Merge tag 'dmaengine-4.7-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "This time round the update brings in following changes:

   - new tegra driver for ADMA device

   - support for Xilinx AXI Direct Memory Access Engine and Xilinx AXI
     Central Direct Memory Access Engine and few updates to this driver

   - new cyclic capability to sun6i and few updates

   - slave-sg support in bcm2835

   - updates to many drivers like designware, hsu, mv_xor, pxa, edma,
     qcom_hidma & bam"

* tag 'dmaengine-4.7-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (84 commits)
  dmaengine: ioatdma: disable relaxed ordering for ioatdma
  dmaengine: of_dma: approximate an average distribution
  dmaengine: core: Use IS_ENABLED() instead of checking for built-in or module
  dmaengine: edma: Re-evaluate errors when ccerr is triggered w/o error event
  dmaengine: qcom_hidma: add support for object hierarchy
  dmaengine: qcom_hidma: add debugfs hooks
  dmaengine: qcom_hidma: implement lower level hardware interface
  dmaengine: vdma: Add clock support
  Documentation: DT: vdma: Add clock support for dmas
  dmaengine: vdma: Add config structure to differentiate dmas
  MAINTAINERS: Update Tegra DMA maintainers
  dmaengine: tegra-adma: Add support for Tegra210 ADMA
  Documentation: DT: Add binding documentation for NVIDIA ADMA
  dmaengine: vdma: Add Support for Xilinx AXI Central Direct Memory Access Engine
  Documentation: DT: vdma: update binding doc for AXI CDMA
  dmaengine: vdma: Add Support for Xilinx AXI Direct Memory Access Engine
  Documentation: DT: vdma: update binding doc for AXI DMA
  dmaengine: vdma: Rename xilinx_vdma_ prefix to xilinx_dma
  dmaengine: slave means at least one of DMA_SLAVE, DMA_CYCLIC
  dmaengine: mv_xor: Allow selecting mv_xor for mvebu only compatible SoC
  ...

35 files changed, 4741 insertions, 1084 deletions

diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 902034991517..2cb6f7e04b5c 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -201,8 +201,8 @@ static struct sata_dwc_host_priv host_pvt;
 static struct dw_dma_slave sata_dwc_dma_dws = {
 	.src_id = 0,
 	.dst_id = 0,
-	.src_master = 0,
-	.dst_master = 1,
+	.m_master = 1,
+	.p_master = 0,
 };
 
 /*
@@ -1248,7 +1248,7 @@ static int sata_dwc_probe(struct platform_device *ofdev)
 	hsdev->dma->dev = &ofdev->dev;
 
 	/* Initialize AHB DMAC */
-	err = dw_dma_probe(hsdev->dma, NULL);
+	err = dw_dma_probe(hsdev->dma);
 	if (err)
 		goto error_dma_iomap;
 
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index d96d87c56f2e..8c98779a12b1 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -332,7 +332,7 @@ config MPC512X_DMA
 
 config MV_XOR
 	bool "Marvell XOR engine support"
-	depends on PLAT_ORION
+	depends on PLAT_ORION || ARCH_MVEBU || COMPILE_TEST
 	select DMA_ENGINE
 	select DMA_ENGINE_RAID
 	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
@@ -467,6 +467,20 @@ config TEGRA20_APB_DMA
 	  This DMA controller transfers data from memory to peripheral fifo
 	  or vice versa. It does not support memory to memory data transfer.
 
+config TEGRA210_ADMA
+	bool "NVIDIA Tegra210 ADMA support"
+	depends on ARCH_TEGRA_210_SOC
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	select PM_CLK
+	help
+	  Support for the NVIDIA Tegra210 ADMA controller driver. The
+	  DMA controller has multiple DMA channels and is used to service
+	  various audio clients in the Tegra210 audio processing engine
+	  (APE). This DMA controller transfers data from memory to
+	  peripheral and vice versa. It does not support memory to
+	  memory data transfer.
+
 config TIMB_DMA
 	tristate "Timberdale FPGA DMA support"
 	depends on MFD_TIMBERDALE
@@ -507,7 +521,7 @@ config XGENE_DMA
 
