s_ids_per_zone;	/* max. no ids in one zone */
+	__u32		s_idlen;	/* length of ID in map */
+	__u32		s_map_size;	/* sector size of a map	*/
+	unsigned long	s_size;		/* total size (in blocks) of this fs */
+	signed int	s_map2blk;	/* shift left by this for map->sector*/
+	unsigned int	s_log2sharesize;/* log2 share size */
+	__le32		s_version;	/* disc format version */
 	unsigned int	s_namelen;	/* maximum number of characters in name	 */
 };
 
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index a4cbdf9824c7..d250604f985a 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/parser.h>
 #include <linux/module.h>
+#include <linux/pagemap.h>
 #include <linux/sched.h>
 #include <linux/statfs.h>
 #include <linux/seq_file.h>
diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h
deleted file mode 100644
index 0297e5875798..000000000000
--- a/include/asm-generic/dma-coherent.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef DMA_COHERENT_H
-#define DMA_COHERENT_H
-
-#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
-/*
- * These three functions are only for dma allocator.
- * Don't use them in device drivers.
- */
-int dma_alloc_from_coherent(struct device *dev, ssize_t size,
-				       dma_addr_t *dma_handle, void **ret);
-int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
-
-int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
-			    void *cpu_addr, size_t size, int *ret);
-/*
- * Standard interface
- */
-#define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
-int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
-				dma_addr_t device_addr, size_t size, int flags);
-
-void dma_release_declared_memory(struct device *dev);
-
-void *dma_mark_declared_memory_occupied(struct device *dev,
-					dma_addr_t device_addr, size_t size);
-#else
-#define dma_alloc_from_coherent(dev, size, handle, ret) (0)
-#define dma_release_from_coherent(dev, order, vaddr) (0)
-#define dma_mmap_from_coherent(dev, vma, vaddr, order, ret) (0)
-#endif
-
-#endif
diff --git a/include/asm-generic/dma-mapping-broken.h b/include/asm-generic/dma-mapping-broken.h
deleted file mode 100644
index 6c32af918c2f..000000000000
--- a/include/asm-generic/dma-mapping-broken.h
+++ /dev/null
@@ -1,95 +0,0 @@
-#ifndef _ASM_GENERIC_DMA_MAPPING_H
-#define _ASM_GENERIC_DMA_MAPPING_H
-
-/* define the dma api to allow compilation but not linking of
- * dma dependent code.  Code that depends on the dma-mapping
- * API needs to set 'depends on HAS_DMA' in its Kconfig
- */
-
-struct scatterlist;
-
-extern void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		   gfp_t flag);
-
-extern void
-dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-		    dma_addr_t dma_handle);
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t flag,
-				    struct dma_attrs *attrs)
-{
-	/* attrs is not supported and ignored */
-	return dma_alloc_coherent(dev, size, dma_handle, flag);
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				  void *cpu_addr, dma_addr_t dma_handle,
-				  struct dma_attrs *attrs)
-{
-	/* attrs is not supported and ignored */
-	dma_free_coherent(dev, size, cpu_addr, dma_handle);
-}
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-
-extern dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction direction);
-
-extern void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction);
-
-extern int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	   enum dma_data_direction direction);
-
-extern void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction);
-
-extern dma_addr_t
-dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-	     size_t size, enum dma_data_direction direction);
-
-extern void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction);
-
-extern void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-			enum dma_data_direction direction);
-
-extern void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction direction);
-
-extern void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
-		    enum dma_data_direction direction);
-
-#define dma_sync_single_for_device dma_sync_single_for_cpu
-#define dma_sync_single_range_for_device dma_sync_single_range_for_cpu
-#define dma_sync_sg_for_device dma_sync_sg_for_cpu
-
-extern int
-dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
-
-extern int
-dma_supported(struct device *dev, u64 mask);
-
-extern int
-dma_set_mask(struct device *dev, u64 mask);
-
-extern int
-dma_get_cache_alignment(void);
-
-extern void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction);
-
-#endif /* _ASM_GENERIC_DMA_MAPPING_H */
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
deleted file mode 100644
index b1bc954eccf3..000000000000
--- a/include/asm-generic/dma-mapping-common.h
+++ /dev/null
@@ -1,358 +0,0 @@
-#ifndef _ASM_GENERIC_DMA_MAPPING_H
-#define _ASM_GENERIC_DMA_MAPPING_H
-
-#include <linux/kmemcheck.h>
-#include <linux/bug.h>
-#include <linux/scatterlist.h>
-#include <linux/dma-debug.h>
-#include <linux/dma-attrs.h>
-#include <asm-generic/dma-coherent.h>
-
-static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
-					      size_t size,
-					      enum dma_data_direction dir,
-					      struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	kmemcheck_mark_initialized(ptr, size);
-	BUG_ON(!valid_dma_direction(dir));
-	addr = ops->map_page(dev, virt_to_page(ptr),
-			     (unsigned long)ptr & ~PAGE_MASK, size,
-			     dir, attrs);
-	debug_dma_map_page(dev, virt_to_page(ptr),
-			   (unsigned long)ptr & ~PAGE_MASK, size,
-			   dir, addr, true);
-	return addr;
-}
-
-static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr,
-					  size_t size,
-					  enum dma_data_direction dir,
-					  struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, attrs);
-	debug_dma_unmap_page(dev, addr, size, dir, true);
-}
-
-/*
- * dma_maps_sg_attrs returns 0 on error and > 0 on success.
- * It should never return a value < 0.
- */
-static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
-				   int nents, enum dma_data_direction dir,
-				   struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	int i, ents;
-	struct scatterlist *s;
-
-	for_each_sg(sg, s, nents, i)
-		kmemcheck_mark_initialized(sg_virt(s), s->length);
-	BUG_ON(!valid_dma_direction(dir));
-	ents = ops->map_sg(dev, sg, nents, dir, attrs);
-	BUG_ON(ents < 0);
-	debug_dma_map_sg(dev, sg, nents, ents, dir);
-
-	return ents;
-}
-
-static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
-				      int nents, enum dma_data_direction dir,
-				      struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	debug_dma_unmap_sg(dev, sg, nents, dir);
-	if (ops->unmap_sg)
-		ops->unmap_sg(dev, sg, nents, dir, attrs);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	kmemcheck_mark_initialized(page_address(page) + offset, size);
-	BUG_ON(!valid_dma_direction(dir));
-	addr = ops->map_page(dev, page, offset, size, dir, NULL);
-	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
-
-	return addr;
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
-				  size_t size, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, NULL);
-	debug_dma_unmap_page(dev, addr, size, dir, false);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
-					   size_t size,
-					   enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(dev, addr, size, dir);
-	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_for_device(struct device *dev,
-					      dma_addr_t addr, size_t size,
-					      enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
-		ops->sync_single_for_device(dev, addr, size, dir);
-	debug_dma_sync_single_for_device(dev, addr, size, dir);
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-						 dma_addr_t addr,
-						 unsigned long offset,
-						 size_t size,
-						 enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(dev, addr + offset, size, dir);
-	debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-						    dma_addr_t addr,
-						    unsigned long offset,
-						    size_t size,
-						    enum dma_data_direction dir)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
-		ops->sync_single_for_device(dev, addr + offset, size, dir);
-	debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-		    int nelems, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_cpu)
-		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-		       int nelems, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_device)
-		ops->sync_sg_for_device(dev, sg, nelems, dir);
-	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
-
-}
-
-#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL)
-#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, NULL)
-#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL)
-#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, NULL)
-
-extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
-			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
-
-void *dma_common_contiguous_remap(struct page *page, size_t size,
-			unsigned long vm_flags,
-			pgprot_t prot, const void *caller);
-
-void *dma_common_pages_remap(struct page **pages, size_t size,
-			unsigned long vm_flags, pgprot_t prot,
-			const void *caller);
-void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
-
-/**
- * dma_mmap_attrs - map a coherent DMA allocation into user space
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @vma: vm_area_struct describing requested user mapping
- * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs
- * @handle: device-view address returned from dma_alloc_attrs
- * @size: size of memory originally requested in dma_alloc_attrs
- * @attrs: attributes of mapping properties requested in dma_alloc_attrs
- *
- * Map a coherent DMA buffer previously allocated by dma_alloc_attrs
- * into user space.  The coherent DMA buffer must not be freed by the
- * driver until the user space mapping has been released.
- */
-static inline int
-dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr,
-	       dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	BUG_ON(!ops);
-	if (ops->mmap)
-		return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
-}
-
-#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
-
-int
-dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
-		       void *cpu_addr, dma_addr_t dma_addr, size_t size);
-
-static inline int
-dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
-		      dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	BUG_ON(!ops);
-	if (ops->get_sgtable)
-		return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
-					attrs);
-	return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size);
-}
-
-#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, NULL)
-
-#ifndef arch_dma_alloc_attrs
-#define arch_dma_alloc_attrs(dev, flag)	(true)
-#endif
-
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
-				       struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	void *cpu_addr;
-
-	BUG_ON(!ops);
-
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &cpu_addr))
-		return cpu_addr;
-
-	if (!arch_dma_alloc_attrs(&dev, &flag))
-		return NULL;
-	if (!ops->alloc)
-		return NULL;
-
-	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
-	return cpu_addr;
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle,
-				     struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!ops);
-	WARN_ON(irqs_disabled());
-
-	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
-		return;
-
-	if (!ops->free)
-		return;
-
-	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	ops->free(dev, size, cpu_addr, dma_handle, attrs);
-}
-
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flag)
-{
-	return dma_alloc_attrs(dev, size, dma_handle, flag, NULL);
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle)
-{
-	return dma_free_attrs(dev, size, cpu_addr, dma_handle, NULL);
-}
-
-static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp)
-{
-	DEFINE_DMA_ATTRS(attrs);
-
-	dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs);
-	return dma_alloc_attrs(dev, size, dma_handle, gfp, &attrs);
-}
-
-static inline void dma_free_noncoherent(struct device *dev, size_t size,
-		void *cpu_addr, dma_addr_t dma_handle)
-{
-	DEFINE_DMA_ATTRS(attrs);
-
-	dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs);
-	dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs);
-}
-
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	debug_dma_mapping_error(dev, dma_addr);
-
-	if (get_dma_ops(dev)->mapping_error)
-		return get_dma_ops(dev)->mapping_error(dev, dma_addr);
-
-#ifdef DMA_ERROR_CODE
-	return dma_addr == DMA_ERROR_CODE;
-#else
-	return 0;
-#endif
-}
-
-#ifndef HAVE_ARCH_DMA_SUPPORTED
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (!ops)
-		return 0;
-	if (!ops->dma_supported)
-		return 1;
-	return ops->dma_supported(dev, mask);
-}
-#endif
-
-#ifndef HAVE_ARCH_DMA_SET_MASK
-static inline int dma_set_mask(struct device *dev, u64 mask)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	if (ops->set_dma_mask)
-		return ops->set_dma_mask(dev, mask);
-
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-	*dev->dma_mask = mask;
-	return 0;
-}
-#endif
-
-#endif
diff --git a/include/linux/dma-attrs.h b/include/linux/dma-attrs.h
index c8e1831d7572..99c0be00b47c 100644
--- a/include/linux/dma-attrs.h
+++ b/include/linux/dma-attrs.h
@@ -41,7 +41,6 @@ static inline void init_dma_attrs(struct dma_attrs *attrs)
 	bitmap_zero(attrs->flags, __DMA_ATTRS_LONGS);
 }
 
