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

Pull slave-dmaengine updates from Vinod Koul:
 - new Xilixn VDMA driver from Srikanth
 - bunch of updates for edma driver by Thomas, Joel and Peter
 - fixes and updates on dw, ste_dma, freescale, mpc512x, sudmac etc

* 'for-linus' of git://git.infradead.org/users/vkoul/slave-dma: (45 commits)
  dmaengine: sh: don't use dynamic static allocation
  dmaengine: sh: fix print specifier warnings
  dmaengine: sh: make shdma_prep_dma_cyclic static
  dmaengine: Kconfig: Update MXS_DMA help text to include MX6Q/MX6DL
  of: dma: Grammar s/requests/request/, s/used required/required/
  dmaengine: shdma: Enable driver compilation with COMPILE_TEST
  dmaengine: rcar-hpbdma: Include linux/err.h
  dmaengine: sudmac: Include linux/err.h
  dmaengine: sudmac: Keep #include sorted alphabetically
  dmaengine: shdmac: Include linux/err.h
  dmaengine: shdmac: Keep #include sorted alphabetically
  dmaengine: s3c24xx-dma: Add cyclic transfer support
  dmaengine: s3c24xx-dma: Process whole SG chain
  dmaengine: imx: correct sdmac->status for cyclic dma tx
  dmaengine: pch: fix compilation for alpha target
  dmaengine: dw: check return code of dma_async_device_register()
  dmaengine: dw: fix regression in dw_probe() function
  dmaengine: dw: enable clock before access
  dma: pch_dma: Fix Kconfig dependencies
  dmaengine: mpc512x: add support for peripheral transfers
  ...

Documentation/devicetree/bindings/dma/mmp-dma.txt

 * MARVELL MMP DMA controller
 
 Marvell Peripheral DMA Controller
-Used platfroms: pxa688, pxa910, pxa3xx, etc
+Used platforms: pxa688, pxa910, pxa3xx, etc
 
 Required properties:
 - compatible: Should be "marvell,pdma-1.0"
 - reg: Should contain DMA registers location and length.
 - interrupts: Either contain all of the per-channel DMA interrupts
 		or one irq for pdma device
-- #dma-channels: Number of DMA channels supported by the controller.
+
+Optional properties:
+- #dma-channels: Number of DMA channels supported by the controller (defaults
+  to 32 when not specified)
 
 "marvell,pdma-1.0"
-Used platfroms: pxa25x, pxa27x, pxa3xx, pxa93x, pxa168, pxa910, pxa688.
+Used platforms: pxa25x, pxa27x, pxa3xx, pxa93x, pxa168, pxa910, pxa688.
 
 Examples:
 
@@ -45,7 +48,7 @@ pdma: dma-controller@d4000000 {
 
 
 Marvell Two Channel DMA Controller used specifically for audio
-Used platfroms: pxa688, pxa910
+Used platforms: pxa688, pxa910
 
 Required properties:
 - compatible: Should be "marvell,adma-1.0" or "marvell,pxa910-squ"

Documentation/devicetree/bindings/dma/xilinx/xilinx_vdma.txt

+Xilinx AXI VDMA engine, it does transfers between memory and video devices.
+It can be configured to have one channel or two channels. If configured
+as two channels, one is to transmit to the video device and another is
+to receive from the video device.
+
+Required properties:
+- compatible: Should be "xlnx,axi-vdma-1.00.a"
+- #dma-cells: Should be <1>, see "dmas" property below
+- reg: Should contain VDMA registers location and length.
+- xlnx,num-fstores: Should be the number of framebuffers as configured in h/w.
+- dma-channel child node: Should have at least one channel and can have up to
+	two channels per device. This node specifies the properties of each
+	DMA channel (see child node properties below).
+
+Optional properties:
+- xlnx,include-sg: Tells configured for Scatter-mode in
+	the hardware.
+- xlnx,flush-fsync: Tells which channel to Flush on Frame sync.
+	It takes following values:
+	{1}, flush both channels
+	{2}, flush mm2s channel
+	{3}, flush s2mm channel
+
+Required child node properties:
+- compatible: It should be either "xlnx,axi-vdma-mm2s-channel" or
+	"xlnx,axi-vdma-s2mm-channel".
+- interrupts: Should contain per channel VDMA interrupts.
+- xlnx,data-width: Should contain the stream data width, take values
+	{32,64...1024}.
+
+Optional child node properties:
+- xlnx,include-dre: Tells hardware is configured for Data
+	Realignment Engine.
+- xlnx,genlock-mode: Tells Genlock synchronization is
+	enabled/disabled in hardware.
+
+Example:
+++++++++
+
+axi_vdma_0: axivdma@40030000 {
+	compatible = "xlnx,axi-vdma-1.00.a";
+	#dma_cells = <1>;
+	reg = < 0x40030000 0x10000 >;
+	xlnx,num-fstores = <0x8>;
+	xlnx,flush-fsync = <0x1>;
+	dma-channel@40030000 {
+		compatible = "xlnx,axi-vdma-mm2s-channel";
+		interrupts = < 0 54 4 >;
+		xlnx,datawidth = <0x40>;
+	} ;
+	dma-channel@40030030 {
+		compatible = "xlnx,axi-vdma-s2mm-channel";
+		interrupts = < 0 53 4 >;
+		xlnx,datawidth = <0x40>;
+	} ;
+} ;
+
+
+* DMA client
+
+Required properties:
+- dmas: a list of <[Video DMA device phandle] [Channel ID]> pairs,
+	where Channel ID is '0' for write/tx and '1' for read/rx
+	channel.
+- dma-names: a list of DMA channel names, one per "dmas" entry
+
+Example:
+++++++++
+
+vdmatest_0: vdmatest@0 {
+	compatible ="xlnx,axi-vdma-test-1.00.a";
+	dmas = <&axi_vdma_0 0
+		&axi_vdma_0 1>;
+	dma-names = "vdma0", "vdma1";
+} ;

