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

Pull slave-dmaengine updates from Vinod Koul:
 - New driver for Qcom bam dma
 - New driver for RCAR peri-peri
 - New driver for FSL eDMA
 - Various odd fixes and updates thru the subsystem

* 'for-linus' of git://git.infradead.org/users/vkoul/slave-dma: (29 commits)
  dmaengine: add Qualcomm BAM dma driver
  shdma: add R-Car Audio DMAC peri peri driver
  dmaengine: sirf: enable generic dt binding for dma channels
  dma: omap-dma: Implement device_slave_caps callback
  dmaengine: qcom_bam_dma: Add device tree binding
  dma: dw: Add suspend and resume handling for PCI mode DW_DMAC.
  dma: dw: allocate memory in two stages in probe
  Add new line to test result strings produced in verbose mode
  dmaengine: pch_dma: use tasklet_kill in teardown
  dmaengine: at_hdmac: use tasklet_kill in teardown
  dma: cppi41: start tear down only if channel is busy
  usb: musb: musb_cppi41: Dont reprogram DMA if tear down is initiated
  dmaengine: s3c24xx-dma: make phy->irq signed for error handling
  dma: imx-dma: Add missing module owner field
  dma: imx-dma: Replace printk with dev_*
  dma: fsl-edma: fix static checker warning of NULL dereference
  dma: Remove comment about embedding dma_slave_config into custom structs
  dma: mmp_tdma: move to generic device tree binding
  dma: mmp_pdma: add IRQF_SHARED when request irq
  dma: edma: Fix memory leak in edma_prep_dma_cyclic()
  ...

27 files changed, 2630 insertions, 58 deletions

diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 605b016bcea4..ba06d1d2f99e 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -308,7 +308,7 @@ config DMA_OMAP
 
 config DMA_BCM2835
 	tristate "BCM2835 DMA engine support"
-	depends on (ARCH_BCM2835 || MACH_BCM2708)
+	depends on ARCH_BCM2835
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 
@@ -350,6 +350,16 @@ config MOXART_DMA
 	select DMA_VIRTUAL_CHANNELS
 	help
 	  Enable support for the MOXA ART SoC DMA controller.
+ 
+config FSL_EDMA
+	tristate "Freescale eDMA engine support"
+	depends on OF
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support the Freescale eDMA engine with programmable channel
+	  multiplexing capability for DMA request sources(slot).
+	  This module can be found on Freescale Vybrid and LS-1 SoCs.
 
 config DMA_ENGINE
 	bool
@@ -401,4 +411,13 @@ config DMATEST
 config DMA_ENGINE_RAID
 	bool
 
+config QCOM_BAM_DMA
+	tristate "QCOM BAM DMA support"
+	depends on ARCH_QCOM || (COMPILE_TEST && OF && ARM)
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	---help---
+	  Enable support for the QCOM BAM DMA controller.  This controller
+	  provides DMA capabilities for a variety of on-chip devices.
+
 endif
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index a029d0f4a1be..5150c82c9caf 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -44,3 +44,5 @@ 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
+obj-$(CONFIG_FSL_EDMA) += fsl-edma.o
+obj-$(CONFIG_QCOM_BAM_DMA) += qcom_bam_dma.o
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 1e506afa33f5..de361a156b34 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/device.h>
+#include <linux/err.h>
 #include <linux/module.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -265,7 +266,7 @@ EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_register);
  */
 void devm_acpi_dma_controller_free(struct device *dev)
 {
-	WARN_ON(devres_destroy(dev, devm_acpi_dma_release, NULL, NULL));
+	WARN_ON(devres_release(dev, devm_acpi_dma_release, NULL, NULL));
 }
 EXPORT_SYMBOL_GPL(devm_acpi_dma_controller_free);
 
@@ -343,7 +344,7 @@ static int acpi_dma_parse_fixed_dma(struct acpi_resource *res, void *data)
  * @index:	index of FixedDMA descriptor for @dev
  *
  * Return:
- * Pointer to appropriate dma channel on success or NULL on error.
+ * Pointer to appropriate dma channel on success or an error pointer.
  */
 struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 		size_t index)
@@ -358,10 +359,10 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 
 	/* Check if the device was enumerated by ACPI */
 	if (!dev || !ACPI_HANDLE(dev))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	if (acpi_bus_get_device(ACPI_HANDLE(dev), &adev))
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	memset(&pdata, 0, sizeof(pdata));
 	pdata.index = index;
@@ -376,7 +377,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 	acpi_dev_free_resource_list(&resource_list);
 
 	if (dma_spec->slave_id < 0 || dma_spec->chan_id < 0)
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	mutex_lock(&acpi_dma_lock);
 
@@ -399,7 +400,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 	}
 
 	mutex_unlock(&acpi_dma_lock);
-	return chan;
+	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
 }
 EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_index);
 
@@ -413,7 +414,7 @@ EXPORT_SYMBOL_GPL(acpi_dma_request_slave_chan_by_index);
  * the first FixedDMA descriptor is TX and second is RX.
  *
  * Return:
- * Pointer to appropriate dma channel on success or NULL on error.
+ * Pointer to appropriate dma channel on success or an error pointer.
  */
 struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev,
 		const char *name)
@@ -425,7 +426,7 @@ struct dma_chan *acpi_dma_request_slave_chan_by_name(struct device *dev,
 	else if (!strcmp(name, "rx"))
 		index = 1;
 	else
-		return NULL;
+		return ERR_PTR(-ENODEV);
 
 	return acpi_dma_request_slave_chan_by_index(dev, index);
 }
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index e2c04dc81e2a..c13a3bb0f594 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -1569,7 +1569,6 @@ static int at_dma_remove(struct platform_device *pdev)
 
 		/* Disable interrupts */
 		atc_disable_chan_irq(atdma, chan->chan_id);
-		tasklet_disable(&atchan->tasklet);
 
 		tasklet_kill(&atchan->tasklet);
 		list_del(&chan->device_node);
diff --git a/drivers/dma/cppi41.c b/drivers/dma/cppi41.c
index c18aebf7d5aa..d028f36ae655 100644
--- a/drivers/dma/cppi41.c
+++ b/drivers/dma/cppi41.c
@@ -620,12 +620,15 @@ static int cppi41_stop_chan(struct dma_chan *chan)
 	u32 desc_phys;
 	int ret;
 
+	desc_phys = lower_32_bits(c->desc_phys);
+	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
+	if (!cdd->chan_busy[desc_num])
+		return 0;
+
 	ret = cppi41_tear_down_chan(c);
 	if (ret)
 		return ret;
 
-	desc_phys = lower_32_bits(c->desc_phys);
-	desc_num = (desc_phys - cdd->descs_phys) / sizeof(struct cppi41_desc);
 	WARN_ON(!cdd->chan_busy[desc_num]);
 	cdd->chan_busy[desc_num] = NULL;
 
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index ed610b497518..a886713937fd 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -627,18 +627,13 @@ EXPORT_SYMBOL_GPL(__dma_request_channel);
 struct dma_chan *dma_request_slave_channel_reason(struct device *dev,
 						  const char *name)
 {
-	struct dma_chan *chan;
-
 	/* If device-tree is present get slave info from here */
 	if (dev->of_node)
 		return of_dma_request_slave_channel(dev->of_node, name);
 
 	/* If device was enumerated by ACPI get slave info from here */
-	if (ACPI_HANDLE(dev)) {
-		chan = acpi_dma_request_slave_chan_by_name(dev, name);
-		if (chan)
-			return chan;
-	}
+	if (ACPI_HANDLE(dev))
+		return acpi_dma_request_slave_chan_by_name(dev, name);
 
 	return ERR_PTR(-ENODEV);
 }
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index 05b6dea770a4..e27cec25c59e 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -340,7 +340,7 @@ static unsigned int min_odd(unsigned int x, unsigned int y)
 static void result(const char *err, unsigned int n, unsigned int src_off,
 		   unsigned int dst_off, unsigned int len, unsigned long data)
 {
-	pr_info("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)",
+	pr_info("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)\n",
 		current->comm, n, err, src_off, dst_off, len, data);
 }
 
@@ -348,7 +348,7 @@ static void dbg_result(const char *err, unsigned int n, unsigned int src_off,
 		       unsigned int dst_off, unsigned int len,
 		       unsigned long data)
 {
-	pr_debug("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)",
+	pr_debug("%s: result #%u: '%s' with src_off=0x%x dst_off=0x%x len=0x%x (%lu)\n",
 		   current->comm, n, err, src_off, dst_off, len, data);
 }
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 13ac3f240e79..cfdbb92aae1d 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -33,8 +33,8 @@
  * of which use ARM any more).  See the "Databook" from Synopsys for
  * information beyond what licensees probably provide.
  *
- * The driver has currently been tested only with the Atmel AT32AP7000,
- * which does not support descriptor writeback.
+ * The driver has been tested with the Atmel AT32AP7000, which does not
+ * support descriptor writeback.
  */
 
 static inline bool is_request_line_unset(struct dw_dma_chan *dwc)
@@ -1479,7 +1479,6 @@ static void dw_dma_off(struct dw_dma *dw)
 int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 {
 	struct dw_dma		*dw;
-	size_t			size;
 	bool			autocfg;
 	unsigned int		dw_params;
 	unsigned int		nr_channels;
@@ -1487,6 +1486,13 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	int			err;
 	int			i;
 
+	dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	dw->regs = chip->regs;
+	chip->dw = dw;
+
 	dw_params = dma_read_byaddr(chip->regs, DW_PARAMS);
 	autocfg = dw_params >> DW_PARAMS_EN & 0x1;
 
@@ -1509,9 +1515,9 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	else
 		nr_channels = pdata->nr_channels;
 
-	size = sizeof(struct dw_dma) + nr_channels * sizeof(struct dw_dma_chan);
-	dw = devm_kzalloc(chip->dev, size, GFP_KERNEL);
-	if (!dw)
+	dw->chan = devm_kcalloc(chip->dev, nr_channels, sizeof(*dw->chan),
+				GFP_KERNEL);
+	if (!dw->chan)
 		return -ENOMEM;
 
 	dw->clk = devm_clk_get(chip->dev, "hclk");
@@ -1519,9 +1525,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 		return PTR_ERR(dw->clk);
 	clk_prepare_enable(dw->clk);
 
-	dw->regs = chip->regs;
-	chip->dw = dw;
-
 	/* Get hardware configuration parameters */
 	if (autocfg) {
 		max_blk_size = dma_readl(dw, MAX_BLK_SIZE);
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index e89fc24b8293..fec59f1a77bb 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -75,6 +75,36 @@ static void dw_pci_remove(struct pci_dev *pdev)
 		dev_warn(&pdev->dev, "can't remove device properly: %d\n", ret);
 }
 
+#ifdef CONFIG_PM_SLEEP
+
+static int dw_pci_suspend_late(struct device *dev)
+{
+	struct pci_dev *pci = to_pci_dev(dev);
+	struct dw_dma_chip *chip = pci_get_drvdata(pci);
+
+	return dw_dma_suspend(chip);
+};
+
+static int dw_pci_resume_early(struct device *dev)
+{
+	struct pci_dev *pci = to_pci_dev(dev);
+	struct dw_dma_chip *chip = pci_get_drvdata(pci);
+
+	return dw_dma_resume(chip);
+};
+
+#else /* !CONFIG_PM_SLEEP */
+
+#define dw_pci_suspend_late	NULL
+#define dw_pci_resume_early	NULL
+
+#endif /* !CONFIG_PM_SLEEP */
+
+static const struct dev_pm_ops dw_pci_dev_pm_ops = {
+	.suspend_late = dw_pci_suspend_late,
+	.resume_early = dw_pci_resume_early,
+};
+
 static DEFINE_PCI_DEVICE_TABLE(dw_pci_id_table) = {
 	/* Medfield */
 	{ PCI_VDEVICE(INTEL, 0x0827), (kernel_ulong_t)&dw_pci_pdata },
@@ -83,6 +113,9 @@ static DEFINE_PCI_DEVICE_TABLE(dw_pci_id_table) = {
 	/* BayTrail */
 	{ PCI_VDEVICE(INTEL, 0x0f06), (kernel_ulong_t)&dw_pci_pdata },
 	{ PCI_VDEVICE(INTEL, 0x0f40), (kernel_ulong_t)&dw_pci_pdata },
+
+	/* Haswell */
+	{ PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_pci_pdata },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, dw_pci_id_table);
@@ -92,6 +125,9 @@ static struct pci_driver dw_pci_driver = {
 	.id_table	= dw_pci_id_table,
 	.probe		= dw_pci_probe,
 	.remove		= dw_pci_remove,
+	.driver	= {
+		.pm	= &dw_pci_dev_pm_ops,
+	},
 };
 
 module_pci_driver(dw_pci_driver);
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index deb4274f80f4..bb98d3e91e8b 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -252,13 +252,13 @@ struct dw_dma {
 	struct tasklet_struct	tasklet;
 	struct clk		*clk;
 
+	/* channels */
+	struct dw_dma_chan	*chan;
 	u8			all_chan_mask;
 