 config XILINX_VDMA
 	tristate "Xilinx AXI VDMA Engine"
-	depends on (ARCH_ZYNQ || MICROBLAZE)
+	depends on (ARCH_ZYNQ || MICROBLAZE || ARM64)
 	select DMA_ENGINE
 	help
 	  Enable support for Xilinx AXI VDMA Soft IP.
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 6084127c1486..614f28b0b739 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_STM32_DMA) += stm32-dma.o
 obj-$(CONFIG_S3C24XX_DMAC) += s3c24xx-dma.o
 obj-$(CONFIG_TXX9_DMAC) += txx9dmac.o
 obj-$(CONFIG_TEGRA20_APB_DMA) += tegra20-apb-dma.o
+obj-$(CONFIG_TEGRA210_ADMA) += tegra210-adma.o
 obj-$(CONFIG_TIMB_DMA) += timb_dma.o
 obj-$(CONFIG_TI_CPPI41) += cppi41.o
 obj-$(CONFIG_TI_DMA_CROSSBAR) += ti-dma-crossbar.o
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 9b42c0588550..81db1c4811ce 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -107,16 +107,20 @@ struct pl08x_driver_data;
 /**
  * struct vendor_data - vendor-specific config parameters for PL08x derivatives
  * @channels: the number of channels available in this variant
+ * @signals: the number of request signals available from the hardware
  * @dualmaster: whether this version supports dual AHB masters or not.
  * @nomadik: whether the channels have Nomadik security extension bits
  *	that need to be checked for permission before use and some registers are
  *	missing
  * @pl080s: whether this version is a PL080S, which has separate register and
  *	LLI word for transfer size.
+ * @max_transfer_size: the maximum single element transfer size for this
+ *	PL08x variant.
  */
 struct vendor_data {
 	u8 config_offset;
 	u8 channels;
+	u8 signals;
 	bool dualmaster;
 	bool nomadik;
 	bool pl080s;
@@ -235,7 +239,7 @@ struct pl08x_dma_chan {
 	struct virt_dma_chan vc;
 	struct pl08x_phy_chan *phychan;
 	const char *name;
-	const struct pl08x_channel_data *cd;
+	struct pl08x_channel_data *cd;
 	struct dma_slave_config cfg;
 	struct pl08x_txd *at;
 	struct pl08x_driver_data *host;
@@ -1909,6 +1913,12 @@ static int pl08x_dma_init_virtual_channels(struct pl08x_driver_data *pl08x,
 
 		if (slave) {
 			chan->cd = &pl08x->pd->slave_channels[i];
+			/*
+			 * Some implementations have muxed signals, whereas some
+			 * use a mux in front of the signals and need dynamic
+			 * assignment of signals.
+			 */
+			chan->signal = i;
 			pl08x_dma_slave_init(chan);
 		} else {
 			chan->cd = &pl08x->pd->memcpy_channel;
@@ -2050,40 +2060,33 @@ static struct dma_chan *pl08x_of_xlate(struct of_phandle_args *dma_spec,
 				       struct of_dma *ofdma)
 {
 	struct pl08x_driver_data *pl08x = ofdma->of_dma_data;
-	struct pl08x_channel_data *data;
-	struct pl08x_dma_chan *chan;
 	struct dma_chan *dma_chan;
+	struct pl08x_dma_chan *plchan;
 
 	if (!pl08x)
 		return NULL;
 
-	if (dma_spec->args_count != 2)
+	if (dma_spec->args_count != 2) {
+		dev_err(&pl08x->adev->dev,
+			"DMA channel translation requires two cells\n");
 		return NULL;
+	}
 
 	dma_chan = pl08x_find_chan_id(pl08x, dma_spec->args[0]);
-	if (dma_chan)
-		return dma_get_slave_channel(dma_chan);
-
-	chan = devm_kzalloc(pl08x->slave.dev, sizeof(*chan) + sizeof(*data),
-			    GFP_KERNEL);
-	if (!chan)
+	if (!dma_chan) {
+		dev_err(&pl08x->adev->dev,
+			"DMA slave channel not found\n");
 		return NULL;
+	}
 
