Merge tag 'dmaengine-4.2-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:
 "This time we have support for few new devices, few new features and
  odd fixes spread thru the subsystem.

  New devices added:
   - support for CSRatlas7 dma controller
   - Allwinner H3(sun8i) controller
   - TI DMA crossbar driver on DRA7x
   - new pxa driver

  New features added:
   - memset support is bought back now that we have a user in xdmac controller
   - interleaved transfers support different source and destination strides
   - supporting DMA routers and configuration thru DT
   - support for reusing descriptors
   - xdmac memset and interleaved transfer support
   - hdmac support for interleaved transfers
   - omap-dma support for memcpy

  Others:
   - Constify platform_device_id
   - mv_xor fixes and improvements"

* tag 'dmaengine-4.2-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (46 commits)
  dmaengine: xgene: fix file permission
  dmaengine: fsl-edma: clear pending interrupts on initialization
  dmaengine: xdmac: Add memset support
  Documentation: dmaengine: document DMA_CTRL_ACK
  dmaengine: virt-dma: don't always free descriptor upon completion
  dmaengine: Revert "drivers/dma: remove unused support for MEMSET operations"
  dmaengine: hdmac: Implement interleaved transfers
  dmaengine: Move icg helpers to global header
  dmaengine: mv_xor: improve descriptors list handling and reduce locking
  dmaengine: mv_xor: Enlarge descriptor pool size
  dmaengine: mv_xor: add support for a38x command in descriptor mode
  dmaengine: mv_xor: Rename function for consistent naming
  dmaengine: mv_xor: bug fix for racing condition in descriptors cleanup
  dmaengine: pl330: fix wording in mcbufsz message
  dmaengine: sirf: add CSRatlas7 SoC support
  dmaengine: xgene-dma: Fix "incorrect type in assignement" warnings
  dmaengine: fix kernel-doc documentation
  dmaengine: pxa_dma: add support for legacy transition
  dmaengine: pxa_dma: add debug information
  dmaengine: pxa: add pxa dmaengine driver
  ...

40 files changed, 3329 insertions, 497 deletions

diff --git a/Documentation/devicetree/bindings/dma/dma.txt b/Documentation/devicetree/bindings/dma/dma.txt
index 82104271e754..6312fb00ce8d 100644
--- a/Documentation/devicetree/bindings/dma/dma.txt
+++ b/Documentation/devicetree/bindings/dma/dma.txt
@@ -31,6 +31,34 @@ Example:
 		dma-requests = <127>;
 	};
 
+* DMA router
+
+DMA routers are transparent IP blocks used to route DMA request lines from
+devices to the DMA controller. Some SoCs (like TI DRA7x) have more peripherals
+integrated with DMA requests than what the DMA controller can handle directly.
+
+Required property:
+- dma-masters:		phandle of the DMA controller or list of phandles for
+			the DMA controllers the router can direct the signal to.
+- #dma-cells: 		Must be at least 1. Used to provide DMA router specific
+			information. See DMA client binding below for more
+			details.
+
+Optional properties:
+- dma-requests: 	Number of incoming request lines the router can handle.
+- In the node pointed by the dma-masters:
+	- dma-requests:	The router driver might need to look for this in order
+			to configure the routing.
+
+Example:
+	sdma_xbar: dma-router@4a002b78 {
+		compatible = "ti,dra7-dma-crossbar";
+		reg = <0x4a002b78 0xfc>;
+		#dma-cells = <1>;
+		dma-requests = <205>;
+		ti,dma-safe-map = <0>;
+		dma-masters = <&sdma>;
+	};
 
 * DMA client
 
diff --git a/Documentation/devicetree/bindings/dma/mv-xor.txt b/Documentation/devicetree/bindings/dma/mv-xor.txt
index 7c6cb7fcecd2..cc29c35266e2 100644
--- a/Documentation/devicetree/bindings/dma/mv-xor.txt
+++ b/Documentation/devicetree/bindings/dma/mv-xor.txt
@@ -1,7 +1,7 @@
 * Marvell XOR engines
 