-#ifdef CONFIG_HAVE_DMA_ATTRS
 /**
  * dma_set_attr - set a specific attribute
  * @attr: attribute to set
@@ -67,14 +66,5 @@ static inline int dma_get_attr(enum dma_attr attr, struct dma_attrs *attrs)
 	BUG_ON(attr >= DMA_ATTR_MAX);
 	return test_bit(attr, attrs->flags);
 }
-#else /* !CONFIG_HAVE_DMA_ATTRS */
-static inline void dma_set_attr(enum dma_attr attr, struct dma_attrs *attrs)
-{
-}
 
-static inline int dma_get_attr(enum dma_attr attr, struct dma_attrs *attrs)
-{
-	return 0;
-}
-#endif /* CONFIG_HAVE_DMA_ATTRS */
 #endif /* _DMA_ATTR_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 440a0fab12df..c0b27ff2c784 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -6,8 +6,11 @@
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/dma-attrs.h>
+#include <linux/dma-debug.h>
 #include <linux/dma-direction.h>
 #include <linux/scatterlist.h>
+#include <linux/kmemcheck.h>
+#include <linux/bug.h>
 
 /*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.
@@ -85,10 +88,383 @@ static inline int is_device_dma_capable(struct device *dev)
 	return dev->dma_mask != NULL && *dev->dma_mask != DMA_MASK_NONE;
 }
 
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
+/*
+ * These three functions are only for dma allocator.
+ * Don't use them in device drivers.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+				       dma_addr_t *dma_handle, void **ret);
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr);
+
+int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma,
+			    void *cpu_addr, size_t size, int *ret);
+#else
+#define dma_alloc_from_coherent(dev, size, handle, ret) (0)
+#define dma_release_from_coherent(dev, order, vaddr) (0)
+#define dma_mmap_from_coherent(dev, vma, vaddr, order, ret) (0)
+#endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */
+
 #ifdef CONFIG_HAS_DMA
 #include <asm/dma-mapping.h>
 #else
-#include <asm-generic/dma-mapping-broken.h>
+/*
+ * Define the dma api to allow compilation but not linking of
+ * dma dependent code.  Code that depends on the dma-mapping
+ * API needs to set 'depends on HAS_DMA' in its Kconfig
+ */
+extern struct dma_map_ops bad_dma_ops;
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	return &bad_dma_ops;
+}
+#endif
+
+static inline dma_addr_t dma_map_single_attrs(struct device *dev, void *ptr,
+					      size_t size,
+					      enum dma_data_direction dir,
+					      struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	kmemcheck_mark_initialized(ptr, size);
+	BUG_ON(!valid_dma_direction(dir));
+	addr = ops->map_page(dev, virt_to_page(ptr),
+			     offset_in_page(ptr), size,
+			     dir, attrs);
+	debug_dma_map_page(dev, virt_to_page(ptr),
+			   offset_in_page(ptr), size,
+			   dir, addr, true);
+	return addr;
+}
+
+static inline void dma_unmap_single_attrs(struct device *dev, dma_addr_t addr,
+					  size_t size,
+					  enum dma_data_direction dir,
+					  struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->unmap_page)
+		ops->unmap_page(dev, addr, size, dir, attrs);
+	debug_dma_unmap_page(dev, addr, size, dir, true);
+}
+
+/*
+ * dma_maps_sg_attrs returns 0 on error and > 0 on success.
+ * It should never return a value < 0.
+ */
+static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
+				   int nents, enum dma_data_direction dir,
+				   struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	int i, ents;
+	struct scatterlist *s;
+
+	for_each_sg(sg, s, nents, i)
+		kmemcheck_mark_initialized(sg_virt(s), s->length);
+	BUG_ON(!valid_dma_direction(dir));
+	ents = ops->map_sg(dev, sg, nents, dir, attrs);
+	BUG_ON(ents < 0);
+	debug_dma_map_sg(dev, sg, nents, ents, dir);
+
+	return ents;
+}
+
+static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
+				      int nents, enum dma_data_direction dir,
+				      struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	debug_dma_unmap_sg(dev, sg, nents, dir);
+	if (ops->unmap_sg)
+		ops->unmap_sg(dev, sg, nents, dir, attrs);
+}
+
+static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
+				      size_t offset, size_t size,
+				      enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	dma_addr_t addr;
+
+	kmemcheck_mark_initialized(page_address(page) + offset, size);
+	BUG_ON(!valid_dma_direction(dir));
+	addr = ops->map_page(dev, page, offset, size, dir, NULL);
+	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
+
+	return addr;
+}
+
+static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
+				  size_t size, enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->unmap_page)
+		ops->unmap_page(dev, addr, size, dir, NULL);
+	debug_dma_unmap_page(dev, addr, size, dir, false);
+}
+
+static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
+					   size_t size,
+					   enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(dev, addr, size, dir);
+	debug_dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static inline void dma_sync_single_for_device(struct device *dev,
+					      dma_addr_t addr, size_t size,
+					      enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_single_for_device)
+		ops->sync_single_for_device(dev, addr, size, dir);
+	debug_dma_sync_single_for_device(dev, addr, size, dir);
+}
+
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+						 dma_addr_t addr,
+						 unsigned long offset,
+						 size_t size,
+						 enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(dev, addr + offset, size, dir);
+	debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
+}
+
+static inline void dma_sync_single_range_for_device(struct device *dev,
+						    dma_addr_t addr,
+						    unsigned long offset,
+						    size_t size,
+						    enum dma_data_direction dir)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_single_for_device)
+		ops->sync_single_for_device(dev, addr + offset, size, dir);
+	debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		    int nelems, enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_sg_for_cpu)
+		ops->sync_sg_for_cpu(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		       int nelems, enum dma_data_direction dir)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(dir));
+	if (ops->sync_sg_for_device)
+		ops->sync_sg_for_device(dev, sg, nelems, dir);
+	debug_dma_sync_sg_for_device(dev, sg, nelems, dir);
+
+}
+
+#define dma_map_single(d, a, s, r) dma_map_single_attrs(d, a, s, r, NULL)
+#define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, NULL)
+#define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, NULL)
+#define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, NULL)
+
+extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+			   void *cpu_addr, dma_addr_t dma_addr, size_t size);
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+			unsigned long vm_flags,
+			pgprot_t prot, const void *caller);
+
+void *dma_common_pages_remap(struct page **pages, size_t size,
+			unsigned long vm_flags, pgprot_t prot,
+			const void *caller);
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags);
+
+/**
+ * dma_mmap_attrs - map a coherent DMA allocation into user space
+ * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
+ * @vma: vm_area_struct describing requested user mapping
+ * @cpu_addr: kernel CPU-view address returned from dma_alloc_attrs
+ * @handle: device-view address returned from dma_alloc_attrs
+ * @size: size of memory originally requested in dma_alloc_attrs
+ * @attrs: attributes of mapping properties requested in dma_alloc_attrs
+ *
+ * Map a coherent DMA buffer previously allocated by dma_alloc_attrs
+ * into user space.  The coherent DMA buffer must not be freed by the
+ * driver until the user space mapping has been released.
+ */
+static inline int
+dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma, void *cpu_addr,
+	       dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+	if (ops->mmap)
+		return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
+	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
+
+int
+dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+		       void *cpu_addr, dma_addr_t dma_addr, size_t size);
+
+static inline int
+dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
+		      dma_addr_t dma_addr, size_t size, struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	BUG_ON(!ops);
+	if (ops->get_sgtable)
+		return ops->get_sgtable(dev, sgt, cpu_addr, dma_addr, size,
+					attrs);
+	return dma_common_get_sgtable(dev, sgt, cpu_addr, dma_addr, size);
+}
+
+#define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, NULL)
+
+#ifndef arch_dma_alloc_attrs
+#define arch_dma_alloc_attrs(dev, flag)	(true)
+#endif
+
+static inline void *dma_alloc_attrs(struct device *dev, size_t size,
+				       dma_addr_t *dma_handle, gfp_t flag,
+				       struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *cpu_addr;
+
+	BUG_ON(!ops);
+
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &cpu_addr))
+		return cpu_addr;
+
+	if (!arch_dma_alloc_attrs(&dev, &flag))
+		return NULL;
+	if (!ops->alloc)
+		return NULL;
+
+	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+	return cpu_addr;
+}
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle,
+				     struct dma_attrs *attrs)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!ops);
+	WARN_ON(irqs_disabled());
+
+	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
+		return;
+
+	if (!ops->free)
+		return;
+
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flag)
+{
+	return dma_alloc_attrs(dev, size, dma_handle, flag, NULL);
+}
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle)
+{
+	return dma_free_attrs(dev, size, cpu_addr, dma_handle, NULL);
+}
+
+static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp)
+{
+	DEFINE_DMA_ATTRS(attrs);
+
+	dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs);
+	return dma_alloc_attrs(dev, size, dma_handle, gfp, &attrs);
+}
+
+static inline void dma_free_noncoherent(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle)
+{
+	DEFINE_DMA_ATTRS(attrs);
+
+	dma_set_attr(DMA_ATTR_NON_CONSISTENT, &attrs);
+	dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs);
+}
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	debug_dma_mapping_error(dev, dma_addr);
+
+	if (get_dma_ops(dev)->mapping_error)
+		return get_dma_ops(dev)->mapping_error(dev, dma_addr);
+
+#ifdef DMA_ERROR_CODE
+	return dma_addr == DMA_ERROR_CODE;
+#else
+	return 0;
+#endif
+}
+
+#ifndef HAVE_ARCH_DMA_SUPPORTED
+static inline int dma_supported(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (!ops)
+		return 0;
+	if (!ops->dma_supported)
+		return 1;
+	return ops->dma_supported(dev, mask);
+}
+#endif
+
+#ifndef HAVE_ARCH_DMA_SET_MASK
+static inline int dma_set_mask(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (ops->set_dma_mask)
+		return ops->set_dma_mask(dev, mask);
+
+	if (!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+	*dev->dma_mask = mask;
+	return 0;
+}
 #endif
 
 static inline u64 dma_get_mask(struct device *dev)
@@ -210,7 +586,13 @@ static inline int dma_get_cache_alignment(void)
 #define DMA_MEMORY_INCLUDES_CHILDREN	0x04
 #define DMA_MEMORY_EXCLUSIVE		0x08
 
-#ifndef ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+				dma_addr_t device_addr, size_t size, int flags);
+void dma_release_declared_memory(struct device *dev);
+void *dma_mark_declared_memory_occupied(struct device *dev,
+					dma_addr_t device_addr, size_t size);
+#else
 static inline int
 dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 			    dma_addr_t device_addr, size_t size, int flags)
@@ -229,7 +611,7 @@ dma_mark_declared_memory_occupied(struct device *dev,
 {
 	return ERR_PTR(-EBUSY);
 }
-#endif
+#endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */
 
