Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:

 - a few misc things

 - kexec updates

 - DMA-mapping updates to better support networking DMA operations

 - IPC updates

 - various MM changes to improve DAX fault handling

 - lots of radix-tree changes, mainly to the test suite. All leading up
   to reimplementing the IDA/IDR code to be a wrapper layer over the
   radix-tree. However the final trigger-pulling patch is held off for
   4.11.

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (114 commits)
  radix tree test suite: delete unused rcupdate.c
  radix tree test suite: add new tag check
  radix-tree: ensure counts are initialised
  radix tree test suite: cache recently freed objects
  radix tree test suite: add some more functionality
  idr: reduce the number of bits per level from 8 to 6
  rxrpc: abstract away knowledge of IDR internals
  tpm: use idr_find(), not idr_find_slowpath()
  idr: add ida_is_empty
  radix tree test suite: check multiorder iteration
  radix-tree: fix replacement for multiorder entries
  radix-tree: add radix_tree_split_preload()
  radix-tree: add radix_tree_split
  radix-tree: add radix_tree_join
  radix-tree: delete radix_tree_range_tag_if_tagged()
  radix-tree: delete radix_tree_locate_item()
  radix-tree: improve multiorder iterators
  btrfs: fix race in btrfs_free_dummy_fs_info()
  radix-tree: improve dump output
  radix-tree: make radix_tree_find_next_bit more useful
  ...

26 files changed, 211 insertions, 66 deletions

diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index cd8aad8226dd..08450a1a5b5f 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -158,7 +158,10 @@ static dma_addr_t arc_dma_map_page(struct device *dev, struct page *page,
 		unsigned long attrs)
 {
 	phys_addr_t paddr = page_to_phys(page) + offset;
-	_dma_cache_sync(paddr, size, dir);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		_dma_cache_sync(paddr, size, dir);
+
 	return plat_phys_to_dma(dev, paddr);
 }
 
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index 301281645d08..75055df1cda3 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -243,7 +243,8 @@ static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
 }
 
 static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
-		enum dma_data_direction dir)
+				    enum dma_data_direction dir,
+				    unsigned long attrs)
 {
 	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
 	struct safe_buffer *buf;
@@ -262,7 +263,8 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
 		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
 		buf->safe, buf->safe_dma_addr);
 
-	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
+	if ((dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) &&
+	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
 		dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
 			__func__, ptr, buf->safe, size);
 		memcpy(buf->safe, ptr, size);
@@ -272,7 +274,8 @@ static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
 }
 
 static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
-		size_t size, enum dma_data_direction dir)
+				size_t size, enum dma_data_direction dir,
+				unsigned long attrs)
 {
 	BUG_ON(buf->size != size);
 	BUG_ON(buf->direction != dir);
@@ -283,7 +286,8 @@ static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
 
 	DO_STATS(dev->archdata.dmabounce->bounce_count++);
 
-	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
+	if ((dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) &&
+	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
 		void *ptr = buf->ptr;
 
 		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
@@ -334,7 +338,7 @@ static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page,
 		return DMA_ERROR_CODE;
 	}
 
-	return map_single(dev, page_address(page) + offset, size, dir);
+	return map_single(dev, page_address(page) + offset, size, dir, attrs);
 }
 
 /*
@@ -357,7 +361,7 @@ static void dmabounce_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t
 		return;
 	}
 
-	unmap_single(dev, buf, size, dir);
+	unmap_single(dev, buf, size, dir, attrs);
 }
 
 static int __dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
diff --git a/arch/avr32/mm/dma-coherent.c b/arch/avr32/mm/dma-coherent.c
index 58610d0df7ed..54534e5d0781 100644
--- a/arch/avr32/mm/dma-coherent.c
+++ b/arch/avr32/mm/dma-coherent.c
@@ -146,7 +146,8 @@ static dma_addr_t avr32_dma_map_page(struct device *dev, struct page *page,
 {
 	void *cpu_addr = page_address(page) + offset;
 
-	dma_cache_sync(dev, cpu_addr, size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_cache_sync(dev, cpu_addr, size, direction);
 	return virt_to_bus(cpu_addr);
 }
 
