Initial commit; kernel source import

drivers/dma/sh/Kconfig

@@ -0,0 +1,24 @@
+#
+# DMA engine configuration for sh
+#
+
+config SH_DMAE_BASE
+	bool "Renesas SuperH DMA Engine support"
+	depends on (SUPERH && SH_DMA) || (ARM && ARCH_SHMOBILE)
+	depends on !SH_DMA_API
+	default y
+	select DMA_ENGINE
+	help
+	  Enable support for the Renesas SuperH DMA controllers.
+
+config SH_DMAE
+	tristate "Renesas SuperH DMAC support"
+	depends on SH_DMAE_BASE
+	help
+	  Enable support for the Renesas SuperH DMA controllers.
+
+config SUDMAC
+	tristate "Renesas SUDMAC support"
+	depends on SH_DMAE_BASE
+	help
+	  Enable support for the Renesas SUDMAC controllers.

drivers/dma/sh/Makefile

@@ -0,0 +1,3 @@
+obj-$(CONFIG_SH_DMAE_BASE) += shdma-base.o
+obj-$(CONFIG_SH_DMAE) += shdma.o
+obj-$(CONFIG_SUDMAC) += sudmac.o

drivers/dma/sh/shdma-base.c

@@ -0,0 +1,940 @@
+/*
+ * Dmaengine driver base library for DMA controllers, found on SH-based SoCs
+ *
+ * extracted from shdma.c
+ *
+ * Copyright (C) 2011-2012 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
+ * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
+ * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/shdma-base.h>
+#include <linux/dmaengine.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include "../dmaengine.h"
+
+/* DMA descriptor control */
+enum shdma_desc_status {
+	DESC_IDLE,
+	DESC_PREPARED,
+	DESC_SUBMITTED,
+	DESC_COMPLETED,	/* completed, have to call callback */
+	DESC_WAITING,	/* callback called, waiting for ack / re-submit */
+};
+
+#define NR_DESCS_PER_CHANNEL 32
+
+#define to_shdma_chan(c) container_of(c, struct shdma_chan, dma_chan)
+#define to_shdma_dev(d) container_of(d, struct shdma_dev, dma_dev)
+
+/*
+ * For slave DMA we assume, that there is a finite number of DMA slaves in the
+ * system, and that each such slave can only use a finite number of channels.
+ * We use slave channel IDs to make sure, that no such slave channel ID is
+ * allocated more than once.
+ */
+static unsigned int slave_num = 256;
+module_param(slave_num, uint, 0444);
+
+/* A bitmask with slave_num bits */
+static unsigned long *shdma_slave_used;
+
+/* Called under spin_lock_irq(&schan->chan_lock") */
+static void shdma_chan_xfer_ld_queue(struct shdma_chan *schan)
+{
+	struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device);
+	const struct shdma_ops *ops = sdev->ops;
+	struct shdma_desc *sdesc;
+
+	/* DMA work check */
+	if (ops->channel_busy(schan))
+		return;
+
+	/* Find the first not transferred descriptor */
+	list_for_each_entry(sdesc, &schan->ld_queue, node)
+		if (sdesc->mark == DESC_SUBMITTED) {
+			ops->start_xfer(schan, sdesc);
+			break;
+		}
+}
+
+static dma_cookie_t shdma_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct shdma_desc *chunk, *c, *desc =
+		container_of(tx, struct shdma_desc, async_tx),
+		*last = desc;
+	struct shdma_chan *schan = to_shdma_chan(tx->chan);
+	dma_async_tx_callback callback = tx->callback;
+	dma_cookie_t cookie;
+	bool power_up;
+
+	spin_lock_irq(&schan->chan_lock);
+
+	power_up = list_empty(&schan->ld_queue);
+
+	cookie = dma_cookie_assign(tx);
+
+	/* Mark all chunks of this descriptor as submitted, move to the queue */
+	list_for_each_entry_safe(chunk, c, desc->node.prev, node) {
+		/*
+		 * All chunks are on the global ld_free, so, we have to find
+		 * the end of the chain ourselves
+		 */
+		if (chunk != desc && (chunk->mark == DESC_IDLE ||
+				      chunk->async_tx.cookie > 0 ||
+				      chunk->async_tx.cookie == -EBUSY ||
+				      &chunk->node == &schan->ld_free))
+			break;
+		chunk->mark = DESC_SUBMITTED;
+		/* Callback goes to the last chunk */
+		chunk->async_tx.callback = NULL;
+		chunk->cookie = cookie;
+		list_move_tail(&chunk->node, &schan->ld_queue);
+		last = chunk;
+
+		dev_dbg(schan->dev, "submit #%d@%p on %d\n",
+			tx->cookie, &last->async_tx, schan->id);
+	}
+
+	last->async_tx.callback = callback;
+	last->async_tx.callback_param = tx->callback_param;
+
+	if (power_up) {
+		int ret;
+		schan->pm_state = SHDMA_PM_BUSY;
+
+		ret = pm_runtime_get(schan->dev);
+
+		spin_unlock_irq(&schan->chan_lock);
+		if (ret < 0)
+			dev_err(schan->dev, "%s(): GET = %d\n", __func__, ret);
+
+		pm_runtime_barrier(schan->dev);
+
+		spin_lock_irq(&schan->chan_lock);
+
+		/* Have we been reset, while waiting? */
+		if (schan->pm_state != SHDMA_PM_ESTABLISHED) {
+			struct shdma_dev *sdev =
+				to_shdma_dev(schan->dma_chan.device);
+			const struct shdma_ops *ops = sdev->ops;
+			dev_dbg(schan->dev, "Bring up channel %d\n",
+				schan->id);
+			/*
+			 * TODO: .xfer_setup() might fail on some platforms.
+			 * Make it int then, on error remove chunks from the
+			 * queue again
+			 */
+			ops->setup_xfer(schan, schan->slave_id);
+
+			if (schan->pm_state == SHDMA_PM_PENDING)
+				shdma_chan_xfer_ld_queue(schan);
+			schan->pm_state = SHDMA_PM_ESTABLISHED;
+		}
+	} else {
+		/*
+		 * Tell .device_issue_pending() not to run the queue, interrupts
+		 * will do it anyway
+		 */
+		schan->pm_state = SHDMA_PM_PENDING;
+	}
+
+	spin_unlock_irq(&schan->chan_lock);
+
+	return cookie;
+}
+
+/* Called with desc_lock held */
+static struct shdma_desc *shdma_get_desc(struct shdma_chan *schan)
+{
+	struct shdma_desc *sdesc;
+
+	list_for_each_entry(sdesc, &schan->ld_free, node)
+		if (sdesc->mark != DESC_PREPARED) {
+			BUG_ON(sdesc->mark != DESC_IDLE);
+			list_del(&sdesc->node);
+			return sdesc;
+		}
+
+	return NULL;
+}
+
+static int shdma_setup_slave(struct shdma_chan *schan, int slave_id)
+{
+	struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device);
+	const struct shdma_ops *ops = sdev->ops;
+	int ret;
+
+	if (slave_id < 0 || slave_id >= slave_num)
+		return -EINVAL;
+
+	if (test_and_set_bit(slave_id, shdma_slave_used))
+		return -EBUSY;
+
+	ret = ops->set_slave(schan, slave_id, false);
+	if (ret < 0) {
+		clear_bit(slave_id, shdma_slave_used);
+		return ret;
+	}
+
+	schan->slave_id = slave_id;
+
+	return 0;
+}
+
+/*
+ * This is the standard shdma filter function to be used as a replacement to the
+ * "old" method, using the .private pointer. If for some reason you allocate a
+ * channel without slave data, use something like ERR_PTR(-EINVAL) as a filter
+ * parameter. If this filter is used, the slave driver, after calling
+ * dma_request_channel(), will also have to call dmaengine_slave_config() with
+ * .slave_id, .direction, and either .src_addr or .dst_addr set.
+ * NOTE: this filter doesn't support multiple DMAC drivers with the DMA_SLAVE
+ * capability! If this becomes a requirement, hardware glue drivers, using this
+ * services would have to provide their own filters, which first would check
+ * the device driver, similar to how other DMAC drivers, e.g., sa11x0-dma.c, do
+ * this, and only then, in case of a match, call this common filter.
+ */
+bool shdma_chan_filter(struct dma_chan *chan, void *arg)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+	struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device);
+	const struct shdma_ops *ops = sdev->ops;
+	int slave_id = (int)arg;
+	int ret;
+
+	if (slave_id < 0)
+		/* No slave requested - arbitrary channel */
+		return true;
+
+	if (slave_id >= slave_num)
+		return false;
+
+	ret = ops->set_slave(schan, slave_id, true);
+	if (ret < 0)
+		return false;
+
+	return true;
+}
+EXPORT_SYMBOL(shdma_chan_filter);
+
+static int shdma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+	struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device);
+	const struct shdma_ops *ops = sdev->ops;
+	struct shdma_desc *desc;
+	struct shdma_slave *slave = chan->private;
+	int ret, i;
+
+	/*
+	 * This relies on the guarantee from dmaengine that alloc_chan_resources
+	 * never runs concurrently with itself or free_chan_resources.