 /*
  * Managed DMA API
@@ -242,13 +624,13 @@ extern void *dmam_alloc_noncoherent(struct device *dev, size_t size,
 				    dma_addr_t *dma_handle, gfp_t gfp);
 extern void dmam_free_noncoherent(struct device *dev, size_t size, void *vaddr,
 				  dma_addr_t dma_handle);
-#ifdef ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
 extern int dmam_declare_coherent_memory(struct device *dev,
 					phys_addr_t phys_addr,
 					dma_addr_t device_addr, size_t size,
 					int flags);
 extern void dmam_release_declared_memory(struct device *dev);
-#else /* ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY */
+#else /* CONFIG_HAVE_GENERIC_DMA_COHERENT */
 static inline int dmam_declare_coherent_memory(struct device *dev,
 				phys_addr_t phys_addr, dma_addr_t device_addr,
 				size_t size, gfp_t gfp)
@@ -259,24 +641,8 @@ static inline int dmam_declare_coherent_memory(struct device *dev,
 static inline void dmam_release_declared_memory(struct device *dev)
 {
 }
-#endif /* ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY */
-
-#ifndef CONFIG_HAVE_DMA_ATTRS
-struct dma_attrs;
-
-#define dma_map_single_attrs(dev, cpu_addr, size, dir, attrs) \
-	dma_map_single(dev, cpu_addr, size, dir)
+#endif /* CONFIG_HAVE_GENERIC_DMA_COHERENT */
 
-#define dma_unmap_single_attrs(dev, dma_addr, size, dir, attrs) \
-	dma_unmap_single(dev, dma_addr, size, dir)
-
-#define dma_map_sg_attrs(dev, sgl, nents, dir, attrs) \
-	dma_map_sg(dev, sgl, nents, dir)
-
-#define dma_unmap_sg_attrs(dev, sgl, nents, dir, attrs) \
-	dma_unmap_sg(dev, sgl, nents, dir)
-
-#else
 static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
 					   dma_addr_t *dma_addr, gfp_t gfp)
 {
@@ -302,7 +668,6 @@ static inline int dma_mmap_writecombine(struct device *dev,
 	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
 	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
 }
-#endif /* CONFIG_HAVE_DMA_ATTRS */
 
 #ifdef CONFIG_NEED_DMA_MAP_STATE
 #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)        dma_addr_t ADDR_NAME
diff --git a/include/linux/iio/sw_trigger.h b/include/linux/iio/sw_trigger.h
new file mode 100644
index 000000000000..c2f33b2b35a5
--- /dev/null
+++ b/include/linux/iio/sw_trigger.h
@@ -0,0 +1,71 @@
+/*
+ * Industrial I/O software trigger interface
+ *
+ * Copyright (c) 2015 Intel Corporation
+ *
+ * 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.
+ */
+
+#ifndef __IIO_SW_TRIGGER
+#define __IIO_SW_TRIGGER
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/iio/iio.h>
+#include <linux/configfs.h>
+
+#define module_iio_sw_trigger_driver(__iio_sw_trigger_type) \
+	module_driver(__iio_sw_trigger_type, iio_register_sw_trigger_type, \
+		      iio_unregister_sw_trigger_type)
+
+extern struct configfs_subsystem iio_configfs_subsys;
+struct iio_sw_trigger_ops;
+
+struct iio_sw_trigger_type {
+	const char *name;
+	struct module *owner;
+	const struct iio_sw_trigger_ops *ops;
+	struct list_head list;
+	struct config_group *group;
+};
+
+struct iio_sw_trigger {
+	struct iio_trigger *trigger;
+	struct iio_sw_trigger_type *trigger_type;
+	struct config_group group;
+};
+
+struct iio_sw_trigger_ops {
+	struct iio_sw_trigger* (*probe)(const char *);
+	int (*remove)(struct iio_sw_trigger *);
+};
+
+static inline
+struct iio_sw_trigger *to_iio_sw_trigger(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct iio_sw_trigger,
+			    group);
+}
+
+int iio_register_sw_trigger_type(struct iio_sw_trigger_type *tt);
+void iio_unregister_sw_trigger_type(struct iio_sw_trigger_type *tt);
+
+struct iio_sw_trigger *iio_sw_trigger_create(const char *, const char *);
+void iio_sw_trigger_destroy(struct iio_sw_trigger *);
+
+int iio_sw_trigger_type_configfs_register(struct iio_sw_trigger_type *tt);
+void iio_sw_trigger_type_configfs_unregister(struct iio_sw_trigger_type *tt);
+
+static inline
+void iio_swt_group_init_type_name(struct iio_sw_trigger *t,
+				  const char *name,
+				  struct config_item_type *type)
+{
+#ifdef CONFIG_CONFIGFS_FS
+	config_group_init_type_name(&t->group, name, type);
+#endif
+}
+
+#endif /* __IIO_SW_TRIGGER */
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 2a6b9947aaa3..cb0ba9f2a9a2 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -40,7 +40,7 @@ struct list_lru_node {
 	spinlock_t		lock;
 	/* global list, used for the root cgroup in cgroup aware lrus */
 	struct list_lru_one	lru;
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 	/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
 	struct list_lru_memcg	*memcg_lrus;
 #endif
@@ -48,7 +48,7 @@ struct list_lru_node {
 
 struct list_lru {
 	struct list_lru_node	*node;
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 	struct list_head	list;
 #endif
 };
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 189f04d4d2ec..166661708410 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -85,12 +85,6 @@ enum mem_cgroup_events_target {
 	MEM_CGROUP_NTARGETS,
 };
 
-struct cg_proto {
-	struct page_counter	memory_allocated;	/* Current allocated memory. */
-	int			memory_pressure;
-	bool			active;
-};
-
 #ifdef CONFIG_MEMCG
 struct mem_cgroup_stat_cpu {
 	long count[MEM_CGROUP_STAT_NSTATS];
@@ -152,6 +146,12 @@ struct mem_cgroup_thresholds {
 	struct mem_cgroup_threshold_ary *spare;
 };
 
+enum memcg_kmem_state {
+	KMEM_NONE,
+	KMEM_ALLOCATED,
+	KMEM_ONLINE,
+};
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -163,8 +163,12 @@ struct mem_cgroup {
 
 	/* Accounted resources */
 	struct page_counter memory;
+	struct page_counter swap;
+
+	/* Legacy consumer-oriented counters */
 	struct page_counter memsw;
 	struct page_counter kmem;
+	struct page_counter tcpmem;
 
 	/* Normal memory consumption range */
 	unsigned long low;
@@ -178,9 +182,6 @@ struct mem_cgroup {
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
 
-	/* css_online() has been completed */
-	int initialized;
-
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
@@ -227,14 +228,16 @@ struct mem_cgroup {
 	 */
 	struct mem_cgroup_stat_cpu __percpu *stat;
 
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
-	struct cg_proto tcp_mem;
-#endif
-#if defined(CONFIG_MEMCG_KMEM)
+	unsigned long		socket_pressure;
+
+	/* Legacy tcp memory accounting */
+	bool			tcpmem_active;
+	int			tcpmem_pressure;
+
+#ifndef CONFIG_SLOB
         /* Index in the kmem_cache->memcg_params.memcg_caches array */
 	int kmemcg_id;
-	bool kmem_acct_activated;
-	bool kmem_acct_active;
+	enum memcg_kmem_state kmem_state;
 #endif
 
 	int last_scanned_node;
@@ -249,10 +252,6 @@ struct mem_cgroup {
 	struct wb_domain cgwb_domain;
 #endif
 
-#ifdef CONFIG_INET
-	unsigned long		socket_pressure;
-#endif
-
 	/* List of events which userspace want to receive */
 	struct list_head event_list;
 	spinlock_t event_list_lock;
@@ -356,6 +355,13 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
+static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
+		return true;
+	return !!(memcg->css.flags & CSS_ONLINE);
+}
+
 /*
  * For memory reclaim.
  */
@@ -364,20 +370,6 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 		int nr_pages);
 
-static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
-{
-	struct mem_cgroup_per_zone *mz;
-	struct mem_cgroup *memcg;
-
-	if (mem_cgroup_disabled())
-		return true;
-
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
-	memcg = mz->memcg;
-
-	return !!(memcg->css.flags & CSS_ONLINE);
-}
-
 static inline
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
@@ -590,13 +582,13 @@ static inline bool mem_cgroup_disabled(void)
 	return true;
 }
 
-static inline bool
-mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
+static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 {
 	return true;
 }
 
-static inline bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
+static inline bool
+mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 {
 	return true;
 }
@@ -707,15 +699,13 @@ void sock_update_memcg(struct sock *sk);
 void sock_release_memcg(struct sock *sk);
 bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
 void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
-#if defined(CONFIG_MEMCG) && defined(CONFIG_INET)
+#ifdef CONFIG_MEMCG
 extern struct static_key_false memcg_sockets_enabled_key;
 #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
 static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
-#ifdef CONFIG_MEMCG_KMEM
-	if (memcg->tcp_mem.memory_pressure)
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
 		return true;
-#endif
 	do {
 		if (time_before(jiffies, memcg->socket_pressure))
 			return true;
@@ -730,7 +720,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 }
 #endif
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 extern struct static_key_false memcg_kmem_enabled_key;
 
 extern int memcg_nr_cache_ids;
@@ -750,9 +740,9 @@ static inline bool memcg_kmem_enabled(void)
 	return static_branch_unlikely(&memcg_kmem_enabled_key);
 }
 
-static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+static inline bool memcg_kmem_online(struct mem_cgroup *memcg)
 {
-	return memcg->kmem_acct_active;
+	return memcg->kmem_state == KMEM_ONLINE;
 }
 
 /*
@@ -850,7 +840,7 @@ static inline bool memcg_kmem_enabled(void)
 	return false;
 }
 
-static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+static inline bool memcg_kmem_online(struct mem_cgroup *memcg)
 {
 	return false;
 }
@@ -886,5 +876,6 @@ memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 static inline void memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
+
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/property.h b/include/linux/property.h
index 3a8c7d7773e6..b8c4e420fe87 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -175,12 +175,19 @@ struct property_entry {
 	};
 };
 
+/*
+ * Note: the below four initializers for the anonymous union are carefully
+ * crafted to avoid gcc-4.4.4's problems with initialization of anon unions
+ * and structs.
+ */
+
 #define PROPERTY_ENTRY_INTEGER_ARRAY(_name_, _type_, _val_)	\
 {								\
 	.name = _name_,						\
 	.length = ARRAY_SIZE(_val_) * sizeof(_type_),		\
 	.is_array = true,					\
-	.pointer._type_##_data = _val_,				\
+	.is_string = false,					\
+	{ .pointer = { _type_##_data = _val_ } },		\
 }
 
 #define PROPERTY_ENTRY_U8_ARRAY(_name_, _val_)			\
@@ -198,14 +205,15 @@ struct property_entry {
 	.length = ARRAY_SIZE(_val_) * sizeof(const char *),	\
 	.is_array = true,					\
 	.is_string = true,					\
-	.pointer.str = _val_,					\
+	{ .pointer = { .str = _val_ } },			\
 }
 
 #define PROPERTY_ENTRY_INTEGER(_name_, _type_, _val_)	\
 {							\
 	.name = _name_,					\
 	.length = sizeof(_type_),			\
-	.value._type_##_data = _val_,			\
+	.is_string = false,				\
+	{ .value = { ._type_##_data = _val_ } },	\
 }
 
 #define PROPERTY_ENTRY_U8(_name_, _val_)		\
@@ -222,7 +230,7 @@ struct property_entry {
 	.name = _name_,					\
 	.length = sizeof(_val_),			\
 	.is_string = true,				\
-	.value.str = _val_,				\
+	{ .value = {.str = _val_} },			\
 }
 
