Merge branch 'for-linus' of git://git.infradead.org/users/vkoul/slave-dma

Pull slave-dma updates from Vinod Koul:
 - new driver for BCM2835 used in R-pi
 - new driver for MOXA ART
 - dma_get_any_slave_channel API for DT based systems
 - minor fixes and updates spread acrooss driver

[ The fsl-ssi dual fifo mode support addition clashed badly with the
  other changes to fsl-ssi that came in through the sound merge.  I did
  a very rough cut at fixing up the conflict, but Nicolin Chen (author
  of both sides) will need to verify and check things ]

* 'for-linus' of git://git.infradead.org/users/vkoul/slave-dma: (36 commits)
  dmaengine: mmp_pdma: fix mismerge
  dma: pl08x: Export pl08x_filter_id
  acpi-dma: align documentation with kernel-doc format
  dma: fix vchan_cookie_complete() debug print
  DMA: dmatest: extend the "device" module parameter to 32 characters
  drivers/dma: fix error return code
  dma: omap: Set debug level to debugging messages
  dmaengine: fix kernel-doc style typos for few comments
  dma: tegra: add support for Tegra148/124
  dma: dw: use %pad instead of casting dma_addr_t
  dma: dw: join split up messages
  dma: dw: fix style of multiline comment
  dmaengine: k3dma: fix sparse warnings
  dma: pl330: Use dma_get_slave_channel() in the of xlate callback
  dma: pl330: Differentiate between submitted and issued descriptors
  dmaengine: sirf: Add device_slave_caps interface
  DMA: Freescale: change BWC from 256 bytes to 1024 bytes
  dmaengine: Add MOXA ART DMA engine driver
  dmaengine: Add DMA_PRIVATE to BCM2835 driver
  dma: imx-sdma: Assign a default script number for ROM firmware cases
  ...

21 files changed, 1737 insertions, 184 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index c10eb89..9bed1a2 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -306,6 +306,12 @@ config DMA_OMAP
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 
+config DMA_BCM2835
+	tristate "BCM2835 DMA engine support"
+	depends on (ARCH_BCM2835 || MACH_BCM2708)
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+
 config TI_CPPI41
 	tristate "AM33xx CPPI41 DMA support"
 	depends on ARCH_OMAP
@@ -336,6 +342,14 @@ config K3_DMA
 	  Support the DMA engine for Hisilicon K3 platform
 	  devices.
 
+config MOXART_DMA
+	tristate "MOXART DMA support"
+	depends on ARCH_MOXART
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the MOXA ART SoC DMA controller.
+
 config DMA_ENGINE
 	bool
 
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 0ce2da9..a029d0f4 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -38,7 +38,9 @@ obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
 obj-$(CONFIG_MMP_TDMA) += mmp_tdma.o
 obj-$(CONFIG_DMA_OMAP) += omap-dma.o
+obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o
 obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
 obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o
 obj-$(CONFIG_TI_CPPI41) += cppi41.o
 obj-$(CONFIG_K3_DMA) += k3dma.o
+obj-$(CONFIG_MOXART_DMA) += moxart-dma.o
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index e69b03c..1e506af 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -30,11 +30,12 @@ static DEFINE_MUTEX(acpi_dma_lock);
  * @adev:	ACPI device to match with
  * @adma:	struct acpi_dma of the given DMA controller
  *
- * Returns 1 on success, 0 when no information is available, or appropriate
- * errno value on error.
- *
  * In order to match a device from DSDT table to the corresponding CSRT device
  * we use MMIO address and IRQ.
+ *
+ * Return:
+ * 1 on success, 0 when no information is available, or appropriate errno value
+ * on error.
  */
 static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
 		struct acpi_device *adev, struct acpi_dma *adma)
@@ -101,7 +102,6 @@ static int acpi_dma_parse_resource_group(const struct acpi_csrt_group *grp,
  *
  * We are using this table to get the request line range of the specific DMA
  * controller to be used later.
- *
  */
 static void acpi_dma_parse_csrt(struct acpi_device *adev, struct acpi_dma *adma)
 {
@@ -141,10 +141,11 @@ static void acpi_dma_parse_csrt(struct acpi_device *adev, struct acpi_dma *adma)
  * @data		pointer to controller specific data to be used by
  *			translation function
  *
- * Returns 0 on success or appropriate errno value on error.
- *
  * Allocated memory should be freed with appropriate acpi_dma_controller_free()
  * call.
+ *
+ * Return:
+ * 0 on success or appropriate errno value on error.
  */
 int acpi_dma_controller_register(struct device *dev,
 		struct dma_chan *(*acpi_dma_xlate)
@@ -188,6 +189,9 @@ EXPORT_SYMBOL_GPL(acpi_dma_controller_register);
  * @dev:	struct device of DMA controller
  *
  * Memory allocated by acpi_dma_controller_register() is freed here.
+ *
+ * Return:
+ * 0 on success or appropriate errno value on error.
  */
 int acpi_dma_controller_free(struct device *dev)
 {
@@ -225,6 +229,9 @@ static void devm_acpi_dma_release(struct device *dev, void *res)
  * Managed acpi_dma_controller_register(). DMA controller registered by this
  * function are automatically freed on driver detach. See
  * acpi_dma_controller_register() for more information.
+ *
+ * Return:
+ * 0 on success or appropriate errno value on error.
  */
 int devm_acpi_dma_controller_register(struct device *dev,
 		struct dma_chan *(*acpi_dma_xlate)
@@ -267,8 +274,6 @@ EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_free);
  * @adma:	struct acpi_dma of DMA controller
  * @dma_spec:	dma specifier to update
  *
- * Returns 0, if no information is avaiable, -1 on mismatch, and 1 otherwise.
- *
  * Accordingly to ACPI 5.0 Specification Table 6-170 "Fixed DMA Resource
  * Descriptor":
  *	DMA Request Line bits is a platform-relative number uniquely
@@ -276,6 +281,9 @@ EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_free);
  *	mapping is done in a controller-specific OS driver.
  * That's why we can safely adjust slave_id when the appropriate controller is
  * found.
+ *
+ * Return:
+ * 0, if no information is avaiable, -1 on mismatch, and 1 otherwise.
  */
 static int acpi_dma_update_dma_spec(struct acpi_dma *adma,
 		struct acpi_dma_spec *dma_spec)
@@ -334,7 +342,8 @@ static int acpi_dma_parse_fixed_dma(struct acpi_resource *res, void *data)
  * @dev:	struct device to get DMA request from
  * @index:	index of FixedDMA descriptor for @dev
  *
- * Returns pointer to appropriate dma channel on success or NULL on error.
+ * Return:
+ * Pointer to appropriate dma channel on success or NULL on error.
  */
 struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 		size_t index)
@@ -403,7 +412,8 @@ EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_index);
  * translate the names "tx" and "rx" here based on the most common case where
  * the first FixedDMA descriptor is TX and second is RX.
  *
- * Returns pointer to appropriate dma channel on success or NULL on error.
+ * Return:
+ * Pointer to appropriate dma channel on success or NULL on error.
  */
 struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev,
 		const char *name)
@@ -427,8 +437,10 @@ EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_name);
  * @adma: pointer to ACPI DMA controller data
  *
  * A simple translation function for ACPI based devices. Passes &struct
- * dma_spec to the DMA controller driver provided filter function. Returns
- * pointer to the channel if found or %NULL otherwise.
+ * dma_spec to the DMA controller driver provided filter function.
+ *
+ * Return:
+ * Pointer to the channel if found or %NULL otherwise.
  */
 struct dma_chan *acpi_dma_simple_xlate(struct acpi_dma_spec *dma_spec,
 		struct acpi_dma *adma)
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index ec4ee5c..8114731 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -83,6 +83,7 @@
 #include <linux/dmaengine.h>
 #include <linux/dmapool.h>
 #include <linux/dma-mapping.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
@@ -1771,6 +1772,7 @@ bool pl08x_filter_id(struct dma_chan *chan, void *chan_id)
 
 	return false;
 }
+EXPORT_SYMBOL_GPL(pl08x_filter_id);
 
