microblaze: Support DMA

Add DMA support for Microblaze. There are some part of this new feature:
1. Basic DMA support
2. Enable DMA debug option
3. Setup notifier

Ad 1. dma-mapping come from powerpc and x86 version and it is based on
generic dma-mapping-common.h

Ad 2. DMA support debug features which is used in generic file.
For more information please look at Documentation/DMA-API.txt

Ad 3. notifier is very important to setup dma_ops. Without this part
for example ll_temac driver failed because there are no setup dma operations.

Signed-off-by: Michal Simek <monstr@monstr.eu>
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index b008168..71ec041 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -14,6 +14,8 @@
 	select USB_ARCH_HAS_EHCI
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select HAVE_OPROFILE
+	select HAVE_DMA_ATTRS
+	select HAVE_DMA_API_DEBUG
 	select TRACING_SUPPORT
 
 config SWAP
@@ -76,9 +78,6 @@
 config PCI
 	def_bool n
 
-config NO_DMA
-	def_bool y
-
 config DTC
 	def_bool y
 
diff --git a/arch/microblaze/include/asm/device.h b/arch/microblaze/include/asm/device.h
index 78a0384..402b46e 100644
--- a/arch/microblaze/include/asm/device.h
+++ b/arch/microblaze/include/asm/device.h
@@ -14,6 +14,10 @@
 struct dev_archdata {
 	/* Optional pointer to an OF device node */
 	struct device_node	*of_node;
+
+	/* DMA operations on that device */
+	struct dma_map_ops	*dma_ops;
+	void                    *dma_data;
 };
 
 struct pdev_archdata {
diff --git a/arch/microblaze/include/asm/dma-mapping.h b/arch/microblaze/include/asm/dma-mapping.h
index d00e400..096fa96 100644
--- a/arch/microblaze/include/asm/dma-mapping.h
+++ b/arch/microblaze/include/asm/dma-mapping.h
@@ -1 +1,154 @@
-#include <asm-generic/dma-mapping-broken.h>
+/*
+ * Implements the generic device dma API for microblaze and the pci
+ *
+ * Copyright (C) 2009-2010 Michal Simek <monstr@monstr.eu>
+ * Copyright (C) 2009-2010 PetaLogix
+ *
+ * This file is subject to the terms and conditions of the GNU General
+ * Public License. See the file COPYING in the main directory of this
+ * archive for more details.
+ *
+ * This file is base on powerpc and x86 dma-mapping.h versions
+ * Copyright (C) 2004 IBM
+ */
+
+#ifndef _ASM_MICROBLAZE_DMA_MAPPING_H
+#define _ASM_MICROBLAZE_DMA_MAPPING_H
+
+/*
+ * See Documentation/PCI/PCI-DMA-mapping.txt and
+ * Documentation/DMA-API.txt for documentation.
+ */
+
+#include <linux/types.h>
+#include <linux/cache.h>
+#include <linux/mm.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-debug.h>
+#include <linux/dma-attrs.h>
+#include <asm/io.h>
+#include <asm-generic/dma-coherent.h>
+
+#define DMA_ERROR_CODE		(~(dma_addr_t)0x0)
+
+#define __dma_alloc_coherent(dev, gfp, size, handle)	NULL
+#define __dma_free_coherent(size, addr)		((void)0)
+#define __dma_sync(addr, size, rw)		((void)0)
+#define __dma_sync_page(pg, off, sz, rw)	((void)0)
+
+static inline unsigned long device_to_mask(struct device *dev)