-	data = (void *)&chan[1];
-	data->bus_id = "(none)";
-	data->periph_buses = dma_spec->args[1];
-
-	chan->cd = data;
-	chan->host = pl08x;
-	chan->slave = true;
-	chan->name = data->bus_id;
-	chan->state = PL08X_CHAN_IDLE;
-	chan->signal = dma_spec->args[0];
-	chan->vc.desc_free = pl08x_desc_free;
-
-	vchan_init(&chan->vc, &pl08x->slave);
+	plchan = to_pl08x_chan(dma_chan);
+	dev_dbg(&pl08x->adev->dev,
+		"translated channel for signal %d\n",
+		dma_spec->args[0]);
 
-	return dma_get_slave_channel(&chan->vc.chan);
+	/* Augment channel data for applicable AHB buses */
+	plchan->cd->periph_buses = dma_spec->args[1];
+	return dma_get_slave_channel(dma_chan);
 }
 
 static int pl08x_of_probe(struct amba_device *adev,
@@ -2091,9 +2094,11 @@ static int pl08x_of_probe(struct amba_device *adev,
 			  struct device_node *np)
 {
 	struct pl08x_platform_data *pd;
+	struct pl08x_channel_data *chanp = NULL;
 	u32 cctl_memcpy = 0;
 	u32 val;
 	int ret;
+	int i;
 
 	pd = devm_kzalloc(&adev->dev, sizeof(*pd), GFP_KERNEL);
 	if (!pd)
@@ -2195,6 +2200,27 @@ static int pl08x_of_probe(struct amba_device *adev,
 	/* Use the buses that can access memory, obviously */
 	pd->memcpy_channel.periph_buses = pd->mem_buses;
 
+	/*
+	 * Allocate channel data for all possible slave channels (one
+	 * for each possible signal), channels will then be allocated
+	 * for a device and have it's AHB interfaces set up at
+	 * translation time.
+	 */
+	chanp = devm_kcalloc(&adev->dev,
+			pl08x->vd->signals,
+			sizeof(struct pl08x_channel_data),
+			GFP_KERNEL);
+	if (!chanp)
+		return -ENOMEM;
+
+	pd->slave_channels = chanp;
+	for (i = 0; i < pl08x->vd->signals; i++) {
+		/* chanp->periph_buses will be assigned at translation */
+		chanp->bus_id = kasprintf(GFP_KERNEL, "slave%d", i);
+		chanp++;
+	}
+	pd->num_slave_channels = pl08x->vd->signals;
+
 	pl08x->pd = pd;
 
 	return of_dma_controller_register(adev->dev.of_node, pl08x_of_xlate,
@@ -2234,6 +2260,10 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		goto out_no_pl08x;
 	}
 
+	/* Assign useful pointers to the driver state */
+	pl08x->adev = adev;
+	pl08x->vd = vd;
+
 	/* Initialize memcpy engine */
 	dma_cap_set(DMA_MEMCPY, pl08x->memcpy.cap_mask);
 	pl08x->memcpy.dev = &adev->dev;
@@ -2284,10 +2314,6 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 		}
 	}
 