arch/powerpc/boot/dts/mpc8308_p1m.dts

@@ -296,7 +296,7 @@ ipic-msi@7c0 {
 		};
 
 		dma@2c000 {
-			compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma";
+			compatible = "fsl,mpc8308-dma";
 			reg = <0x2c000 0x1800>;
 			interrupts = <3 0x8
 					94 0x8>;

arch/powerpc/boot/dts/mpc8308rdb.dts

@@ -265,7 +265,7 @@ ipic-msi@7c0 {
 		};
 
 		dma@2c000 {
-			compatible = "fsl,mpc8308-dma", "fsl,mpc5121-dma";
+			compatible = "fsl,mpc8308-dma";
 			reg = <0x2c000 0x1800>;
 			interrupts = <3 0x8
 					94 0x8>;

drivers/dma/Kconfig

@@ -234,7 +234,7 @@ config PL330_DMA
 
 config PCH_DMA
 	tristate "Intel EG20T PCH / LAPIS Semicon IOH(ML7213/ML7223/ML7831) DMA"
-	depends on PCI && X86
+	depends on PCI && (X86_32 || COMPILE_TEST)
 	select DMA_ENGINE
 	help
 	  Enable support for Intel EG20T PCH DMA engine.
@@ -269,7 +269,7 @@ config MXS_DMA
 	select DMA_ENGINE
 	help
 	  Support the MXS DMA engine. This engine including APBH-DMA
-	  and APBX-DMA is integrated into Freescale i.MX23/28 chips.
+	  and APBX-DMA is integrated into Freescale i.MX23/28/MX6Q/MX6DL chips.
 
 config EP93XX_DMA
 	bool "Cirrus Logic EP93xx DMA support"
@@ -361,6 +361,20 @@ config FSL_EDMA
 	  multiplexing capability for DMA request sources(slot).
 	  This module can be found on Freescale Vybrid and LS-1 SoCs.
 
+config XILINX_VDMA
+	tristate "Xilinx AXI VDMA Engine"
+	depends on (ARCH_ZYNQ || MICROBLAZE)
+	select DMA_ENGINE
+	help
+	  Enable support for Xilinx AXI VDMA Soft IP.
+
+	  This engine provides high-bandwidth direct memory access
+	  between memory and AXI4-Stream video type target
+	  peripherals including peripherals which support AXI4-
+	  Stream Video Protocol.  It has two stream interfaces/
+	  channels, Memory Mapped to Stream (MM2S) and Stream to
+	  Memory Mapped (S2MM) for the data transfers.
+
 config DMA_ENGINE
 	bool
 

drivers/dma/Makefile

@@ -46,3 +46,4 @@ 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
+obj-y += xilinx/

drivers/dma/dw/core.c

@@ -1493,6 +1493,13 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	dw->regs = chip->regs;
 	chip->dw = dw;
 
+	dw->clk = devm_clk_get(chip->dev, "hclk");
+	if (IS_ERR(dw->clk))
+		return PTR_ERR(dw->clk);
+	err = clk_prepare_enable(dw->clk);
+	if (err)
+		return err;
+
 	dw_params = dma_read_byaddr(chip->regs, DW_PARAMS);
 	autocfg = dw_params >> DW_PARAMS_EN & 0x1;
 
@@ -1500,15 +1507,19 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 	if (!pdata && autocfg) {
 		pdata = devm_kzalloc(chip->dev, sizeof(*pdata), GFP_KERNEL);
-		if (!pdata)
-			return -ENOMEM;
+		if (!pdata) {
+			err = -ENOMEM;
+			goto err_pdata;
+		}
 
 		/* Fill platform data with the default values */
 		pdata->is_private = true;
 		pdata->chan_allocation_order = CHAN_ALLOCATION_ASCENDING;
 		pdata->chan_priority = CHAN_PRIORITY_ASCENDING;
-	} else if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS)
-		return -EINVAL;
+	} else if (!pdata || pdata->nr_channels > DW_DMA_MAX_NR_CHANNELS) {
+		err = -EINVAL;
+		goto err_pdata;
+	}
 
 	if (autocfg)
 		nr_channels = (dw_params >> DW_PARAMS_NR_CHAN & 0x7) + 1;
@@ -1517,13 +1528,10 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 	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");
-	if (IS_ERR(dw->clk))
-		return PTR_ERR(dw->clk);
-	clk_prepare_enable(dw->clk);
+	if (!dw->chan) {
+		err = -ENOMEM;
+		goto err_pdata;
+	}
 
 	/* Get hardware configuration parameters */
 	if (autocfg) {
@@ -1553,7 +1561,8 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 					 sizeof(struct dw_desc), 4, 0);
 	if (!dw->desc_pool) {
 		dev_err(chip->dev, "No memory for descriptors dma pool\n");
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto err_pdata;
 	}
 
 	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
@@ -1561,7 +1570,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
 			  "dw_dmac", dw);
 	if (err)
-		return err;
+		goto err_pdata;
 
 	INIT_LIST_HEAD(&dw->dma.channels);
 	for (i = 0; i < nr_channels; i++) {
@@ -1650,12 +1659,20 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 	dma_writel(dw, CFG, DW_CFG_DMA_EN);
 
+	err = dma_async_device_register(&dw->dma);
+	if (err)
+		goto err_dma_register;
+
 	dev_info(chip->dev, "DesignWare DMA Controller, %d channels\n",
 		 nr_channels);
 
-	dma_async_device_register(&dw->dma);
-
 	return 0;
+
+err_dma_register:
+	free_irq(chip->irq, dw);
+err_pdata:
+	clk_disable_unprepare(dw->clk);
+	return err;
 }
 EXPORT_SYMBOL_GPL(dw_dma_probe);
 
