[mm PATCH v3 00/23] Add support for DMA writable pages being writable by the network stack

@@ -133,7 +133,10 @@ 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);
 }
 

--

@@ -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,

--

@@ -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);
 	}
 

--

@@ -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;
 }

--

@@ -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);
 	}

@@ -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;
 }
 

@@ -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;
 }
 

--

@@ -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;

@@ -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);

--

@@ -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)

--

@@ -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 */

--

@@ -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

--

@@ -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);
 	}
 }

--

@@ -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;

--

@@ -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);
 }
 

--

@@ -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,

--

@@ -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);
 

@@ -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));
 		}

--

@@ -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,

--

@@ -237,29 +237,33 @@ static inline void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *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)
+static inline dma_addr_t dma_map_page_attrs(struct device *dev,
+					    struct page *page,
+					    size_t offset, size_t size,
+					    enum dma_data_direction dir,
+					    unsigned long attrs)
 {
 	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, 0);
+	addr = ops->map_page(dev, page, offset, size, dir, attrs);
 	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)
+static inline void dma_unmap_page_attrs(struct device *dev,
+					dma_addr_t addr, size_t size,
+					enum dma_data_direction dir,
+					unsigned long attrs)
 {
 	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, 0);
+		ops->unmap_page(dev, addr, size, dir, attrs);
 	debug_dma_unmap_page(dev, addr, size, dir, false);
 }
 

@@ -344,6 +348,8 @@ dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 #define dma_unmap_single(d, a, s, r) dma_unmap_single_attrs(d, a, s, r, 0)
 #define dma_map_sg(d, s, n, r) dma_map_sg_attrs(d, s, n, r, 0)
 #define dma_unmap_sg(d, s, n, r) dma_unmap_sg_attrs(d, s, n, r, 0)
+#define dma_map_page(d, p, o, s, r) dma_map_page_attrs(d, p, o, s, r, 0)
+#define dma_unmap_page(d, a, s, r) dma_unmap_page_attrs(d, a, s, r, 0)
 
 extern int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
 			   void *cpu_addr, dma_addr_t dma_addr, size_t size);

@@ -506,6 +506,8 @@ extern void free_hot_cold_page(struct page *page, bool cold);
 extern void free_hot_cold_page_list(struct list_head *list, bool cold);
 
 struct page_frag_cache;
+extern void __page_frag_drain(struct page *page, unsigned int order,
+			      unsigned int count);
 extern void *__alloc_page_frag(struct page_frag_cache *nc,
 			       unsigned int fragsz, gfp_t gfp_mask);
 extern void __free_page_frag(void *addr);

@@ -3912,6 +3912,20 @@ static struct page *__page_frag_refill(struct page_frag_cache *nc,
 	return page;
 }
 
+void __page_frag_drain(struct page *page, unsigned int order,
+		       unsigned int count)
+{
+	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+
+	if (page_ref_sub_and_test(page, count)) {
+		if (order == 0)
+			free_hot_cold_page(page, false);
+		else
+			__free_pages_ok(page, order);
+	}
+}
+EXPORT_SYMBOL(__page_frag_drain);
+
 void *__alloc_page_frag(struct page_frag_cache *nc,
 			unsigned int fragsz, gfp_t gfp_mask)
 {

--

@@ -3922,10 +3922,21 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 		if (!buffer_info->page)
 			continue;
 
-		dma_unmap_page(rx_ring->dev,
-			       buffer_info->dma,
-			       PAGE_SIZE,
-			       DMA_FROM_DEVICE);
+		/* Invalidate cache lines that may have been written to by
+		 * device so that we avoid corrupting memory.
+		 */
+		dma_sync_single_range_for_cpu(rx_ring->dev,
+					      buffer_info->dma,
+					      buffer_info->page_offset,
+					      IGB_RX_BUFSZ,
+					      DMA_FROM_DEVICE);
+
+		/* free resources associated with mapping */
+		dma_unmap_page_attrs(rx_ring->dev,
+				     buffer_info->dma,
+				     PAGE_SIZE,
+				     DMA_FROM_DEVICE,
+				     DMA_ATTR_SKIP_CPU_SYNC);
 		__free_page(buffer_info->page);
 
 		buffer_info->page = NULL;

@@ -6791,12 +6802,6 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
 
 	/* transfer page from old buffer to new buffer */
 	*new_buff = *old_buff;
-
-	/* sync the buffer for use by the device */
-	dma_sync_single_range_for_device(rx_ring->dev, old_buff->dma,
-					 old_buff->page_offset,
-					 IGB_RX_BUFSZ,
-					 DMA_FROM_DEVICE);
 }
 
 static inline bool igb_page_is_reserved(struct page *page)