 Required properties:
-- compatible: Should be "marvell,orion-xor"
+- compatible: Should be "marvell,orion-xor" or "marvell,armada-380-xor"
 - reg: Should contain registers location and length (two sets)
     the first set is the low registers, the second set the high
     registers for the XOR engine.
diff --git a/Documentation/devicetree/bindings/dma/sirfsoc-dma.txt b/Documentation/devicetree/bindings/dma/sirfsoc-dma.txt
index ecbc96ad36f8..ccd52d6a231a 100644
--- a/Documentation/devicetree/bindings/dma/sirfsoc-dma.txt
+++ b/Documentation/devicetree/bindings/dma/sirfsoc-dma.txt
@@ -3,7 +3,8 @@
 See dma.txt first
 
 Required properties:
-- compatible: Should be "sirf,prima2-dmac" or "sirf,marco-dmac"
+- compatible: Should be "sirf,prima2-dmac", "sirf,atlas7-dmac" or
+  "sirf,atlas7-dmac-v2"
 - reg: Should contain DMA registers location and length.
 - interrupts: Should contain one interrupt shared by all channel
 - #dma-cells: must be <1>. used to represent the number of integer
diff --git a/Documentation/devicetree/bindings/dma/sun6i-dma.txt b/Documentation/devicetree/bindings/dma/sun6i-dma.txt
index 9cdcba24d7c3..d13c136cef8c 100644
--- a/Documentation/devicetree/bindings/dma/sun6i-dma.txt
+++ b/Documentation/devicetree/bindings/dma/sun6i-dma.txt
@@ -4,7 +4,10 @@ This driver follows the generic DMA bindings defined in dma.txt.
 
 Required properties:
 
-- compatible:	Must be "allwinner,sun6i-a31-dma" or "allwinner,sun8i-a23-dma"
+- compatible:	Must be one of
+		  "allwinner,sun6i-a31-dma"
+		  "allwinner,sun8i-a23-dma"
+		  "allwinner,sun8i-h3-dma"
 - reg:		Should contain the registers base address and length
 - interrupts:	Should contain a reference to the interrupt used by this device
 - clocks:	Should contain a reference to the parent AHB clock
diff --git a/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt b/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
new file mode 100644
index 000000000000..63a48928f3a8
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/ti-dma-crossbar.txt
@@ -0,0 +1,52 @@
+Texas Instruments DMA Crossbar (DMA request router)
+
+Required properties:
+- compatible:	"ti,dra7-dma-crossbar" for DRA7xx DMA crossbar
+- reg:		Memory map for accessing module
+- #dma-cells:	Should be set to <1>.
+		Clients should use the crossbar request number (input)
+- dma-requests:	Number of DMA requests the crossbar can receive
+- dma-masters:	phandle pointing to the DMA controller
+
+The DMA controller node need to have the following poroperties:
+- dma-requests:	Number of DMA requests the controller can handle
+
+Optional properties:
+- ti,dma-safe-map: Safe routing value for unused request lines
+
+Example:
+
+/* DMA controller */
+sdma: dma-controller@4a056000 {
+	compatible = "ti,omap4430-sdma";
+	reg = <0x4a056000 0x1000>;
+	interrupts =	<GIC_SPI 7 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 9 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>;
+	#dma-cells = <1>;
+	dma-channels = <32>;
+	dma-requests = <127>;
+};
+
+/* DMA crossbar */
+sdma_xbar: dma-router@4a002b78 {
+	compatible = "ti,dra7-dma-crossbar";
+	reg = <0x4a002b78 0xfc>;
+	#dma-cells = <1>;
+	dma-requests = <205>;
+	ti,dma-safe-map = <0>;
+	dma-masters = <&sdma>;
+};
+
+/* DMA client */
+uart1: serial@4806a000 {
+	compatible = "ti,omap4-uart";
+	reg = <0x4806a000 0x100>;
+	interrupts-extended = <&gic GIC_SPI 67 IRQ_TYPE_LEVEL_HIGH>;
+	ti,hwmods = "uart1";
+	clock-frequency = <48000000>;
+	status = "disabled";
+	dmas = <&sdma_xbar 49>, <&sdma_xbar 50>;
+	dma-names = "tx", "rx";
+};
diff --git a/Documentation/dmaengine/provider.txt b/Documentation/dmaengine/provider.txt
index 05d2280190f1..ca67b0f04c6e 100644
--- a/Documentation/dmaengine/provider.txt
+++ b/Documentation/dmaengine/provider.txt
@@ -345,11 +345,12 @@ where to put them)
       that abstracts it away.
 