-	/* Assign useful pointers to the driver state */
-	pl08x->adev = adev;
-	pl08x->vd = vd;
-
 	/* By default, AHB1 only.  If dualmaster, from platform */
 	pl08x->lli_buses = PL08X_AHB1;
 	pl08x->mem_buses = PL08X_AHB1;
@@ -2438,6 +2464,7 @@ out_no_pl08x:
 static struct vendor_data vendor_pl080 = {
 	.config_offset = PL080_CH_CONFIG,
 	.channels = 8,
+	.signals = 16,
 	.dualmaster = true,
 	.max_transfer_size = PL080_CONTROL_TRANSFER_SIZE_MASK,
 };
@@ -2445,6 +2472,7 @@ static struct vendor_data vendor_pl080 = {
 static struct vendor_data vendor_nomadik = {
 	.config_offset = PL080_CH_CONFIG,
 	.channels = 8,
+	.signals = 32,
 	.dualmaster = true,
 	.nomadik = true,
 	.max_transfer_size = PL080_CONTROL_TRANSFER_SIZE_MASK,
@@ -2453,6 +2481,7 @@ static struct vendor_data vendor_nomadik = {
 static struct vendor_data vendor_pl080s = {
 	.config_offset = PL080S_CH_CONFIG,
 	.channels = 8,
+	.signals = 32,
 	.pl080s = true,
 	.max_transfer_size = PL080S_CONTROL_TRANSFER_SIZE_MASK,
 };
@@ -2460,6 +2489,7 @@ static struct vendor_data vendor_pl080s = {
 static struct vendor_data vendor_pl081 = {
 	.config_offset = PL080_CH_CONFIG,
 	.channels = 2,
+	.signals = 16,
 	.dualmaster = false,
 	.max_transfer_size = PL080_CONTROL_TRANSFER_SIZE_MASK,
 };
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index 996c4b00d323..6149b27c33ad 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -46,6 +46,9 @@
 
 #include "virt-dma.h"
 
+#define BCM2835_DMA_MAX_DMA_CHAN_SUPPORTED 14
+#define BCM2835_DMA_CHAN_NAME_SIZE 8
+
 struct bcm2835_dmadev {
 	struct dma_device ddev;
 	spinlock_t lock;
@@ -73,7 +76,6 @@ struct bcm2835_chan {
 	struct list_head node;
 
 	struct dma_slave_config	cfg;
-	bool cyclic;
 	unsigned int dreq;
 
 	int ch;
@@ -82,6 +84,9 @@ struct bcm2835_chan {
 
 	void __iomem *chan_base;
 	int irq_number;
+	unsigned int irq_flags;
+
+	bool is_lite_channel;
 };
 
 struct bcm2835_desc {
@@ -89,47 +94,104 @@ struct bcm2835_desc {
 	struct virt_dma_desc vd;
 	enum dma_transfer_direction dir;
 
-	struct bcm2835_cb_entry *cb_list;
-
 	unsigned int frames;
 	size_t size;
+
+	bool cyclic;
+
+	struct bcm2835_cb_entry cb_list[];
 };
 
 #define BCM2835_DMA_CS		0x00
 #define BCM2835_DMA_ADDR	0x04
+#define BCM2835_DMA_TI		0x08
 #define BCM2835_DMA_SOURCE_AD	0x0c
 #define BCM2835_DMA_DEST_AD	0x10
-#define BCM2835_DMA_NEXTCB	0x1C
+#define BCM2835_DMA_LEN		0x14
+#define BCM2835_DMA_STRIDE	0x18
+#define BCM2835_DMA_NEXTCB	0x1c
+#define BCM2835_DMA_DEBUG	0x20
 
 /* DMA CS Control and Status bits */
-#define BCM2835_DMA_ACTIVE	BIT(0)
-#define BCM2835_DMA_INT	BIT(2)
+#define BCM2835_DMA_ACTIVE	BIT(0)  /* activate the DMA */
+#define BCM2835_DMA_END		BIT(1)  /* current CB has ended */
+#define BCM2835_DMA_INT		BIT(2)  /* interrupt status */
+#define BCM2835_DMA_DREQ	BIT(3)  /* DREQ state */
 #define BCM2835_DMA_ISPAUSED	BIT(4)  /* Pause requested or not active */
 #define BCM2835_DMA_ISHELD	BIT(5)  /* Is held by DREQ flow control */
-#define BCM2835_DMA_ERR	BIT(8)
+#define BCM2835_DMA_WAITING_FOR_WRITES BIT(6) /* waiting for last
+					       * AXI-write to ack
+					       */
+#define BCM2835_DMA_ERR		BIT(8)
+#define BCM2835_DMA_PRIORITY(x) ((x & 15) << 16) /* AXI priority */
+#define BCM2835_DMA_PANIC_PRIORITY(x) ((x & 15) << 20) /* panic priority */
+/* current value of TI.BCM2835_DMA_WAIT_RESP */
+#define BCM2835_DMA_WAIT_FOR_WRITES BIT(28)
+#define BCM2835_DMA_DIS_DEBUG	BIT(29) /* disable debug pause signal */
 #define BCM2835_DMA_ABORT	BIT(30) /* Stop current CB, go to next, WO */
 #define BCM2835_DMA_RESET	BIT(31) /* WO, self clearing */
 