@@ -162,6 +163,10 @@ static int avr32_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 		sg->dma_address = page_to_bus(sg_page(sg)) + sg->offset;
 		virt = sg_virt(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		dma_cache_sync(dev, virt, sg->length, direction);
 	}
 
diff --git a/arch/blackfin/kernel/dma-mapping.c b/arch/blackfin/kernel/dma-mapping.c
index 53fbbb61aa86..a27a74a18fb0 100644
--- a/arch/blackfin/kernel/dma-mapping.c
+++ b/arch/blackfin/kernel/dma-mapping.c
@@ -118,6 +118,10 @@ static int bfin_dma_map_sg(struct device *dev, struct scatterlist *sg_list,
 
 	for_each_sg(sg_list, sg, nents, i) {
 		sg->dma_address = (dma_addr_t) sg_virt(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		__dma_sync(sg_dma_address(sg), sg_dma_len(sg), direction);
 	}
 
@@ -143,7 +147,9 @@ static dma_addr_t bfin_dma_map_page(struct device *dev, struct page *page,
 {
 	dma_addr_t handle = (dma_addr_t)(page_address(page) + offset);
 
-	_dma_sync(handle, size, dir);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		_dma_sync(handle, size, dir);
+
 	return handle;
 }
 
diff --git a/arch/c6x/kernel/dma.c b/arch/c6x/kernel/dma.c
index db4a6a301f5e..6752df32ef06 100644
--- a/arch/c6x/kernel/dma.c
+++ b/arch/c6x/kernel/dma.c
@@ -42,14 +42,17 @@ static dma_addr_t c6x_dma_map_page(struct device *dev, struct page *page,
 {
 	dma_addr_t handle = virt_to_phys(page_address(page) + offset);
 
-	c6x_dma_sync(handle, size, dir);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		c6x_dma_sync(handle, size, dir);
+
 	return handle;
 }
 
 static void c6x_dma_unmap_page(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
-	c6x_dma_sync(handle, size, dir);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		c6x_dma_sync(handle, size, dir);
 }
 
 static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -60,7 +63,8 @@ static int c6x_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
-		c6x_dma_sync(sg->dma_address, sg->length, dir);
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			c6x_dma_sync(sg->dma_address, sg->length, dir);
 	}
 
 	return nents;
@@ -72,9 +76,11 @@ static void c6x_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct scatterlist *sg;
 	int i;
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	for_each_sg(sglist, sg, nents, i)
 		c6x_dma_sync(sg_dma_address(sg), sg->length, dir);
-
 }
 
 static void c6x_dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
diff --git a/arch/frv/mb93090-mb00/pci-dma-nommu.c b/arch/frv/mb93090-mb00/pci-dma-nommu.c
index 90f2e4cb33d6..187688128c65 100644
--- a/arch/frv/mb93090-mb00/pci-dma-nommu.c
+++ b/arch/frv/mb93090-mb00/pci-dma-nommu.c
@@ -109,16 +109,19 @@ static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 		int nents, enum dma_data_direction direction,
 		unsigned long attrs)
 {
-	int i;
 	struct scatterlist *sg;
+	int i;
+
+	BUG_ON(direction == DMA_NONE);
+
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return nents;
 
 	for_each_sg(sglist, sg, nents, i) {
 		frv_cache_wback_inv(sg_dma_address(sg),
 				    sg_dma_address(sg) + sg_dma_len(sg));
 	}
 
-	BUG_ON(direction == DMA_NONE);
-
 	return nents;
 }
 
@@ -127,7 +130,10 @@ static dma_addr_t frv_dma_map_page(struct device *dev, struct page *page,
 		enum dma_data_direction direction, unsigned long attrs)
 {
 	BUG_ON(direction == DMA_NONE);
-	flush_dcache_page(page);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		flush_dcache_page(page);
+
 	return (dma_addr_t) page_to_phys(page) + offset;
 }
 
diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c
index f585745b1abc..dba7df918144 100644
--- a/arch/frv/mb93090-mb00/pci-dma.c
+++ b/arch/frv/mb93090-mb00/pci-dma.c
@@ -40,13 +40,16 @@ static int frv_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 		int nents, enum dma_data_direction direction,
 		unsigned long attrs)
 {
+	struct scatterlist *sg;
 	unsigned long dampr2;
 	void *vaddr;
 	int i;
-	struct scatterlist *sg;
 