 	/* hardware configuration */
 	unsigned char		nr_masters;
 	unsigned char		data_width[4];
-
-	struct dw_dma_chan	chan[0];
 };
 
 static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index cd8da451d199..cd04eb7b182e 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -539,6 +539,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 				edma_alloc_slot(EDMA_CTLR(echan->ch_num),
 						EDMA_SLOT_ANY);
 			if (echan->slot[i] < 0) {
+				kfree(edesc);
 				dev_err(dev, "Failed to allocate slot\n");
 				return NULL;
 			}
@@ -553,8 +554,10 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 		ret = edma_config_pset(chan, &edesc->pset[i], src_addr,
 				       dst_addr, burst, dev_width, period_len,
 				       direction);
-		if (ret < 0)
+		if (ret < 0) {
+			kfree(edesc);
 			return NULL;
+		}
 
 		if (direction == DMA_DEV_TO_MEM)
 			dst_addr += period_len;
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
new file mode 100644
index 000000000000..381e793184ba
--- /dev/null
+++ b/drivers/dma/fsl-edma.c
@@ -0,0 +1,975 @@
+/*
+ * drivers/dma/fsl-edma.c
+ *
+ * Copyright 2013-2014 Freescale Semiconductor, Inc.
+ *
+ * Driver for the Freescale eDMA engine with flexible channel multiplexing
+ * capability for DMA request sources. The eDMA block can be found on some
+ * Vybrid and Layerscape SoCs.
+ *
+ * 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.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_dma.h>
+
+#include "virt-dma.h"
+
+#define EDMA_CR			0x00
+#define EDMA_ES			0x04
+#define EDMA_ERQ		0x0C
+#define EDMA_EEI		0x14
+#define EDMA_SERQ		0x1B
+#define EDMA_CERQ		0x1A
+#define EDMA_SEEI		0x19
+#define EDMA_CEEI		0x18
+#define EDMA_CINT		0x1F
+#define EDMA_CERR		0x1E
+#define EDMA_SSRT		0x1D
+#define EDMA_CDNE		0x1C
+#define EDMA_INTR		0x24
+#define EDMA_ERR		0x2C
+
+#define EDMA_TCD_SADDR(x)	(0x1000 + 32 * (x))
+#define EDMA_TCD_SOFF(x)	(0x1004 + 32 * (x))
+#define EDMA_TCD_ATTR(x)	(0x1006 + 32 * (x))
+#define EDMA_TCD_NBYTES(x)	(0x1008 + 32 * (x))
+#define EDMA_TCD_SLAST(x)	(0x100C + 32 * (x))
+#define EDMA_TCD_DADDR(x)	(0x1010 + 32 * (x))
+#define EDMA_TCD_DOFF(x)	(0x1014 + 32 * (x))
+#define EDMA_TCD_CITER_ELINK(x)	(0x1016 + 32 * (x))
+#define EDMA_TCD_CITER(x)	(0x1016 + 32 * (x))
+#define EDMA_TCD_DLAST_SGA(x)	(0x1018 + 32 * (x))
+#define EDMA_TCD_CSR(x)		(0x101C + 32 * (x))
+#define EDMA_TCD_BITER_ELINK(x)	(0x101E + 32 * (x))
+#define EDMA_TCD_BITER(x)	(0x101E + 32 * (x))
+
+#define EDMA_CR_EDBG		BIT(1)
+#define EDMA_CR_ERCA		BIT(2)
+#define EDMA_CR_ERGA		BIT(3)
+#define EDMA_CR_HOE		BIT(4)
+#define EDMA_CR_HALT		BIT(5)
+#define EDMA_CR_CLM		BIT(6)
+#define EDMA_CR_EMLM		BIT(7)
+#define EDMA_CR_ECX		BIT(16)
+#define EDMA_CR_CX		BIT(17)
+
+#define EDMA_SEEI_SEEI(x)	((x) & 0x1F)
+#define EDMA_CEEI_CEEI(x)	((x) & 0x1F)
+#define EDMA_CINT_CINT(x)	((x) & 0x1F)
+#define EDMA_CERR_CERR(x)	((x) & 0x1F)
+
+#define EDMA_TCD_ATTR_DSIZE(x)		(((x) & 0x0007))
+#define EDMA_TCD_ATTR_DMOD(x)		(((x) & 0x001F) << 3)
+#define EDMA_TCD_ATTR_SSIZE(x)		(((x) & 0x0007) << 8)
+#define EDMA_TCD_ATTR_SMOD(x)		(((x) & 0x001F) << 11)
+#define EDMA_TCD_ATTR_SSIZE_8BIT	(0x0000)
+#define EDMA_TCD_ATTR_SSIZE_16BIT	(0x0100)
+#define EDMA_TCD_ATTR_SSIZE_32BIT	(0x0200)
+#define EDMA_TCD_ATTR_SSIZE_64BIT	(0x0300)
+#define EDMA_TCD_ATTR_SSIZE_32BYTE	(0x0500)
+#define EDMA_TCD_ATTR_DSIZE_8BIT	(0x0000)
+#define EDMA_TCD_ATTR_DSIZE_16BIT	(0x0001)
+#define EDMA_TCD_ATTR_DSIZE_32BIT	(0x0002)
+#define EDMA_TCD_ATTR_DSIZE_64BIT	(0x0003)
+#define EDMA_TCD_ATTR_DSIZE_32BYTE	(0x0005)
+
+#define EDMA_TCD_SOFF_SOFF(x)		(x)
+#define EDMA_TCD_NBYTES_NBYTES(x)	(x)
+#define EDMA_TCD_SLAST_SLAST(x)		(x)
+#define EDMA_TCD_DADDR_DADDR(x)		(x)
+#define EDMA_TCD_CITER_CITER(x)		((x) & 0x7FFF)
+#define EDMA_TCD_DOFF_DOFF(x)		(x)
+#define EDMA_TCD_DLAST_SGA_DLAST_SGA(x)	(x)
+#define EDMA_TCD_BITER_BITER(x)		((x) & 0x7FFF)
+
+#define EDMA_TCD_CSR_START		BIT(0)
+#define EDMA_TCD_CSR_INT_MAJOR		BIT(1)
+#define EDMA_TCD_CSR_INT_HALF		BIT(2)
+#define EDMA_TCD_CSR_D_REQ		BIT(3)
+#define EDMA_TCD_CSR_E_SG		BIT(4)
+#define EDMA_TCD_CSR_E_LINK		BIT(5)
+#define EDMA_TCD_CSR_ACTIVE		BIT(6)
+#define EDMA_TCD_CSR_DONE		BIT(7)
+
+#define EDMAMUX_CHCFG_DIS		0x0
+#define EDMAMUX_CHCFG_ENBL		0x80
+#define EDMAMUX_CHCFG_SOURCE(n)		((n) & 0x3F)
+
+#define DMAMUX_NR	2
+
+#define FSL_EDMA_BUSWIDTHS	BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+				BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+				BIT(DMA_SLAVE_BUSWIDTH_4_BYTES) | \
+				BIT(DMA_SLAVE_BUSWIDTH_8_BYTES)
+
+struct fsl_edma_hw_tcd {
+	u32	saddr;
+	u16	soff;
+	u16	attr;
+	u32	nbytes;
+	u32	slast;
+	u32	daddr;
+	u16	doff;
+	u16	citer;
+	u32	dlast_sga;
+	u16	csr;
+	u16	biter;
+};
+
+struct fsl_edma_sw_tcd {
+	dma_addr_t			ptcd;
+	struct fsl_edma_hw_tcd		*vtcd;
+};
+
+struct fsl_edma_slave_config {
+	enum dma_transfer_direction	dir;
+	enum dma_slave_buswidth		addr_width;
+	u32				dev_addr;
+	u32				burst;
+	u32				attr;
+};
+
+struct fsl_edma_chan {
+	struct virt_dma_chan		vchan;
+	enum dma_status			status;
+	struct fsl_edma_engine		*edma;
+	struct fsl_edma_desc		*edesc;
+	struct fsl_edma_slave_config	fsc;
+	struct dma_pool			*tcd_pool;
+};
+
+struct fsl_edma_desc {
+	struct virt_dma_desc		vdesc;
+	struct fsl_edma_chan		*echan;
+	bool				iscyclic;
+	unsigned int			n_tcds;
+	struct fsl_edma_sw_tcd		tcd[];
+};
+
+struct fsl_edma_engine {
+	struct dma_device	dma_dev;
+	void __iomem		*membase;
+	void __iomem		*muxbase[DMAMUX_NR];
+	struct clk		*muxclk[DMAMUX_NR];
+	struct mutex		fsl_edma_mutex;
+	u32			n_chans;
+	int			txirq;
+	int			errirq;
+	bool			big_endian;
+	struct fsl_edma_chan	chans[];
+};
+
+/*
+ * R/W functions for big- or little-endian registers
+ * the eDMA controller's endian is independent of the CPU core's endian.
+ */
+
+static u16 edma_readw(struct fsl_edma_engine *edma, void __iomem *addr)
+{
+	if (edma->big_endian)
+		return ioread16be(addr);
+	else
+		return ioread16(addr);
+}
+
+static u32 edma_readl(struct fsl_edma_engine *edma, void __iomem *addr)
+{
+	if (edma->big_endian)
+		return ioread32be(addr);
+	else
+		return ioread32(addr);
+}
+
+static void edma_writeb(struct fsl_edma_engine *edma, u8 val, void __iomem *addr)
+{
+	iowrite8(val, addr);
+}
+
+static void edma_writew(struct fsl_edma_engine *edma, u16 val, void __iomem *addr)
+{
+	if (edma->big_endian)
+		iowrite16be(val, addr);
+	else
+		iowrite16(val, addr);
+}
+
+static void edma_writel(struct fsl_edma_engine *edma, u32 val, void __iomem *addr)
+{
+	if (edma->big_endian)
+		iowrite32be(val, addr);
+	else
+		iowrite32(val, addr);
+}
+
+static struct fsl_edma_chan *to_fsl_edma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct fsl_edma_chan, vchan.chan);
+}
+
+static struct fsl_edma_desc *to_fsl_edma_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct fsl_edma_desc, vdesc);
+}
+
+static void fsl_edma_enable_request(struct fsl_edma_chan *fsl_chan)
+{
+	void __iomem *addr = fsl_chan->edma->membase;
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+
+	edma_writeb(fsl_chan->edma, EDMA_SEEI_SEEI(ch), addr + EDMA_SEEI);
+	edma_writeb(fsl_chan->edma, ch, addr + EDMA_SERQ);
+}
+
+static void fsl_edma_disable_request(struct fsl_edma_chan *fsl_chan)
+{
+	void __iomem *addr = fsl_chan->edma->membase;
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+
+	edma_writeb(fsl_chan->edma, ch, addr + EDMA_CERQ);
+	edma_writeb(fsl_chan->edma, EDMA_CEEI_CEEI(ch), addr + EDMA_CEEI);
+}
+
+static void fsl_edma_chan_mux(struct fsl_edma_chan *fsl_chan,
+			unsigned int slot, bool enable)
+{
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+	void __iomem *muxaddr = fsl_chan->edma->muxbase[ch / DMAMUX_NR];
+	unsigned chans_per_mux, ch_off;
+
+	chans_per_mux = fsl_chan->edma->n_chans / DMAMUX_NR;
+	ch_off = fsl_chan->vchan.chan.chan_id % chans_per_mux;
+
+	if (enable)
+		edma_writeb(fsl_chan->edma,
+				EDMAMUX_CHCFG_ENBL | EDMAMUX_CHCFG_SOURCE(slot),
+				muxaddr + ch_off);
+	else
+		edma_writeb(fsl_chan->edma, EDMAMUX_CHCFG_DIS, muxaddr + ch_off);
+}
+
+static unsigned int fsl_edma_get_tcd_attr(enum dma_slave_buswidth addr_width)
+{
+	switch (addr_width) {
+	case 1:
+		return EDMA_TCD_ATTR_SSIZE_8BIT | EDMA_TCD_ATTR_DSIZE_8BIT;
+	case 2:
+		return EDMA_TCD_ATTR_SSIZE_16BIT | EDMA_TCD_ATTR_DSIZE_16BIT;
+	case 4:
+		return EDMA_TCD_ATTR_SSIZE_32BIT | EDMA_TCD_ATTR_DSIZE_32BIT;
+	case 8:
+		return EDMA_TCD_ATTR_SSIZE_64BIT | EDMA_TCD_ATTR_DSIZE_64BIT;
+	default:
+		return EDMA_TCD_ATTR_SSIZE_32BIT | EDMA_TCD_ATTR_DSIZE_32BIT;
+	}
+}
+
+static void fsl_edma_free_desc(struct virt_dma_desc *vdesc)
+{
+	struct fsl_edma_desc *fsl_desc;
+	int i;
+
+	fsl_desc = to_fsl_edma_desc(vdesc);
+	for (i = 0; i < fsl_desc->n_tcds; i++)
+			dma_pool_free(fsl_desc->echan->tcd_pool,
+					fsl_desc->tcd[i].vtcd,
+					fsl_desc->tcd[i].ptcd);
+	kfree(fsl_desc);
+}
+
+static int fsl_edma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+		unsigned long arg)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct dma_slave_config *cfg = (void *)arg;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	switch (cmd) {
+	case DMA_TERMINATE_ALL:
+		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+		fsl_edma_disable_request(fsl_chan);
+		fsl_chan->edesc = NULL;
+		vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+		vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
+		return 0;
+
+	case DMA_SLAVE_CONFIG:
+		fsl_chan->fsc.dir = cfg->direction;
+		if (cfg->direction == DMA_DEV_TO_MEM) {
+			fsl_chan->fsc.dev_addr = cfg->src_addr;
+			fsl_chan->fsc.addr_width = cfg->src_addr_width;
+			fsl_chan->fsc.burst = cfg->src_maxburst;
+			fsl_chan->fsc.attr = fsl_edma_get_tcd_attr(cfg->src_addr_width);
+		} else if (cfg->direction == DMA_MEM_TO_DEV) {
+			fsl_chan->fsc.dev_addr = cfg->dst_addr;
+			fsl_chan->fsc.addr_width = cfg->dst_addr_width;
+			fsl_chan->fsc.burst = cfg->dst_maxburst;
+			fsl_chan->fsc.attr = fsl_edma_get_tcd_attr(cfg->dst_addr_width);
+		} else {
+			return -EINVAL;
+		}
+		return 0;
+
+	case DMA_PAUSE:
+		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+		if (fsl_chan->edesc) {
+			fsl_edma_disable_request(fsl_chan);
+			fsl_chan->status = DMA_PAUSED;
+		}
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+		return 0;
+
+	case DMA_RESUME:
+		spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+		if (fsl_chan->edesc) {
+			fsl_edma_enable_request(fsl_chan);
+			fsl_chan->status = DMA_IN_PROGRESS;
+		}
+		spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+		return 0;
+
+	default:
+		return -ENXIO;
+	}
+}
+
+static size_t fsl_edma_desc_residue(struct fsl_edma_chan *fsl_chan,
+		struct virt_dma_desc *vdesc, bool in_progress)
+{
+	struct fsl_edma_desc *edesc = fsl_chan->edesc;
+	void __iomem *addr = fsl_chan->edma->membase;
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+	enum dma_transfer_direction dir = fsl_chan->fsc.dir;
+	dma_addr_t cur_addr, dma_addr;
+	size_t len, size;
+	int i;
+
+	/* calculate the total size in this desc */
+	for (len = i = 0; i < fsl_chan->edesc->n_tcds; i++)
+		len += edma_readl(fsl_chan->edma, &(edesc->tcd[i].vtcd->nbytes))
+			* edma_readw(fsl_chan->edma, &(edesc->tcd[i].vtcd->biter));
+
+	if (!in_progress)
+		return len;
+
+	if (dir == DMA_MEM_TO_DEV)
+		cur_addr = edma_readl(fsl_chan->edma, addr + EDMA_TCD_SADDR(ch));
+	else
+		cur_addr = edma_readl(fsl_chan->edma, addr + EDMA_TCD_DADDR(ch));
+
+	/* figure out the finished and calculate the residue */
+	for (i = 0; i < fsl_chan->edesc->n_tcds; i++) {
+		size = edma_readl(fsl_chan->edma, &(edesc->tcd[i].vtcd->nbytes))
+			* edma_readw(fsl_chan->edma, &(edesc->tcd[i].vtcd->biter));
+		if (dir == DMA_MEM_TO_DEV)
+			dma_addr = edma_readl(fsl_chan->edma,
+					&(edesc->tcd[i].vtcd->saddr));
+		else
+			dma_addr = edma_readl(fsl_chan->edma,
+					&(edesc->tcd[i].vtcd->daddr));
+
+		len -= size;
+		if (cur_addr > dma_addr && cur_addr < dma_addr + size) {
+			len += dma_addr + size - cur_addr;
+			break;
+		}
+	}
+
+	return len;
+}
+
+static enum dma_status fsl_edma_tx_status(struct dma_chan *chan,
+		dma_cookie_t cookie, struct dma_tx_state *txstate)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct virt_dma_desc *vdesc;
+	enum dma_status status;
+	unsigned long flags;
+
+	status = dma_cookie_status(chan, cookie, txstate);
+	if (status == DMA_COMPLETE)
+		return status;
+
+	if (!txstate)
+		return fsl_chan->status;
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	vdesc = vchan_find_desc(&fsl_chan->vchan, cookie);
+	if (fsl_chan->edesc && cookie == fsl_chan->edesc->vdesc.tx.cookie)
+		txstate->residue = fsl_edma_desc_residue(fsl_chan, vdesc, true);
+	else if (vdesc)
+		txstate->residue = fsl_edma_desc_residue(fsl_chan, vdesc, false);
+	else
+		txstate->residue = 0;
+
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+
+	return fsl_chan->status;
+}
+
+static void fsl_edma_set_tcd_params(struct fsl_edma_chan *fsl_chan,
+		u32 src, u32 dst, u16 attr, u16 soff, u32 nbytes,
+		u32 slast, u16 citer, u16 biter, u32 doff, u32 dlast_sga,
+		u16 csr)
+{
+	void __iomem *addr = fsl_chan->edma->membase;
+	u32 ch = fsl_chan->vchan.chan.chan_id;
+
+	/*
+	 * TCD parameters have been swapped in fill_tcd_params(),
+	 * so just write them to registers in the cpu endian here
+	 */
+	writew(0, addr + EDMA_TCD_CSR(ch));
+	writel(src, addr + EDMA_TCD_SADDR(ch));
+	writel(dst, addr + EDMA_TCD_DADDR(ch));
+	writew(attr, addr + EDMA_TCD_ATTR(ch));
+	writew(soff, addr + EDMA_TCD_SOFF(ch));
+	writel(nbytes, addr + EDMA_TCD_NBYTES(ch));
+	writel(slast, addr + EDMA_TCD_SLAST(ch));
+	writew(citer, addr + EDMA_TCD_CITER(ch));
+	writew(biter, addr + EDMA_TCD_BITER(ch));
+	writew(doff, addr + EDMA_TCD_DOFF(ch));
+	writel(dlast_sga, addr + EDMA_TCD_DLAST_SGA(ch));
+	writew(csr, addr + EDMA_TCD_CSR(ch));
+}
+
+static void fill_tcd_params(struct fsl_edma_engine *edma,
+		struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
+		u16 attr, u16 soff, u32 nbytes, u32 slast, u16 citer,
+		u16 biter, u16 doff, u32 dlast_sga, bool major_int,
+		bool disable_req, bool enable_sg)
+{
+	u16 csr = 0;
+
+	/*
+	 * eDMA hardware SGs require the TCD parameters stored in memory
+	 * the same endian as the eDMA module so that they can be loaded