+{
+	if (dev->dma_mask && *dev->dma_mask)
+		return *dev->dma_mask;
+	/* Assume devices without mask can take 32 bit addresses */
+	return 0xfffffffful;
+}
+
+extern struct dma_map_ops *dma_ops;
+
+/*
+ * Available generic sets of operations
+ */
+extern struct dma_map_ops dma_direct_ops;
+
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
+{
+	/* We don't handle the NULL dev case for ISA for now. We could
+	 * do it via an out of line call but it is not needed for now. The
+	 * only ISA DMA device we support is the floppy and we have a hack
+	 * in the floppy driver directly to get a device for us.
+	 */
+	if (unlikely(!dev) || !dev->archdata.dma_ops)
+		return NULL;
+
+	return dev->archdata.dma_ops;
+}
+
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+	dev->archdata.dma_ops = ops;
+}
+
+static inline int dma_supported(struct device *dev, u64 mask)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (unlikely(!ops))
+		return 0;
+	if (!ops->dma_supported)
+		return 1;
+	return ops->dma_supported(dev, mask);
+}
+
+#ifdef CONFIG_PCI
+/* We have our own implementation of pci_set_dma_mask() */
+#define HAVE_ARCH_PCI_SET_DMA_MASK
+
+#endif
+
+static inline int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	if (unlikely(ops == NULL))
+		return -EIO;
+	if (ops->set_dma_mask)
+		return ops->set_dma_mask(dev, dma_mask);
+	if (!dev->dma_mask || !dma_supported(dev, dma_mask))
+		return -EIO;
+	*dev->dma_mask = dma_mask;
+	return 0;
+}
+
+#include <asm-generic/dma-mapping-common.h>
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	if (ops->mapping_error)
+		return ops->mapping_error(dev, dma_addr);
+
+	return (dma_addr == DMA_ERROR_CODE);
+}
+
+#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_is_consistent(d, h)	(1)
+
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+					dma_addr_t *dma_handle, gfp_t flag)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+	void *memory;
+
+	BUG_ON(!ops);
+
+	memory = ops->alloc_coherent(dev, size, dma_handle, flag);
+
+	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
+	return memory;
+}
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *cpu_addr, dma_addr_t dma_handle)
+{
+	struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!ops);
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free_coherent(dev, size, cpu_addr, dma_handle);
+}
+
+static inline int dma_get_cache_alignment(void)
+{
+	return L1_CACHE_BYTES;
+}
+
+static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction direction)
+{
+	BUG_ON(direction == DMA_NONE);
+	__dma_sync(vaddr, size, (int)direction);
+}
+
+#endif	/* _ASM_MICROBLAZE_DMA_MAPPING_H */
diff --git a/arch/microblaze/include/asm/io.h b/arch/microblaze/include/asm/io.h
index 267c7c7..9ac409a 100644
--- a/arch/microblaze/include/asm/io.h
+++ b/arch/microblaze/include/asm/io.h
@@ -16,6 +16,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>          /* Get struct page {...} */
 