 	BUG_ON(direction == DMA_NONE);
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return nents;
+
 	dampr2 = __get_DAMPR(2);
 
 	for_each_sg(sglist, sg, nents, i) {
@@ -70,7 +73,9 @@ 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, unsigned long attrs)
 {
-	flush_dcache_page(page);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		flush_dcache_page(page);
+
 	return (dma_addr_t) page_to_phys(page) + offset;
 }
 
diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c
index b9017785fb71..dbc4f1003da4 100644
--- a/arch/hexagon/kernel/dma.c
+++ b/arch/hexagon/kernel/dma.c
@@ -119,6 +119,9 @@ static int hexagon_map_sg(struct device *hwdev, struct scatterlist *sg,
 
 		s->dma_length = s->length;
 
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		flush_dcache_range(dma_addr_to_virt(s->dma_address),
 				   dma_addr_to_virt(s->dma_address + s->length));
 	}
@@ -180,7 +183,8 @@ static dma_addr_t hexagon_map_page(struct device *dev, struct page *page,
 	if (!check_addr("map_single", dev, bus, size))
 		return bad_dma_address;
 
-	dma_sync(dma_addr_to_virt(bus), size, dir);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_sync(dma_addr_to_virt(bus), size, dir);
 
 	return bus;
 }
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 8cf97cbadc91..07070065a425 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -134,7 +134,9 @@ static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page,
 {
 	dma_addr_t handle = page_to_phys(page) + offset;
 
-	dma_sync_single_for_device(dev, handle, size, dir);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_sync_single_for_device(dev, handle, size, dir);
+
 	return handle;
 }
 
@@ -146,6 +148,10 @@ static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
 					   dir);
 	}
diff --git a/arch/metag/kernel/dma.c b/arch/metag/kernel/dma.c
index 0db31e24c541..91968d92652b 100644
--- a/arch/metag/kernel/dma.c
+++ b/arch/metag/kernel/dma.c
@@ -484,8 +484,9 @@ 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, unsigned long attrs)
 {
-	dma_sync_for_device((void *)(page_to_phys(page) + offset), size,
-			    direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_sync_for_device((void *)(page_to_phys(page) + offset),
+				    size, direction);
 	return page_to_phys(page) + offset;
 }
 
@@ -493,7 +494,8 @@ static void metag_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 		size_t size, enum dma_data_direction direction,
 		unsigned long attrs)
 {
-	dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
 }
 
 static int metag_dma_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -507,6 +509,10 @@ static int metag_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 		BUG_ON(!sg_page(sg));
 
 		sg->dma_address = sg_phys(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		dma_sync_for_device(sg_virt(sg), sg->length, direction);
 	}
 
@@ -525,6 +531,10 @@ static void metag_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		BUG_ON(!sg_page(sg));
 
 		sg->dma_address = sg_phys(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
 	}
 }
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
index ec04dc1e2527..818daf230eb4 100644
--- a/arch/microblaze/kernel/dma.c
+++ b/arch/microblaze/kernel/dma.c
@@ -61,6 +61,10 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	/* FIXME this part of code is untested */
 	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		__dma_sync(page_to_phys(sg_page(sg)) + sg->offset,
 							sg->length, direction);
 	}
@@ -80,7 +84,8 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 					     enum dma_data_direction direction,
 					     unsigned long attrs)
 {
-	__dma_sync(page_to_phys(page) + offset, size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync(page_to_phys(page) + offset, size, direction);
 	return page_to_phys(page) + offset;
 }
 