@@ -1676,6 +1693,8 @@ int dw_dma_remove(struct dw_dma_chip *chip)
 		channel_clear_bit(dw, CH_EN, dwc->mask);
 	}
 
+	clk_disable_unprepare(dw->clk);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dw_dma_remove);

drivers/dma/dw/pci.c

@@ -93,19 +93,13 @@ static int dw_pci_resume_early(struct device *dev)
 	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 */
+#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,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_pci_suspend_late, dw_pci_resume_early)
 };
 
-static DEFINE_PCI_DEVICE_TABLE(dw_pci_id_table) = {
+static const struct pci_device_id dw_pci_id_table[] = {
 	/* Medfield */
 	{ PCI_VDEVICE(INTEL, 0x0827), (kernel_ulong_t)&dw_pci_pdata },
 	{ PCI_VDEVICE(INTEL, 0x0830), (kernel_ulong_t)&dw_pci_pdata },

drivers/dma/dw/platform.c

@@ -256,7 +256,7 @@ MODULE_DEVICE_TABLE(acpi, dw_dma_acpi_id_table);
 
 #ifdef CONFIG_PM_SLEEP
 
-static int dw_suspend_noirq(struct device *dev)
+static int dw_suspend_late(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
@@ -264,7 +264,7 @@ static int dw_suspend_noirq(struct device *dev)
 	return dw_dma_suspend(chip);
 }
 
-static int dw_resume_noirq(struct device *dev)
+static int dw_resume_early(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
@@ -272,20 +272,10 @@ static int dw_resume_noirq(struct device *dev)
 	return dw_dma_resume(chip);
 }
 
-#else /* !CONFIG_PM_SLEEP */
-
-#define dw_suspend_noirq	NULL
-#define dw_resume_noirq		NULL
-
-#endif /* !CONFIG_PM_SLEEP */
+#endif /* CONFIG_PM_SLEEP */
 
 static const struct dev_pm_ops dw_dev_pm_ops = {
-	.suspend_noirq = dw_suspend_noirq,
-	.resume_noirq = dw_resume_noirq,
-	.freeze_noirq = dw_suspend_noirq,
-	.thaw_noirq = dw_resume_noirq,
-	.restore_noirq = dw_resume_noirq,
-	.poweroff_noirq = dw_suspend_noirq,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_suspend_late, dw_resume_early)
 };
 
 static struct platform_driver dw_driver = {

drivers/dma/imx-sdma.c

@@ -607,8 +607,6 @@ static void sdma_handle_channel_loop(struct sdma_channel *sdmac)
 
 		if (bd->mode.status & BD_RROR)
 			sdmac->status = DMA_ERROR;
-		else
-			sdmac->status = DMA_IN_PROGRESS;
 
 		bd->mode.status |= BD_DONE;
 		sdmac->buf_tail++;

drivers/dma/mmp_pdma.c

@@ -29,8 +29,8 @@
 #define DALGN		0x00a0
 #define DINT		0x00f0
 #define DDADR		0x0200
-#define DSADR		0x0204
-#define DTADR		0x0208
+#define DSADR(n)	(0x0204 + ((n) << 4))
+#define DTADR(n)	(0x0208 + ((n) << 4))
 #define DCMD		0x020c
 
 #define DCSR_RUN	BIT(31)	/* Run Bit (read / write) */
@@ -277,7 +277,7 @@ static void mmp_pdma_free_phy(struct mmp_pdma_chan *pchan)
 		return;
 
 	/* clear the channel mapping in DRCMR */
-	reg = DRCMR(pchan->phy->vchan->drcmr);
+	reg = DRCMR(pchan->drcmr);
 	writel(0, pchan->phy->base + reg);
 
 	spin_lock_irqsave(&pdev->phy_lock, flags);
@@ -748,11 +748,92 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 	return 0;
 }
 
+static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan,
+				     dma_cookie_t cookie)
+{
+	struct mmp_pdma_desc_sw *sw;
+	u32 curr, residue = 0;
+	bool passed = false;
+	bool cyclic = chan->cyclic_first != NULL;
+
+	/*
+	 * If the channel does not have a phy pointer anymore, it has already
+	 * been completed. Therefore, its residue is 0.
+	 */
+	if (!chan->phy)
+		return 0;
+
+	if (chan->dir == DMA_DEV_TO_MEM)
+		curr = readl(chan->phy->base + DTADR(chan->phy->idx));
+	else
+		curr = readl(chan->phy->base + DSADR(chan->phy->idx));
+
+	list_for_each_entry(sw, &chan->chain_running, node) {
+		u32 start, end, len;
+
+		if (chan->dir == DMA_DEV_TO_MEM)
+			start = sw->desc.dtadr;
+		else
+			start = sw->desc.dsadr;
+
+		len = sw->desc.dcmd & DCMD_LENGTH;
+		end = start + len;
+
+		/*
+		 * 'passed' will be latched once we found the descriptor which
+		 * lies inside the boundaries of the curr pointer. All
+		 * descriptors that occur in the list _after_ we found that
+		 * partially handled descriptor are still to be processed and
+		 * are hence added to the residual bytes counter.
+		 */
+
+		if (passed) {
+			residue += len;
+		} else if (curr >= start && curr <= end) {
+			residue += end - curr;
+			passed = true;
+		}
+
+		/*
+		 * Descriptors that have the ENDIRQEN bit set mark the end of a
+		 * transaction chain, and the cookie assigned with it has been
+		 * returned previously from mmp_pdma_tx_submit().
+		 *
+		 * In case we have multiple transactions in the running chain,
+		 * and the cookie does not match the one the user asked us
+		 * about, reset the state variables and start over.
+		 *
+		 * This logic does not apply to cyclic transactions, where all
+		 * descriptors have the ENDIRQEN bit set, and for which we
+		 * can't have multiple transactions on one channel anyway.
+		 */
+		if (cyclic || !(sw->desc.dcmd & DCMD_ENDIRQEN))
+			continue;
+
+		if (sw->async_tx.cookie == cookie) {
+			return residue;
+		} else {
+			residue = 0;
+			passed = false;
+		}
+	}
+
+	/* We should only get here in case of cyclic transactions */
+	return residue;
+}
+
 static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan,
 					  dma_cookie_t cookie,
 					  struct dma_tx_state *txstate)
 {
-	return dma_cookie_status(dchan, cookie, txstate);
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+	enum dma_status ret;
+
+	ret = dma_cookie_status(dchan, cookie, txstate);
+	if (likely(ret != DMA_ERROR))
+		dma_set_residue(txstate, mmp_pdma_residue(chan, cookie));
+
+	return ret;
 }
 