+	 */
+	if (slave) {
+		/* Legacy mode: .private is set in filter */
+		ret = shdma_setup_slave(schan, slave->slave_id);
+		if (ret < 0)
+			goto esetslave;
+	} else {
+		schan->slave_id = -EINVAL;
+	}
+
+	schan->desc = kcalloc(NR_DESCS_PER_CHANNEL,
+			      sdev->desc_size, GFP_KERNEL);
+	if (!schan->desc) {
+		ret = -ENOMEM;
+		goto edescalloc;
+	}
+	schan->desc_num = NR_DESCS_PER_CHANNEL;
+
+	for (i = 0; i < NR_DESCS_PER_CHANNEL; i++) {
+		desc = ops->embedded_desc(schan->desc, i);
+		dma_async_tx_descriptor_init(&desc->async_tx,
+					     &schan->dma_chan);
+		desc->async_tx.tx_submit = shdma_tx_submit;
+		desc->mark = DESC_IDLE;
+
+		list_add(&desc->node, &schan->ld_free);
+	}
+
+	return NR_DESCS_PER_CHANNEL;
+
+edescalloc:
+	if (slave)
+esetslave:
+		clear_bit(slave->slave_id, shdma_slave_used);
+	chan->private = NULL;
+	return ret;
+}
+
+static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
+{
+	struct shdma_desc *desc, *_desc;
+	/* Is the "exposed" head of a chain acked? */
+	bool head_acked = false;
+	dma_cookie_t cookie = 0;
+	dma_async_tx_callback callback = NULL;
+	void *param = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&schan->chan_lock, flags);
+	list_for_each_entry_safe(desc, _desc, &schan->ld_queue, node) {
+		struct dma_async_tx_descriptor *tx = &desc->async_tx;
+
+		BUG_ON(tx->cookie > 0 && tx->cookie != desc->cookie);
+		BUG_ON(desc->mark != DESC_SUBMITTED &&
+		       desc->mark != DESC_COMPLETED &&
+		       desc->mark != DESC_WAITING);
+
+		/*
+		 * queue is ordered, and we use this loop to (1) clean up all
+		 * completed descriptors, and to (2) update descriptor flags of
+		 * any chunks in a (partially) completed chain
+		 */
+		if (!all && desc->mark == DESC_SUBMITTED &&
+		    desc->cookie != cookie)
+			break;
+
+		if (tx->cookie > 0)
+			cookie = tx->cookie;
+
+		if (desc->mark == DESC_COMPLETED && desc->chunks == 1) {
+			if (schan->dma_chan.completed_cookie != desc->cookie - 1)
+				dev_dbg(schan->dev,
+					"Completing cookie %d, expected %d\n",
+					desc->cookie,
+					schan->dma_chan.completed_cookie + 1);
+			schan->dma_chan.completed_cookie = desc->cookie;
+		}
+
+		/* Call callback on the last chunk */
+		if (desc->mark == DESC_COMPLETED && tx->callback) {
+			desc->mark = DESC_WAITING;
+			callback = tx->callback;
+			param = tx->callback_param;
+			dev_dbg(schan->dev, "descriptor #%d@%p on %d callback\n",
+				tx->cookie, tx, schan->id);
+			BUG_ON(desc->chunks != 1);
+			break;
+		}
+
+		if (tx->cookie > 0 || tx->cookie == -EBUSY) {
+			if (desc->mark == DESC_COMPLETED) {
+				BUG_ON(tx->cookie < 0);
+				desc->mark = DESC_WAITING;
+			}
+			head_acked = async_tx_test_ack(tx);
+		} else {
+			switch (desc->mark) {
+			case DESC_COMPLETED:
+				desc->mark = DESC_WAITING;
+				/* Fall through */
+			case DESC_WAITING:
+				if (head_acked)
+					async_tx_ack(&desc->async_tx);
+			}
+		}
+
+		dev_dbg(schan->dev, "descriptor %p #%d completed.\n",
+			tx, tx->cookie);
+
+		if (((desc->mark == DESC_COMPLETED ||
+		      desc->mark == DESC_WAITING) &&
+		     async_tx_test_ack(&desc->async_tx)) || all) {
+			/* Remove from ld_queue list */
+			desc->mark = DESC_IDLE;
+
+			list_move(&desc->node, &schan->ld_free);
+
+			if (list_empty(&schan->ld_queue)) {
+				dev_dbg(schan->dev, "Bring down channel %d\n", schan->id);
+				pm_runtime_put(schan->dev);
+				schan->pm_state = SHDMA_PM_ESTABLISHED;
+			}
+		}
+	}
+
+	if (all && !callback)
+		/*
+		 * Terminating and the loop completed normally: forgive
+		 * uncompleted cookies
+		 */
+		schan->dma_chan.completed_cookie = schan->dma_chan.cookie;
+
+	spin_unlock_irqrestore(&schan->chan_lock, flags);
+
+	if (callback)
+		callback(param);
+
+	return callback;
+}
+
+/*
+ * shdma_chan_ld_cleanup - Clean up link descriptors
+ *
+ * Clean up the ld_queue of DMA channel.
+ */
+static void shdma_chan_ld_cleanup(struct shdma_chan *schan, bool all)
+{
+	while (__ld_cleanup(schan, all))
+		;
+}
+
+/*
+ * shdma_free_chan_resources - Free all resources of the channel.
+ */
+static void shdma_free_chan_resources(struct dma_chan *chan)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+	struct shdma_dev *sdev = to_shdma_dev(chan->device);
+	const struct shdma_ops *ops = sdev->ops;
+	LIST_HEAD(list);
+
+	/* Protect against ISR */
+	spin_lock_irq(&schan->chan_lock);
+	ops->halt_channel(schan);
+	spin_unlock_irq(&schan->chan_lock);
+
+	/* Now no new interrupts will occur */
+
+	/* Prepared and not submitted descriptors can still be on the queue */
+	if (!list_empty(&schan->ld_queue))
+		shdma_chan_ld_cleanup(schan, true);
+
+	if (schan->slave_id >= 0) {
+		/* The caller is holding dma_list_mutex */
+		clear_bit(schan->slave_id, shdma_slave_used);
+		chan->private = NULL;
+	}
+
+	spin_lock_irq(&schan->chan_lock);
+
+	list_splice_init(&schan->ld_free, &list);
+	schan->desc_num = 0;
+
+	spin_unlock_irq(&schan->chan_lock);
+
+	kfree(schan->desc);
+}
+
+/**
+ * shdma_add_desc - get, set up and return one transfer descriptor
+ * @schan:	DMA channel
+ * @flags:	DMA transfer flags
+ * @dst:	destination DMA address, incremented when direction equals
+ *		DMA_DEV_TO_MEM or DMA_MEM_TO_MEM
+ * @src:	source DMA address, incremented when direction equals
+ *		DMA_MEM_TO_DEV or DMA_MEM_TO_MEM
+ * @len:	DMA transfer length
+ * @first:	if NULL, set to the current descriptor and cookie set to -EBUSY
+ * @direction:	needed for slave DMA to decide which address to keep constant,
+ *		equals DMA_MEM_TO_MEM for MEMCPY
+ * Returns 0 or an error
+ * Locks: called with desc_lock held
+ */
+static struct shdma_desc *shdma_add_desc(struct shdma_chan *schan,
+	unsigned long flags, dma_addr_t *dst, dma_addr_t *src, size_t *len,
+	struct shdma_desc **first, enum dma_transfer_direction direction)
+{
+	struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device);
+	const struct shdma_ops *ops = sdev->ops;
+	struct shdma_desc *new;
+	size_t copy_size = *len;
+
+	if (!copy_size)
+		return NULL;
+
+	/* Allocate the link descriptor from the free list */
+	new = shdma_get_desc(schan);
+	if (!new) {
+		dev_err(schan->dev, "No free link descriptor available\n");
+		return NULL;
+	}
+
+	ops->desc_setup(schan, new, *src, *dst, &copy_size);
+
+	if (!*first) {
+		/* First desc */
+		new->async_tx.cookie = -EBUSY;
+		*first = new;
+	} else {
+		/* Other desc - invisible to the user */
+		new->async_tx.cookie = -EINVAL;
+	}
+
+	dev_dbg(schan->dev,
+		"chaining (%u/%u)@%x -> %x with %p, cookie %d\n",
+		copy_size, *len, *src, *dst, &new->async_tx,
+		new->async_tx.cookie);
+
+	new->mark = DESC_PREPARED;
+	new->async_tx.flags = flags;
+	new->direction = direction;
+	new->partial = 0;
+
+	*len -= copy_size;
+	if (direction == DMA_MEM_TO_MEM || direction == DMA_MEM_TO_DEV)
+		*src += copy_size;
+	if (direction == DMA_MEM_TO_MEM || direction == DMA_DEV_TO_MEM)
+		*dst += copy_size;
+
+	return new;
+}
+
+/*
+ * shdma_prep_sg - prepare transfer descriptors from an SG list
+ *
+ * Common routine for public (MEMCPY) and slave DMA. The MEMCPY case is also
+ * converted to scatter-gather to guarantee consistent locking and a correct
+ * list manipulation. For slave DMA direction carries the usual meaning, and,
+ * logically, the SG list is RAM and the addr variable contains slave address,
+ * e.g., the FIFO I/O register. For MEMCPY direction equals DMA_MEM_TO_MEM
+ * and the SG list contains only one element and points at the source buffer.