@@ -95,7 +100,8 @@ static inline void dma_direct_unmap_page(struct device *dev,
  * phys_to_virt is here because in __dma_sync_page is __virt_to_phys and
  * dma_address is physical address
  */
-	__dma_sync(dma_address, size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync(dma_address, size, direction);
 }
 
 static inline void
diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
index 1a80b6f73ab2..aab4fd681e1f 100644
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ b/arch/mips/loongson64/common/dma-swiotlb.c
@@ -61,7 +61,7 @@ static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg,
 				int nents, enum dma_data_direction dir,
 				unsigned long attrs)
 {
-	int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, 0);
+	int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs);
 	mb();
 
 	return r;
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 46d5696c4f27..a39c36af97ad 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -293,7 +293,7 @@ static inline void __dma_sync(struct page *page,
 static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
 	size_t size, enum dma_data_direction direction, unsigned long attrs)
 {
-	if (cpu_needs_post_dma_flush(dev))
+	if (cpu_needs_post_dma_flush(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		__dma_sync(dma_addr_to_page(dev, dma_addr),
 			   dma_addr & ~PAGE_MASK, size, direction);
 	plat_post_dma_flush(dev);
@@ -307,7 +307,8 @@ static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 	struct scatterlist *sg;
 
 	for_each_sg(sglist, sg, nents, i) {
-		if (!plat_device_is_coherent(dev))
+		if (!plat_device_is_coherent(dev) &&
+		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
@@ -324,7 +325,7 @@ static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page,
 	unsigned long offset, size_t size, enum dma_data_direction direction,
 	unsigned long attrs)
 {
-	if (!plat_device_is_coherent(dev))
+	if (!plat_device_is_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		__dma_sync(page, offset, size, direction);
 
 	return plat_map_dma_mem_page(dev, page) + offset;
@@ -339,6 +340,7 @@ static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nhwentries, i) {
 		if (!plat_device_is_coherent(dev) &&
+		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 		    direction != DMA_TO_DEVICE)
 			__dma_sync(sg_page(sg), sg->offset, sg->length,
 				   direction);
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index d800fad87896..f6a5dcf9d682 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -98,13 +98,17 @@ static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	int i;
 
 	for_each_sg(sg, sg, nents, i) {
-		void *addr;
+		void *addr = sg_virt(sg);
 
-		addr = sg_virt(sg);
-		if (addr) {
-			__dma_sync_for_device(addr, sg->length, direction);
-			sg->dma_address = sg_phys(sg);
-		}
+		if (!addr)
+			continue;
+
+		sg->dma_address = sg_phys(sg);
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
+		__dma_sync_for_device(addr, sg->length, direction);
 	}
 
 	return nents;
@@ -117,7 +121,9 @@ static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page,
 {
 	void *addr = page_address(page) + offset;
 
-	__dma_sync_for_device(addr, size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync_for_device(addr, size, direction);
+
 	return page_to_phys(page) + offset;
 }
 
@@ -125,7 +131,8 @@ static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 		size_t size, enum dma_data_direction direction,
 		unsigned long attrs)
 {
-	__dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
 }
 
 static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
@@ -138,6 +145,9 @@ static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	if (direction == DMA_TO_DEVICE)
 		return;
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	for_each_sg(sg, sg, nhwentries, i) {
 		addr = sg_virt(sg);
 		if (addr)
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 140c99140649..906998bac957 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -141,6 +141,9 @@ or1k_map_page(struct device *dev, struct page *page,
 	unsigned long cl;
 	dma_addr_t addr = page_to_phys(page) + offset;
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return addr;
+
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		/* Flush the dcache for the requested range */
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 494ff6e8c88a..b6298a85e8ae 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -459,7 +459,9 @@ static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page,
 	void *addr = page_address(page) + offset;
 	BUG_ON(direction == DMA_NONE);
 
-	flush_kernel_dcache_range((unsigned long) addr, size);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		flush_kernel_dcache_range((unsigned long) addr, size);
+
 	return virt_to_phys(addr);
 }
 
@@ -469,8 +471,11 @@ static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 {
 	BUG_ON(direction == DMA_NONE);
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	if (direction == DMA_TO_DEVICE)
-	    return;
+		return;
 
 	/*
 	 * For PCI_DMA_FROMDEVICE this flush is not necessary for the
@@ -479,7 +484,6 @@ static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
 	 */
 