 /**
@@ -858,8 +939,7 @@ static int mmp_pdma_chan_init(struct mmp_pdma_device *pdev, int idx, int irq)
 	struct mmp_pdma_chan *chan;
 	int ret;
 
-	chan = devm_kzalloc(pdev->dev, sizeof(struct mmp_pdma_chan),
-			    GFP_KERNEL);
+	chan = devm_kzalloc(pdev->dev, sizeof(*chan), GFP_KERNEL);
 	if (chan == NULL)
 		return -ENOMEM;
 
@@ -946,8 +1026,7 @@ static int mmp_pdma_probe(struct platform_device *op)
 			irq_num++;
 	}
 
-	pdev->phy = devm_kcalloc(pdev->dev,
-				 dma_channels, sizeof(struct mmp_pdma_chan),
+	pdev->phy = devm_kcalloc(pdev->dev, dma_channels, sizeof(*pdev->phy),
 				 GFP_KERNEL);
 	if (pdev->phy == NULL)
 		return -ENOMEM;

drivers/dma/pch_dma.c

@@ -21,6 +21,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/pci.h>
+#include <linux/slab.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/pch_dma.h>
@@ -996,7 +997,7 @@ static void pch_dma_remove(struct pci_dev *pdev)
 #define PCI_DEVICE_ID_ML7831_DMA1_8CH	0x8810
 #define PCI_DEVICE_ID_ML7831_DMA2_4CH	0x8815
 
-DEFINE_PCI_DEVICE_TABLE(pch_dma_id_table) = {
+const struct pci_device_id pch_dma_id_table[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_8CH), 8 },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_EG20T_PCH_DMA_4CH), 4 },
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ML7213_DMA1_8CH), 8}, /* UART Video */

drivers/dma/s3c24xx-dma.c

@@ -164,6 +164,7 @@ struct s3c24xx_sg {
  * @disrcc: value for source control register
  * @didstc: value for destination control register
  * @dcon: base value for dcon register
+ * @cyclic: indicate cyclic transfer
  */
 struct s3c24xx_txd {
 	struct virt_dma_desc vd;
@@ -173,6 +174,7 @@ struct s3c24xx_txd {
 	u32 disrcc;
 	u32 didstc;
 	u32 dcon;
+	bool cyclic;
 };
 
 struct s3c24xx_dma_chan;
@@ -669,8 +671,10 @@ static irqreturn_t s3c24xx_dma_irq(int irq, void *data)
 		/* when more sg's are in this txd, start the next one */
 		if (!list_is_last(txd->at, &txd->dsg_list)) {
 			txd->at = txd->at->next;
+			if (txd->cyclic)
+				vchan_cyclic_callback(&txd->vd);
 			s3c24xx_dma_start_next_sg(s3cchan, txd);
-		} else {
+		} else if (!txd->cyclic) {
 			s3cchan->at = NULL;
 			vchan_cookie_complete(&txd->vd);
 
@@ -682,6 +686,12 @@ static irqreturn_t s3c24xx_dma_irq(int irq, void *data)
 				s3c24xx_dma_start_next_txd(s3cchan);
 			else
 				s3c24xx_dma_phy_free(s3cchan);
+		} else {
+			vchan_cyclic_callback(&txd->vd);
+
+			/* Cyclic: reset at beginning */
+			txd->at = txd->dsg_list.next;
+			s3c24xx_dma_start_next_sg(s3cchan, txd);
 		}
 	}
 	spin_unlock(&s3cchan->vc.lock);
@@ -877,6 +887,104 @@ static struct dma_async_tx_descriptor *s3c24xx_dma_prep_memcpy(
 	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
 }
 