+	 * automatically by the engine
+	 */
+	edma_writel(edma, src, &(tcd->saddr));
+	edma_writel(edma, dst, &(tcd->daddr));
+	edma_writew(edma, attr, &(tcd->attr));
+	edma_writew(edma, EDMA_TCD_SOFF_SOFF(soff), &(tcd->soff));
+	edma_writel(edma, EDMA_TCD_NBYTES_NBYTES(nbytes), &(tcd->nbytes));
+	edma_writel(edma, EDMA_TCD_SLAST_SLAST(slast), &(tcd->slast));
+	edma_writew(edma, EDMA_TCD_CITER_CITER(citer), &(tcd->citer));
+	edma_writew(edma, EDMA_TCD_DOFF_DOFF(doff), &(tcd->doff));
+	edma_writel(edma, EDMA_TCD_DLAST_SGA_DLAST_SGA(dlast_sga), &(tcd->dlast_sga));
+	edma_writew(edma, EDMA_TCD_BITER_BITER(biter), &(tcd->biter));
+	if (major_int)
+		csr |= EDMA_TCD_CSR_INT_MAJOR;
+
+	if (disable_req)
+		csr |= EDMA_TCD_CSR_D_REQ;
+
+	if (enable_sg)
+		csr |= EDMA_TCD_CSR_E_SG;
+
+	edma_writew(edma, csr, &(tcd->csr));
+}
+
+static struct fsl_edma_desc *fsl_edma_alloc_desc(struct fsl_edma_chan *fsl_chan,
+		int sg_len)
+{
+	struct fsl_edma_desc *fsl_desc;
+	int i;
+
+	fsl_desc = kzalloc(sizeof(*fsl_desc) + sizeof(struct fsl_edma_sw_tcd) * sg_len,
+				GFP_NOWAIT);
+	if (!fsl_desc)
+		return NULL;
+
+	fsl_desc->echan = fsl_chan;
+	fsl_desc->n_tcds = sg_len;
+	for (i = 0; i < sg_len; i++) {
+		fsl_desc->tcd[i].vtcd = dma_pool_alloc(fsl_chan->tcd_pool,
+					GFP_NOWAIT, &fsl_desc->tcd[i].ptcd);
+		if (!fsl_desc->tcd[i].vtcd)
+			goto err;
+	}
+	return fsl_desc;
+
+err:
+	while (--i >= 0)
+		dma_pool_free(fsl_chan->tcd_pool, fsl_desc->tcd[i].vtcd,
+				fsl_desc->tcd[i].ptcd);
+	kfree(fsl_desc);
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
+		struct dma_chan *chan, dma_addr_t dma_addr, size_t buf_len,
+		size_t period_len, enum dma_transfer_direction direction,
+		unsigned long flags, void *context)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct fsl_edma_desc *fsl_desc;
+	dma_addr_t dma_buf_next;
+	int sg_len, i;
+	u32 src_addr, dst_addr, last_sg, nbytes;
+	u16 soff, doff, iter;
+
+	if (!is_slave_direction(fsl_chan->fsc.dir))
+		return NULL;
+
+	sg_len = buf_len / period_len;
+	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
+	if (!fsl_desc)
+		return NULL;
+	fsl_desc->iscyclic = true;
+
+	dma_buf_next = dma_addr;
+	nbytes = fsl_chan->fsc.addr_width * fsl_chan->fsc.burst;
+	iter = period_len / nbytes;
+
+	for (i = 0; i < sg_len; i++) {
+		if (dma_buf_next >= dma_addr + buf_len)
+			dma_buf_next = dma_addr;
+
+		/* get next sg's physical address */
+		last_sg = fsl_desc->tcd[(i + 1) % sg_len].ptcd;
+
+		if (fsl_chan->fsc.dir == DMA_MEM_TO_DEV) {
+			src_addr = dma_buf_next;
+			dst_addr = fsl_chan->fsc.dev_addr;
+			soff = fsl_chan->fsc.addr_width;
+			doff = 0;
+		} else {
+			src_addr = fsl_chan->fsc.dev_addr;
+			dst_addr = dma_buf_next;
+			soff = 0;
+			doff = fsl_chan->fsc.addr_width;
+		}
+
+		fill_tcd_params(fsl_chan->edma, fsl_desc->tcd[i].vtcd, src_addr,
+				dst_addr, fsl_chan->fsc.attr, soff, nbytes, 0,
+				iter, iter, doff, last_sg, true, false, true);
+		dma_buf_next += period_len;
+	}
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags);
+}
+
+static struct dma_async_tx_descriptor *fsl_edma_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 fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct fsl_edma_desc *fsl_desc;
+	struct scatterlist *sg;
+	u32 src_addr, dst_addr, last_sg, nbytes;
+	u16 soff, doff, iter;
+	int i;
+
+	if (!is_slave_direction(fsl_chan->fsc.dir))
+		return NULL;
+
+	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
+	if (!fsl_desc)
+		return NULL;
+	fsl_desc->iscyclic = false;
+
+	nbytes = fsl_chan->fsc.addr_width * fsl_chan->fsc.burst;
+	for_each_sg(sgl, sg, sg_len, i) {
+		/* get next sg's physical address */
+		last_sg = fsl_desc->tcd[(i + 1) % sg_len].ptcd;
+
+		if (fsl_chan->fsc.dir == DMA_MEM_TO_DEV) {
+			src_addr = sg_dma_address(sg);
+			dst_addr = fsl_chan->fsc.dev_addr;
+			soff = fsl_chan->fsc.addr_width;
+			doff = 0;
+		} else {
+			src_addr = fsl_chan->fsc.dev_addr;
+			dst_addr = sg_dma_address(sg);
+			soff = 0;
+			doff = fsl_chan->fsc.addr_width;
+		}
+
+		iter = sg_dma_len(sg) / nbytes;
+		if (i < sg_len - 1) {
+			last_sg = fsl_desc->tcd[(i + 1)].ptcd;
+			fill_tcd_params(fsl_chan->edma, fsl_desc->tcd[i].vtcd,
+					src_addr, dst_addr, fsl_chan->fsc.attr,
+					soff, nbytes, 0, iter, iter, doff, last_sg,
+					false, false, true);
+		} else {
+			last_sg = 0;
+			fill_tcd_params(fsl_chan->edma, fsl_desc->tcd[i].vtcd,
+					src_addr, dst_addr, fsl_chan->fsc.attr,
+					soff, nbytes, 0, iter, iter, doff, last_sg,
+					true, true, false);
+		}
+	}
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags);
+}
+
+static void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
+{
+	struct fsl_edma_hw_tcd *tcd;
+	struct virt_dma_desc *vdesc;
+
+	vdesc = vchan_next_desc(&fsl_chan->vchan);
+	if (!vdesc)
+		return;
+	fsl_chan->edesc = to_fsl_edma_desc(vdesc);
+	tcd = fsl_chan->edesc->tcd[0].vtcd;
+	fsl_edma_set_tcd_params(fsl_chan, tcd->saddr, tcd->daddr, tcd->attr,
+			tcd->soff, tcd->nbytes, tcd->slast, tcd->citer,
+			tcd->biter, tcd->doff, tcd->dlast_sga, tcd->csr);
+	fsl_edma_enable_request(fsl_chan);
+	fsl_chan->status = DMA_IN_PROGRESS;
+}
+
+static irqreturn_t fsl_edma_tx_handler(int irq, void *dev_id)
+{
+	struct fsl_edma_engine *fsl_edma = dev_id;
+	unsigned int intr, ch;
+	void __iomem *base_addr;
+	struct fsl_edma_chan *fsl_chan;
+
+	base_addr = fsl_edma->membase;
+
+	intr = edma_readl(fsl_edma, base_addr + EDMA_INTR);
+	if (!intr)
+		return IRQ_NONE;
+
+	for (ch = 0; ch < fsl_edma->n_chans; ch++) {
+		if (intr & (0x1 << ch)) {
+			edma_writeb(fsl_edma, EDMA_CINT_CINT(ch),
+				base_addr + EDMA_CINT);
+
+			fsl_chan = &fsl_edma->chans[ch];
+
+			spin_lock(&fsl_chan->vchan.lock);
+			if (!fsl_chan->edesc->iscyclic) {
+				list_del(&fsl_chan->edesc->vdesc.node);
+				vchan_cookie_complete(&fsl_chan->edesc->vdesc);
+				fsl_chan->edesc = NULL;
+				fsl_chan->status = DMA_COMPLETE;
+			} else {
+				vchan_cyclic_callback(&fsl_chan->edesc->vdesc);
+			}
+
+			if (!fsl_chan->edesc)
+				fsl_edma_xfer_desc(fsl_chan);
+
+			spin_unlock(&fsl_chan->vchan.lock);
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fsl_edma_err_handler(int irq, void *dev_id)
+{
+	struct fsl_edma_engine *fsl_edma = dev_id;
+	unsigned int err, ch;
+
+	err = edma_readl(fsl_edma, fsl_edma->membase + EDMA_ERR);
+	if (!err)
+		return IRQ_NONE;
+
+	for (ch = 0; ch < fsl_edma->n_chans; ch++) {
+		if (err & (0x1 << ch)) {
+			fsl_edma_disable_request(&fsl_edma->chans[ch]);
+			edma_writeb(fsl_edma, EDMA_CERR_CERR(ch),
+				fsl_edma->membase + EDMA_CERR);
+			fsl_edma->chans[ch].status = DMA_ERROR;
+		}
+	}
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fsl_edma_irq_handler(int irq, void *dev_id)
+{
+	if (fsl_edma_tx_handler(irq, dev_id) == IRQ_HANDLED)
+		return IRQ_HANDLED;
+
+	return fsl_edma_err_handler(irq, dev_id);
+}
+
+static void fsl_edma_issue_pending(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+
+	if (vchan_issue_pending(&fsl_chan->vchan) && !fsl_chan->edesc)
+		fsl_edma_xfer_desc(fsl_chan);
+
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+}
+
+static struct dma_chan *fsl_edma_xlate(struct of_phandle_args *dma_spec,
+		struct of_dma *ofdma)
+{
+	struct fsl_edma_engine *fsl_edma = ofdma->of_dma_data;
+	struct dma_chan *chan, *_chan;
+
+	if (dma_spec->args_count != 2)
+		return NULL;
+
+	mutex_lock(&fsl_edma->fsl_edma_mutex);
+	list_for_each_entry_safe(chan, _chan, &fsl_edma->dma_dev.channels, device_node) {
+		if (chan->client_count)
+			continue;
+		if ((chan->chan_id / DMAMUX_NR) == dma_spec->args[0]) {
+			chan = dma_get_slave_channel(chan);
+			if (chan) {
+				chan->device->privatecnt++;
+				fsl_edma_chan_mux(to_fsl_edma_chan(chan),
+					dma_spec->args[1], true);
+				mutex_unlock(&fsl_edma->fsl_edma_mutex);
+				return chan;
+			}
+		}
+	}
+	mutex_unlock(&fsl_edma->fsl_edma_mutex);
+	return NULL;
+}
+
+static int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+
+	fsl_chan->tcd_pool = dma_pool_create("tcd_pool", chan->device->dev,
+				sizeof(struct fsl_edma_hw_tcd),
+				32, 0);
+	return 0;
+}
+
+static void fsl_edma_free_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	fsl_edma_disable_request(fsl_chan);
+	fsl_edma_chan_mux(fsl_chan, 0, false);
+	fsl_chan->edesc = NULL;
+	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
+	dma_pool_destroy(fsl_chan->tcd_pool);
+	fsl_chan->tcd_pool = NULL;
+}
+
+static int fsl_dma_device_slave_caps(struct dma_chan *dchan,
+		struct dma_slave_caps *caps)
+{
+	caps->src_addr_widths = FSL_EDMA_BUSWIDTHS;
+	caps->dstn_addr_widths = FSL_EDMA_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
+fsl_edma_irq_init(struct platform_device *pdev, struct fsl_edma_engine *fsl_edma)
+{
+	int ret;
+
+	fsl_edma->txirq = platform_get_irq_byname(pdev, "edma-tx");
+	if (fsl_edma->txirq < 0) {
+		dev_err(&pdev->dev, "Can't get edma-tx irq.\n");
+		return fsl_edma->txirq;
+	}
+
+	fsl_edma->errirq = platform_get_irq_byname(pdev, "edma-err");
+	if (fsl_edma->errirq < 0) {
+		dev_err(&pdev->dev, "Can't get edma-err irq.\n");
+		return fsl_edma->errirq;
+	}
+
+	if (fsl_edma->txirq == fsl_edma->errirq) {
+		ret = devm_request_irq(&pdev->dev, fsl_edma->txirq,
+				fsl_edma_irq_handler, 0, "eDMA", fsl_edma);
+		if (ret) {
+			dev_err(&pdev->dev, "Can't register eDMA IRQ.\n");
+			 return  ret;
+		}
+	} else {
+		ret = devm_request_irq(&pdev->dev, fsl_edma->txirq,
+				fsl_edma_tx_handler, 0, "eDMA tx", fsl_edma);
+		if (ret) {
+			dev_err(&pdev->dev, "Can't register eDMA tx IRQ.\n");
+			return  ret;
+		}
+
+		ret = devm_request_irq(&pdev->dev, fsl_edma->errirq,
+				fsl_edma_err_handler, 0, "eDMA err", fsl_edma);
+		if (ret) {
+			dev_err(&pdev->dev, "Can't register eDMA err IRQ.\n");
+			return  ret;
+		}
+	}
+
+	return 0;
+}
+
+static int fsl_edma_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct fsl_edma_engine *fsl_edma;
+	struct fsl_edma_chan *fsl_chan;
+	struct resource *res;
+	int len, chans;
+	int ret, i;
+
+	ret = of_property_read_u32(np, "dma-channels", &chans);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get dma-channels.\n");
+		return ret;
+	}
+
+	len = sizeof(*fsl_edma) + sizeof(*fsl_chan) * chans;
+	fsl_edma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_edma)
+		return -ENOMEM;
+
+	fsl_edma->n_chans = chans;
+	mutex_init(&fsl_edma->fsl_edma_mutex);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	fsl_edma->membase = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_edma->membase))
+		return PTR_ERR(fsl_edma->membase);
+
+	for (i = 0; i < DMAMUX_NR; i++) {
+		char clkname[32];
+
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 1 + i);
+		fsl_edma->muxbase[i] = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(fsl_edma->muxbase[i]))
+			return PTR_ERR(fsl_edma->muxbase[i]);
+
+		sprintf(clkname, "dmamux%d", i);
+		fsl_edma->muxclk[i] = devm_clk_get(&pdev->dev, clkname);
+		if (IS_ERR(fsl_edma->muxclk[i])) {
+			dev_err(&pdev->dev, "Missing DMAMUX block clock.\n");
+			return PTR_ERR(fsl_edma->muxclk[i]);
+		}
+
+		ret = clk_prepare_enable(fsl_edma->muxclk[i]);
+		if (ret) {
+			dev_err(&pdev->dev, "DMAMUX clk block failed.\n");
+			return ret;
+		}
+
+	}
+
+	ret = fsl_edma_irq_init(pdev, fsl_edma);
+	if (ret)
+		return ret;
+
+	fsl_edma->big_endian = of_property_read_bool(np, "big-endian");
+
+	INIT_LIST_HEAD(&fsl_edma->dma_dev.channels);
+	for (i = 0; i < fsl_edma->n_chans; i++) {
+		struct fsl_edma_chan *fsl_chan = &fsl_edma->chans[i];
+
+		fsl_chan->edma = fsl_edma;
+
+		fsl_chan->vchan.desc_free = fsl_edma_free_desc;
+		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
+
+		edma_writew(fsl_edma, 0x0, fsl_edma->membase + EDMA_TCD_CSR(i));
+		fsl_edma_chan_mux(fsl_chan, 0, false);
+	}
+
+	dma_cap_set(DMA_PRIVATE, fsl_edma->dma_dev.cap_mask);
+	dma_cap_set(DMA_SLAVE, fsl_edma->dma_dev.cap_mask);
+	dma_cap_set(DMA_CYCLIC, fsl_edma->dma_dev.cap_mask);
+
+	fsl_edma->dma_dev.dev = &pdev->dev;
+	fsl_edma->dma_dev.device_alloc_chan_resources
+		= fsl_edma_alloc_chan_resources;
+	fsl_edma->dma_dev.device_free_chan_resources
+		= fsl_edma_free_chan_resources;
+	fsl_edma->dma_dev.device_tx_status = fsl_edma_tx_status;
+	fsl_edma->dma_dev.device_prep_slave_sg = fsl_edma_prep_slave_sg;
+	fsl_edma->dma_dev.device_prep_dma_cyclic = fsl_edma_prep_dma_cyclic;
+	fsl_edma->dma_dev.device_control = fsl_edma_control;
+	fsl_edma->dma_dev.device_issue_pending = fsl_edma_issue_pending;
+	fsl_edma->dma_dev.device_slave_caps = fsl_dma_device_slave_caps;
+
+	platform_set_drvdata(pdev, fsl_edma);
+
+	ret = dma_async_device_register(&fsl_edma->dma_dev);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't register Freescale eDMA engine.\n");
+		return ret;
+	}
+
+	ret = of_dma_controller_register(np, fsl_edma_xlate, fsl_edma);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't register Freescale eDMA of_dma.\n");
+		dma_async_device_unregister(&fsl_edma->dma_dev);
+		return ret;
+	}
+
+	/* enable round robin arbitration */
+	edma_writel(fsl_edma, EDMA_CR_ERGA | EDMA_CR_ERCA, fsl_edma->membase + EDMA_CR);
+
+	return 0;
+}
+
+static int fsl_edma_remove(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct fsl_edma_engine *fsl_edma = platform_get_drvdata(pdev);
+	int i;
+
+	of_dma_controller_free(np);
+	dma_async_device_unregister(&fsl_edma->dma_dev);
+
+	for (i = 0; i < DMAMUX_NR; i++)
+		clk_disable_unprepare(fsl_edma->muxclk[i]);
+
+	return 0;
+}
+
+static const struct of_device_id fsl_edma_dt_ids[] = {
+	{ .compatible = "fsl,vf610-edma", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids);
+
+static struct platform_driver fsl_edma_driver = {
+	.driver		= {
+		.name	= "fsl-edma",
+		.owner  = THIS_MODULE,
+		.of_match_table = fsl_edma_dt_ids,
+	},
+	.probe          = fsl_edma_probe,
+	.remove		= fsl_edma_remove,
+};
+
+module_platform_driver(fsl_edma_driver);
+
+MODULE_ALIAS("platform:fsl-edma");
+MODULE_DESCRIPTION("Freescale eDMA engine driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 6f9ac2022abd..286660a12cc6 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -422,12 +422,12 @@ static irqreturn_t imxdma_err_handler(int irq, void *dev_id)
 		/* Tasklet error handler */
 		tasklet_schedule(&imxdma->channel[i].dma_tasklet);
 