 	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), size);
-	return;
 }
 
 static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -496,6 +500,10 @@ static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 		sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
 		sg_dma_len(sg) = sg->length;
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		flush_kernel_dcache_range(vaddr, sg->length);
 	}
 	return nents;
@@ -510,14 +518,16 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 
 	BUG_ON(direction == DMA_NONE);
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	if (direction == DMA_TO_DEVICE)
-	    return;
+		return;
 
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
 	for_each_sg(sglist, sg, nents, i)
 		flush_kernel_vmap_range(sg_virt(sg), sg->length);
-	return;
 }
 
 static void pa11_dma_sync_single_for_cpu(struct device *dev,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index e64a6016fba7..6877e3fa95bb 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -203,6 +203,10 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = sg_phys(sg) + get_dma_offset(dev);
 		sg->dma_length = sg->length;
+
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+
 		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
 	}
 
@@ -235,7 +239,10 @@ static inline dma_addr_t dma_direct_map_page(struct device *dev,
 					     unsigned long attrs)
 {
 	BUG_ON(dir == DMA_NONE);
-	__dma_sync_page(page, offset, size, dir);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_sync_page(page, offset, size, dir);
+
 	return page_to_phys(page) + offset + get_dma_offset(dev);
 }
 
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 06254467e4dd..3a147122bc98 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -236,7 +236,6 @@ static int
 spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct spu_context *ctx	= vma->vm_file->private_data;
-	unsigned long address = (unsigned long)vmf->virtual_address;
 	unsigned long pfn, offset;
 
 	offset = vmf->pgoff << PAGE_SHIFT;
@@ -244,7 +243,7 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	pr_debug("spufs_mem_mmap_fault address=0x%lx, offset=0x%lx\n",
-			address, offset);
+			vmf->address, offset);
 
 	if (spu_acquire(ctx))
 		return VM_FAULT_NOPAGE;
@@ -256,7 +255,7 @@ spufs_mem_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
 		pfn = (ctx->spu->local_store_phys + offset) >> PAGE_SHIFT;
 	}
-	vm_insert_pfn(vma, address, pfn);
+	vm_insert_pfn(vma, vmf->address, pfn);
 
 	spu_release(ctx);
 
@@ -355,8 +354,7 @@ static int spufs_ps_fault(struct vm_area_struct *vma,
 		down_read(&current->mm->mmap_sem);
 	} else {
 		area = ctx->spu->problem_phys + ps_offs;
-		vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
-					(area + offset) >> PAGE_SHIFT);
+		vm_insert_pfn(vma, vmf->address, (area + offset) >> PAGE_SHIFT);
 		spu_context_trace(spufs_ps_fault__insert, ctx, ctx->spu);
 	}
 
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
index eadb669a7329..47fee3b6e29c 100644
--- a/arch/sh/kernel/dma-nommu.c
+++ b/arch/sh/kernel/dma-nommu.c
@@ -18,7 +18,9 @@ static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
 	dma_addr_t addr = page_to_phys(page) + offset;
 
 	WARN_ON(size == 0);
-	dma_cache_sync(dev, page_address(page) + offset, size, dir);
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		dma_cache_sync(dev, page_address(page) + offset, size, dir);
 
 	return addr;
 }
@@ -35,7 +37,8 @@ static int nommu_map_sg(struct device *dev, struct scatterlist *sg,
 	for_each_sg(sg, s, nents, i) {
 		BUG_ON(!sg_page(s));
 
-		dma_cache_sync(dev, sg_virt(s), s->length, dir);
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			dma_cache_sync(dev, sg_virt(s), s->length, dir);
 
 		s->dma_address = sg_phys(s);
 		s->dma_length = s->length;
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 852a3291db96..9df997995f6b 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -415,7 +415,7 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
 		ctx = (iopte_val(*base) & IOPTE_CONTEXT) >> 47UL;
 
 	/* Step 1: Kick data out of streaming buffers if necessary. */
-	if (strbuf->strbuf_enabled)
+	if (strbuf->strbuf_enabled && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		strbuf_flush(strbuf, iommu, bus_addr, ctx,
 			     npages, direction);
 
@@ -640,7 +640,7 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		base = iommu->page_table + entry;
 
 		dma_handle &= IO_PAGE_MASK;
-		if (strbuf->strbuf_enabled)
+		if (strbuf->strbuf_enabled && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 			strbuf_flush(strbuf, iommu, dma_handle, ctx,
 				     npages, direction);
 