   * DMA_CTRL_ACK
-    - Undocumented feature
-    - No one really has an idea of what it's about, besides being
-      related to reusing the DMA transaction descriptors or having
-      additional transactions added to it in the async-tx API
-    - Useless in the case of the slave API
+    - If set, the transfer can be reused after being completed.
+    - There is a guarantee the transfer won't be freed until it is acked
+      by async_tx_ack().
+    - As a consequence, if a device driver wants to skip the dma_map_sg() and
+      dma_unmap_sg() in between 2 transfers, because the DMA'd data wasn't used,
+      it can resubmit the transfer right after its completion.
 
 General Design Notes
 --------------------
diff --git a/Documentation/dmaengine/pxa_dma.txt b/Documentation/dmaengine/pxa_dma.txt
new file mode 100644
index 000000000000..413ef9cfaa4d
--- /dev/null
+++ b/Documentation/dmaengine/pxa_dma.txt
@@ -0,0 +1,153 @@
+PXA/MMP - DMA Slave controller
+==============================
+
+Constraints
+-----------
+  a) Transfers hot queuing
+     A driver submitting a transfer and issuing it should be granted the transfer
+     is queued even on a running DMA channel.
+     This implies that the queuing doesn't wait for the previous transfer end,
+     and that the descriptor chaining is not only done in the irq/tasklet code
+     triggered by the end of the transfer.
+     A transfer which is submitted and issued on a phy doesn't wait for a phy to
+     stop and restart, but is submitted on a "running channel". The other
+     drivers, especially mmp_pdma waited for the phy to stop before relaunching
+     a new transfer.
+
+  b) All transfers having asked for confirmation should be signaled
+     Any issued transfer with DMA_PREP_INTERRUPT should trigger a callback call.
+     This implies that even if an irq/tasklet is triggered by end of tx1, but
+     at the time of irq/dma tx2 is already finished, tx1->complete() and
+     tx2->complete() should be called.
+
+  c) Channel running state
+     A driver should be able to query if a channel is running or not. For the
+     multimedia case, such as video capture, if a transfer is submitted and then
+     a check of the DMA channel reports a "stopped channel", the transfer should
+     not be issued until the next "start of frame interrupt", hence the need to
+     know if a channel is in running or stopped state.
+
+  d) Bandwidth guarantee
+     The PXA architecture has 4 levels of DMAs priorities : high, normal, low.
+     The high prorities get twice as much bandwidth as the normal, which get twice
+     as much as the low priorities.
+     A driver should be able to request a priority, especially the real-time
+     ones such as pxa_camera with (big) throughputs.
+
+Design
+------
+  a) Virtual channels
+     Same concept as in sa11x0 driver, ie. a driver was assigned a "virtual
+     channel" linked to the requestor line, and the physical DMA channel is
+     assigned on the fly when the transfer is issued.
+
+  b) Transfer anatomy for a scatter-gather transfer
+     +------------+-----+---------------+----------------+-----------------+
+     | desc-sg[0] | ... | desc-sg[last] | status updater | finisher/linker |
+     +------------+-----+---------------+----------------+-----------------+
+
+     This structure is pointed by dma->sg_cpu.
+     The descriptors are used as follows :
+      - desc-sg[i]: i-th descriptor, transferring the i-th sg
+        element to the video buffer scatter gather
+      - status updater
+        Transfers a single u32 to a well known dma coherent memory to leave
+        a trace that this transfer is done. The "well known" is unique per
+        physical channel, meaning that a read of this value will tell which
+        is the last finished transfer at that point in time.
+      - finisher: has ddadr=DADDR_STOP, dcmd=ENDIRQEN
+      - linker: has ddadr= desc-sg[0] of next transfer, dcmd=0
+
+  c) Transfers hot-chaining
+     Suppose the running chain is :
+         Buffer 1         Buffer 2
+     +---------+----+---+  +----+----+----+---+
+     | d0 | .. | dN | l |  | d0 | .. | dN | f |
+     +---------+----+-|-+  ^----+----+----+---+
+                      |    |
+                      +----+
+
+     After a call to dmaengine_submit(b3), the chain will look like :
+          Buffer 1              Buffer 2             Buffer 3
+     +---------+----+---+  +----+----+----+---+  +----+----+----+---+