+/* Transfer information bits - also bcm2835_cb.info field */
 #define BCM2835_DMA_INT_EN	BIT(0)
+#define BCM2835_DMA_TDMODE	BIT(1) /* 2D-Mode */
+#define BCM2835_DMA_WAIT_RESP	BIT(3) /* wait for AXI-write to be acked */
 #define BCM2835_DMA_D_INC	BIT(4)
-#define BCM2835_DMA_D_DREQ	BIT(6)
+#define BCM2835_DMA_D_WIDTH	BIT(5) /* 128bit writes if set */
+#define BCM2835_DMA_D_DREQ	BIT(6) /* enable DREQ for destination */
+#define BCM2835_DMA_D_IGNORE	BIT(7) /* ignore destination writes */
 #define BCM2835_DMA_S_INC	BIT(8)
-#define BCM2835_DMA_S_DREQ	BIT(10)
-
-#define BCM2835_DMA_PER_MAP(x)	((x) << 16)
+#define BCM2835_DMA_S_WIDTH	BIT(9) /* 128bit writes if set */
+#define BCM2835_DMA_S_DREQ	BIT(10) /* enable SREQ for source */
+#define BCM2835_DMA_S_IGNORE	BIT(11) /* ignore source reads - read 0 */
+#define BCM2835_DMA_BURST_LENGTH(x) ((x & 15) << 12)
+#define BCM2835_DMA_PER_MAP(x)	((x & 31) << 16) /* REQ source */
+#define BCM2835_DMA_WAIT(x)	((x & 31) << 21) /* add DMA-wait cycles */
+#define BCM2835_DMA_NO_WIDE_BURSTS BIT(26) /* no 2 beat write bursts */
+
+/* debug register bits */
+#define BCM2835_DMA_DEBUG_LAST_NOT_SET_ERR	BIT(0)
+#define BCM2835_DMA_DEBUG_FIFO_ERR		BIT(1)
+#define BCM2835_DMA_DEBUG_READ_ERR		BIT(2)
+#define BCM2835_DMA_DEBUG_OUTSTANDING_WRITES_SHIFT 4
+#define BCM2835_DMA_DEBUG_OUTSTANDING_WRITES_BITS 4
+#define BCM2835_DMA_DEBUG_ID_SHIFT		16
+#define BCM2835_DMA_DEBUG_ID_BITS		9
+#define BCM2835_DMA_DEBUG_STATE_SHIFT		16
+#define BCM2835_DMA_DEBUG_STATE_BITS		9
+#define BCM2835_DMA_DEBUG_VERSION_SHIFT		25
+#define BCM2835_DMA_DEBUG_VERSION_BITS		3
+#define BCM2835_DMA_DEBUG_LITE			BIT(28)
+
+/* shared registers for all dma channels */
+#define BCM2835_DMA_INT_STATUS         0xfe0
+#define BCM2835_DMA_ENABLE             0xff0
 
 #define BCM2835_DMA_DATA_TYPE_S8	1
 #define BCM2835_DMA_DATA_TYPE_S16	2
 #define BCM2835_DMA_DATA_TYPE_S32	4
 #define BCM2835_DMA_DATA_TYPE_S128	16
 
-#define BCM2835_DMA_BULK_MASK	BIT(0)
-#define BCM2835_DMA_FIQ_MASK	(BIT(2) | BIT(3))
-
 /* Valid only for channels 0 - 14, 15 has its own base address */
 #define BCM2835_DMA_CHAN(n)	((n) << 8) /* Base address */
 #define BCM2835_DMA_CHANIO(base, n) ((base) + BCM2835_DMA_CHAN(n))
 