 /*
  * Just check that the device is there and active
@@ -2167,7 +2169,7 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 	/* Register slave channels */
 	ret = pl08x_dma_init_virtual_channels(pl08x, &pl08x->slave,
 			pl08x->pd->num_slave_channels, true);
-	if (ret <= 0) {
+	if (ret < 0) {
 		dev_warn(&pl08x->adev->dev,
 			"%s failed to enumerate slave channels - %d\n",
 				__func__, ret);
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
new file mode 100644
index 0000000..a036021
--- /dev/null
+++ b/drivers/dma/bcm2835-dma.c
@@ -0,0 +1,707 @@
+/*
+ * BCM2835 DMA engine support
+ *
+ * This driver only supports cyclic DMA transfers
+ * as needed for the I2S module.
+ *
+ * Author:      Florian Meier <florian.meier@koalo.de>
+ *              Copyright 2013
+ *
+ * Based on
+ *	OMAP DMAengine support by Russell King
+ *
+ *	BCM2708 DMA Driver
+ *	Copyright (C) 2010 Broadcom
+ *
+ *	Raspberry Pi PCM I2S ALSA Driver
+ *	Copyright (c) by Phil Poole 2013
+ *
+ *	MARVELL MMP Peripheral DMA Driver
+ *	Copyright 2012 Marvell International Ltd.
+ *
+ * This program 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/spinlock.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+
+#include "virt-dma.h"
+
+struct bcm2835_dmadev {
+	struct dma_device ddev;
+	spinlock_t lock;
+	void __iomem *base;
+	struct device_dma_parameters dma_parms;
+};
+
+struct bcm2835_dma_cb {
+	uint32_t info;
+	uint32_t src;
+	uint32_t dst;
+	uint32_t length;
+	uint32_t stride;
+	uint32_t next;
+	uint32_t pad[2];
+};
+
+struct bcm2835_chan {
+	struct virt_dma_chan vc;
+	struct list_head node;
+
+	struct dma_slave_config	cfg;
+	bool cyclic;
+	unsigned int dreq;
+
+	int ch;
+	struct bcm2835_desc *desc;
+
+	void __iomem *chan_base;
+	int irq_number;
+};
+
+struct bcm2835_desc {
+	struct virt_dma_desc vd;
+	enum dma_transfer_direction dir;
+
+	unsigned int control_block_size;
+	struct bcm2835_dma_cb *control_block_base;
+	dma_addr_t control_block_base_phys;
+
+	unsigned int frames;
+	size_t size;
+};
+
+#define BCM2835_DMA_CS		0x00
+#define BCM2835_DMA_ADDR	0x04
+#define BCM2835_DMA_SOURCE_AD	0x0c
+#define BCM2835_DMA_DEST_AD	0x10
+#define BCM2835_DMA_NEXTCB	0x1C
+
+/* DMA CS Control and Status bits */
+#define BCM2835_DMA_ACTIVE	BIT(0)
+#define BCM2835_DMA_INT	BIT(2)
+#define BCM2835_DMA_ISPAUSED	BIT(4)  /* Pause requested or not active */
+#define BCM2835_DMA_ISHELD	BIT(5)  /* Is held by DREQ flow control */
+#define BCM2835_DMA_ERR	BIT(8)
+#define BCM2835_DMA_ABORT	BIT(30) /* Stop current CB, go to next, WO */
+#define BCM2835_DMA_RESET	BIT(31) /* WO, self clearing */
+
+#define BCM2835_DMA_INT_EN	BIT(0)
+#define BCM2835_DMA_D_INC	BIT(4)
+#define BCM2835_DMA_D_DREQ	BIT(6)
+#define BCM2835_DMA_S_INC	BIT(8)
+#define BCM2835_DMA_S_DREQ	BIT(10)
+
+#define BCM2835_DMA_PER_MAP(x)	((x) << 16)
+
+#define BCM2835_DMA_DATA_TYPE_S8	1
+#define BCM2835_DMA_DATA_TYPE_S16	2
+#define BCM2835_DMA_DATA_TYPE_S32	4
+#define BCM2835_DMA_DATA_TYPE_S128	16
+
+#define BCM2835_DMA_BULK_MASK	BIT(0)
+#define BCM2835_DMA_FIQ_MASK	(BIT(2) | BIT(3))
+
+/* Valid only for channels 0 - 14, 15 has its own base address */
+#define BCM2835_DMA_CHAN(n)	((n) << 8) /* Base address */
+#define BCM2835_DMA_CHANIO(base, n) ((base) + BCM2835_DMA_CHAN(n))
+
+static inline struct bcm2835_dmadev *to_bcm2835_dma_dev(struct dma_device *d)
+{
+	return container_of(d, struct bcm2835_dmadev, ddev);
+}
+
+static inline struct bcm2835_chan *to_bcm2835_dma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct bcm2835_chan, vc.chan);
+}
+
+static inline struct bcm2835_desc *to_bcm2835_dma_desc(
+		struct dma_async_tx_descriptor *t)
+{
+	return container_of(t, struct bcm2835_desc, vd.tx);
+}
+
+static void bcm2835_dma_desc_free(struct virt_dma_desc *vd)
+{
+	struct bcm2835_desc *desc = container_of(vd, struct bcm2835_desc, vd);
+	dma_free_coherent(desc->vd.tx.chan->device->dev,
+			desc->control_block_size,
+			desc->control_block_base,
+			desc->control_block_base_phys);
+	kfree(desc);
+}
+
+static int bcm2835_dma_abort(void __iomem *chan_base)
+{
+	unsigned long cs;
+	long int timeout = 10000;
+
+	cs = readl(chan_base + BCM2835_DMA_CS);
+	if (!(cs & BCM2835_DMA_ACTIVE))
+		return 0;
+
+	/* Write 0 to the active bit - Pause the DMA */
+	writel(0, chan_base + BCM2835_DMA_CS);
+
+	/* Wait for any current AXI transfer to complete */
+	while ((cs & BCM2835_DMA_ISPAUSED) && --timeout) {
+		cpu_relax();
+		cs = readl(chan_base + BCM2835_DMA_CS);
+	}
+
+	/* We'll un-pause when we set of our next DMA */
+	if (!timeout)
+		return -ETIMEDOUT;
+
+	if (!(cs & BCM2835_DMA_ACTIVE))
+		return 0;
+
+	/* Terminate the control block chain */
+	writel(0, chan_base + BCM2835_DMA_NEXTCB);
+
+	/* Abort the whole DMA */
+	writel(BCM2835_DMA_ABORT | BCM2835_DMA_ACTIVE,
+	       chan_base + BCM2835_DMA_CS);
+
+	return 0;
+}
+
+static void bcm2835_dma_start_desc(struct bcm2835_chan *c)
+{
+	struct virt_dma_desc *vd = vchan_next_desc(&c->vc);
+	struct bcm2835_desc *d;
+
+	if (!vd) {
+		c->desc = NULL;
+		return;
+	}
+
+	list_del(&vd->node);
+
+	c->desc = d = to_bcm2835_dma_desc(&vd->tx);
+
+	writel(d->control_block_base_phys, c->chan_base + BCM2835_DMA_ADDR);
+	writel(BCM2835_DMA_ACTIVE, c->chan_base + BCM2835_DMA_CS);
+}
+
+static irqreturn_t bcm2835_dma_callback(int irq, void *data)
+{
+	struct bcm2835_chan *c = data;
+	struct bcm2835_desc *d;
+	unsigned long flags;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+
+	/* Acknowledge interrupt */
+	writel(BCM2835_DMA_INT, c->chan_base + BCM2835_DMA_CS);
+
+	d = c->desc;
+
+	if (d) {
+		/* TODO Only works for cyclic DMA */
+		vchan_cyclic_callback(&d->vd);
+	}
+
+	/* Keep the DMA engine running */
+	writel(BCM2835_DMA_ACTIVE, c->chan_base + BCM2835_DMA_CS);
+
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+static int bcm2835_dma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+
+	dev_dbg(c->vc.chan.device->dev,
+			"Allocating DMA channel %d\n", c->ch);
+
+	return request_irq(c->irq_number,
+			bcm2835_dma_callback, 0, "DMA IRQ", c);
+}
+
+static void bcm2835_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+
+	vchan_free_chan_resources(&c->vc);
+	free_irq(c->irq_number, c);
+
+	dev_dbg(c->vc.chan.device->dev, "Freeing DMA channel %u\n", c->ch);
+}
+
+static size_t bcm2835_dma_desc_size(struct bcm2835_desc *d)
+{
+	return d->size;
+}
+
+static size_t bcm2835_dma_desc_size_pos(struct bcm2835_desc *d, dma_addr_t addr)
+{
+	unsigned int i;
+	size_t size;
+
+	for (size = i = 0; i < d->frames; i++) {
+		struct bcm2835_dma_cb *control_block =
+			&d->control_block_base[i];
+		size_t this_size = control_block->length;
+		dma_addr_t dma;
+
+		if (d->dir == DMA_DEV_TO_MEM)
+			dma = control_block->dst;
+		else
+			dma = control_block->src;
+
+		if (size)
+			size += this_size;
+		else if (addr >= dma && addr < dma + this_size)
+			size += dma + this_size - addr;
+	}
+
+	return size;
+}
+
+static enum dma_status bcm2835_dma_tx_status(struct dma_chan *chan,
+	dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+	struct virt_dma_desc *vd;
+	enum dma_status ret;
+	unsigned long flags;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE || !txstate)
+		return ret;
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	vd = vchan_find_desc(&c->vc, cookie);
+	if (vd) {
+		txstate->residue =
+			bcm2835_dma_desc_size(to_bcm2835_dma_desc(&vd->tx));
+	} else if (c->desc && c->desc->vd.tx.cookie == cookie) {
+		struct bcm2835_desc *d = c->desc;
+		dma_addr_t pos;
+
+		if (d->dir == DMA_MEM_TO_DEV)
+			pos = readl(c->chan_base + BCM2835_DMA_SOURCE_AD);
+		else if (d->dir == DMA_DEV_TO_MEM)
+			pos = readl(c->chan_base + BCM2835_DMA_DEST_AD);
+		else
+			pos = 0;
+
+		txstate->residue = bcm2835_dma_desc_size_pos(d, pos);
+	} else {
+		txstate->residue = 0;
+	}
+
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+
+	return ret;
+}
+
+static void bcm2835_dma_issue_pending(struct dma_chan *chan)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+	unsigned long flags;
+
+	c->cyclic = true; /* Nothing else is implemented */
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+	if (vchan_issue_pending(&c->vc) && !c->desc)
+		bcm2835_dma_start_desc(c);
+
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+}
+
+static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long flags, void *context)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+	enum dma_slave_buswidth dev_width;
+	struct bcm2835_desc *d;
+	dma_addr_t dev_addr;
+	unsigned int es, sync_type;
+	unsigned int frame;
+
+	/* Grab configuration */
+	if (!is_slave_direction(direction)) {
+		dev_err(chan->device->dev, "%s: bad direction?\n", __func__);
+		return NULL;
+	}
+
+	if (direction == DMA_DEV_TO_MEM) {
+		dev_addr = c->cfg.src_addr;
+		dev_width = c->cfg.src_addr_width;
+		sync_type = BCM2835_DMA_S_DREQ;
+	} else {
+		dev_addr = c->cfg.dst_addr;
+		dev_width = c->cfg.dst_addr_width;
+		sync_type = BCM2835_DMA_D_DREQ;
+	}
+
+	/* Bus width translates to the element size (ES) */
+	switch (dev_width) {
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		es = BCM2835_DMA_DATA_TYPE_S32;
+		break;
+	default:
+		return NULL;
+	}
+
+	/* Now allocate and setup the descriptor. */
+	d = kzalloc(sizeof(*d), GFP_NOWAIT);
+	if (!d)
+		return NULL;
+
+	d->dir = direction;
+	d->frames = buf_len / period_len;
+
+	/* Allocate memory for control blocks */
+	d->control_block_size = d->frames * sizeof(struct bcm2835_dma_cb);
+	d->control_block_base = dma_zalloc_coherent(chan->device->dev,
+			d->control_block_size, &d->control_block_base_phys,
+			GFP_NOWAIT);
+
+	if (!d->control_block_base) {
+		kfree(d);
+		return NULL;
+	}
+
+	/*
+	 * Iterate over all frames, create a control block
+	 * for each frame and link them together.
+	 */
+	for (frame = 0; frame < d->frames; frame++) {
+		struct bcm2835_dma_cb *control_block =
+			&d->control_block_base[frame];
+
+		/* Setup adresses */
+		if (d->dir == DMA_DEV_TO_MEM) {
+			control_block->info = BCM2835_DMA_D_INC;
+			control_block->src = dev_addr;
+			control_block->dst = buf_addr + frame * period_len;
+		} else {
+			control_block->info = BCM2835_DMA_S_INC;
+			control_block->src = buf_addr + frame * period_len;
+			control_block->dst = dev_addr;
+		}
+
+		/* Enable interrupt */
+		control_block->info |= BCM2835_DMA_INT_EN;
+
+		/* Setup synchronization */
+		if (sync_type != 0)
+			control_block->info |= sync_type;
+
+		/* Setup DREQ channel */
+		if (c->dreq != 0)
+			control_block->info |=
+				BCM2835_DMA_PER_MAP(c->dreq);
+
+		/* Length of a frame */
+		control_block->length = period_len;
+		d->size += control_block->length;
+
+		/*
+		 * Next block is the next frame.
+		 * This DMA engine driver currently only supports cyclic DMA.
+		 * Therefore, wrap around at number of frames.
+		 */
+		control_block->next = d->control_block_base_phys +
+			sizeof(struct bcm2835_dma_cb)
+			* ((frame + 1) % d->frames);
+	}
+
+	return vchan_tx_prep(&c->vc, &d->vd, flags);
+}
+
+static int bcm2835_dma_slave_config(struct bcm2835_chan *c,
+		struct dma_slave_config *cfg)
+{
+	if ((cfg->direction == DMA_DEV_TO_MEM &&
+	     cfg->src_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES) ||
+	    (cfg->direction == DMA_MEM_TO_DEV &&
+	     cfg->dst_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES) ||
+	    !is_slave_direction(cfg->direction)) {
+		return -EINVAL;
+	}
+
+	c->cfg = *cfg;
+
+	return 0;
+}
+
+static int bcm2835_dma_terminate_all(struct bcm2835_chan *c)
+{
+	struct bcm2835_dmadev *d = to_bcm2835_dma_dev(c->vc.chan.device);
+	unsigned long flags;
+	int timeout = 10000;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&c->vc.lock, flags);
+
+	/* Prevent this channel being scheduled */
+	spin_lock(&d->lock);
+	list_del_init(&c->node);
+	spin_unlock(&d->lock);
+
+	/*
+	 * Stop DMA activity: we assume the callback will not be called
+	 * after bcm_dma_abort() returns (even if it does, it will see
+	 * c->desc is NULL and exit.)
+	 */
+	if (c->desc) {
+		c->desc = NULL;
+		bcm2835_dma_abort(c->chan_base);
+
+		/* Wait for stopping */
+		while (--timeout) {
+			if (!(readl(c->chan_base + BCM2835_DMA_CS) &
+						BCM2835_DMA_ACTIVE))
+				break;
+
+			cpu_relax();
+		}
+
+		if (!timeout)
+			dev_err(d->ddev.dev, "DMA transfer could not be terminated\n");
+	}
+
+	vchan_get_all_descriptors(&c->vc, &head);
+	spin_unlock_irqrestore(&c->vc.lock, flags);
+	vchan_dma_desc_free_list(&c->vc, &head);
+
+	return 0;
+}
+
+static int bcm2835_dma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+	unsigned long arg)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+
+	switch (cmd) {
+	case DMA_SLAVE_CONFIG:
+		return bcm2835_dma_slave_config(c,
+				(struct dma_slave_config *)arg);
+
+	case DMA_TERMINATE_ALL:
+		return bcm2835_dma_terminate_all(c);
+
+	default:
+		return -ENXIO;
+	}
+}
+
+static int bcm2835_dma_chan_init(struct bcm2835_dmadev *d, int chan_id, int irq)
+{
+	struct bcm2835_chan *c;
+
+	c = devm_kzalloc(d->ddev.dev, sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return -ENOMEM;
+
+	c->vc.desc_free = bcm2835_dma_desc_free;
+	vchan_init(&c->vc, &d->ddev);
+	INIT_LIST_HEAD(&c->node);
+
+	d->ddev.chancnt++;
+
+	c->chan_base = BCM2835_DMA_CHANIO(d->base, chan_id);
+	c->ch = chan_id;
+	c->irq_number = irq;
+
+	return 0;
+}
+
+static void bcm2835_dma_free(struct bcm2835_dmadev *od)
+{
+	struct bcm2835_chan *c, *next;
+
+	list_for_each_entry_safe(c, next, &od->ddev.channels,
+				 vc.chan.device_node) {
+		list_del(&c->vc.chan.device_node);
+		tasklet_kill(&c->vc.task);
+	}
+}
+
+static const struct of_device_id bcm2835_dma_of_match[] = {
+	{ .compatible = "brcm,bcm2835-dma", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, bcm2835_dma_of_match);
+
+static struct dma_chan *bcm2835_dma_xlate(struct of_phandle_args *spec,
+					   struct of_dma *ofdma)
+{
+	struct bcm2835_dmadev *d = ofdma->of_dma_data;
+	struct dma_chan *chan;
+
+	chan = dma_get_any_slave_channel(&d->ddev);
+	if (!chan)
+		return NULL;
+
+	/* Set DREQ from param */
+	to_bcm2835_dma_chan(chan)->dreq = spec->args[0];
+
+	return chan;
+}
+
+static int bcm2835_dma_device_slave_caps(struct dma_chan *dchan,
+	struct dma_slave_caps *caps)
+{
+	caps->src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	caps->dstn_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	caps->cmd_pause = false;
+	caps->cmd_terminate = true;
+
+	return 0;
+}
+
+static int bcm2835_dma_probe(struct platform_device *pdev)
+{
+	struct bcm2835_dmadev *od;
+	struct resource *res;
+	void __iomem *base;
+	int rc;
+	int i;
+	int irq;
+	uint32_t chans_available;
+
+	if (!pdev->dev.dma_mask)
+		pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
+
+	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+	if (rc)
+		return rc;
+
+	od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
+	if (!od)
+		return -ENOMEM;
+
+	pdev->dev.dma_parms = &od->dma_parms;
+	dma_set_max_seg_size(&pdev->dev, 0x3FFFFFFF);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	od->base = base;
+
+	dma_cap_set(DMA_SLAVE, od->ddev.cap_mask);
+	dma_cap_set(DMA_PRIVATE, od->ddev.cap_mask);
+	dma_cap_set(DMA_CYCLIC, od->ddev.cap_mask);
+	od->ddev.device_alloc_chan_resources = bcm2835_dma_alloc_chan_resources;
+	od->ddev.device_free_chan_resources = bcm2835_dma_free_chan_resources;
+	od->ddev.device_tx_status = bcm2835_dma_tx_status;
+	od->ddev.device_issue_pending = bcm2835_dma_issue_pending;
+	od->ddev.device_slave_caps = bcm2835_dma_device_slave_caps;
+	od->ddev.device_prep_dma_cyclic = bcm2835_dma_prep_dma_cyclic;
+	od->ddev.device_control = bcm2835_dma_control;
+	od->ddev.dev = &pdev->dev;
+	INIT_LIST_HEAD(&od->ddev.channels);
+	spin_lock_init(&od->lock);
+
+	platform_set_drvdata(pdev, od);
+
+	/* Request DMA channel mask from device tree */
+	if (of_property_read_u32(pdev->dev.of_node,
+			"brcm,dma-channel-mask",
+			&chans_available)) {
+		dev_err(&pdev->dev, "Failed to get channel mask\n");
+		rc = -EINVAL;
+		goto err_no_dma;
+	}
+
+	/*
+	 * Do not use the FIQ and BULK channels,
+	 * because they are used by the GPU.
+	 */
+	chans_available &= ~(BCM2835_DMA_FIQ_MASK | BCM2835_DMA_BULK_MASK);
+
+	for (i = 0; i < pdev->num_resources; i++) {
+		irq = platform_get_irq(pdev, i);
+		if (irq < 0)
+			break;
+
+		if (chans_available & (1 << i)) {
+			rc = bcm2835_dma_chan_init(od, i, irq);
+			if (rc)
+				goto err_no_dma;
+		}
+	}
+
+	dev_dbg(&pdev->dev, "Initialized %i DMA channels\n", i);
+
+	/* Device-tree DMA controller registration */
+	rc = of_dma_controller_register(pdev->dev.of_node,
+			bcm2835_dma_xlate, od);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to register DMA controller\n");
+		goto err_no_dma;
+	}
+
+	rc = dma_async_device_register(&od->ddev);
+	if (rc) {
+		dev_err(&pdev->dev,
+			"Failed to register slave DMA engine device: %d\n", rc);
+		goto err_no_dma;
+	}
+
+	dev_dbg(&pdev->dev, "Load BCM2835 DMA engine driver\n");
+
+	return 0;
+
+err_no_dma:
+	bcm2835_dma_free(od);
+	return rc;
+}
+
+static int bcm2835_dma_remove(struct platform_device *pdev)
+{
+	struct bcm2835_dmadev *od = platform_get_drvdata(pdev);
+
+	dma_async_device_unregister(&od->ddev);
+	bcm2835_dma_free(od);
+
+	return 0;
+}
+
+static struct platform_driver bcm2835_dma_driver = {
+	.probe	= bcm2835_dma_probe,
+	.remove	= bcm2835_dma_remove,
+	.driver = {
+		.name = "bcm2835-dma",
+		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(bcm2835_dma_of_match),
+	},
+};
+
+module_platform_driver(bcm2835_dma_driver);
+
+MODULE_ALIAS("platform:bcm2835-dma");
+MODULE_DESCRIPTION("BCM2835 DMA engine driver");
+MODULE_AUTHOR("Florian Meier <florian.meier@koalo.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index c29dacf..c18aebf 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -972,8 +972,10 @@ static int cppi41_dma_probe(struct platform_device *pdev)
 		goto err_chans;
 