+     | d0 | .. | dN | l |  | d0 | .. | dN | l |  | d0 | .. | dN | f |
+     +---------+----+-|-+  ^----+----+----+-|-+  ^----+----+----+---+
+                      |    |                |    |
+                      +----+                +----+
+                                           new_link
+
+     If while new_link was created the DMA channel stopped, it is _not_
+     restarted. Hot-chaining doesn't break the assumption that
+     dma_async_issue_pending() is to be used to ensure the transfer is actually started.
+
+     One exception to this rule :
+       - if Buffer1 and Buffer2 had all their addresses 8 bytes aligned
+       - and if Buffer3 has at least one address not 4 bytes aligned
+       - then hot-chaining cannot happen, as the channel must be stopped, the
+         "align bit" must be set, and the channel restarted As a consequence,
+         such a transfer tx_submit() will be queued on the submitted queue, and
+         this specific case if the DMA is already running in aligned mode.
+
+  d) Transfers completion updater
+     Each time a transfer is completed on a channel, an interrupt might be
+     generated or not, up to the client's request. But in each case, the last
+     descriptor of a transfer, the "status updater", will write the latest
+     transfer being completed into the physical channel's completion mark.
+
+     This will speed up residue calculation, for large transfers such as video
+     buffers which hold around 6k descriptors or more. This also allows without
+     any lock to find out what is the latest completed transfer in a running
+     DMA chain.
+
+  e) Transfers completion, irq and tasklet
+     When a transfer flagged as "DMA_PREP_INTERRUPT" is finished, the dma irq
+     is raised. Upon this interrupt, a tasklet is scheduled for the physical
+     channel.
+     The tasklet is responsible for :
+      - reading the physical channel last updater mark
+      - calling all the transfer callbacks of finished transfers, based on
+        that mark, and each transfer flags.
+     If a transfer is completed while this handling is done, a dma irq will
+     be raised, and the tasklet will be scheduled once again, having a new
+     updater mark.
+
+  f) Residue
+     Residue granularity will be descriptor based. The issued but not completed
+     transfers will be scanned for all of their descriptors against the
+     currently running descriptor.
+
+  g) Most complicated case of driver's tx queues
+     The most tricky situation is when :
+       - there are not "acked" transfers (tx0)
+       - a driver submitted an aligned tx1, not chained
+       - a driver submitted an aligned tx2 => tx2 is cold chained to tx1
+       - a driver issued tx1+tx2 => channel is running in aligned mode
+       - a driver submitted an aligned tx3 => tx3 is hot-chained
+       - a driver submitted an unaligned tx4 => tx4 is put in submitted queue,
+         not chained
+       - a driver issued tx4 => tx4 is put in issued queue, not chained
+       - a driver submitted an aligned tx5 => tx5 is put in submitted queue, not
+         chained
+       - a driver submitted an aligned tx6 => tx6 is put in submitted queue,
+         cold chained to tx5
+
+     This translates into (after tx4 is issued) :
+       - issued queue
+     +-----+ +-----+ +-----+ +-----+
+     | tx1 | | tx2 | | tx3 | | tx4 |
+     +---|-+ ^---|-+ ^-----+ +-----+
+         |   |   |   |
+         +---+   +---+
+       - submitted queue
+     +-----+ +-----+
+     | tx5 | | tx6 |
+     +---|-+ ^-----+
+         |   |
+         +---+
+       - completed queue : empty
+       - allocated queue : tx0
+
+     It should be noted that after tx3 is completed, the channel is stopped, and
+     restarted in "unaligned mode" to handle tx4.
+
+Author: Robert Jarzmik <robert.jarzmik@free.fr>
diff --git a/MAINTAINERS b/MAINTAINERS
index abd7a4949319..67e0b863d2af 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8174,6 +8174,7 @@ T:	git git://github.com/hzhuang1/linux.git
 T:	git git://github.com/rjarzmik/linux.git
 S:	Maintained
 F:	arch/arm/mach-pxa/
+F:	drivers/dma/pxa*
 F:	drivers/pcmcia/pxa2xx*
 F:	drivers/spi/spi-pxa2xx*
 F:	drivers/usb/gadget/udc/pxa2*
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index bda2cb06dc7a..88d474b78076 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -162,6 +162,17 @@ config MX3_IPU_IRQS
 	  To avoid bloating the irq_desc[] array we allocate a sufficient
 	  number of IRQ slots and map them dynamically to specific sources.
 