+static struct dma_async_tx_descriptor *s3c24xx_dma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t addr, size_t size, size_t period,
+	enum dma_transfer_direction direction, unsigned long flags,
+	void *context)
+{
+	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
+	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
+	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
+	struct s3c24xx_dma_channel *cdata = &pdata->channels[s3cchan->id];
+	struct s3c24xx_txd *txd;
+	struct s3c24xx_sg *dsg;
+	unsigned sg_len;
+	dma_addr_t slave_addr;
+	u32 hwcfg = 0;
+	int i;
+
+	dev_dbg(&s3cdma->pdev->dev,
+		"prepare cyclic transaction of %zu bytes with period %zu from %s\n",
+		size, period, s3cchan->name);
+
+	if (!is_slave_direction(direction)) {
+		dev_err(&s3cdma->pdev->dev,
+			"direction %d unsupported\n", direction);
+		return NULL;
+	}
+
+	txd = s3c24xx_dma_get_txd();
+	if (!txd)
+		return NULL;
+
+	txd->cyclic = 1;
+
+	if (cdata->handshake)
+		txd->dcon |= S3C24XX_DCON_HANDSHAKE;
+
+	switch (cdata->bus) {
+	case S3C24XX_DMA_APB:
+		txd->dcon |= S3C24XX_DCON_SYNC_PCLK;
+		hwcfg |= S3C24XX_DISRCC_LOC_APB;
+		break;
+	case S3C24XX_DMA_AHB:
+		txd->dcon |= S3C24XX_DCON_SYNC_HCLK;
+		hwcfg |= S3C24XX_DISRCC_LOC_AHB;
+		break;
+	}
+
+	/*
+	 * Always assume our peripheral desintation is a fixed
+	 * address in memory.
+	 */
+	hwcfg |= S3C24XX_DISRCC_INC_FIXED;
+
+	/*
+	 * Individual dma operations are requested by the slave,
+	 * so serve only single atomic operations (S3C24XX_DCON_SERV_SINGLE).
+	 */
+	txd->dcon |= S3C24XX_DCON_SERV_SINGLE;
+
+	if (direction == DMA_MEM_TO_DEV) {
+		txd->disrcc = S3C24XX_DISRCC_LOC_AHB |
+			      S3C24XX_DISRCC_INC_INCREMENT;
+		txd->didstc = hwcfg;
+		slave_addr = s3cchan->cfg.dst_addr;
+		txd->width = s3cchan->cfg.dst_addr_width;
+	} else {
+		txd->disrcc = hwcfg;
+		txd->didstc = S3C24XX_DIDSTC_LOC_AHB |
+			      S3C24XX_DIDSTC_INC_INCREMENT;
+		slave_addr = s3cchan->cfg.src_addr;
+		txd->width = s3cchan->cfg.src_addr_width;
+	}
+
+	sg_len = size / period;
+
+	for (i = 0; i < sg_len; i++) {
+		dsg = kzalloc(sizeof(*dsg), GFP_NOWAIT);
+		if (!dsg) {
+			s3c24xx_dma_free_txd(txd);
+			return NULL;
+		}
+		list_add_tail(&dsg->node, &txd->dsg_list);
+
+		dsg->len = period;
+		/* Check last period length */
+		if (i == sg_len - 1)
+			dsg->len = size - period * i;
+		if (direction == DMA_MEM_TO_DEV) {
+			dsg->src_addr = addr + period * i;
+			dsg->dst_addr = slave_addr;
+		} else { /* DMA_DEV_TO_MEM */
+			dsg->src_addr = slave_addr;
+			dsg->dst_addr = addr + period * i;
+		}
+	}
+
+	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
+}
+
 static struct dma_async_tx_descriptor *s3c24xx_dma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
@@ -961,7 +1069,6 @@ static struct dma_async_tx_descriptor *s3c24xx_dma_prep_slave_sg(
 			dsg->src_addr = slave_addr;
 			dsg->dst_addr = sg_dma_address(sg);
 		}
-		break;
 	}
 
 	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
@@ -1198,6 +1305,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 
 	/* Initialize slave engine for SoC internal dedicated peripherals */
 	dma_cap_set(DMA_SLAVE, s3cdma->slave.cap_mask);
+	dma_cap_set(DMA_CYCLIC, s3cdma->slave.cap_mask);
 	dma_cap_set(DMA_PRIVATE, s3cdma->slave.cap_mask);
 	s3cdma->slave.dev = &pdev->dev;
 	s3cdma->slave.device_alloc_chan_resources =
@@ -1207,6 +1315,7 @@ static int s3c24xx_dma_probe(struct platform_device *pdev)
 	s3cdma->slave.device_tx_status = s3c24xx_dma_tx_status;
 	s3cdma->slave.device_issue_pending = s3c24xx_dma_issue_pending;
 	s3cdma->slave.device_prep_slave_sg = s3c24xx_dma_prep_slave_sg;
+	s3cdma->slave.device_prep_dma_cyclic = s3c24xx_dma_prep_dma_cyclic;
 	s3cdma->slave.device_control = s3c24xx_dma_control;
 
 	/* Register as many memcpy channels as there are physical channels */

drivers/dma/sh/Kconfig

@@ -4,7 +4,7 @@
 
 config SH_DMAE_BASE
 	bool "Renesas SuperH DMA Engine support"
-	depends on (SUPERH && SH_DMA) || (ARM && ARCH_SHMOBILE)
+	depends on (SUPERH && SH_DMA) || ARCH_SHMOBILE || COMPILE_TEST
 	depends on !SH_DMA_API
 	default y
 	select DMA_ENGINE

drivers/dma/sh/rcar-hpbdma.c

@@ -18,6 +18,7 @@
 
 #include <linux/dmaengine.h>
 #include <linux/delay.h>
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>

drivers/dma/sh/shdma-base.c

@@ -73,8 +73,7 @@ static void shdma_chan_xfer_ld_queue(struct shdma_chan *schan)
 static dma_cookie_t shdma_tx_submit(struct dma_async_tx_descriptor *tx)
 {
 	struct shdma_desc *chunk, *c, *desc =
-		container_of(tx, struct shdma_desc, async_tx),
-		*last = desc;
+		container_of(tx, struct shdma_desc, async_tx);
 	struct shdma_chan *schan = to_shdma_chan(tx->chan);
 	dma_async_tx_callback callback = tx->callback;
 	dma_cookie_t cookie;
@@ -98,19 +97,20 @@ static dma_cookie_t shdma_tx_submit(struct dma_async_tx_descriptor *tx)
 				      &chunk->node == &schan->ld_free))
 			break;
 		chunk->mark = DESC_SUBMITTED;
-		/* Callback goes to the last chunk */
-		chunk->async_tx.callback = NULL;
+		if (chunk->chunks == 1) {
+			chunk->async_tx.callback = callback;
+			chunk->async_tx.callback_param = tx->callback_param;
+		} else {
+			/* Callback goes to the last chunk */
+			chunk->async_tx.callback = NULL;
+		}
 		chunk->cookie = cookie;
 		list_move_tail(&chunk->node, &schan->ld_queue);
-		last = chunk;
 
 		dev_dbg(schan->dev, "submit #%d@%p on %d\n",
-			tx->cookie, &last->async_tx, schan->id);
+			tx->cookie, &chunk->async_tx, schan->id);
 	}
 