 #define PROPERTY_ENTRY_BOOL(_name_)		\
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 157e7d36f58b..7b76e395fb80 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1469,10 +1469,10 @@ struct task_struct {
 	unsigned sched_migrated:1;
 #ifdef CONFIG_MEMCG
 	unsigned memcg_may_oom:1;
-#endif
-#ifdef CONFIG_MEMCG_KMEM
+#ifndef CONFIG_SLOB
 	unsigned memcg_kmem_skip_account:1;
 #endif
+#endif
 #ifdef CONFIG_COMPAT_BRK
 	unsigned brk_randomized:1;
 #endif
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 3ffee7422012..3627d5c1bc47 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -86,7 +86,7 @@
 #else
 # define SLAB_FAILSLAB		0x00000000UL
 #endif
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 # define SLAB_ACCOUNT		0x04000000UL	/* Account to memcg */
 #else
 # define SLAB_ACCOUNT		0x00000000UL
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 33d049066c3d..cf139d3fa513 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -69,7 +69,8 @@ struct kmem_cache {
 	 */
 	int obj_offset;
 #endif /* CONFIG_DEBUG_SLAB */
-#ifdef CONFIG_MEMCG_KMEM
+
+#ifdef CONFIG_MEMCG
 	struct memcg_cache_params memcg_params;
 #endif
 
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 33885118523c..b7e57927f521 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -84,7 +84,7 @@ struct kmem_cache {
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
 #endif
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	struct memcg_cache_params memcg_params;
 	int max_attr_size; /* for propagation, maximum size of a stored attr */
 #ifdef CONFIG_SYSFS
diff --git a/include/linux/swap.h b/include/linux/swap.h
index fa872a094e82..b14a2bb33514 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -351,33 +351,7 @@ extern void check_move_unevictable_pages(struct page **, int nr_pages);
 
 extern int kswapd_run(int nid);
 extern void kswapd_stop(int nid);
-#ifdef CONFIG_MEMCG
-static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
-{
-	/* root ? */
-	if (mem_cgroup_disabled() || !memcg->css.parent)
-		return vm_swappiness;
-
-	return memcg->swappiness;
-}
 
-#else
-static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
-{
-	return vm_swappiness;
-}
-#endif
-#ifdef CONFIG_MEMCG_SWAP
-extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
-extern void mem_cgroup_uncharge_swap(swp_entry_t entry);
-#else
-static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
-{
-}
-static inline void mem_cgroup_uncharge_swap(swp_entry_t entry)
-{
-}
-#endif
 #ifdef CONFIG_SWAP
 /* linux/mm/page_io.c */
 extern int swap_readpage(struct page *);
@@ -556,5 +530,55 @@ static inline swp_entry_t get_swap_page(void)
 }
 
 #endif /* CONFIG_SWAP */
+
+#ifdef CONFIG_MEMCG
+static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
+{
+	/* root ? */
+	if (mem_cgroup_disabled() || !memcg->css.parent)
+		return vm_swappiness;
+
+	return memcg->swappiness;
+}
+
+#else
+static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
+{
+	return vm_swappiness;
+}
+#endif
+
+#ifdef CONFIG_MEMCG_SWAP
+extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
+extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
+extern void mem_cgroup_uncharge_swap(swp_entry_t entry);
+extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
+extern bool mem_cgroup_swap_full(struct page *page);
+#else
+static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
+{
+}
+
+static inline int mem_cgroup_try_charge_swap(struct page *page,
+					     swp_entry_t entry)
+{
+	return 0;
+}
+
+static inline void mem_cgroup_uncharge_swap(swp_entry_t entry)
+{
+}
+
+static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
+{
+	return get_nr_swap_pages();
+}
+
+static inline bool mem_cgroup_swap_full(struct page *page)
+{
+	return vm_swap_full();
+}
+#endif
+
 #endif /* __KERNEL__*/
 #endif /* _LINUX_SWAP_H */
diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h
deleted file mode 100644
index 3a17b16ae8aa..000000000000
--- a/include/net/tcp_memcontrol.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _TCP_MEMCG_H
-#define _TCP_MEMCG_H
-
-int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss);
-void tcp_destroy_cgroup(struct mem_cgroup *memcg);
-#endif /* _TCP_MEMCG_H */
diff --git a/init/Kconfig b/init/Kconfig
index faa4d087d69e..e6f5acaa97b0 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -998,17 +998,6 @@ config MEMCG_SWAP_ENABLED
 	  For those who want to have the feature enabled by default should
 	  select this option (if, for some reason, they need to disable it
 	  then swapaccount=0 does the trick).
-config MEMCG_KMEM
-	bool "Memory Resource Controller Kernel Memory accounting"
-	depends on MEMCG
-	depends on SLUB || SLAB
-	help
-	  The Kernel Memory extension for Memory Resource Controller can limit
-	  the amount of memory used by kernel objects in the system. Those are
-	  fundamentally different from the entities handled by the standard
-	  Memory Controller, which are page-based, and can be swapped. Users of
-	  the kmem extension can use it to guarantee that no group of processes
-	  will ever exhaust kernel resources alone.
 
 config BLK_CGROUP
 	bool "IO controller"
@@ -1216,10 +1205,9 @@ config USER_NS
 	  to provide different user info for different servers.
 
 	  When user namespaces are enabled in the kernel it is
-	  recommended that the MEMCG and MEMCG_KMEM options also be
-	  enabled and that user-space use the memory control groups to
-	  limit the amount of memory a memory unprivileged users can
-	  use.
+	  recommended that the MEMCG option also be enabled and that
+	  user-space use the memory control groups to limit the amount
+	  of memory a memory unprivileged users can use.
 
 	  If unsure, say N.
 
diff --git a/mm/list_lru.c b/mm/list_lru.c
index afc71ea9a381..1d05cb9d363d 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -12,7 +12,7 @@
 #include <linux/mutex.h>
 #include <linux/memcontrol.h>
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 static LIST_HEAD(list_lrus);
 static DEFINE_MUTEX(list_lrus_mutex);
 
@@ -37,9 +37,9 @@ static void list_lru_register(struct list_lru *lru)
 static void list_lru_unregister(struct list_lru *lru)
 {
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 static inline bool list_lru_memcg_aware(struct list_lru *lru)
 {
 	/*
@@ -104,7 +104,7 @@ list_lru_from_kmem(struct list_lru_node *nlru, void *ptr)
 {
 	return &nlru->lru;
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 bool list_lru_add(struct list_lru *lru, struct list_head *item)
 {
@@ -292,7 +292,7 @@ static void init_one_lru(struct list_lru_one *l)
 	l->nr_items = 0;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus,
 					  int begin, int end)
 {
@@ -529,7 +529,7 @@ static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
 static void memcg_destroy_list_lru(struct list_lru *lru)
 {
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 int __list_lru_init(struct list_lru *lru, bool memcg_aware,
 		    struct lock_class_key *key)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 3ec2832393f8..48b22c3545b1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -66,7 +66,6 @@
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
-#include <net/tcp_memcontrol.h>
 #include "slab.h"
 
 #include <asm/uaccess.h>
@@ -83,6 +82,9 @@ struct mem_cgroup *root_mem_cgroup __read_mostly;
 /* Socket memory accounting disabled? */
 static bool cgroup_memory_nosocket;
 
+/* Kernel memory accounting disabled? */
+static bool cgroup_memory_nokmem;
+
 /* Whether the swap controller is active */
 #ifdef CONFIG_MEMCG_SWAP
 int do_swap_account __read_mostly;
@@ -239,6 +241,7 @@ enum res_type {
 	_MEMSWAP,
 	_OOM_TYPE,
 	_KMEM,
+	_TCP,
 };
 
 #define MEMFILE_PRIVATE(x, val)	((x) << 16 | (val))
@@ -247,13 +250,6 @@ enum res_type {
 /* Used for OOM nofiier */
 #define OOM_CONTROL		(0)
 
-/*
- * The memcg_create_mutex will be held whenever a new cgroup is created.
- * As a consequence, any change that needs to protect against new child cgroups
- * appearing has to hold it as well.
- */
-static DEFINE_MUTEX(memcg_create_mutex);
-
 /* Some nice accessors for the vmpressure. */
 struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
 {
@@ -297,7 +293,7 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
 	return mem_cgroup_from_css(css);
 }
 
-#ifdef CONFIG_MEMCG_KMEM
+#ifndef CONFIG_SLOB
 /*
  * This will be the memcg's index in each cache's ->memcg_params.memcg_caches.
  * The main reason for not using cgroup id for this:
@@ -349,7 +345,7 @@ void memcg_put_cache_ids(void)
 DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* !CONFIG_SLOB */
 
 static struct mem_cgroup_per_zone *
 mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
@@ -899,17 +895,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		if (css == &root->css)
 			break;
 
-		if (css_tryget(css)) {
-			/*
-			 * Make sure the memcg is initialized:
-			 * mem_cgroup_css_online() orders the the
-			 * initialization against setting the flag.
-			 */
-			if (smp_load_acquire(&memcg->initialized))
-				break;
-
-			css_put(css);
-		}
+		if (css_tryget(css))
+			break;
 
 		memcg = NULL;
 	}
@@ -1235,7 +1222,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 		pr_cont(":");
 
 		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
-			if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account())
+			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 				continue;
 			pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
 				K(mem_cgroup_read_stat(iter, i)));
@@ -1274,9 +1261,12 @@ static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
 	limit = memcg->memory.limit;
 	if (mem_cgroup_swappiness(memcg)) {
 		unsigned long memsw_limit;
+		unsigned long swap_limit;
 
 		memsw_limit = memcg->memsw.limit;
-		limit = min(limit + total_swap_pages, memsw_limit);
+		swap_limit = memcg->swap.limit;
+		swap_limit = min(swap_limit, (unsigned long)total_swap_pages);
+		limit = min(limit + swap_limit, memsw_limit);
 	}
 	return limit;
 }
@@ -2205,7 +2195,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 		unlock_page_lru(page, isolated);
 }
 
-#ifdef CONFIG_MEMCG_KMEM
+#ifndef CONFIG_SLOB
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
@@ -2380,16 +2370,17 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
 	struct page_counter *counter;
 	int ret;
 
-	if (!memcg_kmem_is_active(memcg))
+	if (!memcg_kmem_online(memcg))
 		return 0;
 
-	if (!page_counter_try_charge(&memcg->kmem, nr_pages, &counter))
-		return -ENOMEM;
-
 	ret = try_charge(memcg, gfp, nr_pages);
-	if (ret) {
-		page_counter_uncharge(&memcg->kmem, nr_pages);
+	if (ret)
 		return ret;
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
+	    !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) {
+		cancel_charge(memcg, nr_pages);
+		return -ENOMEM;
 	}
 
 	page->mem_cgroup = memcg;
@@ -2418,7 +2409,9 @@ void __memcg_kmem_uncharge(struct page *page, int order)
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
 
-	page_counter_uncharge(&memcg->kmem, nr_pages);
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		page_counter_uncharge(&memcg->kmem, nr_pages);
+
 	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_memsw_account())
 		page_counter_uncharge(&memcg->memsw, nr_pages);
@@ -2426,7 +2419,7 @@ void __memcg_kmem_uncharge(struct page *page, int order)
 	page->mem_cgroup = NULL;
 	css_put_many(&memcg->css, nr_pages);
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* !CONFIG_SLOB */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
@@ -2686,14 +2679,6 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg)
 {
 	bool ret;
 
-	/*
-	 * The lock does not prevent addition or deletion of children, but
-	 * it prevents a new child from being initialized based on this
-	 * parent in css_online(), so it's enough to decide whether
-	 * hierarchically inherited attributes can still be changed or not.
-	 */
-	lockdep_assert_held(&memcg_create_mutex);
-
 	rcu_read_lock();
 	ret = css_next_child(NULL, &memcg->css);
 	rcu_read_unlock();
@@ -2756,10 +2741,8 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent);
 