 	irq = irq_of_parse_and_map(dev->of_node, 0);
-	if (!irq)
+	if (!irq) {
+		ret = -EINVAL;
 		goto err_irq;
+	}
 
 	cppi_writel(USBSS_IRQ_PD_COMP, cdd->usbss_mem + USBSS_IRQ_ENABLER);
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 9dfcaf5c..05b6dea 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -31,7 +31,7 @@ module_param_string(channel, test_channel, sizeof(test_channel),
 		S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(channel, "Bus ID of the channel to test (default: any)");
 
-static char test_device[20];
+static char test_device[32];
 module_param_string(device, test_device, sizeof(test_device),
 		S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(device, "Bus ID of the DMA Engine to test (default: any)");
@@ -89,7 +89,7 @@ MODULE_PARM_DESC(verbose, "Enable \"success\" result messages (default: off)");
 struct dmatest_params {
 	unsigned int	buf_size;
 	char		channel[20];
-	char		device[20];
+	char		device[32];
 	unsigned int	threads_per_chan;
 	unsigned int	max_channels;
 	unsigned int	iterations;
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 7516be4..13ac3f2 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -218,8 +218,10 @@ static inline void dwc_do_single_block(struct dw_dma_chan *dwc,
 	struct dw_dma	*dw = to_dw_dma(dwc->chan.device);
 	u32		ctllo;
 
-	/* Software emulation of LLP mode relies on interrupts to continue
-	 * multi block transfer. */
+	/*
+	 * Software emulation of LLP mode relies on interrupts to continue
+	 * multi block transfer.
+	 */
 	ctllo = desc->lli.ctllo | DWC_CTLL_INT_EN;
 
 	channel_writel(dwc, SAR, desc->lli.sar);
@@ -253,8 +255,7 @@ static void dwc_dostart(struct dw_dma_chan *dwc, struct dw_desc *first)
 						&dwc->flags);
 		if (was_soft_llp) {
 			dev_err(chan2dev(&dwc->chan),
-				"BUG: Attempted to start new LLP transfer "
-				"inside ongoing one\n");
+				"BUG: Attempted to start new LLP transfer inside ongoing one\n");
 			return;
 		}
 
@@ -420,8 +421,7 @@ static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		return;
 	}
 
-	dev_vdbg(chan2dev(&dwc->chan), "%s: llp=0x%llx\n", __func__,
-			(unsigned long long)llp);
+	dev_vdbg(chan2dev(&dwc->chan), "%s: llp=%pad\n", __func__, &llp);
 
 	list_for_each_entry_safe(desc, _desc, &dwc->active_list, desc_node) {
 		/* Initial residue value */
@@ -567,9 +567,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
 			unlikely(status_xfer & dwc->mask)) {
 		int i;
 
-		dev_err(chan2dev(&dwc->chan), "cyclic DMA unexpected %s "
-				"interrupt, stopping DMA transfer\n",
-				status_xfer ? "xfer" : "error");
+		dev_err(chan2dev(&dwc->chan),
+			"cyclic DMA unexpected %s interrupt, stopping DMA transfer\n",
+			status_xfer ? "xfer" : "error");
 
 		spin_lock_irqsave(&dwc->lock, flags);
 
@@ -711,9 +711,8 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	u32			ctllo;
 
 	dev_vdbg(chan2dev(chan),
-			"%s: d0x%llx s0x%llx l0x%zx f0x%lx\n", __func__,
-			(unsigned long long)dest, (unsigned long long)src,
-			len, flags);
+			"%s: d%pad s%pad l0x%zx f0x%lx\n", __func__,
+			&dest, &src, len, flags);
 
 	if (unlikely(!len)) {
 		dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__);
@@ -1401,9 +1400,9 @@ struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
 	/* Let's make a cyclic list */
 	last->lli.llp = cdesc->desc[0]->txd.phys;
 
-	dev_dbg(chan2dev(&dwc->chan), "cyclic prepared buf 0x%llx len %zu "
-			"period %zu periods %d\n", (unsigned long long)buf_addr,
-			buf_len, period_len, periods);
+	dev_dbg(chan2dev(&dwc->chan),
+			"cyclic prepared buf %pad len %zu period %zu periods %d\n",
+			&buf_addr, buf_len, period_len, periods);
 
 	cdesc->periods = periods;
 	dwc->cdesc = cdesc;
@@ -1603,9 +1602,11 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 			dev_dbg(chip->dev, "DWC_PARAMS[%d]: 0x%08x\n", i,
 					   dwc_params);
 
-			/* Decode maximum block size for given channel. The
+			/*
+			 * Decode maximum block size for given channel. The
 			 * stored 4 bit value represents blocks from 0x00 for 3
-			 * up to 0x0a for 4095. */
+			 * up to 0x0a for 4095.
+			 */
 			dwc->block_size =
 				(4 << ((max_blk_size >> 4 * i) & 0xf)) - 1;
 			dwc->nollp =
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index 2539ea0..cd8da45 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -699,8 +699,8 @@ static int edma_alloc_chan_resources(struct dma_chan *chan)
 	echan->alloced = true;
 	echan->slot[0] = echan->ch_num;
 
-	dev_info(dev, "allocated channel for %u:%u\n",
-		 EDMA_CTLR(echan->ch_num), EDMA_CHAN_SLOT(echan->ch_num));
+	dev_dbg(dev, "allocated channel for %u:%u\n",
+		EDMA_CTLR(echan->ch_num), EDMA_CHAN_SLOT(echan->ch_num));
 
 	return 0;
 
@@ -736,7 +736,7 @@ static void edma_free_chan_resources(struct dma_chan *chan)
 		echan->alloced = false;
 	}
 
-	dev_info(dev, "freeing channel for %u\n", echan->ch_num);
+	dev_dbg(dev, "freeing channel for %u\n", echan->ch_num);
 }
 
 /* Send pending descriptor to hardware */
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 1ffc244..d56e835 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -41,7 +41,7 @@
  * channel is allowed to transfer before the DMA engine pauses
  * the current channel and switches to the next channel
  */
-#define FSL_DMA_MR_BWC         0x08000000
+#define FSL_DMA_MR_BWC         0x0A000000
 
 /* Special MR definition for MPC8349 */
 #define FSL_DMA_MR_EOTIE	0x00000080
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index c75679d..4e79183 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -323,6 +323,7 @@ struct sdma_engine {
 	struct clk			*clk_ipg;
 	struct clk			*clk_ahb;
 	spinlock_t			channel_0_lock;
+	u32				script_number;
 	struct sdma_script_start_addrs	*script_addrs;
 	const struct sdma_driver_data	*drvdata;
 };
@@ -724,6 +725,10 @@ static void sdma_get_pc(struct sdma_channel *sdmac,
 		per_2_emi = sdma->script_addrs->app_2_mcu_addr;
 		emi_2_per = sdma->script_addrs->mcu_2_app_addr;
 		break;
+	case IMX_DMATYPE_SSI_DUAL:
+		per_2_emi = sdma->script_addrs->ssish_2_mcu_addr;
+		emi_2_per = sdma->script_addrs->mcu_2_ssish_addr;
+		break;
 	case IMX_DMATYPE_SSI_SP:
 	case IMX_DMATYPE_MMC:
 	case IMX_DMATYPE_SDHC:
@@ -1238,6 +1243,7 @@ static void sdma_issue_pending(struct dma_chan *chan)
 }
 
 #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1	34
+#define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V2	38
 
 static void sdma_add_scripts(struct sdma_engine *sdma,
 		const struct sdma_script_start_addrs *addr)
@@ -1246,7 +1252,11 @@ static void sdma_add_scripts(struct sdma_engine *sdma,
 	s32 *saddr_arr = (u32 *)sdma->script_addrs;
 	int i;
 
-	for (i = 0; i < SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1; i++)
+	/* use the default firmware in ROM if missing external firmware */
+	if (!sdma->script_number)
+		sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1;
+
+	for (i = 0; i < sdma->script_number; i++)
 		if (addr_arr[i] > 0)
 			saddr_arr[i] = addr_arr[i];
 }
@@ -1272,6 +1282,17 @@ static void sdma_load_firmware(const struct firmware *fw, void *context)
 		goto err_firmware;
 	if (header->ram_code_start + header->ram_code_size > fw->size)
 		goto err_firmware;
+	switch (header->version_major) {
+		case 1:
+			sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1;
+			break;
+		case 2:
+			sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V2;
+			break;
+		default:
+			dev_err(sdma->dev, "unknown firmware version\n");
+			goto err_firmware;
+	}
 
 	addr = (void *)header + header->script_addrs_start;
 	ram_code = (void *)header + header->ram_code_start;
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index e260754..a1f911a 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -477,7 +477,7 @@ static struct dma_async_tx_descriptor *k3_dma_prep_slave_sg(
 	dma_addr_t addr, src = 0, dst = 0;
 	int num = sglen, i;
 
-	if (sgl == 0)
+	if (sgl == NULL)
 		return NULL;
 
 	for_each_sg(sgl, sg, sglen, i) {
@@ -817,7 +817,7 @@ static int k3_dma_resume(struct device *dev)
 	return 0;
 }
 
-SIMPLE_DEV_PM_OPS(k3_dma_pmops, k3_dma_suspend, k3_dma_resume);
+static SIMPLE_DEV_PM_OPS(k3_dma_pmops, k3_dma_suspend, k3_dma_resume);
 
 static struct platform_driver k3_pdma_driver = {
 	.driver		= {
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index c6a01ea..b439679 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -5,6 +5,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -32,38 +33,37 @@
 #define DTADR		0x0208
 #define DCMD		0x020c
 