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 2344103414d1..6ffaec44931a 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -527,7 +527,7 @@ static dma_addr_t pci32_map_page(struct device *dev, struct page *page,
 static void pci32_unmap_page(struct device *dev, dma_addr_t ba, size_t size,
 			     enum dma_data_direction dir, unsigned long attrs)
 {
-	if (dir != PCI_DMA_TODEVICE)
+	if (dir != PCI_DMA_TODEVICE && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
 		dma_make_coherent(ba, PAGE_ALIGN(size));
 }
 
@@ -572,7 +572,7 @@ static void pci32_unmap_sg(struct device *dev, struct scatterlist *sgl,
 	struct scatterlist *sg;
 	int n;
 
-	if (dir != PCI_DMA_TODEVICE) {
+	if (dir != PCI_DMA_TODEVICE && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
 		for_each_sg(sgl, sg, nents, n) {
 			dma_make_coherent(sg_phys(sg), PAGE_ALIGN(sg->length));
 		}
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index a9973bb4a1b2..95e73c63c99d 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -42,7 +42,7 @@ static int panic_on_timeout;
  */
 atomic_t nmi_active = ATOMIC_INIT(0);		/* oprofile uses this */
 EXPORT_SYMBOL(nmi_active);
-
+static int nmi_init_done;
 static unsigned int nmi_hz = HZ;
 static DEFINE_PER_CPU(short, wd_enabled);
 static int endflag __initdata;
@@ -153,6 +153,8 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
 
 void stop_nmi_watchdog(void *unused)
 {
+	if (!__this_cpu_read(wd_enabled))
+		return;
 	pcr_ops->write_pcr(0, pcr_ops->pcr_nmi_disable);
 	__this_cpu_write(wd_enabled, 0);
 	atomic_dec(&nmi_active);
@@ -207,6 +209,9 @@ error:
 
 void start_nmi_watchdog(void *unused)
 {
+	if (__this_cpu_read(wd_enabled))
+		return;
+
 	__this_cpu_write(wd_enabled, 1);
 	atomic_inc(&nmi_active);
 
@@ -259,6 +264,8 @@ int __init nmi_init(void)
 		}
 	}
 
+	nmi_init_done = 1;
+
 	return err;
 }
 
@@ -270,3 +277,38 @@ static int __init setup_nmi_watchdog(char *str)
 	return 0;
 }
 __setup("nmi_watchdog=", setup_nmi_watchdog);
+
+/*
+ * sparc specific NMI watchdog enable function.
+ * Enables watchdog if it is not enabled already.
+ */
+int watchdog_nmi_enable(unsigned int cpu)
+{
+	if (atomic_read(&nmi_active) == -1) {
+		pr_warn("NMI watchdog cannot be enabled or disabled\n");
+		return -1;
+	}
+
+	/*
+	 * watchdog thread could start even before nmi_init is called.
+	 * Just Return in that case. Let nmi_init finish the init
+	 * process first.
+	 */
+	if (!nmi_init_done)
+		return 0;
+
+	smp_call_function_single(cpu, start_nmi_watchdog, NULL, 1);
+
+	return 0;
+}
+/*
+ * sparc specific NMI watchdog disable function.
+ * Disables watchdog if it is not disabled already.
+ */
+void watchdog_nmi_disable(unsigned int cpu)
+{
+	if (atomic_read(&nmi_active) == -1)
+		pr_warn_once("NMI watchdog cannot be enabled or disabled\n");
+	else
+		smp_call_function_single(cpu, stop_nmi_watchdog, NULL, 1);
+}
diff --git a/arch/tile/kernel/pci-dma.c b/arch/tile/kernel/pci-dma.c
index 09bb774b39cd..24e0f8c21f2f 100644
--- a/arch/tile/kernel/pci-dma.c
+++ b/arch/tile/kernel/pci-dma.c
@@ -213,10 +213,12 @@ static int tile_dma_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	for_each_sg(sglist, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
-		__dma_prep_pa_range(sg->dma_address, sg->length, direction);
 #ifdef CONFIG_NEED_SG_DMA_LENGTH
 		sg->dma_length = sg->length;
 #endif
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
+		__dma_prep_pa_range(sg->dma_address, sg->length, direction);
 	}
 