-	mutex_lock(&memcg_create_mutex);
-
 	if (memcg->use_hierarchy == val)
-		goto out;
+		return 0;
 
 	/*
 	 * If parent's use_hierarchy is set, we can't make any modifications
@@ -2778,9 +2761,6 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css,
 	} else
 		retval = -EINVAL;
 
-out:
-	mutex_unlock(&memcg_create_mutex);
-
 	return retval;
 }
 
@@ -2838,6 +2818,9 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 	case _KMEM:
 		counter = &memcg->kmem;
 		break;
+	case _TCP:
+		counter = &memcg->tcpmem;
+		break;
 	default:
 		BUG();
 	}
@@ -2862,103 +2845,176 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 	}
 }
 
-#ifdef CONFIG_MEMCG_KMEM
-static int memcg_activate_kmem(struct mem_cgroup *memcg,
-			       unsigned long nr_pages)
+#ifndef CONFIG_SLOB
+static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
-	int err = 0;
 	int memcg_id;
 
 	BUG_ON(memcg->kmemcg_id >= 0);
-	BUG_ON(memcg->kmem_acct_activated);
-	BUG_ON(memcg->kmem_acct_active);
-
-	/*
-	 * For simplicity, we won't allow this to be disabled.  It also can't
-	 * be changed if the cgroup has children already, or if tasks had
-	 * already joined.
-	 *
-	 * If tasks join before we set the limit, a person looking at
-	 * kmem.usage_in_bytes will have no way to determine when it took
-	 * place, which makes the value quite meaningless.
-	 *
-	 * After it first became limited, changes in the value of the limit are
-	 * of course permitted.
-	 */
-	mutex_lock(&memcg_create_mutex);
-	if (cgroup_is_populated(memcg->css.cgroup) ||
-	    (memcg->use_hierarchy && memcg_has_children(memcg)))
-		err = -EBUSY;
-	mutex_unlock(&memcg_create_mutex);
-	if (err)
-		goto out;
+	BUG_ON(memcg->kmem_state);
 
 	memcg_id = memcg_alloc_cache_id();
-	if (memcg_id < 0) {
-		err = memcg_id;
-		goto out;
-	}
-
-	/*
-	 * We couldn't have accounted to this cgroup, because it hasn't got
-	 * activated yet, so this should succeed.
-	 */
-	err = page_counter_limit(&memcg->kmem, nr_pages);
-	VM_BUG_ON(err);
+	if (memcg_id < 0)
+		return memcg_id;
 
 	static_branch_inc(&memcg_kmem_enabled_key);
 	/*
-	 * A memory cgroup is considered kmem-active as soon as it gets
+	 * A memory cgroup is considered kmem-online as soon as it gets
 	 * kmemcg_id. Setting the id after enabling static branching will
 	 * guarantee no one starts accounting before all call sites are
 	 * patched.
 	 */
 	memcg->kmemcg_id = memcg_id;
-	memcg->kmem_acct_activated = true;
-	memcg->kmem_acct_active = true;
-out:
-	return err;
+	memcg->kmem_state = KMEM_ONLINE;
+
+	return 0;
 }
 
-static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
-				   unsigned long limit)
+static int memcg_propagate_kmem(struct mem_cgroup *parent,
+				struct mem_cgroup *memcg)
 {
-	int ret;
+	int ret = 0;
 
 	mutex_lock(&memcg_limit_mutex);
-	if (!memcg_kmem_is_active(memcg))
-		ret = memcg_activate_kmem(memcg, limit);
-	else
-		ret = page_counter_limit(&memcg->kmem, limit);
+	/*
+	 * If the parent cgroup is not kmem-online now, it cannot be
+	 * onlined after this point, because it has at least one child
+	 * already.
+	 */
+	if (memcg_kmem_online(parent) ||
+	    (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nokmem))
+		ret = memcg_online_kmem(memcg);
 	mutex_unlock(&memcg_limit_mutex);
 	return ret;
 }
 
-static int memcg_propagate_kmem(struct mem_cgroup *memcg)
+static void memcg_offline_kmem(struct mem_cgroup *memcg)
 {
-	int ret = 0;
-	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *parent, *child;
+	int kmemcg_id;
 
+	if (memcg->kmem_state != KMEM_ONLINE)
+		return;
+	/*
+	 * Clear the online state before clearing memcg_caches array
+	 * entries. The slab_mutex in memcg_deactivate_kmem_caches()
+	 * guarantees that no cache will be created for this cgroup
+	 * after we are done (see memcg_create_kmem_cache()).
+	 */
+	memcg->kmem_state = KMEM_ALLOCATED;
+
+	memcg_deactivate_kmem_caches(memcg);
+
+	kmemcg_id = memcg->kmemcg_id;
+	BUG_ON(kmemcg_id < 0);
+
+	parent = parent_mem_cgroup(memcg);
 	if (!parent)
-		return 0;
+		parent = root_mem_cgroup;
 
-	mutex_lock(&memcg_limit_mutex);
 	/*
-	 * If the parent cgroup is not kmem-active now, it cannot be activated
-	 * after this point, because it has at least one child already.
+	 * Change kmemcg_id of this cgroup and all its descendants to the
+	 * parent's id, and then move all entries from this cgroup's list_lrus
+	 * to ones of the parent. After we have finished, all list_lrus
+	 * corresponding to this cgroup are guaranteed to remain empty. The
+	 * ordering is imposed by list_lru_node->lock taken by
+	 * memcg_drain_all_list_lrus().
 	 */
-	if (memcg_kmem_is_active(parent))
-		ret = memcg_activate_kmem(memcg, PAGE_COUNTER_MAX);
-	mutex_unlock(&memcg_limit_mutex);
-	return ret;
+	css_for_each_descendant_pre(css, &memcg->css) {
+		child = mem_cgroup_from_css(css);
+		BUG_ON(child->kmemcg_id != kmemcg_id);
+		child->kmemcg_id = parent->kmemcg_id;
+		if (!memcg->use_hierarchy)
+			break;
+	}
+	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
+
+	memcg_free_cache_id(kmemcg_id);
+}
+
+static void memcg_free_kmem(struct mem_cgroup *memcg)
+{
+	/* css_alloc() failed, offlining didn't happen */
+	if (unlikely(memcg->kmem_state == KMEM_ONLINE))
+		memcg_offline_kmem(memcg);
+
+	if (memcg->kmem_state == KMEM_ALLOCATED) {
+		memcg_destroy_kmem_caches(memcg);
+		static_branch_dec(&memcg_kmem_enabled_key);
+		WARN_ON(page_counter_read(&memcg->kmem));
+	}
 }
 #else
+static int memcg_propagate_kmem(struct mem_cgroup *memcg)
+{
+	return 0;
+}
+static void memcg_offline_kmem(struct mem_cgroup *memcg)
+{
+}
+static void memcg_free_kmem(struct mem_cgroup *memcg)
+{
+}
+#endif /* !CONFIG_SLOB */
+
 static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
 				   unsigned long limit)
 {
-	return -EINVAL;
+	int ret = 0;
+
+	mutex_lock(&memcg_limit_mutex);
+	/* Top-level cgroup doesn't propagate from root */
+	if (!memcg_kmem_online(memcg)) {
+		if (cgroup_is_populated(memcg->css.cgroup) ||
+		    (memcg->use_hierarchy && memcg_has_children(memcg)))
+			ret = -EBUSY;
+		if (ret)
+			goto out;
+		ret = memcg_online_kmem(memcg);
+		if (ret)
+			goto out;
+	}
+	ret = page_counter_limit(&memcg->kmem, limit);
+out:
+	mutex_unlock(&memcg_limit_mutex);
+	return ret;
+}
+
+static int memcg_update_tcp_limit(struct mem_cgroup *memcg, unsigned long limit)
+{
+	int ret;
+
+	mutex_lock(&memcg_limit_mutex);
+
+	ret = page_counter_limit(&memcg->tcpmem, limit);
+	if (ret)
+		goto out;
+
+	if (!memcg->tcpmem_active) {
+		/*
+		 * The active flag needs to be written after the static_key
+		 * update. This is what guarantees that the socket activation
+		 * function is the last one to run. See sock_update_memcg() for
+		 * details, and note that we don't mark any socket as belonging
+		 * to this memcg until that flag is up.
+		 *
+		 * We need to do this, because static_keys will span multiple
+		 * sites, but we can't control their order. If we mark a socket
+		 * as accounted, but the accounting functions are not patched in
+		 * yet, we'll lose accounting.
+		 *
+		 * We never race with the readers in sock_update_memcg(),
+		 * because when this value change, the code to process it is not
+		 * patched in yet.
+		 */
+		static_branch_inc(&memcg_sockets_enabled_key);
+		memcg->tcpmem_active = true;
+	}
+out:
+	mutex_unlock(&memcg_limit_mutex);
+	return ret;
 }
-#endif /* CONFIG_MEMCG_KMEM */
 
 /*
  * The user of this function is...
@@ -2992,6 +3048,9 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
 		case _KMEM:
 			ret = memcg_update_kmem_limit(memcg, nr_pages);
 			break;
+		case _TCP:
+			ret = memcg_update_tcp_limit(memcg, nr_pages);
+			break;
 		}
 		break;
 	case RES_SOFT_LIMIT:
@@ -3018,6 +3077,9 @@ static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
 	case _KMEM:
 		counter = &memcg->kmem;
 		break;
+	case _TCP:
+		counter = &memcg->tcpmem;
+		break;
 	default:
 		BUG();
 	}
@@ -3583,88 +3645,6 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
-static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
-{
-	int ret;
-
-	ret = memcg_propagate_kmem(memcg);
-	if (ret)
-		return ret;
-
-	return tcp_init_cgroup(memcg, ss);
-}
-
-static void memcg_deactivate_kmem(struct mem_cgroup *memcg)
-{
-	struct cgroup_subsys_state *css;
-	struct mem_cgroup *parent, *child;
-	int kmemcg_id;
-
-	if (!memcg->kmem_acct_active)
-		return;
-
-	/*
-	 * Clear the 'active' flag before clearing memcg_caches arrays entries.
-	 * Since we take the slab_mutex in memcg_deactivate_kmem_caches(), it
-	 * guarantees no cache will be created for this cgroup after we are
-	 * done (see memcg_create_kmem_cache()).
-	 */
-	memcg->kmem_acct_active = false;
-
-	memcg_deactivate_kmem_caches(memcg);
-
-	kmemcg_id = memcg->kmemcg_id;
-	BUG_ON(kmemcg_id < 0);
-
-	parent = parent_mem_cgroup(memcg);
-	if (!parent)
-		parent = root_mem_cgroup;
-
-	/*
-	 * Change kmemcg_id of this cgroup and all its descendants to the
-	 * parent's id, and then move all entries from this cgroup's list_lrus
-	 * to ones of the parent. After we have finished, all list_lrus
-	 * corresponding to this cgroup are guaranteed to remain empty. The
-	 * ordering is imposed by list_lru_node->lock taken by
-	 * memcg_drain_all_list_lrus().
-	 */
-	css_for_each_descendant_pre(css, &memcg->css) {
-		child = mem_cgroup_from_css(css);
-		BUG_ON(child->kmemcg_id != kmemcg_id);
-		child->kmemcg_id = parent->kmemcg_id;
-		if (!memcg->use_hierarchy)
-			break;
-	}
-	memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id);
-
-	memcg_free_cache_id(kmemcg_id);
-}
-
-static void memcg_destroy_kmem(struct mem_cgroup *memcg)
-{
-	if (memcg->kmem_acct_activated) {
-		memcg_destroy_kmem_caches(memcg);
-		static_branch_dec(&memcg_kmem_enabled_key);
-		WARN_ON(page_counter_read(&memcg->kmem));
-	}
-	tcp_destroy_cgroup(memcg);
-}
-#else
-static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
-{
-	return 0;
-}
-
-static void memcg_deactivate_kmem(struct mem_cgroup *memcg)
-{
-}
-
-static void memcg_destroy_kmem(struct mem_cgroup *memcg)
-{
-}
-#endif
-
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg)
@@ -4052,7 +4032,6 @@ static struct cftype mem_cgroup_legacy_files[] = {
 		.seq_show = memcg_numa_stat_show,
 	},
 #endif
-#ifdef CONFIG_MEMCG_KMEM
 	{
 		.name = "kmem.limit_in_bytes",
 		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
@@ -4085,7 +4064,29 @@ static struct cftype mem_cgroup_legacy_files[] = {
 		.seq_show = memcg_slab_show,
 	},
 #endif
-#endif
+	{
+		.name = "kmem.tcp.limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_TCP, RES_LIMIT),
+		.write = mem_cgroup_write,
+		.read_u64 = mem_cgroup_read_u64,
+	},
+	{
+		.name = "kmem.tcp.usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_TCP, RES_USAGE),
+		.read_u64 = mem_cgroup_read_u64,
+	},
+	{
+		.name = "kmem.tcp.failcnt",
+		.private = MEMFILE_PRIVATE(_TCP, RES_FAILCNT),
+		.write = mem_cgroup_reset,
+		.read_u64 = mem_cgroup_read_u64,
+	},
+	{
+		.name = "kmem.tcp.max_usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_TCP, RES_MAX_USAGE),
+		.write = mem_cgroup_reset,
+		.read_u64 = mem_cgroup_read_u64,
+	},
 	{ },	/* terminate */
 };
 