-#define DCSR_RUN	(1 << 31)	/* Run Bit (read / write) */
-#define DCSR_NODESC	(1 << 30)	/* No-Descriptor Fetch (read / write) */
-#define DCSR_STOPIRQEN	(1 << 29)	/* Stop Interrupt Enable (read / write) */
-#define DCSR_REQPEND	(1 << 8)	/* Request Pending (read-only) */
-#define DCSR_STOPSTATE	(1 << 3)	/* Stop State (read-only) */
-#define DCSR_ENDINTR	(1 << 2)	/* End Interrupt (read / write) */
-#define DCSR_STARTINTR	(1 << 1)	/* Start Interrupt (read / write) */
-#define DCSR_BUSERR	(1 << 0)	/* Bus Error Interrupt (read / write) */
-
-#define DCSR_EORIRQEN	(1 << 28)       /* End of Receive Interrupt Enable (R/W) */
-#define DCSR_EORJMPEN	(1 << 27)       /* Jump to next descriptor on EOR */
-#define DCSR_EORSTOPEN	(1 << 26)       /* STOP on an EOR */
-#define DCSR_SETCMPST	(1 << 25)       /* Set Descriptor Compare Status */
-#define DCSR_CLRCMPST	(1 << 24)       /* Clear Descriptor Compare Status */
-#define DCSR_CMPST	(1 << 10)       /* The Descriptor Compare Status */
-#define DCSR_EORINTR	(1 << 9)        /* The end of Receive */
-
-#define DRCMR(n)	((((n) < 64) ? 0x0100 : 0x1100) + \
-				 (((n) & 0x3f) << 2))
-#define DRCMR_MAPVLD	(1 << 7)	/* Map Valid (read / write) */
-#define DRCMR_CHLNUM	0x1f		/* mask for Channel Number (read / write) */
+#define DCSR_RUN	BIT(31)	/* Run Bit (read / write) */
+#define DCSR_NODESC	BIT(30)	/* No-Descriptor Fetch (read / write) */
+#define DCSR_STOPIRQEN	BIT(29)	/* Stop Interrupt Enable (read / write) */
+#define DCSR_REQPEND	BIT(8)	/* Request Pending (read-only) */
+#define DCSR_STOPSTATE	BIT(3)	/* Stop State (read-only) */
+#define DCSR_ENDINTR	BIT(2)	/* End Interrupt (read / write) */
+#define DCSR_STARTINTR	BIT(1)	/* Start Interrupt (read / write) */
+#define DCSR_BUSERR	BIT(0)	/* Bus Error Interrupt (read / write) */
+
+#define DCSR_EORIRQEN	BIT(28)	/* End of Receive Interrupt Enable (R/W) */
+#define DCSR_EORJMPEN	BIT(27)	/* Jump to next descriptor on EOR */
+#define DCSR_EORSTOPEN	BIT(26)	/* STOP on an EOR */
+#define DCSR_SETCMPST	BIT(25)	/* Set Descriptor Compare Status */
+#define DCSR_CLRCMPST	BIT(24)	/* Clear Descriptor Compare Status */
+#define DCSR_CMPST	BIT(10)	/* The Descriptor Compare Status */
+#define DCSR_EORINTR	BIT(9)	/* The end of Receive */
+
+#define DRCMR(n)	((((n) < 64) ? 0x0100 : 0x1100) + (((n) & 0x3f) << 2))
+#define DRCMR_MAPVLD	BIT(7)	/* Map Valid (read / write) */
+#define DRCMR_CHLNUM	0x1f	/* mask for Channel Number (read / write) */
 
 #define DDADR_DESCADDR	0xfffffff0	/* Address of next descriptor (mask) */
-#define DDADR_STOP	(1 << 0)	/* Stop (read / write) */
-
-#define DCMD_INCSRCADDR	(1 << 31)	/* Source Address Increment Setting. */
-#define DCMD_INCTRGADDR	(1 << 30)	/* Target Address Increment Setting. */
-#define DCMD_FLOWSRC	(1 << 29)	/* Flow Control by the source. */
-#define DCMD_FLOWTRG	(1 << 28)	/* Flow Control by the target. */
-#define DCMD_STARTIRQEN	(1 << 22)	/* Start Interrupt Enable */
-#define DCMD_ENDIRQEN	(1 << 21)	/* End Interrupt Enable */
-#define DCMD_ENDIAN	(1 << 18)	/* Device Endian-ness. */
+#define DDADR_STOP	BIT(0)	/* Stop (read / write) */
+
+#define DCMD_INCSRCADDR	BIT(31)	/* Source Address Increment Setting. */
+#define DCMD_INCTRGADDR	BIT(30)	/* Target Address Increment Setting. */
+#define DCMD_FLOWSRC	BIT(29)	/* Flow Control by the source. */
+#define DCMD_FLOWTRG	BIT(28)	/* Flow Control by the target. */
+#define DCMD_STARTIRQEN	BIT(22)	/* Start Interrupt Enable */
+#define DCMD_ENDIRQEN	BIT(21)	/* End Interrupt Enable */
+#define DCMD_ENDIAN	BIT(18)	/* Device Endian-ness. */
 #define DCMD_BURST8	(1 << 16)	/* 8 byte burst */
 #define DCMD_BURST16	(2 << 16)	/* 16 byte burst */
 #define DCMD_BURST32	(3 << 16)	/* 32 byte burst */
@@ -132,10 +132,14 @@ struct mmp_pdma_device {
 	spinlock_t phy_lock; /* protect alloc/free phy channels */
 };
 
-#define tx_to_mmp_pdma_desc(tx) container_of(tx, struct mmp_pdma_desc_sw, async_tx)
-#define to_mmp_pdma_desc(lh) container_of(lh, struct mmp_pdma_desc_sw, node)
-#define to_mmp_pdma_chan(dchan) container_of(dchan, struct mmp_pdma_chan, chan)
-#define to_mmp_pdma_dev(dmadev) container_of(dmadev, struct mmp_pdma_device, device)
+#define tx_to_mmp_pdma_desc(tx)					\
+	container_of(tx, struct mmp_pdma_desc_sw, async_tx)
+#define to_mmp_pdma_desc(lh)					\
+	container_of(lh, struct mmp_pdma_desc_sw, node)
+#define to_mmp_pdma_chan(dchan)					\
+	container_of(dchan, struct mmp_pdma_chan, chan)
+#define to_mmp_pdma_dev(dmadev)					\
+	container_of(dmadev, struct mmp_pdma_device, device)
 
 static void set_desc(struct mmp_pdma_phy *phy, dma_addr_t addr)
 {
@@ -162,19 +166,18 @@ static void enable_chan(struct mmp_pdma_phy *phy)
 	writel(dalgn, phy->base + DALGN);
 
 	reg = (phy->idx << 2) + DCSR;
-	writel(readl(phy->base + reg) | DCSR_RUN,
-					phy->base + reg);
+	writel(readl(phy->base + reg) | DCSR_RUN, phy->base + reg);
 }
 
 static void disable_chan(struct mmp_pdma_phy *phy)
 {
 	u32 reg;
 
-	if (phy) {
-		reg = (phy->idx << 2) + DCSR;
-		writel(readl(phy->base + reg) & ~DCSR_RUN,
-						phy->base + reg);
-	}
+	if (!phy)
+		return;
+
+	reg = (phy->idx << 2) + DCSR;
+	writel(readl(phy->base + reg) & ~DCSR_RUN, phy->base + reg);
 }
 
 static int clear_chan_irq(struct mmp_pdma_phy *phy)
@@ -183,26 +186,27 @@ static int clear_chan_irq(struct mmp_pdma_phy *phy)
 	u32 dint = readl(phy->base + DINT);
 	u32 reg = (phy->idx << 2) + DCSR;
 
-	if (dint & BIT(phy->idx)) {
-		/* clear irq */
-		dcsr = readl(phy->base + reg);
-		writel(dcsr, phy->base + reg);
-		if ((dcsr & DCSR_BUSERR) && (phy->vchan))
-			dev_warn(phy->vchan->dev, "DCSR_BUSERR\n");
-		return 0;
-	}
-	return -EAGAIN;
+	if (!(dint & BIT(phy->idx)))
+		return -EAGAIN;
+
+	/* clear irq */
+	dcsr = readl(phy->base + reg);
+	writel(dcsr, phy->base + reg);
+	if ((dcsr & DCSR_BUSERR) && (phy->vchan))
+		dev_warn(phy->vchan->dev, "DCSR_BUSERR\n");
+
+	return 0;
 }
 
 static irqreturn_t mmp_pdma_chan_handler(int irq, void *dev_id)
 {
 	struct mmp_pdma_phy *phy = dev_id;
 
-	if (clear_chan_irq(phy) == 0) {
-		tasklet_schedule(&phy->vchan->tasklet);
-		return IRQ_HANDLED;
-	} else
+	if (clear_chan_irq(phy) != 0)
 		return IRQ_NONE;
+
+	tasklet_schedule(&phy->vchan->tasklet);
+	return IRQ_HANDLED;
 }
 
 static irqreturn_t mmp_pdma_int_handler(int irq, void *dev_id)
@@ -224,8 +228,8 @@ static irqreturn_t mmp_pdma_int_handler(int irq, void *dev_id)
 
 	if (irq_num)
 		return IRQ_HANDLED;
-	else
-		return IRQ_NONE;
+
+	return IRQ_NONE;
 }
 
 /* lookup free phy channel as descending priority */
@@ -245,9 +249,9 @@ static struct mmp_pdma_phy *lookup_phy(struct mmp_pdma_chan *pchan)
 	 */
 
 	spin_lock_irqsave(&pdev->phy_lock, flags);
-	for (prio = 0; prio <= (((pdev->dma_channels - 1) & 0xf) >> 2); prio++) {
+	for (prio = 0; prio <= ((pdev->dma_channels - 1) & 0xf) >> 2; prio++) {
 		for (i = 0; i < pdev->dma_channels; i++) {
-			if (prio != ((i & 0xf) >> 2))
+			if (prio != (i & 0xf) >> 2)
 				continue;
 			phy = &pdev->phy[i];
 			if (!phy->vchan) {
@@ -389,14 +393,16 @@ static int mmp_pdma_alloc_chan_resources(struct dma_chan *dchan)
 	if (chan->desc_pool)
 		return 1;
 
-	chan->desc_pool =
-		dma_pool_create(dev_name(&dchan->dev->device), chan->dev,
-				  sizeof(struct mmp_pdma_desc_sw),
-				  __alignof__(struct mmp_pdma_desc_sw), 0);
+	chan->desc_pool = dma_pool_create(dev_name(&dchan->dev->device),
+					  chan->dev,
+					  sizeof(struct mmp_pdma_desc_sw),
+					  __alignof__(struct mmp_pdma_desc_sw),
+					  0);
 	if (!chan->desc_pool) {
 		dev_err(chan->dev, "unable to allocate descriptor pool\n");
 		return -ENOMEM;
 	}
+
 	mmp_pdma_free_phy(chan);
 	chan->idle = true;
 	chan->dev_addr = 0;
@@ -404,7 +410,7 @@ static int mmp_pdma_alloc_chan_resources(struct dma_chan *dchan)
 }
 
 static void mmp_pdma_free_desc_list(struct mmp_pdma_chan *chan,
-				  struct list_head *list)
+				    struct list_head *list)
 {
 	struct mmp_pdma_desc_sw *desc, *_desc;
 
@@ -434,8 +440,8 @@ static void mmp_pdma_free_chan_resources(struct dma_chan *dchan)
 
 static struct dma_async_tx_descriptor *
 mmp_pdma_prep_memcpy(struct dma_chan *dchan,
-	dma_addr_t dma_dst, dma_addr_t dma_src,
-	size_t len, unsigned long flags)
+		     dma_addr_t dma_dst, dma_addr_t dma_src,
+		     size_t len, unsigned long flags)
 {
 	struct mmp_pdma_chan *chan;
 	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
@@ -515,8 +521,8 @@ fail:
 
 static struct dma_async_tx_descriptor *
 mmp_pdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
-			 unsigned int sg_len, enum dma_transfer_direction dir,
-			 unsigned long flags, void *context)
+		       unsigned int sg_len, enum dma_transfer_direction dir,
+		       unsigned long flags, void *context)
 {
 	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
 	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new = NULL;
@@ -591,10 +597,11 @@ fail:
 	return NULL;
 }
 
-static struct dma_async_tx_descriptor *mmp_pdma_prep_dma_cyclic(
-	struct dma_chan *dchan, dma_addr_t buf_addr, size_t len,
-	size_t period_len, enum dma_transfer_direction direction,
-	unsigned long flags, void *context)
+static struct dma_async_tx_descriptor *
+mmp_pdma_prep_dma_cyclic(struct dma_chan *dchan,
+			 dma_addr_t buf_addr, size_t len, size_t period_len,
+			 enum dma_transfer_direction direction,
+			 unsigned long flags, void *context)
 {
 	struct mmp_pdma_chan *chan;
 	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
@@ -636,8 +643,8 @@ static struct dma_async_tx_descriptor *mmp_pdma_prep_dma_cyclic(
 			goto fail;
 		}
 