+/* the max dma length for different channels */
+#define MAX_DMA_LEN SZ_1G
+#define MAX_LITE_DMA_LEN (SZ_64K - 4)
+
+static inline size_t bcm2835_dma_max_frame_length(struct bcm2835_chan *c)
+{
+	/* lite and normal channels have different max frame length */
+	return c->is_lite_channel ? MAX_LITE_DMA_LEN : MAX_DMA_LEN;
+}
+
+/* how many frames of max_len size do we need to transfer len bytes */
+static inline size_t bcm2835_dma_frames_for_length(size_t len,
+						   size_t max_len)
+{
+	return DIV_ROUND_UP(len, max_len);
+}
+
 static inline struct bcm2835_dmadev *to_bcm2835_dma_dev(struct dma_device *d)
 {
 	return container_of(d, struct bcm2835_dmadev, ddev);
@@ -146,19 +208,209 @@ static inline struct bcm2835_desc *to_bcm2835_dma_desc(
 	return container_of(t, struct bcm2835_desc, vd.tx);
 }
 
-static void bcm2835_dma_desc_free(struct virt_dma_desc *vd)
+static void bcm2835_dma_free_cb_chain(struct bcm2835_desc *desc)
 {
-	struct bcm2835_desc *desc = container_of(vd, struct bcm2835_desc, vd);
-	int i;
+	size_t i;
 
 	for (i = 0; i < desc->frames; i++)
 		dma_pool_free(desc->c->cb_pool, desc->cb_list[i].cb,
 			      desc->cb_list[i].paddr);
 