-		printk(KERN_WARNING
-		       "DMA timeout on channel %d -%s%s%s%s\n", i,
-		       errcode & IMX_DMA_ERR_BURST ?    " burst" : "",
-		       errcode & IMX_DMA_ERR_REQUEST ?  " request" : "",
-		       errcode & IMX_DMA_ERR_TRANSFER ? " transfer" : "",
-		       errcode & IMX_DMA_ERR_BUFFER ?   " buffer" : "");
+		dev_warn(imxdma->dev,
+			 "DMA timeout on channel %d -%s%s%s%s\n", i,
+			 errcode & IMX_DMA_ERR_BURST ?    " burst" : "",
+			 errcode & IMX_DMA_ERR_REQUEST ?  " request" : "",
+			 errcode & IMX_DMA_ERR_TRANSFER ? " transfer" : "",
+			 errcode & IMX_DMA_ERR_BUFFER ?   " buffer" : "");
 	}
 	return IRQ_HANDLED;
 }
@@ -1236,6 +1236,7 @@ static int imxdma_remove(struct platform_device *pdev)
 static struct platform_driver imxdma_driver = {
 	.driver		= {
 		.name	= "imx-dma",
+		.owner	= THIS_MODULE,
 		.of_match_table = imx_dma_of_dev_id,
 	},
 	.id_table	= imx_dma_devtype,
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index b439679f4126..bf02e7beb51a 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -867,8 +867,8 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev, int idx, int irq)
 	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,
+				       IRQF_SHARED, "pdma", phy);
 		if (ret) {
 			dev_err(pdev->dev, "channel request irq fail!\n");
 			return ret;
@@ -957,8 +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,
+				       IRQF_SHARED, "pdma", pdev);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index 33f96aaa80c7..724f7f4c9720 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -22,6 +22,7 @@
 #include <mach/regs-icu.h>
 #include <linux/platform_data/dma-mmp_tdma.h>
 #include <linux/of_device.h>
+#include <linux/of_dma.h>
 
 #include "dmaengine.h"
 
@@ -541,6 +542,45 @@ static int mmp_tdma_chan_init(struct mmp_tdma_device *tdev,
 	return 0;
 }
 
+struct mmp_tdma_filter_param {
+	struct device_node *of_node;
+	unsigned int chan_id;
+};
+
+static bool mmp_tdma_filter_fn(struct dma_chan *chan, void *fn_param)
+{
+	struct mmp_tdma_filter_param *param = fn_param;
+	struct mmp_tdma_chan *tdmac = to_mmp_tdma_chan(chan);
+	struct dma_device *pdma_device = tdmac->chan.device;
+
+	if (pdma_device->dev->of_node != param->of_node)
+		return false;
+
+	if (chan->chan_id != param->chan_id)
+		return false;
+
+	return true;
+}
+
+struct dma_chan *mmp_tdma_xlate(struct of_phandle_args *dma_spec,
+			       struct of_dma *ofdma)
+{
+	struct mmp_tdma_device *tdev = ofdma->of_dma_data;
+	dma_cap_mask_t mask = tdev->device.cap_mask;
+	struct mmp_tdma_filter_param param;
+
+	if (dma_spec->args_count != 1)
+		return NULL;
+
+	param.of_node = ofdma->of_node;
+	param.chan_id = dma_spec->args[0];
+
+	if (param.chan_id >= TDMA_CHANNEL_NUM)
+		return NULL;
+
+	return dma_request_channel(mask, mmp_tdma_filter_fn, &param);
+}
+
 static struct of_device_id mmp_tdma_dt_ids[] = {
 	{ .compatible = "marvell,adma-1.0", .data = (void *)MMP_AUD_TDMA},
 	{ .compatible = "marvell,pxa910-squ", .data = (void *)PXA910_SQU},
@@ -631,6 +671,16 @@ static int mmp_tdma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	if (pdev->dev.of_node) {
+		ret = of_dma_controller_register(pdev->dev.of_node,
+							mmp_tdma_xlate, tdev);
+		if (ret) {
+			dev_err(tdev->device.dev,
+				"failed to register controller\n");
+			dma_async_device_unregister(&tdev->device);
+		}
+	}
+
 	dev_info(tdev->device.dev, "initialized\n");
 	return 0;
 }
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 64ceca2920b8..b19f04f4390b 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -1088,6 +1088,23 @@ static void omap_dma_free(struct omap_dmadev *od)
 	}
 }
 
+#define OMAP_DMA_BUSWIDTHS	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+				 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
+
+static int omap_dma_device_slave_caps(struct dma_chan *dchan,
+				      struct dma_slave_caps *caps)
+{
+	caps->src_addr_widths = OMAP_DMA_BUSWIDTHS;
+	caps->dstn_addr_widths = OMAP_DMA_BUSWIDTHS;
+	caps->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
+	caps->cmd_pause = true;
+	caps->cmd_terminate = true;
+	caps->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+	return 0;
+}
+
 static int omap_dma_probe(struct platform_device *pdev)
 {
 	struct omap_dmadev *od;
@@ -1118,6 +1135,7 @@ static int omap_dma_probe(struct platform_device *pdev)
 	od->ddev.device_prep_slave_sg = omap_dma_prep_slave_sg;
 	od->ddev.device_prep_dma_cyclic = omap_dma_prep_dma_cyclic;
 	od->ddev.device_control = omap_dma_control;
+	od->ddev.device_slave_caps = omap_dma_device_slave_caps;
 	od->ddev.dev = &pdev->dev;
 	INIT_LIST_HEAD(&od->ddev.channels);
 	INIT_LIST_HEAD(&od->pending);
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 61fdc54a3c88..05fa548bd659 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -964,16 +964,16 @@ static void pch_dma_remove(struct pci_dev *pdev)
 	if (pd) {
 		dma_async_device_unregister(&pd->dma);
 
+		free_irq(pdev->irq, pd);
+
 		list_for_each_entry_safe(chan, _c, &pd->dma.channels,
 					 device_node) {
 			pd_chan = to_pd_chan(chan);
 