+#define PCI_DRAM_OFFSET 0
 
 #define IO_SPACE_LIMIT (0xFFFFFFFF)
 
diff --git a/arch/microblaze/kernel/Makefile b/arch/microblaze/kernel/Makefile
index b07594e..e51bc15 100644
--- a/arch/microblaze/kernel/Makefile
+++ b/arch/microblaze/kernel/Makefile
@@ -14,7 +14,7 @@
 
 extra-y := head.o vmlinux.lds
 
-obj-y += exceptions.o \
+obj-y += dma.o exceptions.o \
 	hw_exception_handler.o init_task.o intc.o irq.o of_device.o \
 	of_platform.o process.o prom.o prom_parse.o ptrace.o \
 	setup.o signal.o sys_microblaze.o timer.o traps.o reset.o
diff --git a/arch/microblaze/kernel/dma.c b/arch/microblaze/kernel/dma.c
new file mode 100644
index 0000000..300fea4
--- /dev/null
+++ b/arch/microblaze/kernel/dma.c
@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2009-2010 PetaLogix
+ * Copyright (C) 2006 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * Provide default implementations of the DMA mapping callbacks for
+ * directly mapped busses.
+ */
+
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/dma-debug.h>
+#include <asm/bug.h>
+
+/*
+ * Generic direct DMA implementation
+ *
+ * This implementation supports a per-device offset that can be applied if
+ * the address at which memory is visible to devices is not 0. Platform code
+ * can set archdata.dma_data to an unsigned long holding the offset. By
+ * default the offset is PCI_DRAM_OFFSET.
+ */
+
+static unsigned long get_dma_direct_offset(struct device *dev)
+{
+	if (dev)
+		return (unsigned long)dev->archdata.dma_data;
+
+	return PCI_DRAM_OFFSET; /* FIXME Not sure if is correct */
+}
+
+void *dma_direct_alloc_coherent(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t flag)
+{
+	void *ret;
+	struct page *page;
+	int node = dev_to_node(dev);
+
+	/* ignore region specifiers */
+	flag  &= ~(__GFP_HIGHMEM);
+
+	page = alloc_pages_node(node, flag, get_order(size));
+	if (page == NULL)
+		return NULL;
+	ret = page_address(page);
+	memset(ret, 0, size);
+	*dma_handle = virt_to_phys(ret) + get_dma_direct_offset(dev);
+
+	return ret;
+}
+
+void dma_direct_free_coherent(struct device *dev, size_t size,
+			      void *vaddr, dma_addr_t dma_handle)
+{
+	free_pages((unsigned long)vaddr, get_order(size));
+}
+
+static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
+			     int nents, enum dma_data_direction direction,
+			     struct dma_attrs *attrs)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i) {
+		sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev);
+		sg->dma_length = sg->length;
+		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+	}
+
+	return nents;
+}
+
+static void dma_direct_unmap_sg(struct device *dev, struct scatterlist *sg,
+				int nents, enum dma_data_direction direction,
+				struct dma_attrs *attrs)
+{
+}
+
+static int dma_direct_dma_supported(struct device *dev, u64 mask)
+{
+	return 1;
+}
+
+static inline dma_addr_t dma_direct_map_page(struct device *dev,
+					     struct page *page,
+					     unsigned long offset,
+					     size_t size,
+					     enum dma_data_direction dir,
+					     struct dma_attrs *attrs)
+{
+	BUG_ON(dir == DMA_NONE);
+	__dma_sync_page(page, offset, size, dir);
+	return page_to_phys(page) + offset + get_dma_direct_offset(dev);
+}
+
+static inline void dma_direct_unmap_page(struct device *dev,
+					 dma_addr_t dma_address,
+					 size_t size,
+					 enum dma_data_direction direction,
+					 struct dma_attrs *attrs)
+{
+}
+
+struct dma_map_ops dma_direct_ops = {
+	.alloc_coherent	= dma_direct_alloc_coherent,
+	.free_coherent	= dma_direct_free_coherent,
+	.map_sg		= dma_direct_map_sg,
+	.unmap_sg	= dma_direct_unmap_sg,
+	.dma_supported	= dma_direct_dma_supported,
+	.map_page	= dma_direct_map_page,
+	.unmap_page	= dma_direct_unmap_page,
+};
+EXPORT_SYMBOL(dma_direct_ops);
+
+/* Number of entries preallocated for DMA-API debugging */
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+
+static int __init dma_init(void)
+{
+       dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
+
+       return 0;
+}
+fs_initcall(dma_init);
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index bb8c4b9..bc325ac 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -23,6 +23,8 @@
 #include <linux/bug.h>
 #include <linux/param.h>
 #include <linux/cache.h>
+#include <linux/of_platform.h>
+#include <linux/dma-mapping.h>
 #include <asm/cacheflush.h>
 #include <asm/entry.h>
 #include <asm/cpuinfo.h>
@@ -188,3 +190,37 @@
 }
 arch_initcall(microblaze_debugfs_init);
 #endif
+
+static int dflt_bus_notify(struct notifier_block *nb,
+				unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	/* We are only intereted in device addition */
+	if (action != BUS_NOTIFY_ADD_DEVICE)
+		return 0;
+
+	set_dma_ops(dev, &dma_direct_ops);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block dflt_plat_bus_notifier = {
+	.notifier_call = dflt_bus_notify,
+	.priority = INT_MAX,
+};
+
+static struct notifier_block dflt_of_bus_notifier = {
+	.notifier_call = dflt_bus_notify,
+	.priority = INT_MAX,
+};
+
+static int __init setup_bus_notifier(void)
+{
+	bus_register_notifier(&platform_bus_type, &dflt_plat_bus_notifier);
+	bus_register_notifier(&of_platform_bus_type, &dflt_of_bus_notifier);
+
+	return 0;
+}
+
+arch_initcall(setup_bus_notifier);