-	last->async_tx.callback = callback;
-	last->async_tx.callback_param = tx->callback_param;
-
 	if (power_up) {
 		int ret;
 		schan->pm_state = SHDMA_PM_BUSY;
@@ -304,6 +304,7 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 	dma_async_tx_callback callback = NULL;
 	void *param = NULL;
 	unsigned long flags;
+	LIST_HEAD(cyclic_list);
 
 	spin_lock_irqsave(&schan->chan_lock, flags);
 	list_for_each_entry_safe(desc, _desc, &schan->ld_queue, node) {
@@ -369,10 +370,16 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 		if (((desc->mark == DESC_COMPLETED ||
 		      desc->mark == DESC_WAITING) &&
 		     async_tx_test_ack(&desc->async_tx)) || all) {
-			/* Remove from ld_queue list */
-			desc->mark = DESC_IDLE;
 
-			list_move(&desc->node, &schan->ld_free);
+			if (all || !desc->cyclic) {
+				/* Remove from ld_queue list */
+				desc->mark = DESC_IDLE;
+				list_move(&desc->node, &schan->ld_free);
+			} else {
+				/* reuse as cyclic */
+				desc->mark = DESC_SUBMITTED;
+				list_move_tail(&desc->node, &cyclic_list);
+			}
 
 			if (list_empty(&schan->ld_queue)) {
 				dev_dbg(schan->dev, "Bring down channel %d\n", schan->id);
@@ -389,6 +396,8 @@ static dma_async_tx_callback __ld_cleanup(struct shdma_chan *schan, bool all)
 		 */
 		schan->dma_chan.completed_cookie = schan->dma_chan.cookie;
 
+	list_splice_tail(&cyclic_list, &schan->ld_queue);
+
 	spin_unlock_irqrestore(&schan->chan_lock, flags);
 
 	if (callback)
@@ -521,7 +530,7 @@ static struct shdma_desc *shdma_add_desc(struct shdma_chan *schan,
  */
 static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan,
 	struct scatterlist *sgl, unsigned int sg_len, dma_addr_t *addr,
-	enum dma_transfer_direction direction, unsigned long flags)
+	enum dma_transfer_direction direction, unsigned long flags, bool cyclic)
 {
 	struct scatterlist *sg;
 	struct shdma_desc *first = NULL, *new = NULL /* compiler... */;
@@ -569,7 +578,11 @@ static struct dma_async_tx_descriptor *shdma_prep_sg(struct shdma_chan *schan,
 			if (!new)
 				goto err_get_desc;
 
-			new->chunks = chunks--;
+			new->cyclic = cyclic;
+			if (cyclic)
+				new->chunks = 1;
+			else
+				new->chunks = chunks--;
 			list_add_tail(&new->node, &tx_list);
 		} while (len);
 	}
@@ -612,7 +625,8 @@ static struct dma_async_tx_descriptor *shdma_prep_memcpy(
 	sg_dma_address(&sg) = dma_src;
 	sg_dma_len(&sg) = len;
 
-	return shdma_prep_sg(schan, &sg, 1, &dma_dest, DMA_MEM_TO_MEM, flags);
+	return shdma_prep_sg(schan, &sg, 1, &dma_dest, DMA_MEM_TO_MEM,
+			     flags, false);
 }
 
 static struct dma_async_tx_descriptor *shdma_prep_slave_sg(
@@ -640,7 +654,58 @@ static struct dma_async_tx_descriptor *shdma_prep_slave_sg(
 	slave_addr = ops->slave_addr(schan);
 
 	return shdma_prep_sg(schan, sgl, sg_len, &slave_addr,
-			      direction, flags);
+			     direction, flags, false);
+}
+
+#define SHDMA_MAX_SG_LEN 32
+
+static struct dma_async_tx_descriptor *shdma_prep_dma_cyclic(
+	struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long flags, void *context)
+{
+	struct 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;
+	unsigned int sg_len = buf_len / period_len;
+	int slave_id = schan->slave_id;
+	dma_addr_t slave_addr;
+	struct scatterlist sgl[SHDMA_MAX_SG_LEN];
+	int i;
+
+	if (!chan)
+		return NULL;
+
+	BUG_ON(!schan->desc_num);
+
+	if (sg_len > SHDMA_MAX_SG_LEN) {
+		dev_err(schan->dev, "sg length %d exceds limit %d",
+				sg_len, SHDMA_MAX_SG_LEN);
+		return NULL;
+	}
+
+	/* Someone calling slave DMA on a generic channel? */
+	if (slave_id < 0 || (buf_len < period_len)) {
+		dev_warn(schan->dev,
+			"%s: bad parameter: buf_len=%zu, period_len=%zu, id=%d\n",
+			__func__, buf_len, period_len, slave_id);
+		return NULL;
+	}
+
+	slave_addr = ops->slave_addr(schan);
+
+	sg_init_table(sgl, sg_len);
+	for (i = 0; i < sg_len; i++) {
+		dma_addr_t src = buf_addr + (period_len * i);
+
+		sg_set_page(&sgl[i], pfn_to_page(PFN_DOWN(src)), period_len,
+			    offset_in_page(src));
+		sg_dma_address(&sgl[i]) = src;
+		sg_dma_len(&sgl[i]) = period_len;
+	}
+
+	return shdma_prep_sg(schan, sgl, sg_len, &slave_addr,
+			     direction, flags, true);
 }
 
 static int shdma_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
@@ -915,6 +980,7 @@ int shdma_init(struct device *dev, struct shdma_dev *sdev,
 