-		new->desc.dcmd = chan->dcmd | DCMD_ENDIRQEN |
-					(DCMD_LENGTH & period_len);
+		new->desc.dcmd = (chan->dcmd | DCMD_ENDIRQEN |
+				  (DCMD_LENGTH & period_len));
 		new->desc.dsadr = dma_src;
 		new->desc.dtadr = dma_dst;
 
@@ -677,12 +684,11 @@ fail:
 }
 
 static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
-		unsigned long arg)
+			    unsigned long arg)
 {
 	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
 	struct dma_slave_config *cfg = (void *)arg;
 	unsigned long flags;
-	int ret = 0;
 	u32 maxburst = 0, addr = 0;
 	enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
 
@@ -739,11 +745,12 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 		return -ENOSYS;
 	}
 
-	return ret;
+	return 0;
 }
 
 static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan,
-			dma_cookie_t cookie, struct dma_tx_state *txstate)
+					  dma_cookie_t cookie,
+					  struct dma_tx_state *txstate)
 {
 	return dma_cookie_status(dchan, cookie, txstate);
 }
@@ -845,15 +852,14 @@ static int mmp_pdma_remove(struct platform_device *op)
 	return 0;
 }
 
-static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev,
-							int idx, int irq)
+static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev, int idx, int irq)
 {
 	struct mmp_pdma_phy *phy  = &pdev->phy[idx];
 	struct mmp_pdma_chan *chan;
 	int ret;
 
-	chan = devm_kzalloc(pdev->dev,
-			sizeof(struct mmp_pdma_chan), GFP_KERNEL);
+	chan = devm_kzalloc(pdev->dev, sizeof(struct mmp_pdma_chan),
+			    GFP_KERNEL);
 	if (chan == NULL)
 		return -ENOMEM;
 
@@ -861,8 +867,8 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev,
 	phy->base = pdev->base;
 
 	if (irq) {
-		ret = devm_request_irq(pdev->dev, irq,
-			mmp_pdma_chan_handler, 0, "pdma", phy);
+		ret = devm_request_irq(pdev->dev, irq, mmp_pdma_chan_handler, 0,
+				       "pdma", phy);
 		if (ret) {
 			dev_err(pdev->dev, "channel request irq fail!\n");
 			return ret;
@@ -877,8 +883,7 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev,
 	INIT_LIST_HEAD(&chan->chain_running);
 
 	/* register virt channel to dma engine */
-	list_add_tail(&chan->chan.device_node,
-			&pdev->device.channels);
+	list_add_tail(&chan->chan.device_node, &pdev->device.channels);
 
 	return 0;
 }
@@ -894,14 +899,12 @@ static struct dma_chan *mmp_pdma_dma_xlate(struct of_phandle_args *dma_spec,
 {
 	struct mmp_pdma_device *d = ofdma->of_dma_data;
 	struct dma_chan *chan;
-	struct mmp_pdma_chan *c;
 
 	chan = dma_get_any_slave_channel(&d->device);
 	if (!chan)
 		return NULL;
 
-	c = to_mmp_pdma_chan(chan);
-	c->drcmr = dma_spec->args[0];
+	to_mmp_pdma_chan(chan)->drcmr = dma_spec->args[0];
 
 	return chan;
 }
@@ -918,6 +921,7 @@ static int mmp_pdma_probe(struct platform_device *op)
 	pdev = devm_kzalloc(&op->dev, sizeof(*pdev), GFP_KERNEL);
 	if (!pdev)
 		return -ENOMEM;
+
 	pdev->dev = &op->dev;
 
 	spin_lock_init(&pdev->phy_lock);
@@ -929,8 +933,8 @@ static int mmp_pdma_probe(struct platform_device *op)
 
 	of_id = of_match_device(mmp_pdma_dt_ids, pdev->dev);
 	if (of_id)
-		of_property_read_u32(pdev->dev->of_node,
-				"#dma-channels", &dma_channels);
+		of_property_read_u32(pdev->dev->of_node, "#dma-channels",
+				     &dma_channels);
 	else if (pdata && pdata->dma_channels)
 		dma_channels = pdata->dma_channels;
 	else
@@ -942,8 +946,9 @@ static int mmp_pdma_probe(struct platform_device *op)
 			irq_num++;
 	}
 
-	pdev->phy = devm_kzalloc(pdev->dev,
-		dma_channels * sizeof(struct mmp_pdma_chan), GFP_KERNEL);
+	pdev->phy = devm_kcalloc(pdev->dev,
+				 dma_channels, sizeof(struct mmp_pdma_chan),
+				 GFP_KERNEL);
 	if (pdev->phy == NULL)
 		return -ENOMEM;
 
@@ -952,8 +957,8 @@ static int mmp_pdma_probe(struct platform_device *op)
 	if (irq_num != dma_channels) {
 		/* all chan share one irq, demux inside */
 		irq = platform_get_irq(op, 0);
-		ret = devm_request_irq(pdev->dev, irq,
-			mmp_pdma_int_handler, 0, "pdma", pdev);
+		ret = devm_request_irq(pdev->dev, irq, mmp_pdma_int_handler, 0,
+				       "pdma", pdev);
 		if (ret)
 			return ret;
 	}
@@ -1029,7 +1034,7 @@ bool mmp_pdma_filter_fn(struct dma_chan *chan, void *param)
 	if (chan->device->dev->driver != &mmp_pdma_driver.driver)
 		return false;
 
-	c->drcmr = *(unsigned int *) param;
+	c->drcmr = *(unsigned int *)param;
 
 	return true;
 }
@@ -1037,6 +1042,6 @@ EXPORT_SYMBOL_GPL(mmp_pdma_filter_fn);
 
 module_platform_driver(mmp_pdma_driver);
 
-MODULE_DESCRIPTION("MARVELL MMP Periphera DMA Driver");
+MODULE_DESCRIPTION("MARVELL MMP Peripheral DMA Driver");
 MODULE_AUTHOR("Marvell International Ltd.");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 3ddacc1..33f96aa 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -121,11 +121,13 @@ struct mmp_tdma_chan {
 	int				idx;
 	enum mmp_tdma_type		type;
 	int				irq;
-	unsigned long			reg_base;
+	void __iomem			*reg_base;
 
 	size_t				buf_len;
 	size_t				period_len;
 	size_t				pos;
+
+	struct gen_pool			*pool;
 };
 
 #define TDMA_CHANNEL_NUM 2
@@ -182,7 +184,7 @@ static void mmp_tdma_pause_chan(struct mmp_tdma_chan *tdmac)
 
 static int mmp_tdma_config_chan(struct mmp_tdma_chan *tdmac)
 {
-	unsigned int tdcr;
+	unsigned int tdcr = 0;
 
 	mmp_tdma_disable_chan(tdmac);
 
@@ -324,7 +326,7 @@ static void mmp_tdma_free_descriptor(struct mmp_tdma_chan *tdmac)
 	struct gen_pool *gpool;
 	int size = tdmac->desc_num * sizeof(struct mmp_tdma_desc);
 
-	gpool = sram_get_gpool("asram");
+	gpool = tdmac->pool;
 	if (tdmac->desc_arr)
 		gen_pool_free(gpool, (unsigned long)tdmac->desc_arr,
 				size);
@@ -374,7 +376,7 @@ struct mmp_tdma_desc *mmp_tdma_alloc_descriptor(struct mmp_tdma_chan *tdmac)
 	struct gen_pool *gpool;
 	int size = tdmac->desc_num * sizeof(struct mmp_tdma_desc);
 
-	gpool = sram_get_gpool("asram");
+	gpool = tdmac->pool;
 	if (!gpool)
 		return NULL;
 
@@ -505,7 +507,8 @@ static int mmp_tdma_remove(struct platform_device *pdev)
 }
 
 static int mmp_tdma_chan_init(struct mmp_tdma_device *tdev,
-						int idx, int irq, int type)
+					int idx, int irq,
+					int type, struct gen_pool *pool)
 {
 	struct mmp_tdma_chan *tdmac;
 
@@ -526,7 +529,8 @@ static int mmp_tdma_chan_init(struct mmp_tdma_device *tdev,
 	tdmac->chan.device = &tdev->device;
 	tdmac->idx	   = idx;
 	tdmac->type	   = type;
-	tdmac->reg_base	   = (unsigned long)tdev->base + idx * 4;
+	tdmac->reg_base	   = tdev->base + idx * 4;
+	tdmac->pool	   = pool;
 	tdmac->status = DMA_COMPLETE;
 	tdev->tdmac[tdmac->idx] = tdmac;
 	tasklet_init(&tdmac->tasklet, dma_do_tasklet, (unsigned long)tdmac);
@@ -553,6 +557,7 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 	int i, ret;
 	int irq = 0, irq_num = 0;
 	int chan_num = TDMA_CHANNEL_NUM;
+	struct gen_pool *pool;
 
 	of_id = of_match_device(mmp_tdma_dt_ids, &pdev->dev);
 	if (of_id)
@@ -579,6 +584,15 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 
 	INIT_LIST_HEAD(&tdev->device.channels);
 