-			tasklet_disable(&pd_chan->tasklet);
 			tasklet_kill(&pd_chan->tasklet);
 		}
 
 		pci_pool_destroy(pd->pool);
-		free_irq(pdev->irq, pd);
 		pci_iounmap(pdev, pd->membase);
 		pci_release_regions(pdev);
 		pci_disable_device(pdev);
diff --git a/drivers/dma/qcom_bam_dma.c b/drivers/dma/qcom_bam_dma.c
new file mode 100644
index 000000000000..82c923146e49
--- /dev/null
+++ b/drivers/dma/qcom_bam_dma.c
@@ -0,0 +1,1111 @@
+/*
+ * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ */
+/*
+ * QCOM BAM DMA engine driver
+ *
+ * QCOM BAM DMA blocks are distributed amongst a number of the on-chip
+ * peripherals on the MSM 8x74.  The configuration of the channels are dependent
+ * on the way they are hard wired to that specific peripheral.  The peripheral
+ * device tree entries specify the configuration of each channel.
+ *
+ * The DMA controller requires the use of external memory for storage of the
+ * hardware descriptors for each channel.  The descriptor FIFO is accessed as a
+ * circular buffer and operations are managed according to the offset within the
+ * FIFO.  After pipe/channel reset, all of the pipe registers and internal state
+ * are back to defaults.
+ *
+ * During DMA operations, we write descriptors to the FIFO, being careful to
+ * handle wrapping and then write the last FIFO offset to that channel's
+ * P_EVNT_REG register to kick off the transaction.  The P_SW_OFSTS register
+ * indicates the current FIFO offset that is being processed, so there is some
+ * indication of where the hardware is currently working.
+ */
+
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/of_dma.h>
+#include <linux/clk.h>
+#include <linux/dmaengine.h>
+
+#include "dmaengine.h"
+#include "virt-dma.h"
+
+struct bam_desc_hw {
+	u32 addr;		/* Buffer physical address */
+	u16 size;		/* Buffer size in bytes */
+	u16 flags;
+};
+
+#define DESC_FLAG_INT BIT(15)
+#define DESC_FLAG_EOT BIT(14)
+#define DESC_FLAG_EOB BIT(13)
+
+struct bam_async_desc {
+	struct virt_dma_desc vd;
+
+	u32 num_desc;
+	u32 xfer_len;
+	struct bam_desc_hw *curr_desc;
+
+	enum dma_transfer_direction dir;
+	size_t length;
+	struct bam_desc_hw desc[0];
+};
+
+#define BAM_CTRL			0x0000
+#define BAM_REVISION			0x0004
+#define BAM_SW_REVISION			0x0080
+#define BAM_NUM_PIPES			0x003C
+#define BAM_TIMER			0x0040
+#define BAM_TIMER_CTRL			0x0044
+#define BAM_DESC_CNT_TRSHLD		0x0008
+#define BAM_IRQ_SRCS			0x000C
+#define BAM_IRQ_SRCS_MSK		0x0010
+#define BAM_IRQ_SRCS_UNMASKED		0x0030
+#define BAM_IRQ_STTS			0x0014
+#define BAM_IRQ_CLR			0x0018
+#define BAM_IRQ_EN			0x001C
+#define BAM_CNFG_BITS			0x007C
+#define BAM_IRQ_SRCS_EE(ee)		(0x0800 + ((ee) * 0x80))
+#define BAM_IRQ_SRCS_MSK_EE(ee)		(0x0804 + ((ee) * 0x80))
+#define BAM_P_CTRL(pipe)		(0x1000 + ((pipe) * 0x1000))
+#define BAM_P_RST(pipe)			(0x1004 + ((pipe) * 0x1000))
+#define BAM_P_HALT(pipe)		(0x1008 + ((pipe) * 0x1000))
+#define BAM_P_IRQ_STTS(pipe)		(0x1010 + ((pipe) * 0x1000))
+#define BAM_P_IRQ_CLR(pipe)		(0x1014 + ((pipe) * 0x1000))
+#define BAM_P_IRQ_EN(pipe)		(0x1018 + ((pipe) * 0x1000))
+#define BAM_P_EVNT_DEST_ADDR(pipe)	(0x182C + ((pipe) * 0x1000))
+#define BAM_P_EVNT_REG(pipe)		(0x1818 + ((pipe) * 0x1000))
+#define BAM_P_SW_OFSTS(pipe)		(0x1800 + ((pipe) * 0x1000))
+#define BAM_P_DATA_FIFO_ADDR(pipe)	(0x1824 + ((pipe) * 0x1000))
+#define BAM_P_DESC_FIFO_ADDR(pipe)	(0x181C + ((pipe) * 0x1000))
+#define BAM_P_EVNT_TRSHLD(pipe)		(0x1828 + ((pipe) * 0x1000))
+#define BAM_P_FIFO_SIZES(pipe)		(0x1820 + ((pipe) * 0x1000))
+
+/* BAM CTRL */
+#define BAM_SW_RST			BIT(0)
+#define BAM_EN				BIT(1)
+#define BAM_EN_ACCUM			BIT(4)
+#define BAM_TESTBUS_SEL_SHIFT		5
+#define BAM_TESTBUS_SEL_MASK		0x3F
+#define BAM_DESC_CACHE_SEL_SHIFT	13
+#define BAM_DESC_CACHE_SEL_MASK		0x3
+#define BAM_CACHED_DESC_STORE		BIT(15)
+#define IBC_DISABLE			BIT(16)
+
+/* BAM REVISION */
+#define REVISION_SHIFT		0
+#define REVISION_MASK		0xFF
+#define NUM_EES_SHIFT		8
+#define NUM_EES_MASK		0xF
+#define CE_BUFFER_SIZE		BIT(13)
+#define AXI_ACTIVE		BIT(14)
+#define USE_VMIDMT		BIT(15)
+#define SECURED			BIT(16)
+#define BAM_HAS_NO_BYPASS	BIT(17)
+#define HIGH_FREQUENCY_BAM	BIT(18)
+#define INACTIV_TMRS_EXST	BIT(19)
+#define NUM_INACTIV_TMRS	BIT(20)
+#define DESC_CACHE_DEPTH_SHIFT	21
+#define DESC_CACHE_DEPTH_1	(0 << DESC_CACHE_DEPTH_SHIFT)
+#define DESC_CACHE_DEPTH_2	(1 << DESC_CACHE_DEPTH_SHIFT)
+#define DESC_CACHE_DEPTH_3	(2 << DESC_CACHE_DEPTH_SHIFT)
+#define DESC_CACHE_DEPTH_4	(3 << DESC_CACHE_DEPTH_SHIFT)
+#define CMD_DESC_EN		BIT(23)
+#define INACTIV_TMR_BASE_SHIFT	24
+#define INACTIV_TMR_BASE_MASK	0xFF
+
+/* BAM NUM PIPES */
+#define BAM_NUM_PIPES_SHIFT		0
+#define BAM_NUM_PIPES_MASK		0xFF
+#define PERIPH_NON_PIPE_GRP_SHIFT	16
+#define PERIPH_NON_PIP_GRP_MASK		0xFF
+#define BAM_NON_PIPE_GRP_SHIFT		24
+#define BAM_NON_PIPE_GRP_MASK		0xFF
+
+/* BAM CNFG BITS */
+#define BAM_PIPE_CNFG		BIT(2)
+#define BAM_FULL_PIPE		BIT(11)
+#define BAM_NO_EXT_P_RST	BIT(12)
+#define BAM_IBC_DISABLE		BIT(13)
+#define BAM_SB_CLK_REQ		BIT(14)
+#define BAM_PSM_CSW_REQ		BIT(15)
+#define BAM_PSM_P_RES		BIT(16)
+#define BAM_AU_P_RES		BIT(17)
+#define BAM_SI_P_RES		BIT(18)
+#define BAM_WB_P_RES		BIT(19)
+#define BAM_WB_BLK_CSW		BIT(20)
+#define BAM_WB_CSW_ACK_IDL	BIT(21)
+#define BAM_WB_RETR_SVPNT	BIT(22)
+#define BAM_WB_DSC_AVL_P_RST	BIT(23)
+#define BAM_REG_P_EN		BIT(24)
+#define BAM_PSM_P_HD_DATA	BIT(25)
+#define BAM_AU_ACCUMED		BIT(26)
+#define BAM_CMD_ENABLE		BIT(27)
+
+#define BAM_CNFG_BITS_DEFAULT	(BAM_PIPE_CNFG |	\
+				 BAM_NO_EXT_P_RST |	\
+				 BAM_IBC_DISABLE |	\
+				 BAM_SB_CLK_REQ |	\
+				 BAM_PSM_CSW_REQ |	\
+				 BAM_PSM_P_RES |	\
+				 BAM_AU_P_RES |		\
+				 BAM_SI_P_RES |		\
+				 BAM_WB_P_RES |		\
+				 BAM_WB_BLK_CSW |	\
+				 BAM_WB_CSW_ACK_IDL |	\
+				 BAM_WB_RETR_SVPNT |	\
+				 BAM_WB_DSC_AVL_P_RST |	\
+				 BAM_REG_P_EN |		\
+				 BAM_PSM_P_HD_DATA |	\
+				 BAM_AU_ACCUMED |	\
+				 BAM_CMD_ENABLE)
+
+/* PIPE CTRL */
+#define P_EN			BIT(1)
+#define P_DIRECTION		BIT(3)
+#define P_SYS_STRM		BIT(4)
+#define P_SYS_MODE		BIT(5)
+#define P_AUTO_EOB		BIT(6)
+#define P_AUTO_EOB_SEL_SHIFT	7
+#define P_AUTO_EOB_SEL_512	(0 << P_AUTO_EOB_SEL_SHIFT)
+#define P_AUTO_EOB_SEL_256	(1 << P_AUTO_EOB_SEL_SHIFT)
+#define P_AUTO_EOB_SEL_128	(2 << P_AUTO_EOB_SEL_SHIFT)
+#define P_AUTO_EOB_SEL_64	(3 << P_AUTO_EOB_SEL_SHIFT)
+#define P_PREFETCH_LIMIT_SHIFT	9
+#define P_PREFETCH_LIMIT_32	(0 << P_PREFETCH_LIMIT_SHIFT)
+#define P_PREFETCH_LIMIT_16	(1 << P_PREFETCH_LIMIT_SHIFT)
+#define P_PREFETCH_LIMIT_4	(2 << P_PREFETCH_LIMIT_SHIFT)
+#define P_WRITE_NWD		BIT(11)
+#define P_LOCK_GROUP_SHIFT	16
+#define P_LOCK_GROUP_MASK	0x1F
+
+/* BAM_DESC_CNT_TRSHLD */
+#define CNT_TRSHLD		0xffff
+#define DEFAULT_CNT_THRSHLD	0x4
+
+/* BAM_IRQ_SRCS */
+#define BAM_IRQ			BIT(31)
+#define P_IRQ			0x7fffffff
+
+/* BAM_IRQ_SRCS_MSK */
+#define BAM_IRQ_MSK		BAM_IRQ
+#define P_IRQ_MSK		P_IRQ
+
+/* BAM_IRQ_STTS */
+#define BAM_TIMER_IRQ		BIT(4)
+#define BAM_EMPTY_IRQ		BIT(3)
+#define BAM_ERROR_IRQ		BIT(2)
+#define BAM_HRESP_ERR_IRQ	BIT(1)
+
+/* BAM_IRQ_CLR */
+#define BAM_TIMER_CLR		BIT(4)
+#define BAM_EMPTY_CLR		BIT(3)
+#define BAM_ERROR_CLR		BIT(2)
+#define BAM_HRESP_ERR_CLR	BIT(1)
+
+/* BAM_IRQ_EN */
+#define BAM_TIMER_EN		BIT(4)
+#define BAM_EMPTY_EN		BIT(3)
+#define BAM_ERROR_EN		BIT(2)
+#define BAM_HRESP_ERR_EN	BIT(1)
+
+/* BAM_P_IRQ_EN */
+#define P_PRCSD_DESC_EN		BIT(0)
+#define P_TIMER_EN		BIT(1)
+#define P_WAKE_EN		BIT(2)
+#define P_OUT_OF_DESC_EN	BIT(3)
+#define P_ERR_EN		BIT(4)
+#define P_TRNSFR_END_EN		BIT(5)
+#define P_DEFAULT_IRQS_EN	(P_PRCSD_DESC_EN | P_ERR_EN | P_TRNSFR_END_EN)
+
+/* BAM_P_SW_OFSTS */
+#define P_SW_OFSTS_MASK		0xffff
+
+#define BAM_DESC_FIFO_SIZE	SZ_32K
+#define MAX_DESCRIPTORS (BAM_DESC_FIFO_SIZE / sizeof(struct bam_desc_hw) - 1)
+#define BAM_MAX_DATA_SIZE	(SZ_32K - 8)
+
+struct bam_chan {
+	struct virt_dma_chan vc;
+
+	struct bam_device *bdev;
+
+	/* configuration from device tree */
+	u32 id;
+
+	struct bam_async_desc *curr_txd;	/* current running dma */
+
+	/* runtime configuration */
+	struct dma_slave_config slave;
+
+	/* fifo storage */
+	struct bam_desc_hw *fifo_virt;
+	dma_addr_t fifo_phys;
+
+	/* fifo markers */
+	unsigned short head;		/* start of active descriptor entries */
+	unsigned short tail;		/* end of active descriptor entries */
+
+	unsigned int initialized;	/* is the channel hw initialized? */
+	unsigned int paused;		/* is the channel paused? */
+	unsigned int reconfigure;	/* new slave config? */
+
+	struct list_head node;
+};
+
+static inline struct bam_chan *to_bam_chan(struct dma_chan *common)
+{
+	return container_of(common, struct bam_chan, vc.chan);
+}
+
+struct bam_device {
+	void __iomem *regs;
+	struct device *dev;
+	struct dma_device common;
+	struct device_dma_parameters dma_parms;
+	struct bam_chan *channels;
+	u32 num_channels;
+
+	/* execution environment ID, from DT */
+	u32 ee;
+
+	struct clk *bamclk;
+	int irq;
+
+	/* dma start transaction tasklet */
+	struct tasklet_struct task;
+};
+
+/**
+ * bam_reset_channel - Reset individual BAM DMA channel
+ * @bchan: bam channel
+ *
+ * This function resets a specific BAM channel
+ */
+static void bam_reset_channel(struct bam_chan *bchan)
+{
+	struct bam_device *bdev = bchan->bdev;
+
+	lockdep_assert_held(&bchan->vc.lock);
+
+	/* reset channel */
+	writel_relaxed(1, bdev->regs + BAM_P_RST(bchan->id));
+	writel_relaxed(0, bdev->regs + BAM_P_RST(bchan->id));
+
+	/* don't allow cpu to reorder BAM register accesses done after this */
+	wmb();
+
+	/* make sure hw is initialized when channel is used the first time  */
+	bchan->initialized = 0;
+}
+
+/**
+ * bam_chan_init_hw - Initialize channel hardware
+ * @bchan: bam channel
+ *
+ * This function resets and initializes the BAM channel
+ */
+static void bam_chan_init_hw(struct bam_chan *bchan,
+	enum dma_transfer_direction dir)
+{
+	struct bam_device *bdev = bchan->bdev;
+	u32 val;
+
+	/* Reset the channel to clear internal state of the FIFO */
+	bam_reset_channel(bchan);
+
+	/*
+	 * write out 8 byte aligned address.  We have enough space for this
+	 * because we allocated 1 more descriptor (8 bytes) than we can use
+	 */
+	writel_relaxed(ALIGN(bchan->fifo_phys, sizeof(struct bam_desc_hw)),
+			bdev->regs + BAM_P_DESC_FIFO_ADDR(bchan->id));
+	writel_relaxed(BAM_DESC_FIFO_SIZE, bdev->regs +
+			BAM_P_FIFO_SIZES(bchan->id));
+
+	/* enable the per pipe interrupts, enable EOT, ERR, and INT irqs */
+	writel_relaxed(P_DEFAULT_IRQS_EN, bdev->regs + BAM_P_IRQ_EN(bchan->id));
+
+	/* unmask the specific pipe and EE combo */
+	val = readl_relaxed(bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee));
+	val |= BIT(bchan->id);
+	writel_relaxed(val, bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee));
+
+	/* don't allow cpu to reorder the channel enable done below */
+	wmb();
+
+	/* set fixed direction and mode, then enable channel */
+	val = P_EN | P_SYS_MODE;
+	if (dir == DMA_DEV_TO_MEM)
+		val |= P_DIRECTION;
+
+	writel_relaxed(val, bdev->regs + BAM_P_CTRL(bchan->id));
+
+	bchan->initialized = 1;
+
+	/* init FIFO pointers */
+	bchan->head = 0;
+	bchan->tail = 0;
+}
+
+/**
+ * bam_alloc_chan - Allocate channel resources for DMA channel.
+ * @chan: specified channel
+ *
+ * This function allocates the FIFO descriptor memory
+ */
+static int bam_alloc_chan(struct dma_chan *chan)
+{
+	struct bam_chan *bchan = to_bam_chan(chan);
+	struct bam_device *bdev = bchan->bdev;
+
+	if (bchan->fifo_virt)
+		return 0;
+
+	/* allocate FIFO descriptor space, but only if necessary */
+	bchan->fifo_virt = dma_alloc_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE,
+				&bchan->fifo_phys, GFP_KERNEL);
+
+	if (!bchan->fifo_virt) {
+		dev_err(bdev->dev, "Failed to allocate desc fifo\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * bam_free_chan - Frees dma resources associated with specific channel
+ * @chan: specified channel
+ *
+ * Free the allocated fifo descriptor memory and channel resources
+ *
+ */
+static void bam_free_chan(struct dma_chan *chan)
+{
+	struct bam_chan *bchan = to_bam_chan(chan);
+	struct bam_device *bdev = bchan->bdev;
+	u32 val;
+	unsigned long flags;
+
+	vchan_free_chan_resources(to_virt_chan(chan));
+
+	if (bchan->curr_txd) {
+		dev_err(bchan->bdev->dev, "Cannot free busy channel\n");
+		return;
+	}
+
+	spin_lock_irqsave(&bchan->vc.lock, flags);
+	bam_reset_channel(bchan);
+	spin_unlock_irqrestore(&bchan->vc.lock, flags);
+
+	dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE, bchan->fifo_virt,
+				bchan->fifo_phys);
+	bchan->fifo_virt = NULL;
+
+	/* mask irq for pipe/channel */
+	val = readl_relaxed(bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee));
+	val &= ~BIT(bchan->id);
+	writel_relaxed(val, bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee));
+
+	/* disable irq */
+	writel_relaxed(0, bdev->regs + BAM_P_IRQ_EN(bchan->id));
+}
+
+/**
+ * bam_slave_config - set slave configuration for channel
+ * @chan: dma channel
+ * @cfg: slave configuration
+ *
+ * Sets slave configuration for channel
+ *
+ */
+static void bam_slave_config(struct bam_chan *bchan,
+		struct dma_slave_config *cfg)
+{
+	memcpy(&bchan->slave, cfg, sizeof(*cfg));
+	bchan->reconfigure = 1;
+}
+
+/**
+ * bam_prep_slave_sg - Prep slave sg transaction
+ *
+ * @chan: dma channel
+ * @sgl: scatter gather list
+ * @sg_len: length of sg
+ * @direction: DMA transfer direction
+ * @flags: DMA flags
+ * @context: transfer context (unused)
+ */
+static struct dma_async_tx_descriptor *bam_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 bam_chan *bchan = to_bam_chan(chan);
+	struct bam_device *bdev = bchan->bdev;
+	struct bam_async_desc *async_desc;
+	struct scatterlist *sg;
+	u32 i;
+	struct bam_desc_hw *desc;
+	unsigned int num_alloc = 0;
+
+
+	if (!is_slave_direction(direction)) {
+		dev_err(bdev->dev, "invalid dma direction\n");
+		return NULL;
+	}
+
+	/* calculate number of required entries */
+	for_each_sg(sgl, sg, sg_len, i)
+		num_alloc += DIV_ROUND_UP(sg_dma_len(sg), BAM_MAX_DATA_SIZE);
+
+	/* allocate enough room to accomodate the number of entries */
+	async_desc = kzalloc(sizeof(*async_desc) +
+			(num_alloc * sizeof(struct bam_desc_hw)), GFP_NOWAIT);
+
+	if (!async_desc)
+		goto err_out;
+
+	async_desc->num_desc = num_alloc;
+	async_desc->curr_desc = async_desc->desc;
+	async_desc->dir = direction;
+
+	/* fill in temporary descriptors */
+	desc = async_desc->desc;
+	for_each_sg(sgl, sg, sg_len, i) {
+		unsigned int remainder = sg_dma_len(sg);
+		unsigned int curr_offset = 0;
+
+		do {
+			desc->addr = sg_dma_address(sg) + curr_offset;
+
+			if (remainder > BAM_MAX_DATA_SIZE) {
+				desc->size = BAM_MAX_DATA_SIZE;
+				remainder -= BAM_MAX_DATA_SIZE;
+				curr_offset += BAM_MAX_DATA_SIZE;
+			} else {
+				desc->size = remainder;
+				remainder = 0;
+			}
+
+			async_desc->length += desc->size;
+			desc++;
+		} while (remainder > 0);
+	}
+
+	return vchan_tx_prep(&bchan->vc, &async_desc->vd, flags);
+
+err_out:
+	kfree(async_desc);
+	return NULL;
+}
+
+/**
+ * bam_dma_terminate_all - terminate all transactions on a channel
+ * @bchan: bam dma channel
+ *
+ * Dequeues and frees all transactions
+ * No callbacks are done
+ *
+ */
+static void bam_dma_terminate_all(struct bam_chan *bchan)
+{
+	unsigned long flag;
+	LIST_HEAD(head);
+
+	/* remove all transactions, including active transaction */