 	/* Compulsory for DMA_SLAVE fields */
 	dma_dev->device_prep_slave_sg = shdma_prep_slave_sg;
+	dma_dev->device_prep_dma_cyclic = shdma_prep_dma_cyclic;
 	dma_dev->device_control = shdma_control;
 
 	dma_dev->dev = dev;

drivers/dma/sh/shdmac.c

@@ -18,21 +18,22 @@
  *
  */
 
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/err.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kdebug.h>
 #include <linux/module.h>
+#include <linux/notifier.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/dmaengine.h>
-#include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/rculist.h>
 #include <linux/sh_dma.h>
-#include <linux/notifier.h>
-#include <linux/kdebug.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/rculist.h>
 
 #include "../dmaengine.h"
 #include "shdma.h"

drivers/dma/sh/sudmac.c

@@ -14,12 +14,13 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/dmaengine.h>
+#include <linux/err.h>
 #include <linux/init.h>
-#include <linux/module.h>
-#include <linux/slab.h>
 #include <linux/interrupt.h>
-#include <linux/dmaengine.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 #include <linux/sudmac.h>
 
 struct sudmac_chan {

drivers/dma/ste_dma40.c

@@ -556,7 +556,6 @@ struct d40_gen_dmac {
  * later
  * @reg_val_backup_chan: Backup data for standard channel parameter registers.
  * @gcc_pwr_off_mask: Mask to maintain the channels that can be turned off.
- * @initialized: true if the dma has been initialized
  * @gen_dmac: the struct for generic registers values to represent u8500/8540
  * DMA controller
  */
@@ -594,7 +593,6 @@ struct d40_base {
 	u32				  reg_val_backup_v4[BACKUP_REGS_SZ_MAX];
 	u32				 *reg_val_backup_chan;
 	u16				  gcc_pwr_off_mask;
-	bool				  initialized;
 	struct d40_gen_dmac		  gen_dmac;
 };
 
@@ -1056,62 +1054,6 @@ static int d40_sg_2_dmalen(struct scatterlist *sgl, int sg_len,
 	return len;
 }
 
-
-#ifdef CONFIG_PM
-static void dma40_backup(void __iomem *baseaddr, u32 *backup,
-			 u32 *regaddr, int num, bool save)
-{
-	int i;
-
-	for (i = 0; i < num; i++) {
-		void __iomem *addr = baseaddr + regaddr[i];
-
-		if (save)
-			backup[i] = readl_relaxed(addr);
-		else
-			writel_relaxed(backup[i], addr);
-	}
-}
-
-static void d40_save_restore_registers(struct d40_base *base, bool save)
-{
-	int i;
-
-	/* Save/Restore channel specific registers */
-	for (i = 0; i < base->num_phy_chans; i++) {
-		void __iomem *addr;
-		int idx;
-
-		if (base->phy_res[i].reserved)
-			continue;
-
-		addr = base->virtbase + D40_DREG_PCBASE + i * D40_DREG_PCDELTA;
-		idx = i * ARRAY_SIZE(d40_backup_regs_chan);
-
-		dma40_backup(addr, &base->reg_val_backup_chan[idx],
-			     d40_backup_regs_chan,
-			     ARRAY_SIZE(d40_backup_regs_chan),
-			     save);
-	}
-
-	/* Save/Restore global registers */
-	dma40_backup(base->virtbase, base->reg_val_backup,
-		     d40_backup_regs, ARRAY_SIZE(d40_backup_regs),
-		     save);
-
-	/* Save/Restore registers only existing on dma40 v3 and later */
-	if (base->gen_dmac.backup)
-		dma40_backup(base->virtbase, base->reg_val_backup_v4,
-			     base->gen_dmac.backup,
-			base->gen_dmac.backup_size,
-			save);
-}
-#else
-static void d40_save_restore_registers(struct d40_base *base, bool save)
-{
-}
-#endif
-
 static int __d40_execute_command_phy(struct d40_chan *d40c,
 				     enum d40_command command)
 {
@@ -1495,8 +1437,8 @@ static int d40_pause(struct d40_chan *d40c)
 	if (!d40c->busy)
 		return 0;
 
-	pm_runtime_get_sync(d40c->base->dev);
 	spin_lock_irqsave(&d40c->lock, flags);
+	pm_runtime_get_sync(d40c->base->dev);
 
 	res = d40_channel_execute_command(d40c, D40_DMA_SUSPEND_REQ);
 
@@ -2998,18 +2940,88 @@ static int __init d40_dmaengine_init(struct d40_base *base,
 }
 
 /* Suspend resume functionality */
-#ifdef CONFIG_PM
-static int dma40_pm_suspend(struct device *dev)
+#ifdef CONFIG_PM_SLEEP
+static int dma40_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct d40_base *base = platform_get_drvdata(pdev);
-	int ret = 0;
+	int ret;
+
+	ret = pm_runtime_force_suspend(dev);
+	if (ret)
+		return ret;
 
 	if (base->lcpa_regulator)
 		ret = regulator_disable(base->lcpa_regulator);
 	return ret;
 }
 