+config PXA_DMA
+	bool "PXA DMA support"
+	depends on (ARCH_MMP || ARCH_PXA)
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support the DMA engine for PXA. It is also compatible with MMP PDMA
+	  platform. The internal DMA IP of all PXA variants is supported, with
+	  16 to 32 channels for peripheral to memory or memory to memory
+	  transfers.
+
 config TXX9_DMAC
 	tristate "Toshiba TXx9 SoC DMA support"
 	depends on MACH_TX49XX || MACH_TX39XX
@@ -245,6 +256,9 @@ config TI_EDMA
 	  Enable support for the TI EDMA controller. This DMA
 	  engine is found on TI DaVinci and AM33xx parts.
 
+config TI_DMA_CROSSBAR
+	bool
+
 config ARCH_HAS_ASYNC_TX_FIND_CHANNEL
 	bool
 
@@ -330,6 +344,7 @@ config DMA_OMAP
 	depends on ARCH_OMAP
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
+	select TI_DMA_CROSSBAR if SOC_DRA7XX
 
 config DMA_BCM2835
 	tristate "BCM2835 DMA engine support"
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 69f77d5ba53b..6a4d6f2827da 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_AMCC_PPC440SPE_ADMA) += ppc4xx/
 obj-$(CONFIG_IMX_SDMA) += imx-sdma.o
 obj-$(CONFIG_IMX_DMA) += imx-dma.o
 obj-$(CONFIG_MXS_DMA) += mxs-dma.o
+obj-$(CONFIG_PXA_DMA) += pxa_dma.o
 obj-$(CONFIG_TIMB_DMA) += timb_dma.o
 obj-$(CONFIG_SIRF_DMA) += sirf-dma.o
 obj-$(CONFIG_TI_EDMA) += edma.o
@@ -38,6 +39,7 @@ obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_DMA_SA11X0) += sa11x0-dma.o
 obj-$(CONFIG_MMP_TDMA) += mmp_tdma.o
 obj-$(CONFIG_DMA_OMAP) += omap-dma.o
+obj-$(CONFIG_TI_DMA_CROSSBAR) += ti-dma-crossbar.o
 obj-$(CONFIG_DMA_BCM2835) += bcm2835-dma.o
 obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o
 obj-$(CONFIG_DMA_JZ4740) += dma-jz4740.o
diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index 49d396ec06e5..5de3cf453f35 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -474,7 +474,7 @@ static void pl08x_terminate_phy_chan(struct pl08x_driver_data *pl08x,
 	u32 val = readl(ch->reg_config);
 
 	val &= ~(PL080_CONFIG_ENABLE | PL080_CONFIG_ERR_IRQ_MASK |
-	         PL080_CONFIG_TC_IRQ_MASK);
+		 PL080_CONFIG_TC_IRQ_MASK);
 
 	writel(val, ch->reg_config);
 