+ */
+static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan,
+	struct scatterlist *sgl, unsigned int sg_len, dma_addr_t *addr,
+	enum dma_transfer_direction direction, unsigned long flags)
+{
+	struct scatterlist *sg;
+	struct shdma_desc *first = NULL, *new = NULL /* compiler... */;
+	LIST_HEAD(tx_list);
+	int chunks = 0;
+	unsigned long irq_flags;
+	int i;
+
+	for_each_sg(sgl, sg, sg_len, i)
+		chunks += DIV_ROUND_UP(sg_dma_len(sg), schan->max_xfer_len);
+
+	/* Have to lock the whole loop to protect against concurrent release */
+	spin_lock_irqsave(&schan->chan_lock, irq_flags);
+
+	/*
+	 * Chaining:
+	 * first descriptor is what user is dealing with in all API calls, its
+	 *	cookie is at first set to -EBUSY, at tx-submit to a positive
+	 *	number
+	 * if more than one chunk is needed further chunks have cookie = -EINVAL
+	 * the last chunk, if not equal to the first, has cookie = -ENOSPC
+	 * all chunks are linked onto the tx_list head with their .node heads
+	 *	only during this function, then they are immediately spliced
+	 *	back onto the free list in form of a chain
+	 */
+	for_each_sg(sgl, sg, sg_len, i) {
+		dma_addr_t sg_addr = sg_dma_address(sg);
+		size_t len = sg_dma_len(sg);
+
+		if (!len)
+			goto err_get_desc;
+
+		do {
+			dev_dbg(schan->dev, "Add SG #%d@%p[%d], dma %llx\n",
+				i, sg, len, (unsigned long long)sg_addr);
+
+			if (direction == DMA_DEV_TO_MEM)
+				new = shdma_add_desc(schan, flags,
+						&sg_addr, addr, &len, &first,
+						direction);
+			else
+				new = shdma_add_desc(schan, flags,
+						addr, &sg_addr, &len, &first,
+						direction);
+			if (!new)
+				goto err_get_desc;
+
+			new->chunks = chunks--;
+			list_add_tail(&new->node, &tx_list);
+		} while (len);
+	}
+
+	if (new != first)
+		new->async_tx.cookie = -ENOSPC;
+
+	/* Put them back on the free list, so, they don't get lost */
+	list_splice_tail(&tx_list, &schan->ld_free);
+
+	spin_unlock_irqrestore(&schan->chan_lock, irq_flags);
+
+	return &first->async_tx;
+
+err_get_desc:
+	list_for_each_entry(new, &tx_list, node)
+		new->mark = DESC_IDLE;
+	list_splice(&tx_list, &schan->ld_free);
+
+	spin_unlock_irqrestore(&schan->chan_lock, irq_flags);
+
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *shdma_prep_memcpy(
+	struct dma_chan *chan, dma_addr_t dma_dest, dma_addr_t dma_src,
+	size_t len, unsigned long flags)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+	struct scatterlist sg;
+
+	if (!chan || !len)
+		return NULL;
+
+	BUG_ON(!schan->desc_num);
+
+	sg_init_table(&sg, 1);
+	sg_set_page(&sg, pfn_to_page(PFN_DOWN(dma_src)), len,
+		    offset_in_page(dma_src));
+	sg_dma_address(&sg) = dma_src;
+	sg_dma_len(&sg) = len;
+
+	return shdma_prep_sg(schan, &sg, 1, &dma_dest, DMA_MEM_TO_MEM, flags);
+}
+
+static struct dma_async_tx_descriptor *shdma_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len,
+	enum dma_transfer_direction direction, unsigned long flags, void *context)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+	struct shdma_dev *sdev = to_shdma_dev(schan->dma_chan.device);
+	const struct shdma_ops *ops = sdev->ops;
+	int slave_id = schan->slave_id;
+	dma_addr_t slave_addr;
+
+	if (!chan)
+		return NULL;
+
+	BUG_ON(!schan->desc_num);
+
+	/* Someone calling slave DMA on a generic channel? */
+	if (slave_id < 0 || !sg_len) {
+		dev_warn(schan->dev, "%s: bad parameter: len=%d, id=%d\n",
+			 __func__, sg_len, slave_id);
+		return NULL;
+	}
+
+	slave_addr = ops->slave_addr(schan);
+
+	return shdma_prep_sg(schan, sgl, sg_len, &slave_addr,
+			      direction, flags);
+}
+
+static int shdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+			  unsigned long arg)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+	struct shdma_dev *sdev = to_shdma_dev(chan->device);
+	const struct shdma_ops *ops = sdev->ops;
+	struct dma_slave_config *config;
+	unsigned long flags;
+	int ret;
+
+	switch (cmd) {
+	case DMA_TERMINATE_ALL:
+		spin_lock_irqsave(&schan->chan_lock, flags);
+		ops->halt_channel(schan);
+
+		if (ops->get_partial && !list_empty(&schan->ld_queue)) {
+			/* Record partial transfer */
+			struct shdma_desc *desc = list_first_entry(&schan->ld_queue,
+						struct shdma_desc, node);
+			desc->partial = ops->get_partial(schan, desc);
+		}
+
+		spin_unlock_irqrestore(&schan->chan_lock, flags);
+
+		shdma_chan_ld_cleanup(schan, true);
+		break;
+	case DMA_SLAVE_CONFIG:
+		/*
+		 * So far only .slave_id is used, but the slave drivers are
+		 * encouraged to also set a transfer direction and an address.
+		 */
+		if (!arg)
+			return -EINVAL;
+		/*
+		 * We could lock this, but you shouldn't be configuring the
+		 * channel, while using it...
+		 */
+		config = (struct dma_slave_config *)arg;
+		ret = shdma_setup_slave(schan, config->slave_id);
+		if (ret < 0)
+			return ret;
+		break;
+	default:
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static void shdma_issue_pending(struct dma_chan *chan)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+
+	spin_lock_irq(&schan->chan_lock);
+	if (schan->pm_state == SHDMA_PM_ESTABLISHED)
+		shdma_chan_xfer_ld_queue(schan);
+	else
+		schan->pm_state = SHDMA_PM_PENDING;
+	spin_unlock_irq(&schan->chan_lock);
+}
+
+static enum dma_status shdma_tx_status(struct dma_chan *chan,
+					dma_cookie_t cookie,
+					struct dma_tx_state *txstate)
+{
+	struct shdma_chan *schan = to_shdma_chan(chan);
+	enum dma_status status;
+	unsigned long flags;
+
+	shdma_chan_ld_cleanup(schan, false);
+
+	spin_lock_irqsave(&schan->chan_lock, flags);
+
+	status = dma_cookie_status(chan, cookie, txstate);
+
+	/*
+	 * If we don't find cookie on the queue, it has been aborted and we have
+	 * to report error
+	 */
+	if (status != DMA_SUCCESS) {
+		struct shdma_desc *sdesc;
+		status = DMA_ERROR;
+		list_for_each_entry(sdesc, &schan->ld_queue, node)
+			if (sdesc->cookie == cookie) {
+				status = DMA_IN_PROGRESS;
+				break;
+			}
+	}
+
+	spin_unlock_irqrestore(&schan->chan_lock, flags);
+
+	return status;
+}
+
+/* Called from error IRQ or NMI */
+bool shdma_reset(struct shdma_dev *sdev)
+{
+	const struct shdma_ops *ops = sdev->ops;
+	struct shdma_chan *schan;
+	unsigned int handled = 0;
+	int i;
+
+	/* Reset all channels */
+	shdma_for_each_chan(schan, sdev, i) {
+		struct shdma_desc *sdesc;
+		LIST_HEAD(dl);
+
+		if (!schan)
+			continue;
+
+		spin_lock(&schan->chan_lock);
+
+		/* Stop the channel */
+		ops->halt_channel(schan);
+
+		list_splice_init(&schan->ld_queue, &dl);
+
+		if (!list_empty(&dl)) {
+			dev_dbg(schan->dev, "Bring down channel %d\n", schan->id);
+			pm_runtime_put(schan->dev);
+		}
+		schan->pm_state = SHDMA_PM_ESTABLISHED;
+
+		spin_unlock(&schan->chan_lock);
+
+		/* Complete all  */
+		list_for_each_entry(sdesc, &dl, node) {
+			struct dma_async_tx_descriptor *tx = &sdesc->async_tx;
+			sdesc->mark = DESC_IDLE;
+			if (tx->callback)
+				tx->callback(tx->callback_param);
+		}
+
+		spin_lock(&schan->chan_lock);
+		list_splice(&dl, &schan->ld_free);
+		spin_unlock(&schan->chan_lock);
+
+		handled++;
+	}
+
+	return !!handled;
+}
+EXPORT_SYMBOL(shdma_reset);
+
+static irqreturn_t chan_irq(int irq, void *dev)
+{
+	struct shdma_chan *schan = dev;
+	const struct shdma_ops *ops =
+		to_shdma_dev(schan->dma_chan.device)->ops;
+	irqreturn_t ret;
+
+	spin_lock(&schan->chan_lock);
+
+	ret = ops->chan_irq(schan, irq) ? IRQ_WAKE_THREAD : IRQ_NONE;
+
+	spin_unlock(&schan->chan_lock);
+
+	return ret;
+}
+
+static irqreturn_t chan_irqt(int irq, void *dev)
+{
+	struct shdma_chan *schan = dev;
+	const struct shdma_ops *ops =
+		to_shdma_dev(schan->dma_chan.device)->ops;
+	struct shdma_desc *sdesc;
+
+	spin_lock_irq(&schan->chan_lock);
+	list_for_each_entry(sdesc, &schan->ld_queue, node) {
+		if (sdesc->mark == DESC_SUBMITTED &&
+		    ops->desc_completed(schan, sdesc)) {
+			dev_dbg(schan->dev, "done #%d@%p\n",
+				sdesc->async_tx.cookie, &sdesc->async_tx);
+			sdesc->mark = DESC_COMPLETED;
+			break;
+		}
+	}
+	/* Next desc */
+	shdma_chan_xfer_ld_queue(schan);
+	spin_unlock_irq(&schan->chan_lock);
+
+	shdma_chan_ld_cleanup(schan, false);
+
+	return IRQ_HANDLED;
+}
+
+int shdma_request_irq(struct shdma_chan *schan, int irq,
+			   unsigned long flags, const char *name)
+{
+	int ret = request_threaded_irq(irq, chan_irq, chan_irqt,
+				       flags, name, schan);
+
+	schan->irq = ret < 0 ? ret : irq;
+
+	return ret;
+}
+EXPORT_SYMBOL(shdma_request_irq);
+
+void shdma_free_irq(struct shdma_chan *schan)
+{
+	if (schan->irq >= 0)
+		free_irq(schan->irq, schan);
+}
+EXPORT_SYMBOL(shdma_free_irq);
+
+void shdma_chan_probe(struct shdma_dev *sdev,
+			   struct shdma_chan *schan, int id)
+{
+	schan->pm_state = SHDMA_PM_ESTABLISHED;
+
+	/* reference struct dma_device */
+	schan->dma_chan.device = &sdev->dma_dev;
+	dma_cookie_init(&schan->dma_chan);
+
+	schan->dev = sdev->dma_dev.dev;
+	schan->id = id;
+
+	if (!schan->max_xfer_len)
+		schan->max_xfer_len = PAGE_SIZE;
+
+	spin_lock_init(&schan->chan_lock);
+
+	/* Init descripter manage list */
+	INIT_LIST_HEAD(&schan->ld_queue);
+	INIT_LIST_HEAD(&schan->ld_free);
+
+	/* Add the channel to DMA device channel list */
+	list_add_tail(&schan->dma_chan.device_node,
+			&sdev->dma_dev.channels);
+	sdev->schan[sdev->dma_dev.chancnt++] = schan;
+}
+EXPORT_SYMBOL(shdma_chan_probe);
+
+void shdma_chan_remove(struct shdma_chan *schan)
+{
+	list_del(&schan->dma_chan.device_node);
+}
+EXPORT_SYMBOL(shdma_chan_remove);
+
+int shdma_init(struct device *dev, struct shdma_dev *sdev,
+		    int chan_num)
+{
+	struct dma_device *dma_dev = &sdev->dma_dev;
+
+	/*
+	 * Require all call-backs for now, they can trivially be made optional
+	 * later as required
+	 */
+	if (!sdev->ops ||
+	    !sdev->desc_size ||
+	    !sdev->ops->embedded_desc ||
+	    !sdev->ops->start_xfer ||
+	    !sdev->ops->setup_xfer ||
+	    !sdev->ops->set_slave ||
+	    !sdev->ops->desc_setup ||
+	    !sdev->ops->slave_addr ||
+	    !sdev->ops->channel_busy ||
+	    !sdev->ops->halt_channel ||
+	    !sdev->ops->desc_completed)
+		return -EINVAL;
+
+	sdev->schan = kcalloc(chan_num, sizeof(*sdev->schan), GFP_KERNEL);
+	if (!sdev->schan)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&dma_dev->channels);
+
+	/* Common and MEMCPY operations */
+	dma_dev->device_alloc_chan_resources
+		= shdma_alloc_chan_resources;
+	dma_dev->device_free_chan_resources = shdma_free_chan_resources;
+	dma_dev->device_prep_dma_memcpy = shdma_prep_memcpy;
+	dma_dev->device_tx_status = shdma_tx_status;
+	dma_dev->device_issue_pending = shdma_issue_pending;
+
+	/* Compulsory for DMA_SLAVE fields */
+	dma_dev->device_prep_slave_sg = shdma_prep_slave_sg;
+	dma_dev->device_control = shdma_control;
+
+	dma_dev->dev = dev;
+
+	return 0;
+}
+EXPORT_SYMBOL(shdma_init);
+
+void shdma_cleanup(struct shdma_dev *sdev)
+{
+	kfree(sdev->schan);
+}
+EXPORT_SYMBOL(shdma_cleanup);
+
+static int __init shdma_enter(void)
+{
+	shdma_slave_used = kzalloc(DIV_ROUND_UP(slave_num, BITS_PER_LONG) *
+				    sizeof(long), GFP_KERNEL);
+	if (!shdma_slave_used)
+		return -ENOMEM;
+	return 0;
+}
+module_init(shdma_enter);
+
+static void __exit shdma_exit(void)
+{
+	kfree(shdma_slave_used);
+}
+module_exit(shdma_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("SH-DMA driver base library");
+MODULE_AUTHOR("Guennadi Liakhovetski <g.liakhovetski@gmx.de>");

drivers/dma/sh/shdma.c

@@ -0,0 +1,955 @@
+/*
+ * Renesas SuperH DMA Engine support
+ *
+ * base is drivers/dma/flsdma.c
+ *
+ * Copyright (C) 2011-2012 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
+ * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
+ * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * - DMA of SuperH does not have Hardware DMA chain mode.