@@ -6917,6 +6922,13 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 	page = rx_buffer->page;
 	prefetchw(page);
 
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      size,
+				      DMA_FROM_DEVICE);
+
 	if (likely(!skb)) {
 		void *page_addr = page_address(page) +
 				  rx_buffer->page_offset;

@@ -6941,21 +6953,15 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 		prefetchw(skb->data);
 	}
 
-	/* we are reusing so sync this buffer for CPU use */
-	dma_sync_single_range_for_cpu(rx_ring->dev,
-				      rx_buffer->dma,
-				      rx_buffer->page_offset,
-				      size,
-				      DMA_FROM_DEVICE);
-
 	/* pull page into skb */
 	if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) {
 		/* hand second half of page back to the ring */
 		igb_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
 		/* we are not reusing the buffer so unmap it */
-		dma_unmap_page(rx_ring->dev, rx_buffer->dma,
-			       PAGE_SIZE, DMA_FROM_DEVICE);
+		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
+				     PAGE_SIZE, DMA_FROM_DEVICE,
+				     DMA_ATTR_SKIP_CPU_SYNC);
 	}
 
 	/* clear contents of rx_buffer */

@@ -7213,7 +7219,8 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 	}
 
 	/* map page for use */
-	dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE,
+				 DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
 
 	/* if mapping failed free memory back to system since
 	 * there isn't much point in holding memory we can't use

@@ -7254,6 +7261,12 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 		if (!igb_alloc_mapped_page(rx_ring, bi))
 			break;
 
+		/* sync the buffer for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, bi->dma,
+						 bi->page_offset,
+						 IGB_RX_BUFSZ,
+						 DMA_FROM_DEVICE);
+
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */

--

@@ -210,7 +210,12 @@ struct igb_tx_buffer {
 struct igb_rx_buffer {
 	dma_addr_t dma;
 	struct page *page;
-	unsigned int page_offset;
+#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
+	__u32 page_offset;
+#else
+	__u16 page_offset;
+#endif
+	__u16 pagecnt_bias;
 };
 
 struct igb_tx_queue_stats {

@@ -3937,7 +3937,8 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring)
 				     PAGE_SIZE,
 				     DMA_FROM_DEVICE,
 				     DMA_ATTR_SKIP_CPU_SYNC);
-		__free_page(buffer_info->page);
+		__page_frag_drain(buffer_info->page, 0,
+				  buffer_info->pagecnt_bias);
 
 		buffer_info->page = NULL;
 	}

@@ -6813,13 +6814,15 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 				  struct page *page,
 				  unsigned int truesize)
 {
+	unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--;
+
 	/* avoid re-using remote pages */
 	if (unlikely(igb_page_is_reserved(page)))
 		return false;
 
 #if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
+	if (unlikely(page_ref_count(page) != pagecnt_bias))
 		return false;
 
 	/* flip page offset to other buffer */

@@ -6832,10 +6835,14 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 		return false;
 #endif
 
-	/* Even if we own the page, we are not allowed to use atomic_set()
-	 * This would break get_page_unless_zero() users.
+	/* If we have drained the page fragment pool we need to update
+	 * the pagecnt_bias and page count so that we fully restock the
+	 * number of references the driver holds.
 	 */
-	page_ref_inc(page);
+	if (unlikely(pagecnt_bias == 1)) {
+		page_ref_add(page, USHRT_MAX);
+		rx_buffer->pagecnt_bias = USHRT_MAX;
+	}
 
 	return true;
 }

@@ -6887,7 +6894,6 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 			return true;
 
 		/* this page cannot be reused so discard it */
-		__free_page(page);
 		return false;
 	}
 

@@ -6958,10 +6964,13 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 		/* hand second half of page back to the ring */
 		igb_reuse_rx_page(rx_ring, rx_buffer);
 	} else {
-		/* we are not reusing the buffer so unmap it */
+		/* We are not reusing the buffer so unmap it and free
+		 * any references we are holding to it
+		 */
 		dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma,
 				     PAGE_SIZE, DMA_FROM_DEVICE,
 				     DMA_ATTR_SKIP_CPU_SYNC);
+		__page_frag_drain(page, 0, rx_buffer->pagecnt_bias);
 	}
 
 	/* clear contents of rx_buffer */

@@ -7235,6 +7244,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 	bi->dma = dma;
 	bi->page = page;
 	bi->page_offset = 0;
+	bi->pagecnt_bias = 1;
 
 	return true;
 }

@@ -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);
 }

--

@@ -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,

--

@@ -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;
 }
 

--