@@ -4124,147 +4125,92 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 	kfree(memcg->nodeinfo[node]);
 }
 
-static struct mem_cgroup *mem_cgroup_alloc(void)
-{
-	struct mem_cgroup *memcg;
-	size_t size;
-
-	size = sizeof(struct mem_cgroup);
-	size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
-
-	memcg = kzalloc(size, GFP_KERNEL);
-	if (!memcg)
-		return NULL;
-
-	memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
-	if (!memcg->stat)
-		goto out_free;
-
-	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
-		goto out_free_stat;
-
-	return memcg;
-
-out_free_stat:
-	free_percpu(memcg->stat);
-out_free:
-	kfree(memcg);
-	return NULL;
-}
-
-/*
- * At destroying mem_cgroup, references from swap_cgroup can remain.
- * (scanning all at force_empty is too costly...)
- *
- * Instead of clearing all references at force_empty, we remember
- * the number of reference from swap_cgroup and free mem_cgroup when
- * it goes down to 0.
- *
- * Removal of cgroup itself succeeds regardless of refs from swap.
- */
-
-static void __mem_cgroup_free(struct mem_cgroup *memcg)
+static void mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
-	cancel_work_sync(&memcg->high_work);
-
-	mem_cgroup_remove_from_trees(memcg);
-
+	memcg_wb_domain_exit(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_zone_info(memcg, node);
-
 	free_percpu(memcg->stat);
-	memcg_wb_domain_exit(memcg);
 	kfree(memcg);
 }
 
-static struct cgroup_subsys_state * __ref
-mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
+static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
-	long error = -ENOMEM;
+	size_t size;
 	int node;
 
-	memcg = mem_cgroup_alloc();
+	size = sizeof(struct mem_cgroup);
+	size += nr_node_ids * sizeof(struct mem_cgroup_per_node *);
+
+	memcg = kzalloc(size, GFP_KERNEL);
 	if (!memcg)
-		return ERR_PTR(error);
+		return NULL;
+
+	memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
+	if (!memcg->stat)
+		goto fail;
 
 	for_each_node(node)
 		if (alloc_mem_cgroup_per_zone_info(memcg, node))
-			goto free_out;
+			goto fail;
 
-	/* root ? */
-	if (parent_css == NULL) {
-		root_mem_cgroup = memcg;
-		page_counter_init(&memcg->memory, NULL);
-		memcg->high = PAGE_COUNTER_MAX;
-		memcg->soft_limit = PAGE_COUNTER_MAX;
-		page_counter_init(&memcg->memsw, NULL);
-		page_counter_init(&memcg->kmem, NULL);
-	}
+	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
+		goto fail;
 
 	INIT_WORK(&memcg->high_work, high_work_func);
 	memcg->last_scanned_node = MAX_NUMNODES;
 	INIT_LIST_HEAD(&memcg->oom_notify);
-	memcg->move_charge_at_immigrate = 0;
 	mutex_init(&memcg->thresholds_lock);
 	spin_lock_init(&memcg->move_lock);
 	vmpressure_init(&memcg->vmpressure);
 	INIT_LIST_HEAD(&memcg->event_list);
 	spin_lock_init(&memcg->event_list_lock);
-#ifdef CONFIG_MEMCG_KMEM
+	memcg->socket_pressure = jiffies;
+#ifndef CONFIG_SLOB
 	memcg->kmemcg_id = -1;
 #endif
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&memcg->cgwb_list);
 #endif
-#ifdef CONFIG_INET
-	memcg->socket_pressure = jiffies;
-#endif
-	return &memcg->css;
-
-free_out:
-	__mem_cgroup_free(memcg);
-	return ERR_PTR(error);
+	return memcg;
+fail:
+	mem_cgroup_free(memcg);
+	return NULL;
 }
 
-static int
-mem_cgroup_css_online(struct cgroup_subsys_state *css)
+static struct cgroup_subsys_state * __ref
+mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	struct mem_cgroup *parent = mem_cgroup_from_css(css->parent);
-	int ret;
-
-	if (css->id > MEM_CGROUP_ID_MAX)
-		return -ENOSPC;
-
-	if (!parent)
-		return 0;
-
-	mutex_lock(&memcg_create_mutex);
+	struct mem_cgroup *parent = mem_cgroup_from_css(parent_css);
+	struct mem_cgroup *memcg;
+	long error = -ENOMEM;
 
-	memcg->use_hierarchy = parent->use_hierarchy;
-	memcg->oom_kill_disable = parent->oom_kill_disable;
-	memcg->swappiness = mem_cgroup_swappiness(parent);
+	memcg = mem_cgroup_alloc();
+	if (!memcg)
+		return ERR_PTR(error);
 
-	if (parent->use_hierarchy) {
+	memcg->high = PAGE_COUNTER_MAX;
+	memcg->soft_limit = PAGE_COUNTER_MAX;
+	if (parent) {
+		memcg->swappiness = mem_cgroup_swappiness(parent);
+		memcg->oom_kill_disable = parent->oom_kill_disable;
+	}
+	if (parent && parent->use_hierarchy) {
+		memcg->use_hierarchy = true;
 		page_counter_init(&memcg->memory, &parent->memory);
-		memcg->high = PAGE_COUNTER_MAX;
-		memcg->soft_limit = PAGE_COUNTER_MAX;
+		page_counter_init(&memcg->swap, &parent->swap);
 		page_counter_init(&memcg->memsw, &parent->memsw);
 		page_counter_init(&memcg->kmem, &parent->kmem);
-
-		/*
-		 * No need to take a reference to the parent because cgroup
-		 * core guarantees its existence.
-		 */
+		page_counter_init(&memcg->tcpmem, &parent->tcpmem);
 	} else {
 		page_counter_init(&memcg->memory, NULL);
-		memcg->high = PAGE_COUNTER_MAX;
-		memcg->soft_limit = PAGE_COUNTER_MAX;
+		page_counter_init(&memcg->swap, NULL);
 		page_counter_init(&memcg->memsw, NULL);
 		page_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->tcpmem, NULL);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
@@ -4273,23 +4219,31 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 		if (parent != root_mem_cgroup)
 			memory_cgrp_subsys.broken_hierarchy = true;
 	}
-	mutex_unlock(&memcg_create_mutex);
 
-	ret = memcg_init_kmem(memcg, &memory_cgrp_subsys);
-	if (ret)
-		return ret;
+	/* The following stuff does not apply to the root */
+	if (!parent) {
+		root_mem_cgroup = memcg;
+		return &memcg->css;
+	}
+
+	error = memcg_propagate_kmem(parent, memcg);
+	if (error)
+		goto fail;
 
-#ifdef CONFIG_INET
 	if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
 		static_branch_inc(&memcg_sockets_enabled_key);
-#endif
 
-	/*
-	 * Make sure the memcg is initialized: mem_cgroup_iter()
-	 * orders reading memcg->initialized against its callers
-	 * reading the memcg members.
-	 */
-	smp_store_release(&memcg->initialized, 1);
+	return &memcg->css;
+fail:
+	mem_cgroup_free(memcg);
+	return NULL;
+}
+
+static int
+mem_cgroup_css_online(struct cgroup_subsys_state *css)
+{
+	if (css->id > MEM_CGROUP_ID_MAX)
+		return -ENOSPC;
 
 	return 0;
 }
@@ -4311,10 +4265,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	}
 	spin_unlock(&memcg->event_list_lock);
 
-	vmpressure_cleanup(&memcg->vmpressure);
-
-	memcg_deactivate_kmem(memcg);
-
+	memcg_offline_kmem(memcg);
 	wb_memcg_offline(memcg);
 }
 
@@ -4329,12 +4280,17 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
-	memcg_destroy_kmem(memcg);
-#ifdef CONFIG_INET
 	if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket)
 		static_branch_dec(&memcg_sockets_enabled_key);
-#endif
-	__mem_cgroup_free(memcg);
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_active)
+		static_branch_dec(&memcg_sockets_enabled_key);
+
+	vmpressure_cleanup(&memcg->vmpressure);
+	cancel_work_sync(&memcg->high_work);
+	mem_cgroup_remove_from_trees(memcg);
+	memcg_free_kmem(memcg);
+	mem_cgroup_free(memcg);
 }
 
 /**
@@ -5270,7 +5226,7 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		if (page->mem_cgroup)
 			goto out;
 
-		if (do_memsw_account()) {
+		if (do_swap_account) {
 			swp_entry_t ent = { .val = page_private(page), };
 			unsigned short id = lookup_swap_cgroup_id(ent);
 
@@ -5532,8 +5488,6 @@ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
 	commit_charge(newpage, memcg, true);
 }
 
-#ifdef CONFIG_INET
-
 DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
 EXPORT_SYMBOL(memcg_sockets_enabled_key);
 
@@ -5559,10 +5513,8 @@ void sock_update_memcg(struct sock *sk)
 	memcg = mem_cgroup_from_task(current);
 	if (memcg == root_mem_cgroup)
 		goto out;
-#ifdef CONFIG_MEMCG_KMEM
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcp_mem.active)
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcpmem_active)
 		goto out;
-#endif
 	if (css_tryget_online(&memcg->css))
 		sk->sk_memcg = memcg;
 out:
@@ -5588,20 +5540,18 @@ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	gfp_t gfp_mask = GFP_KERNEL;
 
-#ifdef CONFIG_MEMCG_KMEM
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
-		struct page_counter *counter;
+		struct page_counter *fail;
 