+ * - MAX DMA size is 16MB.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/sh_dma.h>
+#include <linux/notifier.h>
+#include <linux/kdebug.h>
+#include <linux/spinlock.h>
+#include <linux/rculist.h>
+
+#include "../dmaengine.h"
+#include "shdma.h"
+
+#define SH_DMAE_DRV_NAME "sh-dma-engine"
+
+/* Default MEMCPY transfer size = 2^2 = 4 bytes */
+#define LOG2_DEFAULT_XFER_SIZE	2
+#define SH_DMA_SLAVE_NUMBER 256
+#define SH_DMA_TCR_MAX (16 * 1024 * 1024 - 1)
+
+/*
+ * Used for write-side mutual exclusion for the global device list,
+ * read-side synchronization by way of RCU, and per-controller data.
+ */
+static DEFINE_SPINLOCK(sh_dmae_lock);
+static LIST_HEAD(sh_dmae_devices);
+
+static void chclr_write(struct sh_dmae_chan *sh_dc, u32 data)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_dc);
+
+	__raw_writel(data, shdev->chan_reg +
+		     shdev->pdata->channel[sh_dc->shdma_chan.id].chclr_offset);
+}
+
+static void sh_dmae_writel(struct sh_dmae_chan *sh_dc, u32 data, u32 reg)
+{
+	__raw_writel(data, sh_dc->base + reg / sizeof(u32));
+}
+
+static u32 sh_dmae_readl(struct sh_dmae_chan *sh_dc, u32 reg)
+{
+	return __raw_readl(sh_dc->base + reg / sizeof(u32));
+}
+
+static u16 dmaor_read(struct sh_dmae_device *shdev)
+{
+	u32 __iomem *addr = shdev->chan_reg + DMAOR / sizeof(u32);
+
+	if (shdev->pdata->dmaor_is_32bit)
+		return __raw_readl(addr);
+	else
+		return __raw_readw(addr);
+}
+
+static void dmaor_write(struct sh_dmae_device *shdev, u16 data)
+{
+	u32 __iomem *addr = shdev->chan_reg + DMAOR / sizeof(u32);
+
+	if (shdev->pdata->dmaor_is_32bit)
+		__raw_writel(data, addr);
+	else
+		__raw_writew(data, addr);
+}
+
+static void chcr_write(struct sh_dmae_chan *sh_dc, u32 data)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_dc);
+
+	__raw_writel(data, sh_dc->base + shdev->chcr_offset / sizeof(u32));
+}
+
+static u32 chcr_read(struct sh_dmae_chan *sh_dc)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_dc);
+
+	return __raw_readl(sh_dc->base + shdev->chcr_offset / sizeof(u32));
+}
+
+/*
+ * Reset DMA controller
+ *
+ * SH7780 has two DMAOR register
+ */
+static void sh_dmae_ctl_stop(struct sh_dmae_device *shdev)
+{
+	unsigned short dmaor;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sh_dmae_lock, flags);
+
+	dmaor = dmaor_read(shdev);
+	dmaor_write(shdev, dmaor & ~(DMAOR_NMIF | DMAOR_AE | DMAOR_DME));
+
+	spin_unlock_irqrestore(&sh_dmae_lock, flags);
+}
+
+static int sh_dmae_rst(struct sh_dmae_device *shdev)
+{
+	unsigned short dmaor;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sh_dmae_lock, flags);
+
+	dmaor = dmaor_read(shdev) & ~(DMAOR_NMIF | DMAOR_AE | DMAOR_DME);
+
+	if (shdev->pdata->chclr_present) {
+		int i;
+		for (i = 0; i < shdev->pdata->channel_num; i++) {
+			struct sh_dmae_chan *sh_chan = shdev->chan[i];
+			if (sh_chan)
+				chclr_write(sh_chan, 0);
+		}
+	}
+
+	dmaor_write(shdev, dmaor | shdev->pdata->dmaor_init);
+
+	dmaor = dmaor_read(shdev);
+
+	spin_unlock_irqrestore(&sh_dmae_lock, flags);
+
+	if (dmaor & (DMAOR_AE | DMAOR_NMIF)) {
+		dev_warn(shdev->shdma_dev.dma_dev.dev, "Can't initialize DMAOR.\n");
+		return -EIO;
+	}
+	if (shdev->pdata->dmaor_init & ~dmaor)
+		dev_warn(shdev->shdma_dev.dma_dev.dev,
+			 "DMAOR=0x%x hasn't latched the initial value 0x%x.\n",
+			 dmaor, shdev->pdata->dmaor_init);
+	return 0;
+}
+
+static bool dmae_is_busy(struct sh_dmae_chan *sh_chan)
+{
+	u32 chcr = chcr_read(sh_chan);
+
+	if ((chcr & (CHCR_DE | CHCR_TE)) == CHCR_DE)
+		return true; /* working */
+
+	return false; /* waiting */
+}
+
+static unsigned int calc_xmit_shift(struct sh_dmae_chan *sh_chan, u32 chcr)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
+	struct sh_dmae_pdata *pdata = shdev->pdata;
+	int cnt = ((chcr & pdata->ts_low_mask) >> pdata->ts_low_shift) |
+		((chcr & pdata->ts_high_mask) >> pdata->ts_high_shift);
+
+	if (cnt >= pdata->ts_shift_num)
+		cnt = 0;
+
+	return pdata->ts_shift[cnt];
+}
+
+static u32 log2size_to_chcr(struct sh_dmae_chan *sh_chan, int l2size)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
+	struct sh_dmae_pdata *pdata = shdev->pdata;
+	int i;
+
+	for (i = 0; i < pdata->ts_shift_num; i++)
+		if (pdata->ts_shift[i] == l2size)
+			break;
+
+	if (i == pdata->ts_shift_num)
+		i = 0;
+
+	return ((i << pdata->ts_low_shift) & pdata->ts_low_mask) |
+		((i << pdata->ts_high_shift) & pdata->ts_high_mask);
+}
+
+static void dmae_set_reg(struct sh_dmae_chan *sh_chan, struct sh_dmae_regs *hw)
+{
+	sh_dmae_writel(sh_chan, hw->sar, SAR);
+	sh_dmae_writel(sh_chan, hw->dar, DAR);
+	sh_dmae_writel(sh_chan, hw->tcr >> sh_chan->xmit_shift, TCR);
+}
+
+static void dmae_start(struct sh_dmae_chan *sh_chan)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
+	u32 chcr = chcr_read(sh_chan);
+
+	if (shdev->pdata->needs_tend_set)
+		sh_dmae_writel(sh_chan, 0xFFFFFFFF, TEND);
+
+	chcr |= CHCR_DE | shdev->chcr_ie_bit;
+	chcr_write(sh_chan, chcr & ~CHCR_TE);
+}
+
+static void dmae_init(struct sh_dmae_chan *sh_chan)
+{
+	/*
+	 * Default configuration for dual address memory-memory transfer.
+	 * 0x400 represents auto-request.