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 57b2141ddddc..59892126d175 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -247,6 +247,10 @@ static void atc_dostart(struct at_dma_chan *atchan, struct at_desc *first)
 	channel_writel(atchan, CTRLA, 0);
 	channel_writel(atchan, CTRLB, 0);
 	channel_writel(atchan, DSCR, first->txd.phys);
+	channel_writel(atchan, SPIP, ATC_SPIP_HOLE(first->src_hole) |
+		       ATC_SPIP_BOUNDARY(first->boundary));
+	channel_writel(atchan, DPIP, ATC_DPIP_HOLE(first->dst_hole) |
+		       ATC_DPIP_BOUNDARY(first->boundary));
 	dma_writel(atdma, CHER, atchan->mask);
 
 	vdbg_dump_regs(atchan);
@@ -635,6 +639,104 @@ static dma_cookie_t atc_tx_submit(struct dma_async_tx_descriptor *tx)
 }
 
 /**
+ * atc_prep_dma_interleaved - prepare memory to memory interleaved operation
+ * @chan: the channel to prepare operation on
+ * @xt: Interleaved transfer template
+ * @flags: tx descriptor status flags
+ */
+static struct dma_async_tx_descriptor *
+atc_prep_dma_interleaved(struct dma_chan *chan,
+			 struct dma_interleaved_template *xt,
+			 unsigned long flags)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct data_chunk	*first = xt->sgl;
+	struct at_desc		*desc = NULL;
+	size_t			xfer_count;
+	unsigned int		dwidth;
+	u32			ctrla;
+	u32			ctrlb;
+	size_t			len = 0;
+	int			i;
+
+	dev_info(chan2dev(chan),
+		 "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
+		__func__, xt->src_start, xt->dst_start, xt->numf,
+		xt->frame_size, flags);
+
+	if (unlikely(!xt || xt->numf != 1 || !xt->frame_size))
+		return NULL;
+
+	/*
+	 * The controller can only "skip" X bytes every Y bytes, so we
+	 * need to make sure we are given a template that fit that
+	 * description, ie a template with chunks that always have the
+	 * same size, with the same ICGs.
+	 */
+	for (i = 0; i < xt->frame_size; i++) {
+		struct data_chunk *chunk = xt->sgl + i;
+
+		if ((chunk->size != xt->sgl->size) ||
+		    (dmaengine_get_dst_icg(xt, chunk) != dmaengine_get_dst_icg(xt, first)) ||
+		    (dmaengine_get_src_icg(xt, chunk) != dmaengine_get_src_icg(xt, first))) {
+			dev_err(chan2dev(chan),
+				"%s: the controller can transfer only identical chunks\n",
+				__func__);
+			return NULL;
+		}
+
+		len += chunk->size;
+	}
+
+	dwidth = atc_get_xfer_width(xt->src_start,
+				    xt->dst_start, len);
+
+	xfer_count = len >> dwidth;
+	if (xfer_count > ATC_BTSIZE_MAX) {
+		dev_err(chan2dev(chan), "%s: buffer is too big\n", __func__);
+		return NULL;
+	}
+
+	ctrla = ATC_SRC_WIDTH(dwidth) |
+		ATC_DST_WIDTH(dwidth);
+
+	ctrlb =   ATC_DEFAULT_CTRLB | ATC_IEN
+		| ATC_SRC_ADDR_MODE_INCR
+		| ATC_DST_ADDR_MODE_INCR
+		| ATC_SRC_PIP
+		| ATC_DST_PIP
+		| ATC_FC_MEM2MEM;
+
+	/* create the transfer */
+	desc = atc_desc_get(atchan);
+	if (!desc) {
+		dev_err(chan2dev(chan),
+			"%s: couldn't allocate our descriptor\n", __func__);
+		return NULL;
+	}
+
+	desc->lli.saddr = xt->src_start;
+	desc->lli.daddr = xt->dst_start;
+	desc->lli.ctrla = ctrla | xfer_count;
+	desc->lli.ctrlb = ctrlb;
+
+	desc->boundary = first->size >> dwidth;
+	desc->dst_hole = (dmaengine_get_dst_icg(xt, first) >> dwidth) + 1;
+	desc->src_hole = (dmaengine_get_src_icg(xt, first) >> dwidth) + 1;
+
+	desc->txd.cookie = -EBUSY;
+	desc->total_len = desc->len = len;
+	desc->tx_width = dwidth;
+
+	/* set end-of-link to the last link descriptor of list*/
+	set_desc_eol(desc);
+
+	desc->txd.flags = flags; /* client is in control of this ack */
+
+	return &desc->txd;
+}
+
+/**
  * atc_prep_dma_memcpy - prepare a memcpy operation
  * @chan: the channel to prepare operation on
  * @dest: operation virtual destination address
@@ -1609,6 +1711,7 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	/* setup platform data for each SoC */
 	dma_cap_set(DMA_MEMCPY, at91sam9rl_config.cap_mask);
 	dma_cap_set(DMA_SG, at91sam9rl_config.cap_mask);
+	dma_cap_set(DMA_INTERLEAVE, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_MEMCPY, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_SLAVE, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_SG, at91sam9g45_config.cap_mask);
@@ -1713,6 +1816,9 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	atdma->dma_common.dev = &pdev->dev;
 