+	spin_lock_irqsave(&bchan->vc.lock, flag);
+	if (bchan->curr_txd) {
+		list_add(&bchan->curr_txd->vd.node, &bchan->vc.desc_issued);
+		bchan->curr_txd = NULL;
+	}
+
+	vchan_get_all_descriptors(&bchan->vc, &head);
+	spin_unlock_irqrestore(&bchan->vc.lock, flag);
+
+	vchan_dma_desc_free_list(&bchan->vc, &head);
+}
+
+/**
+ * bam_control - DMA device control
+ * @chan: dma channel
+ * @cmd: control cmd
+ * @arg: cmd argument
+ *
+ * Perform DMA control command
+ *
+ */
+static int bam_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
+	unsigned long arg)
+{
+	struct bam_chan *bchan = to_bam_chan(chan);
+	struct bam_device *bdev = bchan->bdev;
+	int ret = 0;
+	unsigned long flag;
+
+	switch (cmd) {
+	case DMA_PAUSE:
+		spin_lock_irqsave(&bchan->vc.lock, flag);
+		writel_relaxed(1, bdev->regs + BAM_P_HALT(bchan->id));
+		bchan->paused = 1;
+		spin_unlock_irqrestore(&bchan->vc.lock, flag);
+		break;
+
+	case DMA_RESUME:
+		spin_lock_irqsave(&bchan->vc.lock, flag);
+		writel_relaxed(0, bdev->regs + BAM_P_HALT(bchan->id));
+		bchan->paused = 0;
+		spin_unlock_irqrestore(&bchan->vc.lock, flag);
+		break;
+
+	case DMA_TERMINATE_ALL:
+		bam_dma_terminate_all(bchan);
+		break;
+
+	case DMA_SLAVE_CONFIG:
+		spin_lock_irqsave(&bchan->vc.lock, flag);
+		bam_slave_config(bchan, (struct dma_slave_config *)arg);
+		spin_unlock_irqrestore(&bchan->vc.lock, flag);
+		break;
+
+	default:
+		ret = -ENXIO;
+		break;
+	}
+
+	return ret;
+}
+
+/**
+ * process_channel_irqs - processes the channel interrupts
+ * @bdev: bam controller
+ *
+ * This function processes the channel interrupts
+ *
+ */
+static u32 process_channel_irqs(struct bam_device *bdev)
+{
+	u32 i, srcs, pipe_stts;
+	unsigned long flags;
+	struct bam_async_desc *async_desc;
+
+	srcs = readl_relaxed(bdev->regs + BAM_IRQ_SRCS_EE(bdev->ee));
+
+	/* return early if no pipe/channel interrupts are present */
+	if (!(srcs & P_IRQ))
+		return srcs;
+
+	for (i = 0; i < bdev->num_channels; i++) {
+		struct bam_chan *bchan = &bdev->channels[i];
+
+		if (!(srcs & BIT(i)))
+			continue;
+
+		/* clear pipe irq */
+		pipe_stts = readl_relaxed(bdev->regs +
+			BAM_P_IRQ_STTS(i));
+
+		writel_relaxed(pipe_stts, bdev->regs +
+				BAM_P_IRQ_CLR(i));
+
+		spin_lock_irqsave(&bchan->vc.lock, flags);
+		async_desc = bchan->curr_txd;
+
+		if (async_desc) {
+			async_desc->num_desc -= async_desc->xfer_len;
+			async_desc->curr_desc += async_desc->xfer_len;
+			bchan->curr_txd = NULL;
+
+			/* manage FIFO */
+			bchan->head += async_desc->xfer_len;
+			bchan->head %= MAX_DESCRIPTORS;
+
+			/*
+			 * if complete, process cookie.  Otherwise
+			 * push back to front of desc_issued so that
+			 * it gets restarted by the tasklet
+			 */
+			if (!async_desc->num_desc)
+				vchan_cookie_complete(&async_desc->vd);
+			else
+				list_add(&async_desc->vd.node,
+					&bchan->vc.desc_issued);
+		}
+
+		spin_unlock_irqrestore(&bchan->vc.lock, flags);
+	}
+
+	return srcs;
+}
+
+/**
+ * bam_dma_irq - irq handler for bam controller
+ * @irq: IRQ of interrupt
+ * @data: callback data
+ *
+ * IRQ handler for the bam controller
+ */
+static irqreturn_t bam_dma_irq(int irq, void *data)
+{
+	struct bam_device *bdev = data;
+	u32 clr_mask = 0, srcs = 0;
+
+	srcs |= process_channel_irqs(bdev);
+
+	/* kick off tasklet to start next dma transfer */
+	if (srcs & P_IRQ)
+		tasklet_schedule(&bdev->task);
+
+	if (srcs & BAM_IRQ)
+		clr_mask = readl_relaxed(bdev->regs + BAM_IRQ_STTS);
+
+	/* don't allow reorder of the various accesses to the BAM registers */
+	mb();
+
+	writel_relaxed(clr_mask, bdev->regs + BAM_IRQ_CLR);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * bam_tx_status - returns status of transaction
+ * @chan: dma channel
+ * @cookie: transaction cookie
+ * @txstate: DMA transaction state
+ *
+ * Return status of dma transaction
+ */
+static enum dma_status bam_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
+		struct dma_tx_state *txstate)
+{
+	struct bam_chan *bchan = to_bam_chan(chan);
+	struct virt_dma_desc *vd;
+	int ret;
+	size_t residue = 0;
+	unsigned int i;
+	unsigned long flags;
+
+	ret = dma_cookie_status(chan, cookie, txstate);
+	if (ret == DMA_COMPLETE)
+		return ret;
+
+	if (!txstate)
+		return bchan->paused ? DMA_PAUSED : ret;
+
+	spin_lock_irqsave(&bchan->vc.lock, flags);
+	vd = vchan_find_desc(&bchan->vc, cookie);
+	if (vd)
+		residue = container_of(vd, struct bam_async_desc, vd)->length;
+	else if (bchan->curr_txd && bchan->curr_txd->vd.tx.cookie == cookie)
+		for (i = 0; i < bchan->curr_txd->num_desc; i++)
+			residue += bchan->curr_txd->curr_desc[i].size;
+
+	spin_unlock_irqrestore(&bchan->vc.lock, flags);
+
+	dma_set_residue(txstate, residue);
+
+	if (ret == DMA_IN_PROGRESS && bchan->paused)
+		ret = DMA_PAUSED;
+
+	return ret;
+}
+
+/**
+ * bam_apply_new_config
+ * @bchan: bam dma channel
+ * @dir: DMA direction
+ */
+static void bam_apply_new_config(struct bam_chan *bchan,
+	enum dma_transfer_direction dir)
+{
+	struct bam_device *bdev = bchan->bdev;
+	u32 maxburst;
+
+	if (dir == DMA_DEV_TO_MEM)
+		maxburst = bchan->slave.src_maxburst;
+	else
+		maxburst = bchan->slave.dst_maxburst;
+
+	writel_relaxed(maxburst, bdev->regs + BAM_DESC_CNT_TRSHLD);
+
+	bchan->reconfigure = 0;
+}
+
+/**
+ * bam_start_dma - start next transaction
+ * @bchan - bam dma channel
+ */
+static void bam_start_dma(struct bam_chan *bchan)
+{
+	struct virt_dma_desc *vd = vchan_next_desc(&bchan->vc);
+	struct bam_device *bdev = bchan->bdev;
+	struct bam_async_desc *async_desc;
+	struct bam_desc_hw *desc;
+	struct bam_desc_hw *fifo = PTR_ALIGN(bchan->fifo_virt,
+					sizeof(struct bam_desc_hw));
+
+	lockdep_assert_held(&bchan->vc.lock);
+
+	if (!vd)
+		return;
+
+	list_del(&vd->node);
+
+	async_desc = container_of(vd, struct bam_async_desc, vd);
+	bchan->curr_txd = async_desc;
+
+	/* on first use, initialize the channel hardware */
+	if (!bchan->initialized)
+		bam_chan_init_hw(bchan, async_desc->dir);
+
+	/* apply new slave config changes, if necessary */
+	if (bchan->reconfigure)
+		bam_apply_new_config(bchan, async_desc->dir);
+
+	desc = bchan->curr_txd->curr_desc;
+
+	if (async_desc->num_desc > MAX_DESCRIPTORS)
+		async_desc->xfer_len = MAX_DESCRIPTORS;
+	else
+		async_desc->xfer_len = async_desc->num_desc;
+
+	/* set INT on last descriptor */
+	desc[async_desc->xfer_len - 1].flags |= DESC_FLAG_INT;
+
+	if (bchan->tail + async_desc->xfer_len > MAX_DESCRIPTORS) {
+		u32 partial = MAX_DESCRIPTORS - bchan->tail;
+
+		memcpy(&fifo[bchan->tail], desc,
+				partial * sizeof(struct bam_desc_hw));
+		memcpy(fifo, &desc[partial], (async_desc->xfer_len - partial) *
+				sizeof(struct bam_desc_hw));
+	} else {
+		memcpy(&fifo[bchan->tail], desc,
+			async_desc->xfer_len * sizeof(struct bam_desc_hw));
+	}
+
+	bchan->tail += async_desc->xfer_len;
+	bchan->tail %= MAX_DESCRIPTORS;
+
+	/* ensure descriptor writes and dma start not reordered */
+	wmb();
+	writel_relaxed(bchan->tail * sizeof(struct bam_desc_hw),
+			bdev->regs + BAM_P_EVNT_REG(bchan->id));
+}
+
+/**
+ * dma_tasklet - DMA IRQ tasklet
+ * @data: tasklet argument (bam controller structure)
+ *
+ * Sets up next DMA operation and then processes all completed transactions
+ */
+static void dma_tasklet(unsigned long data)
+{
+	struct bam_device *bdev = (struct bam_device *)data;
+	struct bam_chan *bchan;
+	unsigned long flags;
+	unsigned int i;
+
+	/* go through the channels and kick off transactions */
+	for (i = 0; i < bdev->num_channels; i++) {
+		bchan = &bdev->channels[i];
+		spin_lock_irqsave(&bchan->vc.lock, flags);
+
+		if (!list_empty(&bchan->vc.desc_issued) && !bchan->curr_txd)
+			bam_start_dma(bchan);
+		spin_unlock_irqrestore(&bchan->vc.lock, flags);
+	}
+}
+
+/**
+ * bam_issue_pending - starts pending transactions
+ * @chan: dma channel
+ *
+ * Calls tasklet directly which in turn starts any pending transactions
+ */
+static void bam_issue_pending(struct dma_chan *chan)
+{
+	struct bam_chan *bchan = to_bam_chan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&bchan->vc.lock, flags);
+
+	/* if work pending and idle, start a transaction */
+	if (vchan_issue_pending(&bchan->vc) && !bchan->curr_txd)
+		bam_start_dma(bchan);
+
+	spin_unlock_irqrestore(&bchan->vc.lock, flags);
+}
+
+/**
+ * bam_dma_free_desc - free descriptor memory
+ * @vd: virtual descriptor
+ *
+ */
+static void bam_dma_free_desc(struct virt_dma_desc *vd)
+{
+	struct bam_async_desc *async_desc = container_of(vd,
+			struct bam_async_desc, vd);
+
+	kfree(async_desc);
+}
+
+static struct dma_chan *bam_dma_xlate(struct of_phandle_args *dma_spec,
+		struct of_dma *of)
+{
+	struct bam_device *bdev = container_of(of->of_dma_data,
+					struct bam_device, common);
+	unsigned int request;
+
+	if (dma_spec->args_count != 1)
+		return NULL;
+
+	request = dma_spec->args[0];
+	if (request >= bdev->num_channels)
+		return NULL;
+
+	return dma_get_slave_channel(&(bdev->channels[request].vc.chan));
+}
+
+/**
+ * bam_init
+ * @bdev: bam device
+ *
+ * Initialization helper for global bam registers
+ */
+static int bam_init(struct bam_device *bdev)
+{
+	u32 val;
+
+	/* read revision and configuration information */
+	val = readl_relaxed(bdev->regs + BAM_REVISION) >> NUM_EES_SHIFT;
+	val &= NUM_EES_MASK;
+
+	/* check that configured EE is within range */
+	if (bdev->ee >= val)
+		return -EINVAL;
+
+	val = readl_relaxed(bdev->regs + BAM_NUM_PIPES);
+	bdev->num_channels = val & BAM_NUM_PIPES_MASK;
+
+	/* s/w reset bam */
+	/* after reset all pipes are disabled and idle */
+	val = readl_relaxed(bdev->regs + BAM_CTRL);
+	val |= BAM_SW_RST;
+	writel_relaxed(val, bdev->regs + BAM_CTRL);
+	val &= ~BAM_SW_RST;
+	writel_relaxed(val, bdev->regs + BAM_CTRL);
+
+	/* make sure previous stores are visible before enabling BAM */
+	wmb();
+
+	/* enable bam */
+	val |= BAM_EN;
+	writel_relaxed(val, bdev->regs + BAM_CTRL);
+
+	/* set descriptor threshhold, start with 4 bytes */
+	writel_relaxed(DEFAULT_CNT_THRSHLD, bdev->regs + BAM_DESC_CNT_TRSHLD);
+
+	/* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */
+	writel_relaxed(BAM_CNFG_BITS_DEFAULT, bdev->regs + BAM_CNFG_BITS);
+
+	/* enable irqs for errors */
+	writel_relaxed(BAM_ERROR_EN | BAM_HRESP_ERR_EN,
+				bdev->regs + BAM_IRQ_EN);
+
+	/* unmask global bam interrupt */
+	writel_relaxed(BAM_IRQ_MSK, bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee));
+
+	return 0;
+}
+
+static void bam_channel_init(struct bam_device *bdev, struct bam_chan *bchan,
+	u32 index)
+{
+	bchan->id = index;
+	bchan->bdev = bdev;
+
+	vchan_init(&bchan->vc, &bdev->common);
+	bchan->vc.desc_free = bam_dma_free_desc;
+}
+
+static int bam_dma_probe(struct platform_device *pdev)
+{
+	struct bam_device *bdev;
+	struct resource *iores;
+	int ret, i;
+
+	bdev = devm_kzalloc(&pdev->dev, sizeof(*bdev), GFP_KERNEL);
+	if (!bdev)
+		return -ENOMEM;
+
+	bdev->dev = &pdev->dev;
+
+	iores = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	bdev->regs = devm_ioremap_resource(&pdev->dev, iores);
+	if (IS_ERR(bdev->regs))
+		return PTR_ERR(bdev->regs);
+
+	bdev->irq = platform_get_irq(pdev, 0);
+	if (bdev->irq < 0)
+		return bdev->irq;
+
+	ret = of_property_read_u32(pdev->dev.of_node, "qcom,ee", &bdev->ee);
+	if (ret) {
+		dev_err(bdev->dev, "Execution environment unspecified\n");
+		return ret;
+	}
+
+	bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk");
+	if (IS_ERR(bdev->bamclk))
+		return PTR_ERR(bdev->bamclk);
+
+	ret = clk_prepare_enable(bdev->bamclk);
+	if (ret) {
+		dev_err(bdev->dev, "failed to prepare/enable clock\n");
+		return ret;
+	}
+
+	ret = bam_init(bdev);
+	if (ret)
+		goto err_disable_clk;
+
+	tasklet_init(&bdev->task, dma_tasklet, (unsigned long)bdev);
+
+	bdev->channels = devm_kcalloc(bdev->dev, bdev->num_channels,
+				sizeof(*bdev->channels), GFP_KERNEL);
+
+	if (!bdev->channels) {
+		ret = -ENOMEM;
+		goto err_disable_clk;
+	}
+
+	/* allocate and initialize channels */
+	INIT_LIST_HEAD(&bdev->common.channels);
+
+	for (i = 0; i < bdev->num_channels; i++)
+		bam_channel_init(bdev, &bdev->channels[i], i);
+
+	ret = devm_request_irq(bdev->dev, bdev->irq, bam_dma_irq,
+			IRQF_TRIGGER_HIGH, "bam_dma", bdev);
+	if (ret)
+		goto err_disable_clk;
+
+	/* set max dma segment size */
+	bdev->common.dev = bdev->dev;
+	bdev->common.dev->dma_parms = &bdev->dma_parms;
+	ret = dma_set_max_seg_size(bdev->common.dev, BAM_MAX_DATA_SIZE);
+	if (ret) {
+		dev_err(bdev->dev, "cannot set maximum segment size\n");
+		goto err_disable_clk;
+	}
+
+	platform_set_drvdata(pdev, bdev);
+
+	/* set capabilities */
+	dma_cap_zero(bdev->common.cap_mask);
+	dma_cap_set(DMA_SLAVE, bdev->common.cap_mask);
+
+	/* initialize dmaengine apis */
+	bdev->common.device_alloc_chan_resources = bam_alloc_chan;
+	bdev->common.device_free_chan_resources = bam_free_chan;
+	bdev->common.device_prep_slave_sg = bam_prep_slave_sg;
+	bdev->common.device_control = bam_control;
+	bdev->common.device_issue_pending = bam_issue_pending;
+	bdev->common.device_tx_status = bam_tx_status;
+	bdev->common.dev = bdev->dev;
+
+	ret = dma_async_device_register(&bdev->common);
+	if (ret) {
+		dev_err(bdev->dev, "failed to register dma async device\n");
+		goto err_disable_clk;
+	}
+
+	ret = of_dma_controller_register(pdev->dev.of_node, bam_dma_xlate,
+					&bdev->common);
+	if (ret)
+		goto err_unregister_dma;
+
+	return 0;
+
+err_unregister_dma:
+	dma_async_device_unregister(&bdev->common);
+err_disable_clk:
+	clk_disable_unprepare(bdev->bamclk);
+	return ret;
+}
+
+static int bam_dma_remove(struct platform_device *pdev)
+{
+	struct bam_device *bdev = platform_get_drvdata(pdev);
+	u32 i;
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&bdev->common);
+
+	/* mask all interrupts for this execution environment */
+	writel_relaxed(0, bdev->regs + BAM_IRQ_SRCS_MSK_EE(bdev->ee));
+
+	devm_free_irq(bdev->dev, bdev->irq, bdev);
+
+	for (i = 0; i < bdev->num_channels; i++) {
+		bam_dma_terminate_all(&bdev->channels[i]);
+		tasklet_kill(&bdev->channels[i].vc.task);
+
+		dma_free_writecombine(bdev->dev, BAM_DESC_FIFO_SIZE,
+			bdev->channels[i].fifo_virt,
+			bdev->channels[i].fifo_phys);
+	}
+
+	tasklet_kill(&bdev->task);
+
+	clk_disable_unprepare(bdev->bamclk);
+
+	return 0;
+}
+
+static const struct of_device_id bam_of_match[] = {
+	{ .compatible = "qcom,bam-v1.4.0", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, bam_of_match);
+
+static struct platform_driver bam_dma_driver = {
+	.probe = bam_dma_probe,
+	.remove = bam_dma_remove,
+	.driver = {
+		.name = "bam-dma-engine",
+		.owner = THIS_MODULE,
+		.of_match_table = bam_of_match,
+	},
+};
+
+module_platform_driver(bam_dma_driver);
+
+MODULE_AUTHOR("Andy Gross <agross@codeaurora.org>");
+MODULE_DESCRIPTION("QCOM BAM DMA engine driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/s3c24xx-dma.c b/drivers/dma/s3c24xx-dma.c
index 4eddedb6eb7d..b209a0f17344 100644
--- a/drivers/dma/s3c24xx-dma.c
+++ b/drivers/dma/s3c24xx-dma.c
@@ -192,7 +192,7 @@ struct s3c24xx_dma_phy {
 	unsigned int			id;
 	bool				valid;
 	void __iomem			*base;
-	unsigned int			irq;
+	int				irq;
 	struct clk			*clk;
 	spinlock_t			lock;
 	struct s3c24xx_dma_chan		*serving;
diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index dadd9e010c0b..b4c813831006 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -29,6 +29,12 @@ config RCAR_HPB_DMAE
 	help
 	  Enable support for the Renesas R-Car series DMA controllers.
 