-	kfree(desc->cb_list);
 	kfree(desc);
 }
 
+static void bcm2835_dma_desc_free(struct virt_dma_desc *vd)
+{
+	bcm2835_dma_free_cb_chain(
+		container_of(vd, struct bcm2835_desc, vd));
+}
+
+static void bcm2835_dma_create_cb_set_length(
+	struct bcm2835_chan *chan,
+	struct bcm2835_dma_cb *control_block,
+	size_t len,
+	size_t period_len,
+	size_t *total_len,
+	u32 finalextrainfo)
+{
+	size_t max_len = bcm2835_dma_max_frame_length(chan);
+
+	/* set the length taking lite-channel limitations into account */
+	control_block->length = min_t(u32, len, max_len);
+
+	/* finished if we have no period_length */
+	if (!period_len)
+		return;
+
+	/*
+	 * period_len means: that we need to generate
+	 * transfers that are terminating at every
+	 * multiple of period_len - this is typically
+	 * used to set the interrupt flag in info
+	 * which is required during cyclic transfers
+	 */
+
+	/* have we filled in period_length yet? */
+	if (*total_len + control_block->length < period_len)
+		return;
+
+	/* calculate the length that remains to reach period_length */
+	control_block->length = period_len - *total_len;
+
+	/* reset total_length for next period */
+	*total_len = 0;
+
+	/* add extrainfo bits in info */
+	control_block->info |= finalextrainfo;
+}
+
+static inline size_t bcm2835_dma_count_frames_for_sg(
+	struct bcm2835_chan *c,
+	struct scatterlist *sgl,
+	unsigned int sg_len)
+{
+	size_t frames = 0;
+	struct scatterlist *sgent;
+	unsigned int i;
+	size_t plength = bcm2835_dma_max_frame_length(c);
+
+	for_each_sg(sgl, sgent, sg_len, i)
+		frames += bcm2835_dma_frames_for_length(
+			sg_dma_len(sgent), plength);
+
+	return frames;
+}
+
+/**
+ * bcm2835_dma_create_cb_chain - create a control block and fills data in
+ *
+ * @chan:           the @dma_chan for which we run this
+ * @direction:      the direction in which we transfer
+ * @cyclic:         it is a cyclic transfer
+ * @info:           the default info bits to apply per controlblock
+ * @frames:         number of controlblocks to allocate
+ * @src:            the src address to assign (if the S_INC bit is set
+ *                  in @info, then it gets incremented)
+ * @dst:            the dst address to assign (if the D_INC bit is set
+ *                  in @info, then it gets incremented)
+ * @buf_len:        the full buffer length (may also be 0)
+ * @period_len:     the period length when to apply @finalextrainfo
+ *                  in addition to the last transfer
+ *                  this will also break some control-blocks early
+ * @finalextrainfo: additional bits in last controlblock
+ *                  (or when period_len is reached in case of cyclic)
+ * @gfp:            the GFP flag to use for allocation
+ */
+static struct bcm2835_desc *bcm2835_dma_create_cb_chain(
+	struct dma_chan *chan, enum dma_transfer_direction direction,
+	bool cyclic, u32 info, u32 finalextrainfo, size_t frames,
+	dma_addr_t src, dma_addr_t dst, size_t buf_len,
+	size_t period_len, gfp_t gfp)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+	size_t len = buf_len, total_len;
+	size_t frame;
+	struct bcm2835_desc *d;
+	struct bcm2835_cb_entry *cb_entry;
+	struct bcm2835_dma_cb *control_block;
+
+	if (!frames)
+		return NULL;
+
+	/* allocate and setup the descriptor. */
+	d = kzalloc(sizeof(*d) + frames * sizeof(struct bcm2835_cb_entry),
+		    gfp);
+	if (!d)
+		return NULL;
+
+	d->c = c;
+	d->dir = direction;
+	d->cyclic = cyclic;
+
+	/*
+	 * Iterate over all frames, create a control block
+	 * for each frame and link them together.
+	 */
+	for (frame = 0, total_len = 0; frame < frames; d->frames++, frame++) {
+		cb_entry = &d->cb_list[frame];
+		cb_entry->cb = dma_pool_alloc(c->cb_pool, gfp,
+					      &cb_entry->paddr);
+		if (!cb_entry->cb)
+			goto error_cb;
+
+		/* fill in the control block */
+		control_block = cb_entry->cb;
+		control_block->info = info;
+		control_block->src = src;
+		control_block->dst = dst;
+		control_block->stride = 0;
+		control_block->next = 0;
+		/* set up length in control_block if requested */
+		if (buf_len) {
+			/* calculate length honoring period_length */
+			bcm2835_dma_create_cb_set_length(
+				c, control_block,
+				len, period_len, &total_len,
+				cyclic ? finalextrainfo : 0);
+
+			/* calculate new remaining length */
+			len -= control_block->length;
+		}
+
+		/* link this the last controlblock */
+		if (frame)
+			d->cb_list[frame - 1].cb->next = cb_entry->paddr;
+
+		/* update src and dst and length */
+		if (src && (info & BCM2835_DMA_S_INC))
+			src += control_block->length;
+		if (dst && (info & BCM2835_DMA_D_INC))
+			dst += control_block->length;
+
+		/* Length of total transfer */
+		d->size += control_block->length;
+	}
+
+	/* the last frame requires extra flags */
+	d->cb_list[d->frames - 1].cb->info |= finalextrainfo;
+
+	/* detect a size missmatch */
+	if (buf_len && (d->size != buf_len))
+		goto error_cb;
+
+	return d;
+error_cb:
+	bcm2835_dma_free_cb_chain(d);
+
+	return NULL;
+}
+
+static void bcm2835_dma_fill_cb_chain_with_sg(
+	struct dma_chan *chan,
+	enum dma_transfer_direction direction,
+	struct bcm2835_cb_entry *cb,
+	struct scatterlist *sgl,
+	unsigned int sg_len)
+{
+	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
+	size_t max_len = bcm2835_dma_max_frame_length(c);
+	unsigned int i, len;
+	dma_addr_t addr;
+	struct scatterlist *sgent;
+
+	for_each_sg(sgl, sgent, sg_len, i) {
+		for (addr = sg_dma_address(sgent), len = sg_dma_len(sgent);
+		     len > 0;
+		     addr += cb->cb->length, len -= cb->cb->length, cb++) {
+			if (direction == DMA_DEV_TO_MEM)
+				cb->cb->dst = addr;
+			else
+				cb->cb->src = addr;
+			cb->cb->length = min(len, max_len);
+		}
+	}
+}
+
 static int bcm2835_dma_abort(void __iomem *chan_base)
 {
 	unsigned long cs;
@@ -218,6 +470,15 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data)
 	struct bcm2835_desc *d;
 	unsigned long flags;
 