 	/* set prep routines based on capability */
+	if (dma_has_cap(DMA_INTERLEAVE, atdma->dma_common.cap_mask))
+		atdma->dma_common.device_prep_interleaved_dma = atc_prep_dma_interleaved;
+
 	if (dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask))
 		atdma->dma_common.device_prep_dma_memcpy = atc_prep_dma_memcpy;
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index 2727ca560572..bc8d5ebedd19 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -196,6 +196,11 @@ struct at_desc {
 	size_t				len;
 	u32				tx_width;
 	size_t				total_len;
+
+	/* Interleaved data */
+	size_t				boundary;
+	size_t				dst_hole;
+	size_t				src_hole;
 };
 
 static inline struct at_desc *
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 7992164ea9ec..cf1213de7865 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -235,6 +235,10 @@ struct at_xdmac_lld {
 	dma_addr_t	mbr_sa;		/* Source Address Member */
 	dma_addr_t	mbr_da;		/* Destination Address Member */
 	u32		mbr_cfg;	/* Configuration Register */
+	u32		mbr_bc;		/* Block Control Register */
+	u32		mbr_ds;		/* Data Stride Register */
+	u32		mbr_sus;	/* Source Microblock Stride Register */
+	u32		mbr_dus;	/* Destination Microblock Stride Register */
 };
 
 
@@ -358,6 +362,8 @@ static void at_xdmac_start_xfer(struct at_xdmac_chan *atchan,
 	if (at_xdmac_chan_is_cyclic(atchan)) {
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV1;
 		at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
+	} else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3) {
+		reg = AT_XDMAC_CNDC_NDVIEW_NDV3;
 	} else {
 		/*
 		 * No need to write AT_XDMAC_CC reg, it will be done when the
@@ -465,6 +471,33 @@ static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan)
 	return desc;
 }
 
+static void at_xdmac_queue_desc(struct dma_chan *chan,
+				struct at_xdmac_desc *prev,
+				struct at_xdmac_desc *desc)
+{
+	if (!prev || !desc)
+		return;
+
+	prev->lld.mbr_nda = desc->tx_dma_desc.phys;
+	prev->lld.mbr_ubc |= AT_XDMAC_MBR_UBC_NDE;
+
+	dev_dbg(chan2dev(chan),	"%s: chain lld: prev=0x%p, mbr_nda=%pad\n",
+		__func__, prev, &prev->lld.mbr_nda);
+}
+
+static inline void at_xdmac_increment_block_count(struct dma_chan *chan,
+						  struct at_xdmac_desc *desc)
+{
+	if (!desc)
+		return;
+
+	desc->lld.mbr_bc++;
+
+	dev_dbg(chan2dev(chan),
+		"%s: incrementing the block count of the desc 0x%p\n",
+		__func__, desc);
+}