+	if (pdev->dev.of_node)
+		pool = of_get_named_gen_pool(pdev->dev.of_node, "asram", 0);
+	else
+		pool = sram_get_gpool("asram");
+	if (!pool) {
+		dev_err(&pdev->dev, "asram pool not available\n");
+		return -ENOMEM;
+	}
+
 	if (irq_num != chan_num) {
 		irq = platform_get_irq(pdev, 0);
 		ret = devm_request_irq(&pdev->dev, irq,
@@ -590,7 +604,7 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 	/* initialize channel parameters */
 	for (i = 0; i < chan_num; i++) {
 		irq = (irq_num != chan_num) ? 0 : platform_get_irq(pdev, i);
-		ret = mmp_tdma_chan_init(tdev, i, irq, type);
+		ret = mmp_tdma_chan_init(tdev, i, irq, type, pool);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/dma/moxart-dma.c b/drivers/dma/moxart-dma.c
new file mode 100644
index 0000000..3258e48
--- /dev/null
+++ b/drivers/dma/moxart-dma.c
@@ -0,0 +1,699 @@
+/*
+ * MOXA ART SoCs DMA Engine support.
+ *
+ * Copyright (C) 2013 Jonas Jensen
+ *
+ * Jonas Jensen <jonas.jensen@gmail.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_dma.h>
+#include <linux/bitops.h>
+
+#include <asm/cacheflush.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+#define APB_DMA_MAX_CHANNEL			4
+
+#define REG_OFF_ADDRESS_SOURCE			0
+#define REG_OFF_ADDRESS_DEST			4
+#define REG_OFF_CYCLES				8
+#define REG_OFF_CTRL				12
+#define REG_OFF_CHAN_SIZE			16
+
+#define APB_DMA_ENABLE				BIT(0)
+#define APB_DMA_FIN_INT_STS			BIT(1)
+#define APB_DMA_FIN_INT_EN			BIT(2)
+#define APB_DMA_BURST_MODE			BIT(3)
+#define APB_DMA_ERR_INT_STS			BIT(4)
+#define APB_DMA_ERR_INT_EN			BIT(5)
+
+/*
+ * Unset: APB
+ * Set:   AHB
+ */
+#define APB_DMA_SOURCE_SELECT			0x40
+#define APB_DMA_DEST_SELECT			0x80
+
+#define APB_DMA_SOURCE				0x100
+#define APB_DMA_DEST				0x1000
+
+#define APB_DMA_SOURCE_MASK			0x700
+#define APB_DMA_DEST_MASK			0x7000
+
+/*
+ * 000: No increment
+ * 001: +1 (Burst=0), +4  (Burst=1)
+ * 010: +2 (Burst=0), +8  (Burst=1)
+ * 011: +4 (Burst=0), +16 (Burst=1)
+ * 101: -1 (Burst=0), -4  (Burst=1)
+ * 110: -2 (Burst=0), -8  (Burst=1)
+ * 111: -4 (Burst=0), -16 (Burst=1)
+ */
+#define APB_DMA_SOURCE_INC_0			0
+#define APB_DMA_SOURCE_INC_1_4			0x100
+#define APB_DMA_SOURCE_INC_2_8			0x200
+#define APB_DMA_SOURCE_INC_4_16			0x300
+#define APB_DMA_SOURCE_DEC_1_4			0x500
+#define APB_DMA_SOURCE_DEC_2_8			0x600
+#define APB_DMA_SOURCE_DEC_4_16			0x700
+#define APB_DMA_DEST_INC_0			0
+#define APB_DMA_DEST_INC_1_4			0x1000
+#define APB_DMA_DEST_INC_2_8			0x2000
+#define APB_DMA_DEST_INC_4_16			0x3000
+#define APB_DMA_DEST_DEC_1_4			0x5000
+#define APB_DMA_DEST_DEC_2_8			0x6000
+#define APB_DMA_DEST_DEC_4_16			0x7000
+
+/*
+ * Request signal select source/destination address for DMA hardware handshake.
+ *
+ * The request line number is a property of the DMA controller itself,
+ * e.g. MMC must always request channels where dma_slave_config->slave_id is 5.
+ *
+ * 0:    No request / Grant signal
+ * 1-15: Request    / Grant signal
+ */
+#define APB_DMA_SOURCE_REQ_NO			0x1000000
+#define APB_DMA_SOURCE_REQ_NO_MASK		0xf000000
+#define APB_DMA_DEST_REQ_NO			0x10000
+#define APB_DMA_DEST_REQ_NO_MASK		0xf0000
+
+#define APB_DMA_DATA_WIDTH			0x100000
+#define APB_DMA_DATA_WIDTH_MASK			0x300000
+/*
+ * Data width of transfer:
+ *
+ * 00: Word
+ * 01: Half
+ * 10: Byte
+ */
+#define APB_DMA_DATA_WIDTH_4			0
+#define APB_DMA_DATA_WIDTH_2			0x100000
+#define APB_DMA_DATA_WIDTH_1			0x200000
+
+#define APB_DMA_CYCLES_MASK			0x00ffffff
+
+#define MOXART_DMA_DATA_TYPE_S8			0x00
+#define MOXART_DMA_DATA_TYPE_S16		0x01
+#define MOXART_DMA_DATA_TYPE_S32		0x02
+
+struct moxart_sg {
+	dma_addr_t addr;
+	uint32_t len;
+};
+
+struct moxart_desc {
+	enum dma_transfer_direction	dma_dir;
+	dma_addr_t			dev_addr;
+	unsigned int			sglen;
+	unsigned int			dma_cycles;
+	struct virt_dma_desc		vd;
+	uint8_t				es;
+	struct moxart_sg		sg[0];
+};
+
+struct moxart_chan {
+	struct virt_dma_chan		vc;
+
+	void __iomem			*base;
+	struct moxart_desc		*desc;
+
+	struct dma_slave_config		cfg;
+
+	bool				allocated;
+	bool				error;
+	int				ch_num;
+	unsigned int			line_reqno;
+	unsigned int			sgidx;
+};
+
+struct moxart_dmadev {
+	struct dma_device		dma_slave;
+	struct moxart_chan		slave_chans[APB_DMA_MAX_CHANNEL];
+};
+
+struct moxart_filter_data {
+	struct moxart_dmadev		*mdc;
+	struct of_phandle_args		*dma_spec;
+};
+
+static const unsigned int es_bytes[] = {
+	[MOXART_DMA_DATA_TYPE_S8] = 1,
+	[MOXART_DMA_DATA_TYPE_S16] = 2,
+	[MOXART_DMA_DATA_TYPE_S32] = 4,
+};
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+static inline struct moxart_chan *to_moxart_dma_chan(struct dma_chan *c)
+{
+	return container_of(c, struct moxart_chan, vc.chan);
+}
+
+static inline struct moxart_desc *to_moxart_dma_desc(
+	struct dma_async_tx_descriptor *t)
+{
+	return container_of(t, struct moxart_desc, vd.tx);
+}
+
+static void moxart_dma_desc_free(struct virt_dma_desc *vd)
+{
+	kfree(container_of(vd, struct moxart_desc, vd));
+}
+
+static int moxart_terminate_all(struct dma_chan *chan)
+{
+	struct moxart_chan *ch = to_moxart_dma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+	u32 ctrl;
+
+	dev_dbg(chan2dev(chan), "%s: ch=%p\n", __func__, ch);
+
+	spin_lock_irqsave(&ch->vc.lock, flags);
+
+	if (ch->desc)
+		ch->desc = NULL;
+
+	ctrl = readl(ch->base + REG_OFF_CTRL);
+	ctrl &= ~(APB_DMA_ENABLE | APB_DMA_FIN_INT_EN | APB_DMA_ERR_INT_EN);
+	writel(ctrl, ch->base + REG_OFF_CTRL);
+
+	vchan_get_all_descriptors(&ch->vc, &head);
+	spin_unlock_irqrestore(&ch->vc.lock, flags);
+	vchan_dma_desc_free_list(&ch->vc, &head);
+
+	return 0;
+}
+
+static int moxart_slave_config(struct dma_chan *chan,
+			       struct dma_slave_config *cfg)
+{
+	struct moxart_chan *ch = to_moxart_dma_chan(chan);
+	u32 ctrl;
+
+	ch->cfg = *cfg;
+
+	ctrl = readl(ch->base + REG_OFF_CTRL);
+	ctrl |= APB_DMA_BURST_MODE;
+	ctrl &= ~(APB_DMA_DEST_MASK | APB_DMA_SOURCE_MASK);
+	ctrl &= ~(APB_DMA_DEST_REQ_NO_MASK | APB_DMA_SOURCE_REQ_NO_MASK);
+
+	switch (ch->cfg.src_addr_width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		ctrl |= APB_DMA_DATA_WIDTH_1;
+		if (ch->cfg.direction != DMA_MEM_TO_DEV)
+			ctrl |= APB_DMA_DEST_INC_1_4;
+		else
+			ctrl |= APB_DMA_SOURCE_INC_1_4;
+		break;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		ctrl |= APB_DMA_DATA_WIDTH_2;
+		if (ch->cfg.direction != DMA_MEM_TO_DEV)
+			ctrl |= APB_DMA_DEST_INC_2_8;
+		else
+			ctrl |= APB_DMA_SOURCE_INC_2_8;
+		break;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		ctrl &= ~APB_DMA_DATA_WIDTH;
+		if (ch->cfg.direction != DMA_MEM_TO_DEV)
+			ctrl |= APB_DMA_DEST_INC_4_16;
+		else
+			ctrl |= APB_DMA_SOURCE_INC_4_16;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ch->cfg.direction == DMA_MEM_TO_DEV) {
+		ctrl &= ~APB_DMA_DEST_SELECT;
+		ctrl |= APB_DMA_SOURCE_SELECT;
+		ctrl |= (ch->line_reqno << 16 &
+			 APB_DMA_DEST_REQ_NO_MASK);
+	} else {
+		ctrl |= APB_DMA_DEST_SELECT;
+		ctrl &= ~APB_DMA_SOURCE_SELECT;
+		ctrl |= (ch->line_reqno << 24 &
+			 APB_DMA_SOURCE_REQ_NO_MASK);
+	}
+
+	writel(ctrl, ch->base + REG_OFF_CTRL);
+
+	return 0;
+}
+
+static int moxart_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+			  unsigned long arg)
+{
+	int ret = 0;
+
+	switch (cmd) {
+	case DMA_PAUSE:
+	case DMA_RESUME:
+		return -EINVAL;
+	case DMA_TERMINATE_ALL:
+		moxart_terminate_all(chan);
+		break;
+	case DMA_SLAVE_CONFIG:
+		ret = moxart_slave_config(chan, (struct dma_slave_config *)arg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	return ret;
+}
+
+static struct dma_async_tx_descriptor *moxart_prep_slave_sg(
+	struct dma_chan *chan, struct scatterlist *sgl,
+	unsigned int sg_len, enum dma_transfer_direction dir,
+	unsigned long tx_flags, void *context)
+{
+	struct moxart_chan *ch = to_moxart_dma_chan(chan);
+	struct moxart_desc *d;
+	enum dma_slave_buswidth dev_width;
+	dma_addr_t dev_addr;
+	struct scatterlist *sgent;
+	unsigned int es;
+	unsigned int i;
+
+	if (!is_slave_direction(dir)) {
+		dev_err(chan2dev(chan), "%s: invalid DMA direction\n",
+			__func__);
+		return NULL;
+	}
+
+	if (dir == DMA_DEV_TO_MEM) {
+		dev_addr = ch->cfg.src_addr;
+		dev_width = ch->cfg.src_addr_width;
+	} else {
+		dev_addr = ch->cfg.dst_addr;
+		dev_width = ch->cfg.dst_addr_width;
+	}
+
+	switch (dev_width) {
+	case DMA_SLAVE_BUSWIDTH_1_BYTE:
+		es = MOXART_DMA_DATA_TYPE_S8;
+		break;
+	case DMA_SLAVE_BUSWIDTH_2_BYTES:
+		es = MOXART_DMA_DATA_TYPE_S16;
+		break;
+	case DMA_SLAVE_BUSWIDTH_4_BYTES:
+		es = MOXART_DMA_DATA_TYPE_S32;
+		break;
+	default:
+		dev_err(chan2dev(chan), "%s: unsupported data width (%u)\n",
+			__func__, dev_width);
+		return NULL;
+	}
+
+	d = kzalloc(sizeof(*d) + sg_len * sizeof(d->sg[0]), GFP_ATOMIC);
+	if (!d)
+		return NULL;
+
+	d->dma_dir = dir;
+	d->dev_addr = dev_addr;
+	d->es = es;
+
+	for_each_sg(sgl, sgent, sg_len, i) {
+		d->sg[i].addr = sg_dma_address(sgent);
+		d->sg[i].len = sg_dma_len(sgent);
+	}
+
+	d->sglen = sg_len;
+
+	ch->error = 0;
+
+	return vchan_tx_prep(&ch->vc, &d->vd, tx_flags);
+}
+
+static struct dma_chan *moxart_of_xlate(struct of_phandle_args *dma_spec,
+					struct of_dma *ofdma)
+{
+	struct moxart_dmadev *mdc = ofdma->of_dma_data;
+	struct dma_chan *chan;
+	struct moxart_chan *ch;
+
+	chan = dma_get_any_slave_channel(&mdc->dma_slave);
+	if (!chan)
+		return NULL;
+
+	ch = to_moxart_dma_chan(chan);
+	ch->line_reqno = dma_spec->args[0];
+
+	return chan;
+}
+
+static int moxart_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct moxart_chan *ch = to_moxart_dma_chan(chan);
+
+	dev_dbg(chan2dev(chan), "%s: allocating channel #%u\n",
+		__func__, ch->ch_num);
+	ch->allocated = 1;
+
+	return 0;
+}
+
+static void moxart_free_chan_resources(struct dma_chan *chan)
+{
+	struct moxart_chan *ch = to_moxart_dma_chan(chan);
+
+	vchan_free_chan_resources(&ch->vc);
+
+	dev_dbg(chan2dev(chan), "%s: freeing channel #%u\n",
+		__func__, ch->ch_num);
+	ch->allocated = 0;
+}
+
+static void moxart_dma_set_params(struct moxart_chan *ch, dma_addr_t src_addr,
+				  dma_addr_t dst_addr)
+{
+	writel(src_addr, ch->base + REG_OFF_ADDRESS_SOURCE);
+	writel(dst_addr, ch->base + REG_OFF_ADDRESS_DEST);
+}
+
+static void moxart_set_transfer_params(struct moxart_chan *ch, unsigned int len)
+{
+	struct moxart_desc *d = ch->desc;
+	unsigned int sglen_div = es_bytes[d->es];
+
+	d->dma_cycles = len >> sglen_div;
+
+	/*
+	 * There are 4 cycles on 64 bytes copied, i.e. one cycle copies 16
+	 * bytes ( when width is APB_DMAB_DATA_WIDTH_4 ).
+	 */
+	writel(d->dma_cycles, ch->base + REG_OFF_CYCLES);
+
+	dev_dbg(chan2dev(&ch->vc.chan), "%s: set %u DMA cycles (len=%u)\n",
+		__func__, d->dma_cycles, len);
+}
+
+static void moxart_start_dma(struct moxart_chan *ch)
+{
+	u32 ctrl;
+
+	ctrl = readl(ch->base + REG_OFF_CTRL);
+	ctrl |= (APB_DMA_ENABLE | APB_DMA_FIN_INT_EN | APB_DMA_ERR_INT_EN);
+	writel(ctrl, ch->base + REG_OFF_CTRL);
+}
+
+static void moxart_dma_start_sg(struct moxart_chan *ch, unsigned int idx)
+{
+	struct moxart_desc *d = ch->desc;
+	struct moxart_sg *sg = ch->desc->sg + idx;
+
+	if (ch->desc->dma_dir == DMA_MEM_TO_DEV)
+		moxart_dma_set_params(ch, sg->addr, d->dev_addr);
+	else if (ch->desc->dma_dir == DMA_DEV_TO_MEM)
+		moxart_dma_set_params(ch, d->dev_addr, sg->addr);
+
+	moxart_set_transfer_params(ch, sg->len);
+
+	moxart_start_dma(ch);
+}
+
+static void moxart_dma_start_desc(struct dma_chan *chan)
+{
+	struct moxart_chan *ch = to_moxart_dma_chan(chan);
+	struct virt_dma_desc *vd;
+
+	vd = vchan_next_desc(&ch->vc);
+
+	if (!vd) {
+		ch->desc = NULL;
+		return;
+	}
+
+	list_del(&vd->node);
+
+	ch->desc = to_moxart_dma_desc(&vd->tx);
+	ch->sgidx = 0;
+
+	moxart_dma_start_sg(ch, 0);
+}
+
+static void moxart_issue_pending(struct dma_chan *chan)
+{
+	struct moxart_chan *ch = to_moxart_dma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ch->vc.lock, flags);
+	if (vchan_issue_pending(&ch->vc) && !ch->desc)
+		moxart_dma_start_desc(chan);
+	spin_unlock_irqrestore(&ch->vc.lock, flags);
+}
+
+static size_t moxart_dma_desc_size(struct moxart_desc *d,
+				   unsigned int completed_sgs)
+{
+	unsigned int i;
+	size_t size;
+
+	for (size = i = completed_sgs; i < d->sglen; i++)
+		size += d->sg[i].len;
+
+	return size;
+}
+
+static size_t moxart_dma_desc_size_in_flight(struct moxart_chan *ch)
+{
+	size_t size;
+	unsigned int completed_cycles, cycles;
+
+	size = moxart_dma_desc_size(ch->desc, ch->sgidx);
+	cycles = readl(ch->base + REG_OFF_CYCLES);
+	completed_cycles = (ch->desc->dma_cycles - cycles);
+	size -= completed_cycles << es_bytes[ch->desc->es];
+
+	dev_dbg(chan2dev(&ch->vc.chan), "%s: size=%zu\n", __func__, size);
+
+	return size;
+}
+
+static enum dma_status moxart_tx_status(struct dma_chan *chan,
+					dma_cookie_t cookie,
+					struct dma_tx_state *txstate)
+{
+	struct moxart_chan *ch = to_moxart_dma_chan(chan);
+	struct virt_dma_desc *vd;
+	struct moxart_desc *d;
+	enum dma_status ret;
+	unsigned long flags;
+
+	/*
+	 * dma_cookie_status() assigns initial residue value.
+	 */
+	ret = dma_cookie_status(chan, cookie, txstate);
+
+	spin_lock_irqsave(&ch->vc.lock, flags);
+	vd = vchan_find_desc(&ch->vc, cookie);
+	if (vd) {
+		d = to_moxart_dma_desc(&vd->tx);
+		txstate->residue = moxart_dma_desc_size(d, 0);
+	} else if (ch->desc && ch->desc->vd.tx.cookie == cookie) {
+		txstate->residue = moxart_dma_desc_size_in_flight(ch);
+	}
+	spin_unlock_irqrestore(&ch->vc.lock, flags);
+
+	if (ch->error)
+		return DMA_ERROR;
+
+	return ret;
+}
+
+static void moxart_dma_init(struct dma_device *dma, struct device *dev)
+{
+	dma->device_prep_slave_sg		= moxart_prep_slave_sg;
+	dma->device_alloc_chan_resources	= moxart_alloc_chan_resources;
+	dma->device_free_chan_resources		= moxart_free_chan_resources;
+	dma->device_issue_pending		= moxart_issue_pending;
+	dma->device_tx_status			= moxart_tx_status;
+	dma->device_control			= moxart_control;
+	dma->dev				= dev;
+
+	INIT_LIST_HEAD(&dma->channels);
+}
+
+static irqreturn_t moxart_dma_interrupt(int irq, void *devid)
+{
+	struct moxart_dmadev *mc = devid;
+	struct moxart_chan *ch = &mc->slave_chans[0];
+	unsigned int i;
+	unsigned long flags;
+	u32 ctrl;
+
+	dev_dbg(chan2dev(&ch->vc.chan), "%s\n", __func__);
+
+	for (i = 0; i < APB_DMA_MAX_CHANNEL; i++, ch++) {
+		if (!ch->allocated)
+			continue;
+
+		ctrl = readl(ch->base + REG_OFF_CTRL);
+
+		dev_dbg(chan2dev(&ch->vc.chan), "%s: ch=%p ch->base=%p ctrl=%x\n",
+			__func__, ch, ch->base, ctrl);
+
+		if (ctrl & APB_DMA_FIN_INT_STS) {
+			ctrl &= ~APB_DMA_FIN_INT_STS;
+			if (ch->desc) {
+				spin_lock_irqsave(&ch->vc.lock, flags);
+				if (++ch->sgidx < ch->desc->sglen) {
+					moxart_dma_start_sg(ch, ch->sgidx);
+				} else {
+					vchan_cookie_complete(&ch->desc->vd);
+					moxart_dma_start_desc(&ch->vc.chan);
+				}
+				spin_unlock_irqrestore(&ch->vc.lock, flags);
+			}
+		}
+
+		if (ctrl & APB_DMA_ERR_INT_STS) {
+			ctrl &= ~APB_DMA_ERR_INT_STS;
+			ch->error = 1;
+		}
+
+		writel(ctrl, ch->base + REG_OFF_CTRL);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int moxart_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *node = dev->of_node;
+	struct resource *res;
+	static void __iomem *dma_base_addr;
+	int ret, i;
+	unsigned int irq;
+	struct moxart_chan *ch;
+	struct moxart_dmadev *mdc;
+
+	mdc = devm_kzalloc(dev, sizeof(*mdc), GFP_KERNEL);
+	if (!mdc) {
+		dev_err(dev, "can't allocate DMA container\n");
+		return -ENOMEM;
+	}
+
+	irq = irq_of_parse_and_map(node, 0);
+	if (irq == NO_IRQ) {
+		dev_err(dev, "no IRQ resource\n");
+		return -EINVAL;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	dma_base_addr = devm_ioremap_resource(dev, res);
+	if (IS_ERR(dma_base_addr))
+		return PTR_ERR(dma_base_addr);
+
+	dma_cap_zero(mdc->dma_slave.cap_mask);
+	dma_cap_set(DMA_SLAVE, mdc->dma_slave.cap_mask);
+	dma_cap_set(DMA_PRIVATE, mdc->dma_slave.cap_mask);
+
+	moxart_dma_init(&mdc->dma_slave, dev);
+
+	ch = &mdc->slave_chans[0];
+	for (i = 0; i < APB_DMA_MAX_CHANNEL; i++, ch++) {
+		ch->ch_num = i;
+		ch->base = dma_base_addr + i * REG_OFF_CHAN_SIZE;
+		ch->allocated = 0;
+
+		ch->vc.desc_free = moxart_dma_desc_free;
+		vchan_init(&ch->vc, &mdc->dma_slave);
+
+		dev_dbg(dev, "%s: chs[%d]: ch->ch_num=%u ch->base=%p\n",
+			__func__, i, ch->ch_num, ch->base);
+	}
+
+	platform_set_drvdata(pdev, mdc);
+
+	ret = devm_request_irq(dev, irq, moxart_dma_interrupt, 0,
+			       "moxart-dma-engine", mdc);
+	if (ret) {
+		dev_err(dev, "devm_request_irq failed\n");
+		return ret;
+	}
+
+	ret = dma_async_device_register(&mdc->dma_slave);
+	if (ret) {
+		dev_err(dev, "dma_async_device_register failed\n");
+		return ret;
+	}
+
+	ret = of_dma_controller_register(node, moxart_of_xlate, mdc);
+	if (ret) {
+		dev_err(dev, "of_dma_controller_register failed\n");
+		dma_async_device_unregister(&mdc->dma_slave);
+		return ret;
+	}
+
+	dev_dbg(dev, "%s: IRQ=%u\n", __func__, irq);
+
+	return 0;
+}
+
+static int moxart_remove(struct platform_device *pdev)
+{
+	struct moxart_dmadev *m = platform_get_drvdata(pdev);
+
+	dma_async_device_unregister(&m->dma_slave);
+
+	if (pdev->dev.of_node)
+		of_dma_controller_free(pdev->dev.of_node);
+
+	return 0;
+}
+
+static const struct of_device_id moxart_dma_match[] = {
+	{ .compatible = "moxa,moxart-dma" },
+	{ }
+};
+
+static struct platform_driver moxart_driver = {
+	.probe	= moxart_probe,
+	.remove	= moxart_remove,
+	.driver = {
+		.name		= "moxart-dma-engine",
+		.owner		= THIS_MODULE,
+		.of_match_table	= moxart_dma_match,
+	},
+};
+
+static int moxart_init(void)
+{
+	return platform_driver_register(&moxart_driver);
+}
+subsys_initcall(moxart_init);
+
+static void __exit moxart_exit(void)
+{
+	platform_driver_unregister(&moxart_driver);
+}
+module_exit(moxart_exit);
+
+MODULE_AUTHOR("Jonas Jensen <jonas.jensen@gmail.com>");
+MODULE_DESCRIPTION("MOXART DMA engine driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 2f66cf4..362e7c4 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -190,7 +190,7 @@ static int omap_dma_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
 