+	 */
+	u32 chcr = DM_INC | SM_INC | 0x400 | log2size_to_chcr(sh_chan,
+						   LOG2_DEFAULT_XFER_SIZE);
+	sh_chan->xmit_shift = calc_xmit_shift(sh_chan, chcr);
+	chcr_write(sh_chan, chcr);
+}
+
+static int dmae_set_chcr(struct sh_dmae_chan *sh_chan, u32 val)
+{
+	/* If DMA is active, cannot set CHCR. TODO: remove this superfluous check */
+	if (dmae_is_busy(sh_chan))
+		return -EBUSY;
+
+	sh_chan->xmit_shift = calc_xmit_shift(sh_chan, val);
+	chcr_write(sh_chan, val);
+
+	return 0;
+}
+
+static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
+	struct sh_dmae_pdata *pdata = shdev->pdata;
+	const struct sh_dmae_channel *chan_pdata = &pdata->channel[sh_chan->shdma_chan.id];
+	u16 __iomem *addr = shdev->dmars;
+	unsigned int shift = chan_pdata->dmars_bit;
+
+	if (dmae_is_busy(sh_chan))
+		return -EBUSY;
+
+	if (pdata->no_dmars)
+		return 0;
+
+	/* in the case of a missing DMARS resource use first memory window */
+	if (!addr)
+		addr = (u16 __iomem *)shdev->chan_reg;
+	addr += chan_pdata->dmars / sizeof(u16);
+
+	__raw_writew((__raw_readw(addr) & (0xff00 >> shift)) | (val << shift),
+		     addr);
+
+	return 0;
+}
+
+static void sh_dmae_start_xfer(struct shdma_chan *schan,
+			       struct shdma_desc *sdesc)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
+						    shdma_chan);
+	struct sh_dmae_desc *sh_desc = container_of(sdesc,
+					struct sh_dmae_desc, shdma_desc);
+	dev_dbg(sh_chan->shdma_chan.dev, "Queue #%d to %d: %u@%x -> %x\n",
+		sdesc->async_tx.cookie, sh_chan->shdma_chan.id,
+		sh_desc->hw.tcr, sh_desc->hw.sar, sh_desc->hw.dar);
+	/* Get the ld start address from ld_queue */
+	dmae_set_reg(sh_chan, &sh_desc->hw);
+	dmae_start(sh_chan);
+}
+
+static bool sh_dmae_channel_busy(struct shdma_chan *schan)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
+						    shdma_chan);
+	return dmae_is_busy(sh_chan);
+}
+
+static void sh_dmae_setup_xfer(struct shdma_chan *schan,
+			       int slave_id)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
+						    shdma_chan);
+
+	if (slave_id >= 0) {
+		const struct sh_dmae_slave_config *cfg =
+			sh_chan->config;
+
+		dmae_set_dmars(sh_chan, cfg->mid_rid);
+		dmae_set_chcr(sh_chan, cfg->chcr);
+	} else {
+		dmae_init(sh_chan);
+	}
+}
+
+static const struct sh_dmae_slave_config *dmae_find_slave(
+	struct sh_dmae_chan *sh_chan, int slave_id)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
+	struct sh_dmae_pdata *pdata = shdev->pdata;
+	const struct sh_dmae_slave_config *cfg;
+	int i;
+
+	if (slave_id >= SH_DMA_SLAVE_NUMBER)
+		return NULL;
+
+	for (i = 0, cfg = pdata->slave; i < pdata->slave_num; i++, cfg++)
+		if (cfg->slave_id == slave_id)
+			return cfg;
+
+	return NULL;
+}
+
+static int sh_dmae_set_slave(struct shdma_chan *schan,
+			     int slave_id, bool try)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
+						    shdma_chan);
+	const struct sh_dmae_slave_config *cfg = dmae_find_slave(sh_chan, slave_id);
+	if (!cfg)
+		return -ENXIO;
+
+	if (!try)
+		sh_chan->config = cfg;
+
+	return 0;
+}
+
+static void dmae_halt(struct sh_dmae_chan *sh_chan)
+{
+	struct sh_dmae_device *shdev = to_sh_dev(sh_chan);
+	u32 chcr = chcr_read(sh_chan);
+
+	chcr &= ~(CHCR_DE | CHCR_TE | shdev->chcr_ie_bit);
+	chcr_write(sh_chan, chcr);
+}
+
+static int sh_dmae_desc_setup(struct shdma_chan *schan,
+			      struct shdma_desc *sdesc,
+			      dma_addr_t src, dma_addr_t dst, size_t *len)
+{
+	struct sh_dmae_desc *sh_desc = container_of(sdesc,
+					struct sh_dmae_desc, shdma_desc);
+
+	if (*len > schan->max_xfer_len)
+		*len = schan->max_xfer_len;
+
+	sh_desc->hw.sar = src;
+	sh_desc->hw.dar = dst;
+	sh_desc->hw.tcr = *len;
+
+	return 0;
+}
+
+static void sh_dmae_halt(struct shdma_chan *schan)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
+						    shdma_chan);
+	dmae_halt(sh_chan);
+}
+
+static bool sh_dmae_chan_irq(struct shdma_chan *schan, int irq)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
+						    shdma_chan);
+
+	if (!(chcr_read(sh_chan) & CHCR_TE))
+		return false;
+
+	/* DMA stop */
+	dmae_halt(sh_chan);
+
+	return true;
+}
+
+static size_t sh_dmae_get_partial(struct shdma_chan *schan,
+				  struct shdma_desc *sdesc)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan, struct sh_dmae_chan,
+						    shdma_chan);
+	struct sh_dmae_desc *sh_desc = container_of(sdesc,
+					struct sh_dmae_desc, shdma_desc);
+	return (sh_desc->hw.tcr - sh_dmae_readl(sh_chan, TCR)) <<
+		sh_chan->xmit_shift;
+}
+
+/* Called from error IRQ or NMI */
+static bool sh_dmae_reset(struct sh_dmae_device *shdev)
+{
+	bool ret;
+
+	/* halt the dma controller */
+	sh_dmae_ctl_stop(shdev);
+
+	/* We cannot detect, which channel caused the error, have to reset all */
+	ret = shdma_reset(&shdev->shdma_dev);
+
+	sh_dmae_rst(shdev);
+
+	return ret;
+}
+
+static irqreturn_t sh_dmae_err(int irq, void *data)
+{
+	struct sh_dmae_device *shdev = data;
+
+	if (!(dmaor_read(shdev) & DMAOR_AE))
+		return IRQ_NONE;
+
+	sh_dmae_reset(shdev);
+	return IRQ_HANDLED;
+}
+
+static bool sh_dmae_desc_completed(struct shdma_chan *schan,
+				   struct shdma_desc *sdesc)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan,
+					struct sh_dmae_chan, shdma_chan);
+	struct sh_dmae_desc *sh_desc = container_of(sdesc,
+					struct sh_dmae_desc, shdma_desc);
+	u32 sar_buf = sh_dmae_readl(sh_chan, SAR);
+	u32 dar_buf = sh_dmae_readl(sh_chan, DAR);
+
+	return	(sdesc->direction == DMA_DEV_TO_MEM &&
+		 (sh_desc->hw.dar + sh_desc->hw.tcr) == dar_buf) ||
+		(sdesc->direction != DMA_DEV_TO_MEM &&
+		 (sh_desc->hw.sar + sh_desc->hw.tcr) == sar_buf);
+}
+
+static bool sh_dmae_nmi_notify(struct sh_dmae_device *shdev)
+{
+	/* Fast path out if NMIF is not asserted for this controller */
+	if ((dmaor_read(shdev) & DMAOR_NMIF) == 0)
+		return false;
+
+	return sh_dmae_reset(shdev);
+}
+
+static int sh_dmae_nmi_handler(struct notifier_block *self,
+			       unsigned long cmd, void *data)
+{
+	struct sh_dmae_device *shdev;
+	int ret = NOTIFY_DONE;
+	bool triggered;
+
+	/*
+	 * Only concern ourselves with NMI events.
+	 *
+	 * Normally we would check the die chain value, but as this needs
+	 * to be architecture independent, check for NMI context instead.
+	 */
+	if (!in_nmi())
+		return NOTIFY_DONE;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(shdev, &sh_dmae_devices, node) {
+		/*
+		 * Only stop if one of the controllers has NMIF asserted,
+		 * we do not want to interfere with regular address error
+		 * handling or NMI events that don't concern the DMACs.
+		 */
+		triggered = sh_dmae_nmi_notify(shdev);
+		if (triggered == true)
+			ret = NOTIFY_OK;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static struct notifier_block sh_dmae_nmi_notifier __read_mostly = {
+	.notifier_call	= sh_dmae_nmi_handler,
+
+	/* Run before NMI debug handler and KGDB */
+	.priority	= 1,
+};
+
+static int sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id,
+					int irq, unsigned long flags)
+{
+	const struct sh_dmae_channel *chan_pdata = &shdev->pdata->channel[id];
+	struct shdma_dev *sdev = &shdev->shdma_dev;
+	struct platform_device *pdev = to_platform_device(sdev->dma_dev.dev);
+	struct sh_dmae_chan *sh_chan;
+	struct shdma_chan *schan;
+	int err;
+
+	sh_chan = kzalloc(sizeof(struct sh_dmae_chan), GFP_KERNEL);
+	if (!sh_chan) {
+		dev_err(sdev->dma_dev.dev,
+			"No free memory for allocating dma channels!\n");
+		return -ENOMEM;
+	}
+
+	schan = &sh_chan->shdma_chan;
+	schan->max_xfer_len = SH_DMA_TCR_MAX + 1;
+
+	shdma_chan_probe(sdev, schan, id);
+
+	sh_chan->base = shdev->chan_reg + chan_pdata->offset / sizeof(u32);
+
+	/* set up channel irq */
+	if (pdev->id >= 0)
+		snprintf(sh_chan->dev_id, sizeof(sh_chan->dev_id),
+			 "sh-dmae%d.%d", pdev->id, id);
+	else
+		snprintf(sh_chan->dev_id, sizeof(sh_chan->dev_id),
+			 "sh-dma%d", id);
+
+	err = shdma_request_irq(schan, irq, flags, sh_chan->dev_id);
+	if (err) {
+		dev_err(sdev->dma_dev.dev,
+			"DMA channel %d request_irq error %d\n",
+			id, err);
+		goto err_no_irq;
+	}
+
+	shdev->chan[id] = sh_chan;
+	return 0;
+
+err_no_irq:
+	/* remove from dmaengine device node */
+	shdma_chan_remove(schan);
+	kfree(sh_chan);
+	return err;
+}
+
+static void sh_dmae_chan_remove(struct sh_dmae_device *shdev)
+{
+	struct dma_device *dma_dev = &shdev->shdma_dev.dma_dev;
+	struct shdma_chan *schan;
+	int i;
+
+	shdma_for_each_chan(schan, &shdev->shdma_dev, i) {
+		struct sh_dmae_chan *sh_chan = container_of(schan,
+					struct sh_dmae_chan, shdma_chan);
+		BUG_ON(!schan);
+
+		shdma_free_irq(&sh_chan->shdma_chan);
+
+		shdma_chan_remove(schan);
+		kfree(sh_chan);
+	}
+	dma_dev->chancnt = 0;
+}
+
+static void sh_dmae_shutdown(struct platform_device *pdev)
+{
+	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
+	sh_dmae_ctl_stop(shdev);
+}
+
+static int sh_dmae_runtime_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int sh_dmae_runtime_resume(struct device *dev)
+{
+	struct sh_dmae_device *shdev = dev_get_drvdata(dev);
+
+	return sh_dmae_rst(shdev);
+}
+
+#ifdef CONFIG_PM
+static int sh_dmae_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int sh_dmae_resume(struct device *dev)
+{
+	struct sh_dmae_device *shdev = dev_get_drvdata(dev);
+	int i, ret;
+
+	ret = sh_dmae_rst(shdev);
+	if (ret < 0)
+		dev_err(dev, "Failed to reset!\n");
+
+	for (i = 0; i < shdev->pdata->channel_num; i++) {
+		struct sh_dmae_chan *sh_chan = shdev->chan[i];
+
+		if (!sh_chan->shdma_chan.desc_num)
+			continue;
+
+		if (sh_chan->shdma_chan.slave_id >= 0) {
+			const struct sh_dmae_slave_config *cfg = sh_chan->config;
+			dmae_set_dmars(sh_chan, cfg->mid_rid);
+			dmae_set_chcr(sh_chan, cfg->chcr);
+		} else {
+			dmae_init(sh_chan);
+		}
+	}
+
+	return 0;
+}
+#else
+#define sh_dmae_suspend NULL
+#define sh_dmae_resume NULL
+#endif
+
+const struct dev_pm_ops sh_dmae_pm = {
+	.suspend		= sh_dmae_suspend,
+	.resume			= sh_dmae_resume,
+	.runtime_suspend	= sh_dmae_runtime_suspend,
+	.runtime_resume		= sh_dmae_runtime_resume,
+};
+
+static dma_addr_t sh_dmae_slave_addr(struct shdma_chan *schan)
+{
+	struct sh_dmae_chan *sh_chan = container_of(schan,
+					struct sh_dmae_chan, shdma_chan);
+
+	/*
+	 * Implicit BUG_ON(!sh_chan->config)
+	 * This is an exclusive slave DMA operation, may only be called after a
+	 * successful slave configuration.