 	return nents;
@@ -232,6 +234,8 @@ static void tile_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	BUG_ON(!valid_dma_direction(direction));
 	for_each_sg(sglist, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
+		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+			continue;
 		__dma_complete_pa_range(sg->dma_address, sg->length,
 					direction);
 	}
@@ -245,7 +249,8 @@ static dma_addr_t tile_dma_map_page(struct device *dev, struct page *page,
 	BUG_ON(!valid_dma_direction(direction));
 
 	BUG_ON(offset + size > PAGE_SIZE);
-	__dma_prep_page(page, offset, size, direction);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		__dma_prep_page(page, offset, size, direction);
 
 	return page_to_pa(page) + offset;
 }
@@ -256,6 +261,9 @@ static void tile_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
 {
 	BUG_ON(!valid_dma_direction(direction));
 
+	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
+		return;
+
 	__dma_complete_page(pfn_to_page(PFN_DOWN(dma_address)),
 			    dma_address & (PAGE_SIZE - 1), size, direction);
 }
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index e739002427ed..40121d14d34d 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -109,7 +109,7 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 		return VM_FAULT_SIGBUS;
 
 	if (sym_offset == image->sym_vvar_page) {
-		ret = vm_insert_pfn(vma, (unsigned long)vmf->virtual_address,
+		ret = vm_insert_pfn(vma, vmf->address,
 				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
 	} else if (sym_offset == image->sym_pvclock_page) {
 		struct pvclock_vsyscall_time_info *pvti =
@@ -117,7 +117,7 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
 			ret = vm_insert_pfn(
 				vma,
-				(unsigned long)vmf->virtual_address,
+				vmf->address,
 				__pa(pvti) >> PAGE_SHIFT);
 		}
 	}
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 8c1f218926d7..307b1f4543de 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -328,7 +328,7 @@ void machine_kexec(struct kimage *image)
 
 void arch_crash_save_vmcoreinfo(void)
 {
-	VMCOREINFO_SYMBOL(phys_base);
+	VMCOREINFO_NUMBER(phys_base);
 	VMCOREINFO_SYMBOL(init_level4_pgt);
 
 #ifdef CONFIG_NUMA
@@ -337,9 +337,7 @@ void arch_crash_save_vmcoreinfo(void)
 #endif
 	vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
 			      kaslr_offset());
-	VMCOREINFO_PAGE_OFFSET(PAGE_OFFSET);
-	VMCOREINFO_VMALLOC_START(VMALLOC_START);
-	VMCOREINFO_VMEMMAP_START(VMEMMAP_START);
+	VMCOREINFO_NUMBER(KERNEL_IMAGE_SIZE);
 }
 
 /* arch-dependent functionality related to kexec file-based syscall */
diff --git a/arch/xtensa/kernel/pci-dma.c b/arch/xtensa/kernel/pci-dma.c
index 1e68806d6695..6a16decf278f 100644
--- a/arch/xtensa/kernel/pci-dma.c
+++ b/arch/xtensa/kernel/pci-dma.c
@@ -189,7 +189,9 @@ static dma_addr_t xtensa_map_page(struct device *dev, struct page *page,
 {
 	dma_addr_t dma_handle = page_to_phys(page) + offset;
 
-	xtensa_sync_single_for_device(dev, dma_handle, size, dir);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		xtensa_sync_single_for_device(dev, dma_handle, size, dir);
+
 	return dma_handle;
 }
 
@@ -197,7 +199,8 @@ static void xtensa_unmap_page(struct device *dev, dma_addr_t dma_handle,
 			      size_t size, enum dma_data_direction dir,
 			      unsigned long attrs)
 {
-	xtensa_sync_single_for_cpu(dev, dma_handle, size, dir);
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		xtensa_sync_single_for_cpu(dev, dma_handle, size, dir);
 }
 
 static int xtensa_map_sg(struct device *dev, struct scatterlist *sg,