+config RCAR_AUDMAC_PP
+	tristate "Renesas R-Car Audio DMAC Peripheral Peripheral support"
+	depends on SH_DMAE_BASE
+	help
+	  Enable support for the Renesas R-Car Audio DMAC Peripheral Peripheral controllers.
+
 config SHDMA_R8A73A4
 	def_bool y
 	depends on ARCH_R8A73A4 && SH_DMAE != n
diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile
index e856af23b789..1ce88b28cfc6 100644
--- a/drivers/dma/sh/Makefile
+++ b/drivers/dma/sh/Makefile
@@ -7,3 +7,4 @@ endif
 shdma-objs := $(shdma-y)
 obj-$(CONFIG_SUDMAC) += sudmac.o
 obj-$(CONFIG_RCAR_HPB_DMAE) += rcar-hpbdma.o
+obj-$(CONFIG_RCAR_AUDMAC_PP) += rcar-audmapp.o
diff --git a/drivers/dma/sh/rcar-audmapp.c b/drivers/dma/sh/rcar-audmapp.c
new file mode 100644
index 000000000000..2de77289a2e9
--- /dev/null
+++ b/drivers/dma/sh/rcar-audmapp.c
@@ -0,0 +1,320 @@
+/*
+ * This is for Renesas R-Car Audio-DMAC-peri-peri.
+ *
+ * Copyright (C) 2014 Renesas Electronics Corporation
+ * Copyright (C) 2014 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * based on the 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 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.
+ *
+ */
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/dmaengine.h>
+#include <linux/platform_data/dma-rcar-audmapp.h>
+#include <linux/platform_device.h>
+#include <linux/shdma-base.h>
+
+/*
+ * DMA register
+ */
+#define PDMASAR		0x00
+#define PDMADAR		0x04
+#define PDMACHCR	0x0c
+
+/* PDMACHCR */
+#define PDMACHCR_DE		(1 << 0)
+
+#define AUDMAPP_MAX_CHANNELS	29
+
+/* Default MEMCPY transfer size = 2^2 = 4 bytes */
+#define LOG2_DEFAULT_XFER_SIZE	2
+#define AUDMAPP_SLAVE_NUMBER	256
+#define AUDMAPP_LEN_MAX		(16 * 1024 * 1024)
+
+struct audmapp_chan {
+	struct shdma_chan shdma_chan;
+	struct audmapp_slave_config *config;
+	void __iomem *base;
+};
+
+struct audmapp_device {
+	struct shdma_dev shdma_dev;
+	struct audmapp_pdata *pdata;
+	struct device *dev;
+	void __iomem *chan_reg;
+};
+
+#define to_chan(chan) container_of(chan, struct audmapp_chan, shdma_chan)
+#define to_dev(chan) container_of(chan->shdma_chan.dma_chan.device,	\
+				  struct audmapp_device, shdma_dev.dma_dev)
+
+static void audmapp_write(struct audmapp_chan *auchan, u32 data, u32 reg)
+{
+	struct audmapp_device *audev = to_dev(auchan);
+	struct device *dev = audev->dev;
+
+	dev_dbg(dev, "w %p : %08x\n", auchan->base + reg, data);
+
+	iowrite32(data, auchan->base + reg);
+}
+
+static u32 audmapp_read(struct audmapp_chan *auchan, u32 reg)
+{
+	return ioread32(auchan->base + reg);
+}
+
+static void audmapp_halt(struct shdma_chan *schan)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	int i;
+
+	audmapp_write(auchan, 0, PDMACHCR);
+
+	for (i = 0; i < 1024; i++) {
+		if (0 == audmapp_read(auchan, PDMACHCR))
+			return;
+		udelay(1);
+	}
+}
+
+static void audmapp_start_xfer(struct shdma_chan *schan,
+			       struct shdma_desc *sdecs)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	struct audmapp_device *audev = to_dev(auchan);
+	struct audmapp_slave_config *cfg = auchan->config;
+	struct device *dev = audev->dev;
+	u32 chcr = cfg->chcr | PDMACHCR_DE;
+
+	dev_dbg(dev, "src/dst/chcr = %pad/%pad/%x\n",
+		&cfg->src, &cfg->dst, cfg->chcr);
+
+	audmapp_write(auchan, cfg->src,	PDMASAR);
+	audmapp_write(auchan, cfg->dst,	PDMADAR);
+	audmapp_write(auchan, chcr,	PDMACHCR);
+}
+
+static struct audmapp_slave_config *
+audmapp_find_slave(struct audmapp_chan *auchan, int slave_id)
+{
+	struct audmapp_device *audev = to_dev(auchan);
+	struct audmapp_pdata *pdata = audev->pdata;
+	struct audmapp_slave_config *cfg;
+	int i;
+
+	if (slave_id >= AUDMAPP_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 audmapp_set_slave(struct shdma_chan *schan, int slave_id,
+			     dma_addr_t slave_addr, bool try)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	struct audmapp_slave_config *cfg =
+		audmapp_find_slave(auchan, slave_id);
+
+	if (!cfg)
+		return -ENODEV;
+	if (try)
+		return 0;
+
+	auchan->config	= cfg;
+
+	return 0;
+}
+
+static int audmapp_desc_setup(struct shdma_chan *schan,
+			      struct shdma_desc *sdecs,
+			      dma_addr_t src, dma_addr_t dst, size_t *len)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	struct audmapp_slave_config *cfg = auchan->config;
+
+	if (!cfg)
+		return -ENODEV;
+
+	if (*len > (size_t)AUDMAPP_LEN_MAX)
+		*len = (size_t)AUDMAPP_LEN_MAX;
+
+	return 0;
+}
+
+static void audmapp_setup_xfer(struct shdma_chan *schan,
+			       int slave_id)
+{
+}
+
+static dma_addr_t audmapp_slave_addr(struct shdma_chan *schan)
+{
+	return 0; /* always fixed address */
+}
+
+static bool audmapp_channel_busy(struct shdma_chan *schan)
+{
+	struct audmapp_chan *auchan = to_chan(schan);
+	u32 chcr = audmapp_read(auchan, PDMACHCR);
+
+	return chcr & ~PDMACHCR_DE;
+}
+
+static bool audmapp_desc_completed(struct shdma_chan *schan,
+				   struct shdma_desc *sdesc)
+{
+	return true;
+}
+
+static struct shdma_desc *audmapp_embedded_desc(void *buf, int i)
+{
+	return &((struct shdma_desc *)buf)[i];
+}
+
+static const struct shdma_ops audmapp_shdma_ops = {
+	.halt_channel	= audmapp_halt,
+	.desc_setup	= audmapp_desc_setup,
+	.set_slave	= audmapp_set_slave,
+	.start_xfer	= audmapp_start_xfer,
+	.embedded_desc	= audmapp_embedded_desc,
+	.setup_xfer	= audmapp_setup_xfer,
+	.slave_addr	= audmapp_slave_addr,
+	.channel_busy	= audmapp_channel_busy,
+	.desc_completed	= audmapp_desc_completed,
+};
+
+static int audmapp_chan_probe(struct platform_device *pdev,
+			      struct audmapp_device *audev, int id)
+{
+	struct shdma_dev *sdev = &audev->shdma_dev;
+	struct audmapp_chan *auchan;
+	struct shdma_chan *schan;
+	struct device *dev = audev->dev;
+
+	auchan = devm_kzalloc(dev, sizeof(*auchan), GFP_KERNEL);
+	if (!auchan)
+		return -ENOMEM;
+
+	schan = &auchan->shdma_chan;
+	schan->max_xfer_len = AUDMAPP_LEN_MAX;
+
+	shdma_chan_probe(sdev, schan, id);
+
+	auchan->base = audev->chan_reg + 0x20 + (0x10 * id);
+	dev_dbg(dev, "%02d : %p / %p", id, auchan->base, audev->chan_reg);
+
+	return 0;
+}
+
+static void audmapp_chan_remove(struct audmapp_device *audev)
+{
+	struct dma_device *dma_dev = &audev->shdma_dev.dma_dev;
+	struct shdma_chan *schan;
+	int i;
+
+	shdma_for_each_chan(schan, &audev->shdma_dev, i) {
+		BUG_ON(!schan);
+		shdma_chan_remove(schan);
+	}
+	dma_dev->chancnt = 0;
+}
+
+static int audmapp_probe(struct platform_device *pdev)
+{
+	struct audmapp_pdata *pdata = pdev->dev.platform_data;
+	struct audmapp_device *audev;
+	struct shdma_dev *sdev;
+	struct dma_device *dma_dev;
+	struct resource *res;
+	int err, i;
+
+	if (!pdata)
+		return -ENODEV;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	audev = devm_kzalloc(&pdev->dev, sizeof(*audev), GFP_KERNEL);
+	if (!audev)
+		return -ENOMEM;
+
+	audev->dev	= &pdev->dev;
+	audev->pdata	= pdata;
+	audev->chan_reg	= devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(audev->chan_reg))
+		return PTR_ERR(audev->chan_reg);
+
+	sdev		= &audev->shdma_dev;
+	sdev->ops	= &audmapp_shdma_ops;
+	sdev->desc_size	= sizeof(struct shdma_desc);
+
+	dma_dev			= &sdev->dma_dev;
+	dma_dev->copy_align	= LOG2_DEFAULT_XFER_SIZE;
+	dma_cap_set(DMA_SLAVE, dma_dev->cap_mask);
+
+	err = shdma_init(&pdev->dev, sdev, AUDMAPP_MAX_CHANNELS);
+	if (err < 0)
+		return err;
+
+	platform_set_drvdata(pdev, audev);
+
+	/* Create DMA Channel */
+	for (i = 0; i < AUDMAPP_MAX_CHANNELS; i++) {
+		err = audmapp_chan_probe(pdev, audev, i);
+		if (err)
+			goto chan_probe_err;
+	}
+
+	err = dma_async_device_register(dma_dev);
+	if (err < 0)
+		goto chan_probe_err;
+
+	return err;
+
+chan_probe_err:
+	audmapp_chan_remove(audev);
+	shdma_cleanup(sdev);
+
+	return err;
+}
+
+static int audmapp_remove(struct platform_device *pdev)
+{
+	struct audmapp_device *audev = platform_get_drvdata(pdev);
+	struct dma_device *dma_dev = &audev->shdma_dev.dma_dev;
+
+	dma_async_device_unregister(dma_dev);
+
+	audmapp_chan_remove(audev);
+	shdma_cleanup(&audev->shdma_dev);
+
+	return 0;
+}
+
+static struct platform_driver audmapp_driver = {
+	.probe		= audmapp_probe,
+	.remove		= audmapp_remove,
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= "rcar-audmapp-engine",
+	},
+};
+module_platform_driver(audmapp_driver);
+
+MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
+MODULE_DESCRIPTION("Renesas R-Car Audio DMAC peri-peri driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/sh/shdma-base.c b/drivers/dma/sh/shdma-base.c
index 2e7b394def80..52396771acbe 100644
--- a/drivers/dma/sh/shdma-base.c
+++ b/drivers/dma/sh/shdma-base.c
@@ -227,7 +227,7 @@ 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 match = (int)arg;
+	int match = (long)arg;
 	int ret;
 