+	 */
+	return sh_chan->config->addr;
+}
+
+static struct shdma_desc *sh_dmae_embedded_desc(void *buf, int i)
+{
+	return &((struct sh_dmae_desc *)buf)[i].shdma_desc;
+}
+
+static const struct shdma_ops sh_dmae_shdma_ops = {
+	.desc_completed = sh_dmae_desc_completed,
+	.halt_channel = sh_dmae_halt,
+	.channel_busy = sh_dmae_channel_busy,
+	.slave_addr = sh_dmae_slave_addr,
+	.desc_setup = sh_dmae_desc_setup,
+	.set_slave = sh_dmae_set_slave,
+	.setup_xfer = sh_dmae_setup_xfer,
+	.start_xfer = sh_dmae_start_xfer,
+	.embedded_desc = sh_dmae_embedded_desc,
+	.chan_irq = sh_dmae_chan_irq,
+	.get_partial = sh_dmae_get_partial,
+};
+
+static int sh_dmae_probe(struct platform_device *pdev)
+{
+	struct sh_dmae_pdata *pdata = pdev->dev.platform_data;
+	unsigned long irqflags = IRQF_DISABLED,
+		chan_flag[SH_DMAE_MAX_CHANNELS] = {};
+	int errirq, chan_irq[SH_DMAE_MAX_CHANNELS];
+	int err, i, irq_cnt = 0, irqres = 0, irq_cap = 0;
+	struct sh_dmae_device *shdev;
+	struct dma_device *dma_dev;
+	struct resource *chan, *dmars, *errirq_res, *chanirq_res;
+
+	/* get platform data */
+	if (!pdata || !pdata->channel_num)
+		return -ENODEV;
+
+	chan = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	/* DMARS area is optional */
+	dmars = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	/*
+	 * IRQ resources:
+	 * 1. there always must be at least one IRQ IO-resource. On SH4 it is
+	 *    the error IRQ, in which case it is the only IRQ in this resource:
+	 *    start == end. If it is the only IRQ resource, all channels also
+	 *    use the same IRQ.
+	 * 2. DMA channel IRQ resources can be specified one per resource or in
+	 *    ranges (start != end)
+	 * 3. iff all events (channels and, optionally, error) on this
+	 *    controller use the same IRQ, only one IRQ resource can be
+	 *    specified, otherwise there must be one IRQ per channel, even if
+	 *    some of them are equal
+	 * 4. if all IRQs on this controller are equal or if some specific IRQs
+	 *    specify IORESOURCE_IRQ_SHAREABLE in their resources, they will be
+	 *    requested with the IRQF_SHARED flag
+	 */
+	errirq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!chan || !errirq_res)
+		return -ENODEV;
+
+	if (!request_mem_region(chan->start, resource_size(chan), pdev->name)) {
+		dev_err(&pdev->dev, "DMAC register region already claimed\n");
+		return -EBUSY;
+	}
+
+	if (dmars && !request_mem_region(dmars->start, resource_size(dmars), pdev->name)) {
+		dev_err(&pdev->dev, "DMAC DMARS region already claimed\n");
+		err = -EBUSY;
+		goto ermrdmars;
+	}
+
+	err = -ENOMEM;
+	shdev = kzalloc(sizeof(struct sh_dmae_device), GFP_KERNEL);
+	if (!shdev) {
+		dev_err(&pdev->dev, "Not enough memory\n");
+		goto ealloc;
+	}
+
+	dma_dev = &shdev->shdma_dev.dma_dev;
+
+	shdev->chan_reg = ioremap(chan->start, resource_size(chan));
+	if (!shdev->chan_reg)
+		goto emapchan;
+	if (dmars) {
+		shdev->dmars = ioremap(dmars->start, resource_size(dmars));
+		if (!shdev->dmars)
+			goto emapdmars;
+	}
+
+	if (!pdata->slave_only)
+		dma_cap_set(DMA_MEMCPY, dma_dev->cap_mask);
+	if (pdata->slave && pdata->slave_num)
+		dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
+
+	/* Default transfer size of 32 bytes requires 32-byte alignment */
+	dma_dev->copy_align = LOG2_DEFAULT_XFER_SIZE;
+
+	shdev->shdma_dev.ops = &sh_dmae_shdma_ops;
+	shdev->shdma_dev.desc_size = sizeof(struct sh_dmae_desc);
+	err = shdma_init(&pdev->dev, &shdev->shdma_dev,
+			      pdata->channel_num);
+	if (err < 0)
+		goto eshdma;
+
+	/* platform data */
+	shdev->pdata = pdev->dev.platform_data;
+
+	if (pdata->chcr_offset)
+		shdev->chcr_offset = pdata->chcr_offset;
+	else
+		shdev->chcr_offset = CHCR;
+
+	if (pdata->chcr_ie_bit)
+		shdev->chcr_ie_bit = pdata->chcr_ie_bit;
+	else
+		shdev->chcr_ie_bit = CHCR_IE;
+
+	platform_set_drvdata(pdev, shdev);
+
+	pm_runtime_enable(&pdev->dev);
+	err = pm_runtime_get_sync(&pdev->dev);
+	if (err < 0)
+		dev_err(&pdev->dev, "%s(): GET = %d\n", __func__, err);
+
+	spin_lock_irq(&sh_dmae_lock);
+	list_add_tail_rcu(&shdev->node, &sh_dmae_devices);
+	spin_unlock_irq(&sh_dmae_lock);
+
+	/* reset dma controller - only needed as a test */
+	err = sh_dmae_rst(shdev);
+	if (err)
+		goto rst_err;
+
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
+	chanirq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 1);
+
+	if (!chanirq_res)
+		chanirq_res = errirq_res;
+	else
+		irqres++;
+
+	if (chanirq_res == errirq_res ||
+	    (errirq_res->flags & IORESOURCE_BITS) == IORESOURCE_IRQ_SHAREABLE)
+		irqflags = IRQF_SHARED;
+
+	errirq = errirq_res->start;
+
+	err = request_irq(errirq, sh_dmae_err, irqflags,
+			  "DMAC Address Error", shdev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"DMA failed requesting irq #%d, error %d\n",
+			errirq, err);
+		goto eirq_err;
+	}
+
+#else
+	chanirq_res = errirq_res;
+#endif /* CONFIG_CPU_SH4 || CONFIG_ARCH_SHMOBILE */
+
+	if (chanirq_res->start == chanirq_res->end &&
+	    !platform_get_resource(pdev, IORESOURCE_IRQ, 1)) {
+		/* Special case - all multiplexed */
+		for (; irq_cnt < pdata->channel_num; irq_cnt++) {
+			if (irq_cnt < SH_DMAE_MAX_CHANNELS) {
+				chan_irq[irq_cnt] = chanirq_res->start;
+				chan_flag[irq_cnt] = IRQF_SHARED;
+			} else {
+				irq_cap = 1;
+				break;
+			}
+		}
+	} else {
+		do {
+			for (i = chanirq_res->start; i <= chanirq_res->end; i++) {
+				if (irq_cnt >= SH_DMAE_MAX_CHANNELS) {
+					irq_cap = 1;
+					break;
+				}
+
+				if ((errirq_res->flags & IORESOURCE_BITS) ==
+				    IORESOURCE_IRQ_SHAREABLE)
+					chan_flag[irq_cnt] = IRQF_SHARED;
+				else
+					chan_flag[irq_cnt] = IRQF_DISABLED;
+				dev_dbg(&pdev->dev,
+					"Found IRQ %d for channel %d\n",
+					i, irq_cnt);
+				chan_irq[irq_cnt++] = i;
+			}
+
+			if (irq_cnt >= SH_DMAE_MAX_CHANNELS)
+				break;
+
+			chanirq_res = platform_get_resource(pdev,
+						IORESOURCE_IRQ, ++irqres);
+		} while (irq_cnt < pdata->channel_num && chanirq_res);
+	}
+
+	/* Create DMA Channel */
+	for (i = 0; i < irq_cnt; i++) {
+		err = sh_dmae_chan_probe(shdev, i, chan_irq[i], chan_flag[i]);
+		if (err)
+			goto chan_probe_err;
+	}
+
+	if (irq_cap)
+		dev_notice(&pdev->dev, "Attempting to register %d DMA "
+			   "channels when a maximum of %d are supported.\n",
+			   pdata->channel_num, SH_DMAE_MAX_CHANNELS);
+
+	pm_runtime_put(&pdev->dev);
+
+	err = dma_async_device_register(&shdev->shdma_dev.dma_dev);
+	if (err < 0)
+		goto edmadevreg;
+
+	return err;
+
+edmadevreg:
+	pm_runtime_get(&pdev->dev);
+
+chan_probe_err:
+	sh_dmae_chan_remove(shdev);
+
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
+	free_irq(errirq, shdev);
+eirq_err:
+#endif
+rst_err:
+	spin_lock_irq(&sh_dmae_lock);
+	list_del_rcu(&shdev->node);
+	spin_unlock_irq(&sh_dmae_lock);
+
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	platform_set_drvdata(pdev, NULL);
+	shdma_cleanup(&shdev->shdma_dev);
+eshdma:
+	if (dmars)
+		iounmap(shdev->dmars);
+emapdmars:
+	iounmap(shdev->chan_reg);
+	synchronize_rcu();
+emapchan:
+	kfree(shdev);
+ealloc:
+	if (dmars)
+		release_mem_region(dmars->start, resource_size(dmars));
+ermrdmars:
+	release_mem_region(chan->start, resource_size(chan));
+
+	return err;
+}
+