-		if (page_counter_try_charge(&memcg->tcp_mem.memory_allocated,
-					    nr_pages, &counter)) {
-			memcg->tcp_mem.memory_pressure = 0;
+		if (page_counter_try_charge(&memcg->tcpmem, nr_pages, &fail)) {
+			memcg->tcpmem_pressure = 0;
 			return true;
 		}
-		page_counter_charge(&memcg->tcp_mem.memory_allocated, nr_pages);
-		memcg->tcp_mem.memory_pressure = 1;
+		page_counter_charge(&memcg->tcpmem, nr_pages);
+		memcg->tcpmem_pressure = 1;
 		return false;
 	}
-#endif
+
 	/* Don't block in the packet receive path */
 	if (in_softirq())
 		gfp_mask = GFP_NOWAIT;
@@ -5620,19 +5570,15 @@ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
  */
 void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-#ifdef CONFIG_MEMCG_KMEM
 	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) {
-		page_counter_uncharge(&memcg->tcp_mem.memory_allocated,
-				      nr_pages);
+		page_counter_uncharge(&memcg->tcpmem, nr_pages);
 		return;
 	}
-#endif
+
 	page_counter_uncharge(&memcg->memory, nr_pages);
 	css_put_many(&memcg->css, nr_pages);
 }
 
-#endif /* CONFIG_INET */
-
 static int __init cgroup_memory(char *s)
 {
 	char *token;
@@ -5642,6 +5588,8 @@ static int __init cgroup_memory(char *s)
 			continue;
 		if (!strcmp(token, "nosocket"))
 			cgroup_memory_nosocket = true;
+		if (!strcmp(token, "nokmem"))
+			cgroup_memory_nokmem = true;
 	}
 	return 0;
 }
@@ -5731,32 +5679,107 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	memcg_check_events(memcg, page);
 }
 
+/*
+ * mem_cgroup_try_charge_swap - try charging a swap entry
+ * @page: page being added to swap
+ * @entry: swap entry to charge
+ *
+ * Try to charge @entry to the memcg that @page belongs to.
+ *
+ * Returns 0 on success, -ENOMEM on failure.
+ */
+int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
+{
+	struct mem_cgroup *memcg;
+	struct page_counter *counter;
+	unsigned short oldid;
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || !do_swap_account)
+		return 0;
+
+	memcg = page->mem_cgroup;
+
+	/* Readahead page, never charged */
+	if (!memcg)
+		return 0;
+
+	if (!mem_cgroup_is_root(memcg) &&
+	    !page_counter_try_charge(&memcg->swap, 1, &counter))
+		return -ENOMEM;
+
+	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
+	VM_BUG_ON_PAGE(oldid, page);
+	mem_cgroup_swap_statistics(memcg, true);
+
+	css_get(&memcg->css);
+	return 0;
+}
+
 /**
  * mem_cgroup_uncharge_swap - uncharge a swap entry
  * @entry: swap entry to uncharge
  *
- * Drop the memsw charge associated with @entry.
+ * Drop the swap charge associated with @entry.
  */
 void mem_cgroup_uncharge_swap(swp_entry_t entry)
 {
 	struct mem_cgroup *memcg;
 	unsigned short id;
 
-	if (!do_memsw_account())
+	if (!do_swap_account)
 		return;
 
 	id = swap_cgroup_record(entry, 0);
 	rcu_read_lock();
 	memcg = mem_cgroup_from_id(id);
 	if (memcg) {
-		if (!mem_cgroup_is_root(memcg))
-			page_counter_uncharge(&memcg->memsw, 1);
+		if (!mem_cgroup_is_root(memcg)) {
+			if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+				page_counter_uncharge(&memcg->swap, 1);
+			else
+				page_counter_uncharge(&memcg->memsw, 1);
+		}
 		mem_cgroup_swap_statistics(memcg, false);
 		css_put(&memcg->css);
 	}
 	rcu_read_unlock();
 }
 
+long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
+{
+	long nr_swap_pages = get_nr_swap_pages();
+
+	if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return nr_swap_pages;
+	for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg))
+		nr_swap_pages = min_t(long, nr_swap_pages,
+				      READ_ONCE(memcg->swap.limit) -
+				      page_counter_read(&memcg->swap));
+	return nr_swap_pages;
+}
+
+bool mem_cgroup_swap_full(struct page *page)
+{
+	struct mem_cgroup *memcg;
+
+	VM_BUG_ON_PAGE(!PageLocked(page), page);
+
+	if (vm_swap_full())
+		return true;
+	if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return false;
+
+	memcg = page->mem_cgroup;
+	if (!memcg)
+		return false;
+
+	for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg))
+		if (page_counter_read(&memcg->swap) * 2 >= memcg->swap.limit)
+			return true;
+
+	return false;
+}
+
 /* for remember boot option*/
 #ifdef CONFIG_MEMCG_SWAP_ENABLED
 static int really_do_swap_account __initdata = 1;
@@ -5774,6 +5797,63 @@ static int __init enable_swap_account(char *s)
 }
 __setup("swapaccount=", enable_swap_account);
 
+static u64 swap_current_read(struct cgroup_subsys_state *css,
+			     struct cftype *cft)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE;
+}
+
+static int swap_max_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	unsigned long max = READ_ONCE(memcg->swap.limit);
+
+	if (max == PAGE_COUNTER_MAX)
+		seq_puts(m, "max\n");
+	else
+		seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE);
+
+	return 0;
+}
+
+static ssize_t swap_max_write(struct kernfs_open_file *of,
+			      char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	unsigned long max;
+	int err;
+
+	buf = strstrip(buf);
+	err = page_counter_memparse(buf, "max", &max);
+	if (err)
+		return err;
+
+	mutex_lock(&memcg_limit_mutex);
+	err = page_counter_limit(&memcg->swap, max);
+	mutex_unlock(&memcg_limit_mutex);
+	if (err)
+		return err;
+
+	return nbytes;
+}
+
+static struct cftype swap_files[] = {
+	{
+		.name = "swap.current",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = swap_current_read,
+	},
+	{
+		.name = "swap.max",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = swap_max_show,
+		.write = swap_max_write,
+	},
+	{ }	/* terminate */
+};
+
 static struct cftype memsw_cgroup_files[] = {
 	{
 		.name = "memsw.usage_in_bytes",
@@ -5805,6 +5885,8 @@ static int __init mem_cgroup_swap_init(void)
 {
 	if (!mem_cgroup_disabled() && really_do_swap_account) {
 		do_swap_account = 1;
+		WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys,
+					       swap_files));
 		WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys,
 						  memsw_cgroup_files));
 	}
diff --git a/mm/memory.c b/mm/memory.c
index 65f081fcab1e..206c8cda1634 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2584,7 +2584,8 @@ int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	swap_free(entry);
-	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
+	if (mem_cgroup_swap_full(page) ||
+	    (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
 	if (page != swapcache) {
diff --git a/mm/shmem.c b/mm/shmem.c
index 83407a046881..d5d1612de662 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -912,6 +912,9 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	if (!swap.val)
 		goto redirty;
 
+	if (mem_cgroup_try_charge_swap(page, swap))
+		goto free_swap;
+
 	/*
 	 * Add inode to shmem_unuse()'s list of swapped-out inodes,
 	 * if it's not already there.  Do it now before the page is
@@ -940,6 +943,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
+free_swap:
 	swapcache_free(swap);
 redirty:
 	set_page_dirty(page);
diff --git a/mm/slab.h b/mm/slab.h
index c63b8699cfa3..834ad240c0bb 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -173,7 +173,7 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
 int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 /*
  * Iterate over all memcg caches of the given root cache. The caller must hold
  * slab_mutex.
@@ -251,7 +251,7 @@ static __always_inline int memcg_charge_slab(struct page *page,
 
 extern void slab_init_memcg_params(struct kmem_cache *);
 
-#else /* !CONFIG_MEMCG_KMEM */
+#else /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 #define for_each_memcg_cache(iter, root) \
 	for ((void)(iter), (void)(root); 0; )
@@ -292,7 +292,7 @@ static inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order,
 static inline void slab_init_memcg_params(struct kmem_cache *s)
 {
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x)
 {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index e016178063e1..b50aef01ccf7 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -128,7 +128,7 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 	return i;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 void slab_init_memcg_params(struct kmem_cache *s)
 {
 	s->memcg_params.is_root_cache = true;
@@ -221,7 +221,7 @@ static inline int init_memcg_params(struct kmem_cache *s,
 static inline void destroy_memcg_params(struct kmem_cache *s)
 {
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 /*
  * Find a mergeable slab cache
@@ -477,7 +477,7 @@ static void release_caches(struct list_head *release, bool need_rcu_barrier)
 	}
 }
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 /*
  * memcg_create_kmem_cache - Create a cache for a memory cgroup.
  * @memcg: The memory cgroup the new cache is for.
@@ -503,10 +503,10 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	mutex_lock(&slab_mutex);
 
 	/*
-	 * The memory cgroup could have been deactivated while the cache
+	 * The memory cgroup could have been offlined while the cache
 	 * creation work was pending.
 	 */
-	if (!memcg_kmem_is_active(memcg))
+	if (!memcg_kmem_online(memcg))
 		goto out_unlock;
 
 	idx = memcg_cache_id(memcg);
@@ -689,7 +689,7 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s,
 {
 	return 0;
 }
-#endif /* CONFIG_MEMCG_KMEM */
+#endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 void slab_kmem_cache_release(struct kmem_cache *s)
 {
@@ -1123,7 +1123,7 @@ static int slab_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
+#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
 int memcg_slab_show(struct seq_file *m, void *p)
 {
 	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
diff --git a/mm/slub.c b/mm/slub.c
index b21fd24b08b1..2e1355ac056b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -5207,7 +5207,7 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 		return -EIO;
 
 	err = attribute->store(s, buf, len);
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	if (slab_state >= FULL && err >= 0 && is_root_cache(s)) {
 		struct kmem_cache *c;
 
@@ -5242,7 +5242,7 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 
 static void memcg_propagate_slab_attrs(struct kmem_cache *s)
 {
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	int i;
 	char *buffer = NULL;
 	struct kmem_cache *root_cache;
@@ -5328,7 +5328,7 @@ static struct kset *slab_kset;
 
 static inline struct kset *cache_kset(struct kmem_cache *s)
 {
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	if (!is_root_cache(s))
 		return s->memcg_params.root_cache->memcg_kset;
 #endif
@@ -5405,7 +5405,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
 	if (err)
 		goto out_del_kobj;
 
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	if (is_root_cache(s)) {
 		s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
 		if (!s->memcg_kset) {
@@ -5438,7 +5438,7 @@ void sysfs_slab_remove(struct kmem_cache *s)
 		 */
 		return;
 
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	kset_unregister(s->memcg_kset);
 #endif
 	kobject_uevent(&s->kobj, KOBJ_REMOVE);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 676ff2991380..69cb2464e7dc 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -170,6 +170,11 @@ int add_to_swap(struct page *page, struct list_head *list)
 	if (!entry.val)
 		return 0;
 
+	if (mem_cgroup_try_charge_swap(page, entry)) {
+		swapcache_free(entry);
+		return 0;
+	}
+
 	if (unlikely(PageTransHuge(page)))
 		if (unlikely(split_huge_page_to_list(page, list))) {
 			swapcache_free(entry);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 31dc94fb0f60..a8062c842fc2 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -785,14 +785,12 @@ static unsigned char swap_entry_free(struct swap_info_struct *p,
 			count--;
 	}
 
-	if (!count)
-		mem_cgroup_uncharge_swap(entry);
-
 	usage = count | has_cache;
 	p->swap_map[offset] = usage;
 