-	dev_info(c->vc.chan.device->dev, "allocating channel for %u\n", c->dma_sig);
+	dev_dbg(c->vc.chan.device->dev, "allocating channel for %u\n", c->dma_sig);
 
 	return omap_request_dma(c->dma_sig, "DMA engine",
 		omap_dma_callback, c, &c->dma_ch);
@@ -203,7 +203,7 @@ static void omap_dma_free_chan_resources(struct dma_chan *chan)
 	vchan_free_chan_resources(&c->vc);
 	omap_free_dma(c->dma_ch);
 
-	dev_info(c->vc.chan.device->dev, "freeing channel for %u\n", c->dma_sig);
+	dev_dbg(c->vc.chan.device->dev, "freeing channel for %u\n", c->dma_sig);
 }
 
 static size_t omap_dma_sg_size(struct omap_sg *sg)
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index c90edec..73fa9b7 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -543,7 +543,9 @@ struct dma_pl330_chan {
 	/* DMA-Engine Channel */
 	struct dma_chan chan;
 
-	/* List of to be xfered descriptors */
+	/* List of submitted descriptors */
+	struct list_head submitted_list;
+	/* List of issued descriptors */
 	struct list_head work_list;
 	/* List of completed descriptors */
 	struct list_head completed_list;
@@ -578,12 +580,16 @@ struct dma_pl330_dmac {
 	/* DMA-Engine Device */
 	struct dma_device ddma;
 
+	/* Holds info about sg limitations */
+	struct device_dma_parameters dma_parms;
+
 	/* Pool of descriptors available for the DMAC's channels */
 	struct list_head desc_pool;
 	/* To protect desc_pool manipulation */
 	spinlock_t pool_lock;
 
 	/* Peripheral channels connected to this DMAC */
+	unsigned int num_peripherals;
 	struct dma_pl330_chan *peripherals; /* keep at end */
 };
 
@@ -606,11 +612,6 @@ struct dma_pl330_desc {
 	struct dma_pl330_chan *pchan;
 };
 
-struct dma_pl330_filter_args {
-	struct dma_pl330_dmac *pdmac;
-	unsigned int chan_id;
-};
-
 static inline void _callback(struct pl330_req *r, enum pl330_op_err err)
 {
 	if (r && r->xfer_cb)
@@ -2298,16 +2299,6 @@ static void dma_pl330_rqcb(void *token, enum pl330_op_err err)
 	tasklet_schedule(&pch->task);
 }
 
-static bool pl330_dt_filter(struct dma_chan *chan, void *param)
-{
-	struct dma_pl330_filter_args *fargs = param;
-
-	if (chan->device != &fargs->pdmac->ddma)
-		return false;
-
-	return (chan->chan_id == fargs->chan_id);
-}
-
 bool pl330_filter(struct dma_chan *chan, void *param)
 {
 	u8 *peri_id;
@@ -2325,23 +2316,16 @@ static struct dma_chan *of_dma_pl330_xlate(struct of_phandle_args *dma_spec,
 {
 	int count = dma_spec->args_count;
 	struct dma_pl330_dmac *pdmac = ofdma->of_dma_data;
-	struct dma_pl330_filter_args fargs;
-	dma_cap_mask_t cap;
-
-	if (!pdmac)
-		return NULL;
+	unsigned int chan_id;
 
 	if (count != 1)
 		return NULL;
 
-	fargs.pdmac = pdmac;
-	fargs.chan_id = dma_spec->args[0];
-
-	dma_cap_zero(cap);
-	dma_cap_set(DMA_SLAVE, cap);
-	dma_cap_set(DMA_CYCLIC, cap);
+	chan_id = dma_spec->args[0];
+	if (chan_id >= pdmac->num_peripherals)
+		return NULL;
 
-	return dma_request_channel(cap, pl330_dt_filter, &fargs);
+	return dma_get_slave_channel(&pdmac->peripherals[chan_id].chan);
 }
 
 static int pl330_alloc_chan_resources(struct dma_chan *chan)
@@ -2385,6 +2369,11 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned
 		pl330_chan_ctrl(pch->pl330_chid, PL330_OP_FLUSH);
 
 		/* Mark all desc done */
+		list_for_each_entry(desc, &pch->submitted_list, node) {
+			desc->status = FREE;
+			dma_cookie_complete(&desc->txd);
+		}
+
 		list_for_each_entry(desc, &pch->work_list , node) {
 			desc->status = FREE;
 			dma_cookie_complete(&desc->txd);
@@ -2395,6 +2384,7 @@ static int pl330_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd, unsigned
 			dma_cookie_complete(&desc->txd);
 		}
 
+		list_splice_tail_init(&pch->submitted_list, &pdmac->desc_pool);
 		list_splice_tail_init(&pch->work_list, &pdmac->desc_pool);
 		list_splice_tail_init(&pch->completed_list, &pdmac->desc_pool);
 		spin_unlock_irqrestore(&pch->lock, flags);
@@ -2453,7 +2443,14 @@ pl330_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 
 static void pl330_issue_pending(struct dma_chan *chan)
 {
-	pl330_tasklet((unsigned long) to_pchan(chan));
+	struct dma_pl330_chan *pch = to_pchan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&pch->lock, flags);
+	list_splice_tail_init(&pch->submitted_list, &pch->work_list);
+	spin_unlock_irqrestore(&pch->lock, flags);
+
+	pl330_tasklet((unsigned long)pch);
 }
 
 /*
@@ -2480,11 +2477,11 @@ static dma_cookie_t pl330_tx_submit(struct dma_async_tx_descriptor *tx)
 
 		dma_cookie_assign(&desc->txd);
 