 	if (match < 0)
@@ -491,8 +491,8 @@ static struct shdma_desc *shdma_add_desc(struct shdma_chan *schan,
 	}
 
 	dev_dbg(schan->dev,
-		"chaining (%u/%u)@%x -> %x with %p, cookie %d\n",
-		copy_size, *len, *src, *dst, &new->async_tx,
+		"chaining (%zu/%zu)@%pad -> %pad with %p, cookie %d\n",
+		copy_size, *len, src, dst, &new->async_tx,
 		new->async_tx.cookie);
 
 	new->mark = DESC_PREPARED;
@@ -555,8 +555,8 @@ static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan,
 			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);
+			dev_dbg(schan->dev, "Add SG #%d@%p[%zu], dma %pad\n",
+				i, sg, len, &sg_addr);
 
 			if (direction == DMA_DEV_TO_MEM)
 				new = shdma_add_desc(schan, flags,
diff --git a/drivers/dma/sh/shdma-of.c b/drivers/dma/sh/shdma-of.c
index 06473a05fe4e..b4ff9d3e56d1 100644
--- a/drivers/dma/sh/shdma-of.c
+++ b/drivers/dma/sh/shdma-of.c
@@ -33,7 +33,8 @@ static struct dma_chan *shdma_of_xlate(struct of_phandle_args *dma_spec,
 	/* Only slave DMA channels can be allocated via DT */
 	dma_cap_set(DMA_SLAVE, mask);
 
-	chan = dma_request_channel(mask, shdma_chan_filter, (void *)id);
+	chan = dma_request_channel(mask, shdma_chan_filter,
+				   (void *)(uintptr_t)id);
 	if (chan)
 		to_shdma_chan(chan)->hw_req = id;
 
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 0d765c0e21ec..dda7e7563f5d 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -443,6 +443,7 @@ static bool sh_dmae_reset(struct sh_dmae_device *shdev)
 	return ret;
 }
 
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARM)
 static irqreturn_t sh_dmae_err(int irq, void *data)
 {
 	struct sh_dmae_device *shdev = data;
@@ -453,6 +454,7 @@ static irqreturn_t sh_dmae_err(int irq, void *data)
 	sh_dmae_reset(shdev);
 	return IRQ_HANDLED;
 }
+#endif
 
 static bool sh_dmae_desc_completed(struct shdma_chan *schan,
 				   struct shdma_desc *sdesc)
@@ -637,7 +639,7 @@ static int sh_dmae_resume(struct device *dev)
 #define sh_dmae_resume NULL
 #endif
 
-const struct dev_pm_ops sh_dmae_pm = {
+static const struct dev_pm_ops sh_dmae_pm = {
 	.suspend		= sh_dmae_suspend,
 	.resume			= sh_dmae_resume,
 	.runtime_suspend	= sh_dmae_runtime_suspend,
@@ -685,9 +687,12 @@ MODULE_DEVICE_TABLE(of, sh_dmae_of_match);
 static int sh_dmae_probe(struct platform_device *pdev)
 {
 	const struct sh_dmae_pdata *pdata;
-	unsigned long irqflags = 0,
-		chan_flag[SH_DMAE_MAX_CHANNELS] = {};
-	int errirq, chan_irq[SH_DMAE_MAX_CHANNELS];
+	unsigned long chan_flag[SH_DMAE_MAX_CHANNELS] = {};
+	int chan_irq[SH_DMAE_MAX_CHANNELS];
+#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARM)
+	unsigned long irqflags = 0;
+	int errirq;
+#endif
 	int err, i, irq_cnt = 0, irqres = 0, irq_cap = 0;
 	struct sh_dmae_device *shdev;
 	struct dma_device *dma_dev;
diff --git a/drivers/dma/sh/sudmac.c b/drivers/dma/sh/sudmac.c
index c7e9cdff0708..4e7df43b50d6 100644
--- a/drivers/dma/sh/sudmac.c
+++ b/drivers/dma/sh/sudmac.c
@@ -178,8 +178,8 @@ static int sudmac_desc_setup(struct shdma_chan *schan,
 	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);
+	dev_dbg(sc->shdma_chan.dev, "%s: src=%pad, dst=%pad, len=%zu\n",
+		__func__, &src, &dst, *len);
 
 	if (*len > schan->max_xfer_len)
 		*len = schan->max_xfer_len;
diff --git a/drivers/dma/sirf-dma.c b/drivers/dma/sirf-dma.c
index d4d3a3109b16..a1bd8298d55f 100644
--- a/drivers/dma/sirf-dma.c
+++ b/drivers/dma/sirf-dma.c
@@ -18,6 +18,7 @@
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
 #include <linux/clk.h>
+#include <linux/of_dma.h>
 #include <linux/sirfsoc_dma.h>
 
 #include "dmaengine.h"
@@ -659,6 +660,18 @@ static int sirfsoc_dma_device_slave_caps(struct dma_chan *dchan,
 	return 0;
 }
 
+static struct dma_chan *of_dma_sirfsoc_xlate(struct of_phandle_args *dma_spec,
+	struct of_dma *ofdma)
+{
+	struct sirfsoc_dma *sdma = ofdma->of_dma_data;
+	unsigned int request = dma_spec->args[0];
+
+	if (request > SIRFSOC_DMA_CHANNELS)
+		return NULL;
+
+	return dma_get_slave_channel(&sdma->channels[request].chan);
+}
+
 static int sirfsoc_dma_probe(struct platform_device *op)
 {
 	struct device_node *dn = op->dev.of_node;
@@ -764,11 +777,20 @@ static int sirfsoc_dma_probe(struct platform_device *op)
 	if (ret)
 		goto free_irq;
 
+	/* Device-tree DMA controller registration */
+	ret = of_dma_controller_register(dn, of_dma_sirfsoc_xlate, sdma);
+	if (ret) {
+		dev_err(dev, "failed to register DMA controller\n");
+		goto unreg_dma_dev;
+	}
+
 	pm_runtime_enable(&op->dev);
 	dev_info(dev, "initialized SIRFSOC DMAC driver\n");
 
 	return 0;
 
+unreg_dma_dev:
+	dma_async_device_unregister(dma);
 free_irq:
 	free_irq(sdma->irq, sdma);
 irq_dispose:
@@ -781,6 +803,7 @@ static int sirfsoc_dma_remove(struct platform_device *op)
 	struct device *dev = &op->dev;
 	struct sirfsoc_dma *sdma = dev_get_drvdata(dev);
 
+	of_dma_controller_free(op->dev.of_node);
 	dma_async_device_unregister(&sdma->dma);
 	free_irq(sdma->irq, sdma);
 	irq_dispose_mapping(sdma->irq);