+static int sh_dmae_remove(struct platform_device *pdev)
+{
+	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
+	struct dma_device *dma_dev = &shdev->shdma_dev.dma_dev;
+	struct resource *res;
+	int errirq = platform_get_irq(pdev, 0);
+
+	dma_async_device_unregister(dma_dev);
+
+	if (errirq > 0)
+		free_irq(errirq, shdev);
+
+	spin_lock_irq(&sh_dmae_lock);
+	list_del_rcu(&shdev->node);
+	spin_unlock_irq(&sh_dmae_lock);
+
+	pm_runtime_disable(&pdev->dev);
+
+	sh_dmae_chan_remove(shdev);
+	shdma_cleanup(&shdev->shdma_dev);
+
+	if (shdev->dmars)
+		iounmap(shdev->dmars);
+	iounmap(shdev->chan_reg);
+
+	platform_set_drvdata(pdev, NULL);
+
+	synchronize_rcu();
+	kfree(shdev);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res)
+		release_mem_region(res->start, resource_size(res));
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (res)
+		release_mem_region(res->start, resource_size(res));
+
+	return 0;
+}
+
+static struct platform_driver sh_dmae_driver = {
+	.driver 	= {
+		.owner	= THIS_MODULE,
+		.pm	= &sh_dmae_pm,
+		.name	= SH_DMAE_DRV_NAME,
+	},
+	.remove		= sh_dmae_remove,
+	.shutdown	= sh_dmae_shutdown,
+};
+
+static int __init sh_dmae_init(void)
+{
+	/* Wire up NMI handling */
+	int err = register_die_notifier(&sh_dmae_nmi_notifier);
+	if (err)
+		return err;
+
+	return platform_driver_probe(&sh_dmae_driver, sh_dmae_probe);
+}
+module_init(sh_dmae_init);
+
+static void __exit sh_dmae_exit(void)
+{
+	platform_driver_unregister(&sh_dmae_driver);
+
+	unregister_die_notifier(&sh_dmae_nmi_notifier);
+}
+module_exit(sh_dmae_exit);
+
+MODULE_AUTHOR("Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>");
+MODULE_DESCRIPTION("Renesas SH DMA Engine driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" SH_DMAE_DRV_NAME);

drivers/dma/sh/shdma.h

@@ -0,0 +1,64 @@
+/*
+ * Renesas SuperH DMA Engine support
+ *
+ * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
+ * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+#ifndef __DMA_SHDMA_H
+#define __DMA_SHDMA_H
+
+#include <linux/sh_dma.h>
+#include <linux/shdma-base.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+
+#define SH_DMAE_MAX_CHANNELS 20
+#define SH_DMAE_TCR_MAX 0x00FFFFFF	/* 16MB */
+
+struct device;
+
+struct sh_dmae_chan {
+	struct shdma_chan shdma_chan;
+	const struct sh_dmae_slave_config *config; /* Slave DMA configuration */
+	int xmit_shift;			/* log_2(bytes_per_xfer) */
+	u32 __iomem *base;
+	char dev_id[16];		/* unique name per DMAC of channel */
+	int pm_error;
+};
+
+struct sh_dmae_device {
+	struct shdma_dev shdma_dev;
+	struct sh_dmae_chan *chan[SH_DMAE_MAX_CHANNELS];
+	struct sh_dmae_pdata *pdata;
+	struct list_head node;
+	u32 __iomem *chan_reg;
+	u16 __iomem *dmars;
+	unsigned int chcr_offset;
+	u32 chcr_ie_bit;
+};
+
+struct sh_dmae_regs {
+	u32 sar; /* SAR / source address */
+	u32 dar; /* DAR / destination address */
+	u32 tcr; /* TCR / transfer count */
+};
+
+struct sh_dmae_desc {
+	struct sh_dmae_regs hw;
+	struct shdma_desc shdma_desc;
+};
+
+#define to_sh_chan(chan) container_of(chan, struct sh_dmae_chan, shdma_chan)
+#define to_sh_desc(lh) container_of(lh, struct sh_desc, node)
+#define tx_to_sh_desc(tx) container_of(tx, struct sh_desc, async_tx)
+#define to_sh_dev(chan) container_of(chan->shdma_chan.dma_chan.device,\
+				     struct sh_dmae_device, shdma_dev.dma_dev)
+
+#endif	/* __DMA_SHDMA_H */

drivers/dma/sh/sudmac.c

@@ -0,0 +1,428 @@
+/*
+ * Renesas SUDMAC support
+ *
+ * Copyright (C) 2013 Renesas Solutions Corp.
+ *
+ * based on drivers/dma/sh/shdma.c:
+ * Copyright (C) 2011-2012 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
+ * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
+ * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/dmaengine.h>
+#include <linux/platform_device.h>
+#include <linux/sudmac.h>
+
+struct sudmac_chan {
+	struct shdma_chan shdma_chan;
+	void __iomem *base;
+	char dev_id[16];	/* unique name per DMAC of channel */
+
+	u32 offset;		/* for CFG, BA, BBC, CA, CBC, DEN */
+	u32 cfg;
+	u32 dint_end_bit;
+};
+
+struct sudmac_device {
+	struct shdma_dev shdma_dev;
+	struct sudmac_pdata *pdata;
+	void __iomem *chan_reg;
+};
+
+struct sudmac_regs {
+	u32 base_addr;
+	u32 base_byte_count;
+};
+
+struct sudmac_desc {
+	struct sudmac_regs hw;
+	struct shdma_desc shdma_desc;
+};
+
+#define to_chan(schan) container_of(schan, struct sudmac_chan, shdma_chan)
+#define to_desc(sdesc) container_of(sdesc, struct sudmac_desc, shdma_desc)
+#define to_sdev(sc) container_of(sc->shdma_chan.dma_chan.device, \
+				 struct sudmac_device, shdma_dev.dma_dev)
+
+/* SUDMAC register */
+#define SUDMAC_CH0CFG		0x00
+#define SUDMAC_CH0BA		0x10
+#define SUDMAC_CH0BBC		0x18
+#define SUDMAC_CH0CA		0x20
+#define SUDMAC_CH0CBC		0x28
+#define SUDMAC_CH0DEN		0x30
+#define SUDMAC_DSTSCLR		0x38
+#define SUDMAC_DBUFCTRL		0x3C
+#define SUDMAC_DINTCTRL		0x40
+#define SUDMAC_DINTSTS		0x44
+#define SUDMAC_DINTSTSCLR	0x48
+#define SUDMAC_CH0SHCTRL	0x50
+
+/* Definitions for the sudmac_channel.config */
+#define SUDMAC_SENDBUFM	0x1000 /* b12: Transmit Buffer Mode */
+#define SUDMAC_RCVENDM	0x0100 /* b8: Receive Data Transfer End Mode */
+#define SUDMAC_LBA_WAIT	0x0030 /* b5-4: Local Bus Access Wait */
+
+/* Definitions for the sudmac_channel.dint_end_bit */
+#define SUDMAC_CH1ENDE	0x0002 /* b1: Ch1 DMA Transfer End Int Enable */
+#define SUDMAC_CH0ENDE	0x0001 /* b0: Ch0 DMA Transfer End Int Enable */
+
+#define SUDMAC_DRV_NAME "sudmac"
+
+static void sudmac_writel(struct sudmac_chan *sc, u32 data, u32 reg)
+{
+	iowrite32(data, sc->base + reg);
+}
+
+static u32 sudmac_readl(struct sudmac_chan *sc, u32 reg)
+{
+	return ioread32(sc->base + reg);
+}
+
+static bool sudmac_is_busy(struct sudmac_chan *sc)
+{
+	u32 den = sudmac_readl(sc, SUDMAC_CH0DEN + sc->offset);
+
+	if (den)
+		return true; /* working */
+
+	return false; /* waiting */
+}
+
+static void sudmac_set_reg(struct sudmac_chan *sc, struct sudmac_regs *hw,
+			   struct shdma_desc *sdesc)
+{
+	sudmac_writel(sc, sc->cfg, SUDMAC_CH0CFG + sc->offset);
+	sudmac_writel(sc, hw->base_addr, SUDMAC_CH0BA + sc->offset);
+	sudmac_writel(sc, hw->base_byte_count, SUDMAC_CH0BBC + sc->offset);
+}
+
+static void sudmac_start(struct sudmac_chan *sc)
+{
+	u32 dintctrl = sudmac_readl(sc, SUDMAC_DINTCTRL);
+
+	sudmac_writel(sc, dintctrl | sc->dint_end_bit, SUDMAC_DINTCTRL);
+	sudmac_writel(sc, 1, SUDMAC_CH0DEN + sc->offset);
+}
+
+static void sudmac_start_xfer(struct shdma_chan *schan,
+			      struct shdma_desc *sdesc)
+{
+	struct sudmac_chan *sc = to_chan(schan);
+	struct sudmac_desc *sd = to_desc(sdesc);
+
+	sudmac_set_reg(sc, &sd->hw, sdesc);
+	sudmac_start(sc);
+}
+
+static bool sudmac_channel_busy(struct shdma_chan *schan)
+{
+	struct sudmac_chan *sc = to_chan(schan);
+
+	return sudmac_is_busy(sc);
+}
+
+static void sudmac_setup_xfer(struct shdma_chan *schan, int slave_id)
+{
+}
+
+static const struct sudmac_slave_config *sudmac_find_slave(
+	struct sudmac_chan *sc, int slave_id)
+{
+	struct sudmac_device *sdev = to_sdev(sc);
+	struct sudmac_pdata *pdata = sdev->pdata;
+	const struct sudmac_slave_config *cfg;
+	int i;
+
+	for (i = 0, cfg = pdata->slave; i < pdata->slave_num; i++, cfg++)
+		if (cfg->slave_id == slave_id)