-		list_move_tail(&desc->node, &pch->work_list);
+		list_move_tail(&desc->node, &pch->submitted_list);
 	}
 
 	cookie = dma_cookie_assign(&last->txd);
-	list_add_tail(&last->node, &pch->work_list);
+	list_add_tail(&last->node, &pch->submitted_list);
 	spin_unlock_irqrestore(&pch->lock, flags);
 
 	return cookie;
@@ -2960,6 +2957,8 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	else
 		num_chan = max_t(int, pi->pcfg.num_peri, pi->pcfg.num_chan);
 
+	pdmac->num_peripherals = num_chan;
+
 	pdmac->peripherals = kzalloc(num_chan * sizeof(*pch), GFP_KERNEL);
 	if (!pdmac->peripherals) {
 		ret = -ENOMEM;
@@ -2974,6 +2973,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 		else
 			pch->chan.private = adev->dev.of_node;
 
+		INIT_LIST_HEAD(&pch->submitted_list);
 		INIT_LIST_HEAD(&pch->work_list);
 		INIT_LIST_HEAD(&pch->completed_list);
 		spin_lock_init(&pch->lock);
@@ -3021,6 +3021,9 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 			"unable to register DMA to the generic DT DMA helpers\n");
 		}
 	}
+
+	adev->dev.dma_parms = &pdmac->dma_parms;
+
 	/*
 	 * This is the limit for transfers with a buswidth of 1, larger
 	 * buswidths will have larger limits.
diff --git a/drivers/dma/ppc4xx/adma.c b/drivers/dma/ppc4xx/adma.c
index 8bba298..ce7a8d7 100644
--- a/drivers/dma/ppc4xx/adma.c
+++ b/drivers/dma/ppc4xx/adma.c
@@ -4114,6 +4114,7 @@ static int ppc440spe_adma_probe(struct platform_device *ofdev)
 	regs = ioremap(res.start, resource_size(&res));
 	if (!regs) {
 		dev_err(&ofdev->dev, "failed to ioremap regs!\n");
+		ret = -ENOMEM;
 		goto err_regs_alloc;
 	}
 
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index 6aec3ad..d4d3a310 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -640,6 +640,25 @@ bool sirfsoc_dma_filter_id(struct dma_chan *chan, void *chan_id)
 }
 EXPORT_SYMBOL(sirfsoc_dma_filter_id);
 
+#define SIRFSOC_DMA_BUSWIDTHS \
+	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) | \
+	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+	BIT(DMA_SLAVE_BUSWIDTH_8_BYTES))
+
+static int sirfsoc_dma_device_slave_caps(struct dma_chan *dchan,
+	struct dma_slave_caps *caps)
+{
+	caps->src_addr_widths = SIRFSOC_DMA_BUSWIDTHS;
+	caps->dstn_addr_widths = SIRFSOC_DMA_BUSWIDTHS;
+	caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	caps->cmd_pause = true;
+	caps->cmd_terminate = true;
+
+	return 0;
+}
+
 static int sirfsoc_dma_probe(struct platform_device *op)
 {
 	struct device_node *dn = op->dev.of_node;
@@ -712,6 +731,7 @@ static int sirfsoc_dma_probe(struct platform_device *op)
 	dma->device_tx_status = sirfsoc_dma_tx_status;
 	dma->device_prep_interleaved_dma = sirfsoc_dma_prep_interleaved;
 	dma->device_prep_dma_cyclic = sirfsoc_dma_prep_cyclic;
+	dma->device_slave_caps = sirfsoc_dma_device_slave_caps;
 
 	INIT_LIST_HEAD(&dma->channels);
 	dma_cap_set(DMA_SLAVE, dma->cap_mask);
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index d11bb36..03ad64e 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -100,6 +100,11 @@
 #define TEGRA_APBDMA_APBSEQ_DATA_SWAP		BIT(27)
 #define TEGRA_APBDMA_APBSEQ_WRAP_WORD_1		(1 << 16)
 
+/* Tegra148 specific registers */
+#define TEGRA_APBDMA_CHAN_WCOUNT		0x20
+
+#define TEGRA_APBDMA_CHAN_WORD_TRANSFER		0x24
+
 /*
  * If any burst is in flight and DMA paused then this is the time to complete
  * on-flight burst and update DMA status register.
@@ -109,21 +114,22 @@
 /* Channel base address offset from APBDMA base address */
 #define TEGRA_APBDMA_CHANNEL_BASE_ADD_OFFSET	0x1000
 
-/* DMA channel register space size */
-#define TEGRA_APBDMA_CHANNEL_REGISTER_SIZE	0x20
-
 struct tegra_dma;
 
 /*
  * tegra_dma_chip_data Tegra chip specific DMA data
  * @nr_channels: Number of channels available in the controller.
+ * @channel_reg_size: Channel register size/stride.
  * @max_dma_count: Maximum DMA transfer count supported by DMA controller.
  * @support_channel_pause: Support channel wise pause of dma.
+ * @support_separate_wcount_reg: Support separate word count register.
  */
 struct tegra_dma_chip_data {
 	int nr_channels;
+	int channel_reg_size;
 	int max_dma_count;
 	bool support_channel_pause;
+	bool support_separate_wcount_reg;
 };
 
 /* DMA channel registers */
@@ -133,6 +139,7 @@ struct tegra_dma_channel_regs {
 	unsigned long	apb_ptr;
 	unsigned long	ahb_seq;
 	unsigned long	apb_seq;
+	unsigned long	wcount;
 };
 
 /*
@@ -426,6 +433,8 @@ static void tegra_dma_start(struct tegra_dma_channel *tdc,
 	tdc_write(tdc, TEGRA_APBDMA_CHAN_APBPTR, ch_regs->apb_ptr);
 	tdc_write(tdc, TEGRA_APBDMA_CHAN_AHBSEQ, ch_regs->ahb_seq);
 	tdc_write(tdc, TEGRA_APBDMA_CHAN_AHBPTR, ch_regs->ahb_ptr);
+	if (tdc->tdma->chip_data->support_separate_wcount_reg)
+		tdc_write(tdc, TEGRA_APBDMA_CHAN_WCOUNT, ch_regs->wcount);
 
 	/* Start DMA */
 	tdc_write(tdc, TEGRA_APBDMA_CHAN_CSR,
@@ -465,6 +474,9 @@ static void tegra_dma_configure_for_next(struct tegra_dma_channel *tdc,
 	/* Safe to program new configuration */
 	tdc_write(tdc, TEGRA_APBDMA_CHAN_APBPTR, nsg_req->ch_regs.apb_ptr);
 	tdc_write(tdc, TEGRA_APBDMA_CHAN_AHBPTR, nsg_req->ch_regs.ahb_ptr);
+	if (tdc->tdma->chip_data->support_separate_wcount_reg)
+		tdc_write(tdc, TEGRA_APBDMA_CHAN_WCOUNT,
+						nsg_req->ch_regs.wcount);
 	tdc_write(tdc, TEGRA_APBDMA_CHAN_CSR,
 				nsg_req->ch_regs.csr | TEGRA_APBDMA_CSR_ENB);
 	nsg_req->configured = true;
@@ -718,6 +730,7 @@ static void tegra_dma_terminate_all(struct dma_chan *dc)
 	struct tegra_dma_desc *dma_desc;
 	unsigned long flags;
 	unsigned long status;
+	unsigned long wcount;
 	bool was_busy;
 
 	spin_lock_irqsave(&tdc->lock, flags);
@@ -738,6 +751,10 @@ static void tegra_dma_terminate_all(struct dma_chan *dc)
 		tdc->isr_handler(tdc, true);
 		status = tdc_read(tdc, TEGRA_APBDMA_CHAN_STATUS);
 	}
+	if (tdc->tdma->chip_data->support_separate_wcount_reg)
+		wcount = tdc_read(tdc, TEGRA_APBDMA_CHAN_WORD_TRANSFER);
+	else
+		wcount = status;
 
 	was_busy = tdc->busy;
 	tegra_dma_stop(tdc);
@@ -746,7 +763,7 @@ static void tegra_dma_terminate_all(struct dma_chan *dc)
 		sgreq = list_first_entry(&tdc->pending_sg_req,
 					typeof(*sgreq), node);
 		sgreq->dma_desc->bytes_transferred +=
-				get_current_xferred_count(tdc, sgreq, status);
+				get_current_xferred_count(tdc, sgreq, wcount);
 	}
 	tegra_dma_resume(tdc);
 
@@ -908,6 +925,17 @@ static int get_transfer_param(struct tegra_dma_channel *tdc,
 	return -EINVAL;
 }
 
+static void tegra_dma_prep_wcount(struct tegra_dma_channel *tdc,
+	struct tegra_dma_channel_regs *ch_regs, u32 len)
+{
+	u32 len_field = (len - 4) & 0xFFFC;
+
+	if (tdc->tdma->chip_data->support_separate_wcount_reg)
+		ch_regs->wcount = len_field;
+	else
+		ch_regs->csr |= len_field;
+}
+
 static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 	struct dma_chan *dc, struct scatterlist *sgl, unsigned int sg_len,
 	enum dma_transfer_direction direction, unsigned long flags,
@@ -991,7 +1019,8 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 
 		sg_req->ch_regs.apb_ptr = apb_ptr;
 		sg_req->ch_regs.ahb_ptr = mem;
-		sg_req->ch_regs.csr = csr | ((len - 4) & 0xFFFC);
+		sg_req->ch_regs.csr = csr;
+		tegra_dma_prep_wcount(tdc, &sg_req->ch_regs, len);
 		sg_req->ch_regs.apb_seq = apb_seq;
 		sg_req->ch_regs.ahb_seq = ahb_seq;
 		sg_req->configured = false;
@@ -1120,7 +1149,8 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 		ahb_seq |= get_burst_size(tdc, burst_size, slave_bw, len);
 		sg_req->ch_regs.apb_ptr = apb_ptr;
 		sg_req->ch_regs.ahb_ptr = mem;
-		sg_req->ch_regs.csr = csr | ((len - 4) & 0xFFFC);
+		sg_req->ch_regs.csr = csr;
+		tegra_dma_prep_wcount(tdc, &sg_req->ch_regs, len);
 		sg_req->ch_regs.apb_seq = apb_seq;
 		sg_req->ch_regs.ahb_seq = ahb_seq;
 		sg_req->configured = false;
@@ -1234,27 +1264,45 @@ static struct dma_chan *tegra_dma_of_xlate(struct of_phandle_args *dma_spec,
 /* Tegra20 specific DMA controller information */
 static const struct tegra_dma_chip_data tegra20_dma_chip_data = {
 	.nr_channels		= 16,
+	.channel_reg_size	= 0x20,
 	.max_dma_count		= 1024UL * 64,
 	.support_channel_pause	= false,
+	.support_separate_wcount_reg = false,
 };
 
 /* Tegra30 specific DMA controller information */
 static const struct tegra_dma_chip_data tegra30_dma_chip_data = {
 	.nr_channels		= 32,
+	.channel_reg_size	= 0x20,
 	.max_dma_count		= 1024UL * 64,
 	.support_channel_pause	= false,
+	.support_separate_wcount_reg = false,
 };
 
 /* Tegra114 specific DMA controller information */
 static const struct tegra_dma_chip_data tegra114_dma_chip_data = {
 	.nr_channels		= 32,
+	.channel_reg_size	= 0x20,
 	.max_dma_count		= 1024UL * 64,
 	.support_channel_pause	= true,
+	.support_separate_wcount_reg = false,
+};
+
+/* Tegra148 specific DMA controller information */
+static const struct tegra_dma_chip_data tegra148_dma_chip_data = {
+	.nr_channels		= 32,
+	.channel_reg_size	= 0x40,
+	.max_dma_count		= 1024UL * 64,
+	.support_channel_pause	= true,
+	.support_separate_wcount_reg = true,
 };
 
 
 static const struct of_device_id tegra_dma_of_match[] = {
 	{
+		.compatible = "nvidia,tegra148-apbdma",
+		.data = &tegra148_dma_chip_data,
+	}, {
 		.compatible = "nvidia,tegra114-apbdma",
 		.data = &tegra114_dma_chip_data,
 	}, {
@@ -1348,7 +1396,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 		struct tegra_dma_channel *tdc = &tdma->channels[i];
 
 		tdc->chan_base_offset = TEGRA_APBDMA_CHANNEL_BASE_ADD_OFFSET +
-					i * TEGRA_APBDMA_CHANNEL_REGISTER_SIZE;
+					i * cdata->channel_reg_size;
 
 		res = platform_get_resource(pdev, IORESOURCE_IRQ, i);
 		if (!res) {
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index 85c19d6..181b952 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -84,10 +84,12 @@ static inline bool vchan_issue_pending(struct virt_dma_chan *vc)
 static inline void vchan_cookie_complete(struct virt_dma_desc *vd)
 {
 	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+	dma_cookie_t cookie;
 
+	cookie = vd->tx.cookie;
 	dma_cookie_complete(&vd->tx);
 	dev_vdbg(vc->chan.device->dev, "txd %p[%x]: marked complete\n",
-		vd, vd->tx.cookie);
+		 vd, cookie);
 	list_add_tail(&vd->node, &vc->desc_completed);
 
 	tasklet_schedule(&vc->task);