+static int dma40_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct d40_base *base = platform_get_drvdata(pdev);
+	int ret = 0;
+
+	if (base->lcpa_regulator) {
+		ret = regulator_enable(base->lcpa_regulator);
+		if (ret)
+			return ret;
+	}
+
+	return pm_runtime_force_resume(dev);
+}
+#endif
+
+#ifdef CONFIG_PM
+static void dma40_backup(void __iomem *baseaddr, u32 *backup,
+			 u32 *regaddr, int num, bool save)
+{
+	int i;
+
+	for (i = 0; i < num; i++) {
+		void __iomem *addr = baseaddr + regaddr[i];
+
+		if (save)
+			backup[i] = readl_relaxed(addr);
+		else
+			writel_relaxed(backup[i], addr);
+	}
+}
+
+static void d40_save_restore_registers(struct d40_base *base, bool save)
+{
+	int i;
+
+	/* Save/Restore channel specific registers */
+	for (i = 0; i < base->num_phy_chans; i++) {
+		void __iomem *addr;
+		int idx;
+
+		if (base->phy_res[i].reserved)
+			continue;
+
+		addr = base->virtbase + D40_DREG_PCBASE + i * D40_DREG_PCDELTA;
+		idx = i * ARRAY_SIZE(d40_backup_regs_chan);
+
+		dma40_backup(addr, &base->reg_val_backup_chan[idx],
+			     d40_backup_regs_chan,
+			     ARRAY_SIZE(d40_backup_regs_chan),
+			     save);
+	}
+
+	/* Save/Restore global registers */
+	dma40_backup(base->virtbase, base->reg_val_backup,
+		     d40_backup_regs, ARRAY_SIZE(d40_backup_regs),
+		     save);
+
+	/* Save/Restore registers only existing on dma40 v3 and later */
+	if (base->gen_dmac.backup)
+		dma40_backup(base->virtbase, base->reg_val_backup_v4,
+			     base->gen_dmac.backup,
+			base->gen_dmac.backup_size,
+			save);
+}
+
 static int dma40_runtime_suspend(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -3030,36 +3042,20 @@ static int dma40_runtime_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct d40_base *base = platform_get_drvdata(pdev);
 
-	if (base->initialized)
-		d40_save_restore_registers(base, false);
+	d40_save_restore_registers(base, false);
 
 	writel_relaxed(D40_DREG_GCC_ENABLE_ALL,
 		       base->virtbase + D40_DREG_GCC);
 	return 0;
 }
-
-static int dma40_resume(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct d40_base *base = platform_get_drvdata(pdev);
-	int ret = 0;
-
-	if (base->lcpa_regulator)
-		ret = regulator_enable(base->lcpa_regulator);
-
-	return ret;
-}
+#endif
 
 static const struct dev_pm_ops dma40_pm_ops = {
-	.suspend		= dma40_pm_suspend,
-	.runtime_suspend	= dma40_runtime_suspend,
-	.runtime_resume		= dma40_runtime_resume,
-	.resume			= dma40_resume,
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(dma40_suspend, dma40_resume)
+	SET_PM_RUNTIME_PM_OPS(dma40_runtime_suspend,
+				dma40_runtime_resume,
+				NULL)
 };
-#define DMA40_PM_OPS	(&dma40_pm_ops)
-#else
-#define DMA40_PM_OPS	NULL
-#endif
 
 /* Initialization functions. */
 
@@ -3645,12 +3641,6 @@ static int __init d40_probe(struct platform_device *pdev)
 		goto failure;
 	}
 
-	pm_runtime_irq_safe(base->dev);
-	pm_runtime_set_autosuspend_delay(base->dev, DMA40_AUTOSUSPEND_DELAY);
-	pm_runtime_use_autosuspend(base->dev);
-	pm_runtime_enable(base->dev);
-	pm_runtime_resume(base->dev);
-
 	if (base->plat_data->use_esram_lcla) {
 
 		base->lcpa_regulator = regulator_get(base->dev, "lcla_esram");
@@ -3671,7 +3661,15 @@ static int __init d40_probe(struct platform_device *pdev)
 		}
 	}
 
-	base->initialized = true;
+	writel_relaxed(D40_DREG_GCC_ENABLE_ALL, base->virtbase + D40_DREG_GCC);
+
+	pm_runtime_irq_safe(base->dev);
+	pm_runtime_set_autosuspend_delay(base->dev, DMA40_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(base->dev);
+	pm_runtime_mark_last_busy(base->dev);
+	pm_runtime_set_active(base->dev);
+	pm_runtime_enable(base->dev);
+
 	ret = d40_dmaengine_init(base, num_reserved_chans);
 	if (ret)
 		goto failure;
@@ -3754,7 +3752,7 @@ static struct platform_driver d40_driver = {
 	.driver = {
 		.owner = THIS_MODULE,
 		.name  = D40_NAME,
-		.pm = DMA40_PM_OPS,
+		.pm = &dma40_pm_ops,
 		.of_match_table = d40_match,
 	},
 };

drivers/dma/xilinx/Makefile

+obj-$(CONFIG_XILINX_VDMA) += xilinx_vdma.o

include/linux/amba/xilinx_dma.h

+/*
+ * Xilinx DMA Engine drivers support header file
+ *
+ * Copyright (C) 2010-2014 Xilinx, Inc. All rights reserved.
+ *
+ * This is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __DMA_XILINX_DMA_H
+#define __DMA_XILINX_DMA_H
+
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+
+/**
+ * struct xilinx_vdma_config - VDMA Configuration structure
+ * @frm_dly: Frame delay
+ * @gen_lock: Whether in gen-lock mode
+ * @master: Master that it syncs to
+ * @frm_cnt_en: Enable frame count enable
+ * @park: Whether wants to park
+ * @park_frm: Frame to park on
+ * @coalesc: Interrupt coalescing threshold
+ * @delay: Delay counter
+ * @reset: Reset Channel
+ * @ext_fsync: External Frame Sync source
+ */
+struct xilinx_vdma_config {
+	int frm_dly;
+	int gen_lock;
+	int master;
+	int frm_cnt_en;
+	int park;
+	int park_frm;
+	int coalesc;
+	int delay;
+	int reset;
+	int ext_fsync;
+};
+
+int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
+					struct xilinx_vdma_config *cfg);
+
+#endif

include/linux/dmaengine.h

@@ -292,7 +292,7 @@ struct dma_chan_dev {
 };
 
 /**
- * enum dma_slave_buswidth - defines bus with of the DMA slave
+ * enum dma_slave_buswidth - defines bus width of the DMA slave
  * device, source or target buses
  */
 enum dma_slave_buswidth {

include/linux/shdma-base.h

@@ -54,6 +54,7 @@ struct shdma_desc {
 	dma_cookie_t cookie;
 	int chunks;
 	int mark;
+	bool cyclic;			/* used as cyclic transfer */
 };
 
 struct shdma_chan {