+	/* check the shared interrupt */
+	if (c->irq_flags & IRQF_SHARED) {
+		/* check if the interrupt is enabled */
+		flags = readl(c->chan_base + BCM2835_DMA_CS);
+		/* if not set then we are not the reason for the irq */
+		if (!(flags & BCM2835_DMA_INT))
+			return IRQ_NONE;
+	}
+
 	spin_lock_irqsave(&c->vc.lock, flags);
 
 	/* Acknowledge interrupt */
@@ -226,12 +487,18 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data)
 	d = c->desc;
 
 	if (d) {
-		/* TODO Only works for cyclic DMA */
-		vchan_cyclic_callback(&d->vd);
-	}
+		if (d->cyclic) {
+			/* call the cyclic callback */
+			vchan_cyclic_callback(&d->vd);
 
-	/* Keep the DMA engine running */
-	writel(BCM2835_DMA_ACTIVE, c->chan_base + BCM2835_DMA_CS);
+			/* Keep the DMA engine running */
+			writel(BCM2835_DMA_ACTIVE,
+			       c->chan_base + BCM2835_DMA_CS);
+		} else {
+			vchan_cookie_complete(&c->desc->vd);
+			bcm2835_dma_start_desc(c);
+		}
+	}
 
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 
@@ -252,8 +519,8 @@ static int bcm2835_dma_alloc_chan_resources(struct dma_chan *chan)
 		return -ENOMEM;
 	}
 
-	return request_irq(c->irq_number,
-			bcm2835_dma_callback, 0, "DMA IRQ", c);
+	return request_irq(c->irq_number, bcm2835_dma_callback,
+			   c->irq_flags, "DMA IRQ", c);
 }
 
 static void bcm2835_dma_free_chan_resources(struct dma_chan *chan)
@@ -339,8 +606,6 @@ static void bcm2835_dma_issue_pending(struct dma_chan *chan)
 	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
 	unsigned long flags;
 
-	c->cyclic = true; /* Nothing else is implemented */
-
 	spin_lock_irqsave(&c->vc.lock, flags);
 	if (vchan_issue_pending(&c->vc) && !c->desc)
 		bcm2835_dma_start_desc(c);
@@ -348,122 +613,160 @@ static void bcm2835_dma_issue_pending(struct dma_chan *chan)
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 }
 
-static struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_cyclic(
-	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
-	size_t period_len, enum dma_transfer_direction direction,
-	unsigned long flags)
+struct dma_async_tx_descriptor *bcm2835_dma_prep_dma_memcpy(
+	struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
+	size_t len, unsigned long flags)
 {
 	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
-	enum dma_slave_buswidth dev_width;
 	struct bcm2835_desc *d;
-	dma_addr_t dev_addr;
-	unsigned int es, sync_type;
-	unsigned int frame;
-	int i;
+	u32 info = BCM2835_DMA_D_INC | BCM2835_DMA_S_INC;
+	u32 extra = BCM2835_DMA_INT_EN | BCM2835_DMA_WAIT_RESP;
+	size_t max_len = bcm2835_dma_max_frame_length(c);
+	size_t frames;
+
+	/* if src, dst or len is not given return with an error */
+	if (!src || !dst || !len)
+		return NULL;
+
+	/* calculate number of frames */
+	frames = bcm2835_dma_frames_for_length(len, max_len);
+
+	/* allocate the CB chain - this also fills in the pointers */
+	d = bcm2835_dma_create_cb_chain(chan, DMA_MEM_TO_MEM, false,
+					info, extra, frames,
+					src, dst, len, 0, GFP_KERNEL);
+	if (!d)
+		retu