+			return cfg;
+
+	return NULL;
+}
+
+static int sudmac_set_slave(struct shdma_chan *schan, int slave_id, bool try)
+{
+	struct sudmac_chan *sc = to_chan(schan);
+	const struct sudmac_slave_config *cfg = sudmac_find_slave(sc, slave_id);
+
+	if (!cfg)
+		return -ENODEV;
+
+	return 0;
+}
+
+static inline void sudmac_dma_halt(struct sudmac_chan *sc)
+{
+	u32 dintctrl = sudmac_readl(sc, SUDMAC_DINTCTRL);
+
+	sudmac_writel(sc, 0, SUDMAC_CH0DEN + sc->offset);
+	sudmac_writel(sc, dintctrl & ~sc->dint_end_bit, SUDMAC_DINTCTRL);
+	sudmac_writel(sc, sc->dint_end_bit, SUDMAC_DINTSTSCLR);
+}
+
+static int sudmac_desc_setup(struct shdma_chan *schan,
+			     struct shdma_desc *sdesc,
+			     dma_addr_t src, dma_addr_t dst, size_t *len)
+{
+	struct sudmac_chan *sc = to_chan(schan);
+	struct sudmac_desc *sd = to_desc(sdesc);
+
+	dev_dbg(sc->shdma_chan.dev, "%s: src=%x, dst=%x, len=%d\n",
+		__func__, src, dst, *len);
+
+	if (*len > schan->max_xfer_len)
+		*len = schan->max_xfer_len;
+
+	if (dst)
+		sd->hw.base_addr = dst;
+	else if (src)
+		sd->hw.base_addr = src;
+	sd->hw.base_byte_count = *len;
+
+	return 0;
+}
+
+static void sudmac_halt(struct shdma_chan *schan)
+{
+	struct sudmac_chan *sc = to_chan(schan);
+
+	sudmac_dma_halt(sc);
+}
+
+static bool sudmac_chan_irq(struct shdma_chan *schan, int irq)
+{
+	struct sudmac_chan *sc = to_chan(schan);
+	u32 dintsts = sudmac_readl(sc, SUDMAC_DINTSTS);
+
+	if (!(dintsts & sc->dint_end_bit))
+		return false;
+
+	/* DMA stop */
+	sudmac_dma_halt(sc);
+
+	return true;
+}
+
+static size_t sudmac_get_partial(struct shdma_chan *schan,
+				 struct shdma_desc *sdesc)
+{
+	struct sudmac_chan *sc = to_chan(schan);
+	struct sudmac_desc *sd = to_desc(sdesc);
+	u32 current_byte_count = sudmac_readl(sc, SUDMAC_CH0CBC + sc->offset);
+
+	return sd->hw.base_byte_count - current_byte_count;
+}
+
+static bool sudmac_desc_completed(struct shdma_chan *schan,
+				  struct shdma_desc *sdesc)
+{
+	struct sudmac_chan *sc = to_chan(schan);
+	struct sudmac_desc *sd = to_desc(sdesc);
+	u32 current_addr = sudmac_readl(sc, SUDMAC_CH0CA + sc->offset);
+
+	return sd->hw.base_addr + sd->hw.base_byte_count == current_addr;
+}
+
+static int sudmac_chan_probe(struct sudmac_device *su_dev, int id, int irq,
+			     unsigned long flags)
+{
+	struct shdma_dev *sdev = &su_dev->shdma_dev;
+	struct platform_device *pdev = to_platform_device(sdev->dma_dev.dev);
+	struct sudmac_chan *sc;
+	struct shdma_chan *schan;
+	int err;
+
+	sc = devm_kzalloc(&pdev->dev, sizeof(struct sudmac_chan), GFP_KERNEL);
+	if (!sc) {
+		dev_err(sdev->dma_dev.dev,
+			"No free memory for allocating dma channels!\n");
+		return -ENOMEM;
+	}
+
+	schan = &sc->shdma_chan;
+	schan->max_xfer_len = 64 * 1024 * 1024 - 1;
+
+	shdma_chan_probe(sdev, schan, id);
+
+	sc->base = su_dev->chan_reg;
+
+	/* get platform_data */
+	sc->offset = su_dev->pdata->channel->offset;
+	if (su_dev->pdata->channel->config & SUDMAC_TX_BUFFER_MODE)
+		sc->cfg |= SUDMAC_SENDBUFM;
+	if (su_dev->pdata->channel->config & SUDMAC_RX_END_MODE)
+		sc->cfg |= SUDMAC_RCVENDM;
+	sc->cfg |= (su_dev->pdata->channel->wait << 4) & SUDMAC_LBA_WAIT;
+
+	if (su_dev->pdata->channel->dint_end_bit & SUDMAC_DMA_BIT_CH0)
+		sc->dint_end_bit |= SUDMAC_CH0ENDE;
+	if (su_dev->pdata->channel->dint_end_bit & SUDMAC_DMA_BIT_CH1)
+		sc->dint_end_bit |= SUDMAC_CH1ENDE;
+
+	/* set up channel irq */
+	if (pdev->id >= 0)
+		snprintf(sc->dev_id, sizeof(sc->dev_id), "sudmac%d.%d",
+			 pdev->id, id);
+	else
+		snprintf(sc->dev_id, sizeof(sc->dev_id), "sudmac%d", id);
+
+	err = shdma_request_irq(schan, irq, flags, sc->dev_id);
+	if (err) {
+		dev_err(sdev->dma_dev.dev,
+			"DMA channel %d request_irq failed %d\n", id, err);
+		goto err_no_irq;
+	}
+
+	return 0;
+
+err_no_irq:
+	/* remove from dmaengine device node */
+	shdma_chan_remove(schan);
+	return err;
+}
+
+static void sudmac_chan_remove(struct sudmac_device *su_dev)
+{
+	struct dma_device *dma_dev = &su_dev->shdma_dev.dma_dev;
+	struct shdma_chan *schan;
+	int i;
+
+	shdma_for_each_chan(schan, &su_dev->shdma_dev, i) {
+		struct sudmac_chan *sc = to_chan(schan);
+
+		BUG_ON(!schan);
+
+		shdma_free_irq(&sc->shdma_chan);
+		shdma_chan_remove(schan);
+	}
+	dma_dev->chancnt = 0;
+}
+
+static dma_addr_t sudmac_slave_addr(struct shdma_chan *schan)
+{
+	/* SUDMAC doesn't need the address */
+	return 0;
+}
+
+static struct shdma_desc *sudmac_embedded_desc(void *buf, int i)
+{
+	return &((struct sudmac_desc *)buf)[i].shdma_desc;
+}
+
+static const struct shdma_ops sudmac_shdma_ops = {
+	.desc_completed = sudmac_desc_completed,
+	.halt_channel = sudmac_halt,
+	.channel_busy = sudmac_channel_busy,
+	.slave_addr = sudmac_slave_addr,
+	.desc_setup = sudmac_desc_setup,
+	.set_slave = sudmac_set_slave,
+	.setup_xfer = sudmac_setup_xfer,
+	.start_xfer = sudmac_start_xfer,
+	.embedded_desc = sudmac_embedded_desc,
+	.chan_irq = sudmac_chan_irq,
+	.get_partial = sudmac_get_partial,
+};
+
+static int sudmac_probe(struct platform_device *pdev)
+{
+	struct sudmac_pdata *pdata = pdev->dev.platform_data;
+	int err, i;
+	struct sudmac_device *su_dev;
+	struct dma_device *dma_dev;
+	struct resource *chan, *irq_res;
+
+	/* get platform data */
+	if (!pdata)
+		return -ENODEV;
+
+	chan = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!chan || !irq_res)
+		return -ENODEV;
+
+	err = -ENOMEM;
+	su_dev = devm_kzalloc(&pdev->dev, sizeof(struct sudmac_device),
+			      GFP_KERNEL);
+	if (!su_dev) {
+		dev_err(&pdev->dev, "Not enough memory\n");
+		return err;
+	}
+
+	dma_dev = &su_dev->shdma_dev.dma_dev;
+
+	su_dev->chan_reg = devm_request_and_ioremap(&pdev->dev, chan);
+	if (!su_dev->chan_reg)
+		return err;
+
+	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
+
+	su_dev->shdma_dev.ops = &sudmac_shdma_ops;
+	su_dev->shdma_dev.desc_size = sizeof(struct sudmac_desc);
+	err = shdma_init(&pdev->dev, &su_dev->shdma_dev, pdata->channel_num);
+	if (err < 0)
+		return err;
+
+	/* platform data */
+	su_dev->pdata = pdev->dev.platform_data;
+
+	platform_set_drvdata(pdev, su_dev);
+
+	/* Create DMA Channel */
+	for (i = 0; i < pdata->channel_num; i++) {
+		err = sudmac_chan_probe(su_dev, i, irq_res->start, IRQF_SHARED);
+		if (err)
+			goto chan_probe_err;
+	}
+
+	err = dma_async_device_register(&su_dev->shdma_dev.dma_dev);
+	if (err < 0)
+		goto chan_probe_err;
+
+	return err;
+
+chan_probe_err:
+	sudmac_chan_remove(su_dev);
+
+	platform_set_drvdata(pdev, NULL);
+	shdma_cleanup(&su_dev->shdma_dev);
+
+	return err;
+}
+
+static int sudmac_remove(struct platform_device *pdev)
+{
+	struct sudmac_device *su_dev = platform_get_drvdata(pdev);
+	struct dma_device *dma_dev = &su_dev->shdma_dev.dma_dev;
+
+	dma_async_device_unregister(dma_dev);
+	sudmac_chan_remove(su_dev);
+	shdma_cleanup(&su_dev->shdma_dev);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static struct platform_driver sudmac_driver = {
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= SUDMAC_DRV_NAME,
+	},
+	.probe		= sudmac_probe,
+	.remove		= sudmac_remove,
+};
+module_platform_driver(sudmac_driver);
+
+MODULE_AUTHOR("Yoshihiro Shimoda");
+MODULE_DESCRIPTION("Renesas SUDMAC driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:" SUDMAC_DRV_NAME);