 	/* free if no reference */
 	if (!usage) {
+		mem_cgroup_uncharge_swap(entry);
 		dec_cluster_info_page(p, p->cluster_info, offset);
 		if (offset < p->lowest_bit)
 			p->lowest_bit = offset;
@@ -1008,7 +1006,7 @@ int free_swap_and_cache(swp_entry_t entry)
 		 * Also recheck PageSwapCache now page is locked (above).
 		 */
 		if (PageSwapCache(page) && !PageWriteback(page) &&
-				(!page_mapped(page) || vm_swap_full())) {
+		    (!page_mapped(page) || mem_cgroup_swap_full(page))) {
 			delete_from_swap_cache(page);
 			SetPageDirty(page);
 		}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 51d45373e609..44ec50ff740b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -411,7 +411,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 	struct shrinker *shrinker;
 	unsigned long freed = 0;
 
-	if (memcg && !memcg_kmem_is_active(memcg))
+	if (memcg && !memcg_kmem_online(memcg))
 		return 0;
 
 	if (nr_scanned == 0)
@@ -1214,7 +1214,7 @@ cull_mlocked:
 
 activate_locked:
 		/* Not a candidate for swapping, so reclaim swap space. */
-		if (PageSwapCache(page) && vm_swap_full())
+		if (PageSwapCache(page) && mem_cgroup_swap_full(page))
 			try_to_free_swap(page);
 		VM_BUG_ON_PAGE(PageActive(page), page);
 		SetPageActive(page);
@@ -1966,10 +1966,11 @@ enum scan_balance {
  * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan
  * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
  */
-static void get_scan_count(struct lruvec *lruvec, int swappiness,
+static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 			   struct scan_control *sc, unsigned long *nr,
 			   unsigned long *lru_pages)
 {
+	int swappiness = mem_cgroup_swappiness(memcg);
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 	u64 fraction[2];
 	u64 denominator = 0;	/* gcc */
@@ -1996,14 +1997,14 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness,
 	if (current_is_kswapd()) {
 		if (!zone_reclaimable(zone))
 			force_scan = true;
-		if (!mem_cgroup_lruvec_online(lruvec))
+		if (!mem_cgroup_online(memcg))
 			force_scan = true;
 	}
 	if (!global_reclaim(sc))
 		force_scan = true;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (!sc->may_swap || (get_nr_swap_pages() <= 0)) {
+	if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) {
 		scan_balance = SCAN_FILE;
 		goto out;
 	}
@@ -2193,9 +2194,10 @@ static inline void init_tlb_ubc(void)
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
-static void shrink_lruvec(struct lruvec *lruvec, int swappiness,
-			  struct scan_control *sc, unsigned long *lru_pages)
+static void shrink_zone_memcg(struct zone *zone, struct mem_cgroup *memcg,
+			      struct scan_control *sc, unsigned long *lru_pages)
 {
+	struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long targets[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
@@ -2205,7 +2207,7 @@ static void shrink_lruvec(struct lruvec *lruvec, int swappiness,
 	struct blk_plug plug;
 	bool scan_adjusted;
 
-	get_scan_count(lruvec, swappiness, sc, nr, lru_pages);
+	get_scan_count(lruvec, memcg, sc, nr, lru_pages);
 
 	/* Record the original scan target for proportional adjustments later */
 	memcpy(targets, nr, sizeof(nr));
@@ -2409,8 +2411,6 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 			unsigned long lru_pages;
 			unsigned long reclaimed;
 			unsigned long scanned;
-			struct lruvec *lruvec;
-			int swappiness;
 
 			if (mem_cgroup_low(root, memcg)) {
 				if (!sc->may_thrash)
@@ -2418,12 +2418,10 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
 				mem_cgroup_events(memcg, MEMCG_LOW, 1);
 			}
 
-			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
-			swappiness = mem_cgroup_swappiness(memcg);
 			reclaimed = sc->nr_reclaimed;
 			scanned = sc->nr_scanned;
 
-			shrink_lruvec(lruvec, swappiness, sc, &lru_pages);
+			shrink_zone_memcg(zone, memcg, sc, &lru_pages);
 			zone_lru_pages += lru_pages;
 
 			if (memcg && is_classzone)
@@ -2876,8 +2874,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 		.may_unmap = 1,
 		.may_swap = !noswap,
 	};
-	struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
-	int swappiness = mem_cgroup_swappiness(memcg);
 	unsigned long lru_pages;
 
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
@@ -2894,7 +2890,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
 	 * will pick up pages from other mem cgroup's as well. We hack
 	 * the priority and make it zero.
 	 */
-	shrink_lruvec(lruvec, swappiness, &sc, &lru_pages);
+	shrink_zone_memcg(zone, memcg, &sc, &lru_pages);
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index c29809f765dc..62c049b647e9 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -56,7 +56,6 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
 obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
 obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
-obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 41ff1f87dfd7..f17ebbb5b745 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -24,7 +24,6 @@
 #include <net/cipso_ipv4.h>
 #include <net/inet_frag.h>
 #include <net/ping.h>
-#include <net/tcp_memcontrol.h>
 
 static int zero;
 static int one = 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 54fb9059cd54..1402fea6ca51 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -73,7 +73,6 @@
 #include <net/timewait_sock.h>
 #include <net/xfrm.h>
 #include <net/secure_seq.h>
-#include <net/tcp_memcontrol.h>
 #include <net/busy_poll.h>
 
 #include <linux/inet.h>
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
deleted file mode 100644
index 18bc7f745e9c..000000000000
--- a/net/ipv4/tcp_memcontrol.c
+++ /dev/null
@@ -1,200 +0,0 @@
-#include <net/tcp.h>
-#include <net/tcp_memcontrol.h>
-#include <net/sock.h>
-#include <net/ip.h>
-#include <linux/nsproxy.h>
-#include <linux/memcontrol.h>
-#include <linux/module.h>
-
-int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
-{
-	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
-	struct page_counter *counter_parent = NULL;
-	/*
-	 * The root cgroup does not use page_counters, but rather,
-	 * rely on the data already collected by the network
-	 * subsystem
-	 */
-	if (memcg == root_mem_cgroup)
-		return 0;
-
-	memcg->tcp_mem.memory_pressure = 0;
-
-	if (parent)
-		counter_parent = &parent->tcp_mem.memory_allocated;
-
-	page_counter_init(&memcg->tcp_mem.memory_allocated, counter_parent);
-
-	return 0;
-}
-
-void tcp_destroy_cgroup(struct mem_cgroup *memcg)
-{
-	if (memcg == root_mem_cgroup)
-		return;
-
-	if (memcg->tcp_mem.active)
-		static_branch_dec(&memcg_sockets_enabled_key);
-}
-
-static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
-{
-	int ret;
-
-	if (memcg == root_mem_cgroup)
-		return -EINVAL;
-
-	ret = page_counter_limit(&memcg->tcp_mem.memory_allocated, nr_pages);
-	if (ret)
-		return ret;
-
-	if (!memcg->tcp_mem.active) {
-		/*
-		 * The active flag needs to be written after the static_key
-		 * update. This is what guarantees that the socket activation
-		 * function is the last one to run. See sock_update_memcg() for
-		 * details, and note that we don't mark any socket as belonging
-		 * to this memcg until that flag is up.
-		 *
-		 * We need to do this, because static_keys will span multiple
-		 * sites, but we can't control their order. If we mark a socket
-		 * as accounted, but the accounting functions are not patched in
-		 * yet, we'll lose accounting.
-		 *
-		 * We never race with the readers in sock_update_memcg(),
-		 * because when this value change, the code to process it is not
-		 * patched in yet.
-		 */
-		static_branch_inc(&memcg_sockets_enabled_key);
-		memcg->tcp_mem.active = true;
-	}
-
-	return 0;
-}
-
-enum {
-	RES_USAGE,
-	RES_LIMIT,
-	RES_MAX_USAGE,
-	RES_FAILCNT,
-};
-
-static DEFINE_MUTEX(tcp_limit_mutex);
-
-static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
-				char *buf, size_t nbytes, loff_t off)
-{
-	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	unsigned long nr_pages;
-	int ret = 0;
-
-	buf = strstrip(buf);
-
-	switch (of_cft(of)->private) {
-	case RES_LIMIT:
-		/* see memcontrol.c */
-		ret = page_counter_memparse(buf, "-1", &nr_pages);
-		if (ret)
-			break;
-		mutex_lock(&tcp_limit_mutex);
-		ret = tcp_update_limit(memcg, nr_pages);
-		mutex_unlock(&tcp_limit_mutex);
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-	return ret ?: nbytes;
-}
-
-static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
-{
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	u64 val;
-
-	switch (cft->private) {
-	case RES_LIMIT:
-		if (memcg == root_mem_cgroup)
-			val = PAGE_COUNTER_MAX;
-		else
-			val = memcg->tcp_mem.memory_allocated.limit;
-		val *= PAGE_SIZE;
-		break;
-	case RES_USAGE:
-		if (memcg == root_mem_cgroup)
-			val = atomic_long_read(&tcp_memory_allocated);
-		else
-			val = page_counter_read(&memcg->tcp_mem.memory_allocated);
-		val *= PAGE_SIZE;
-		break;
-	case RES_FAILCNT:
-		if (memcg == root_mem_cgroup)
-			return 0;
-		val = memcg->tcp_mem.memory_allocated.failcnt;
-		break;
-	case RES_MAX_USAGE:
-		if (memcg == root_mem_cgroup)
-			return 0;
-		val = memcg->tcp_mem.memory_allocated.watermark;
-		val *= PAGE_SIZE;
-		break;
-	default:
-		BUG();
-	}
-	return val;
-}
-
-static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
-				char *buf, size_t nbytes, loff_t off)
-{
-	struct mem_cgroup *memcg;
-
-	memcg = mem_cgroup_from_css(of_css(of));
-	if (memcg == root_mem_cgroup)
-		return nbytes;
-
-	switch (of_cft(of)->private) {
-	case RES_MAX_USAGE:
-		page_counter_reset_watermark(&memcg->tcp_mem.memory_allocated);
-		break;
-	case RES_FAILCNT:
-		memcg->tcp_mem.memory_allocated.failcnt = 0;
-		break;
-	}
-
-	return nbytes;
-}
-
-static struct cftype tcp_files[] = {
-	{
-		.name = "kmem.tcp.limit_in_bytes",
-		.write = tcp_cgroup_write,
-		.read_u64 = tcp_cgroup_read,
-		.private = RES_LIMIT,
-	},
-	{
-		.name = "kmem.tcp.usage_in_bytes",
-		.read_u64 = tcp_cgroup_read,
-		.private = RES_USAGE,
-	},
-	{
-		.name = "kmem.tcp.failcnt",
-		.private = RES_FAILCNT,
-		.write = tcp_cgroup_reset,
-		.read_u64 = tcp_cgroup_read,
-	},
-	{
-		.name = "kmem.tcp.max_usage_in_bytes",
-		.private = RES_MAX_USAGE,
-		.write = tcp_cgroup_reset,
-		.read_u64 = tcp_cgroup_read,
-	},
-	{ }	/* terminate */
-};
-
-static int __init tcp_memcontrol_init(void)
-{
-	WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, tcp_files));
-	return 0;
-}
-__initcall(tcp_memcontrol_init);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a30e589b330f..4f34f2dcbb9d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -61,7 +61,6 @@
 #include <net/timewait_sock.h>
 #include <net/inet_common.h>
 #include <net/secure_seq.h>
-#include <net/tcp_memcontrol.h>
 #include <net/busy_poll.h>
 
 #include <linux/proc_fs.h>