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
  ...

Documentation/ABI/testing/sysfs-platform-hidma

+What:		/sys/devices/platform/hidma-*/chid
+		/sys/devices/platform/QCOM8061:*/chid
+Date:		Dec 2015
+KernelVersion:	4.4
+Contact:	"Sinan Kaya <okaya@cudeaurora.org>"
+Description:
+		Contains the ID of the channel within the HIDMA instance.
+		It is used to associate a given HIDMA channel with the
+		priority and weight calls in the management interface.

Documentation/devicetree/bindings/dma/brcm,bcm2835-dma.txt

@@ -12,6 +12,10 @@ Required properties:
 - reg: Should contain DMA registers location and length.
 - interrupts: Should contain the DMA interrupts associated
 		to the DMA channels in ascending order.
+- interrupt-names: Should contain the names of the interrupt
+		   in the form "dmaXX".
+		   Use "dma-shared-all" for the common interrupt line
+		   that is shared by all dma channels.
 - #dma-cells: Must be <1>, the cell in the dmas property of the
 		client device represents the DREQ number.
 - brcm,dma-channel-mask: Bit mask representing the channels
@@ -34,13 +38,35 @@ dma: dma@7e007000 {
 		     <1 24>,
 		     <1 25>,
 		     <1 26>,
+		     /* dma channel 11-14 share one irq */
 		     <1 27>,
+		     <1 27>,
+		     <1 27>,
+		     <1 27>,
+		     /* unused shared irq for all channels */
 		     <1 28>;
+	interrupt-names = "dma0",
+			  "dma1",
+			  "dma2",
+			  "dma3",
+			  "dma4",
+			  "dma5",
+			  "dma6",
+			  "dma7",
+			  "dma8",
+			  "dma9",
+			  "dma10",
+			  "dma11",
+			  "dma12",
+			  "dma13",
+			  "dma14",
+			  "dma-shared-all";
 
 	#dma-cells = <1>;
 	brcm,dma-channel-mask = <0x7f35>;
 };
 
+
 DMA clients connected to the BCM2835 DMA controller must use the format
 described in the dma.txt file, using a two-cell specifier for each channel.
 

Documentation/devicetree/bindings/dma/mv-xor.txt

 * Marvell XOR engines
 
 Required properties:
-- compatible: Should be "marvell,orion-xor" or "marvell,armada-380-xor"
+- compatible: Should be one of the following:
+  - "marvell,orion-xor"
+  - "marvell,armada-380-xor"
+  - "marvell,armada-3700-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.

Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt

+* NVIDIA Tegra Audio DMA (ADMA) controller
+
+The Tegra Audio DMA controller that is used for transferring data
+between system memory and the Audio Processing Engine (APE).
+
+Required properties:
+- compatible: Must be "nvidia,tegra210-adma".
+- reg: Should contain DMA registers location and length. This should be
+  a single entry that includes all of the per-channel registers in one
+  contiguous bank.
+- interrupt-parent: Phandle to the interrupt parent controller.
+- interrupts: Should contain all of the per-channel DMA interrupts in
+  ascending order with respect to the DMA channel index.
+- clocks: Must contain one entry for the ADMA module clock
+  (TEGRA210_CLK_D_AUDIO).
+- clock-names: Must contain the name "d_audio" for the corresponding
+  'clocks' entry.
+- #dma-cells : Must be 1. The first cell denotes the receive/transmit
+  request number and should be between 1 and the maximum number of
+  requests supported. This value corresponds to the RX/TX_REQUEST_SELECT
+  fields in the ADMA_CHn_CTRL register.
+
+
+Example:
+
+adma: dma@702e2000 {
+	compatible = "nvidia,tegra210-adma";
+	reg = <0x0 0x702e2000 0x0 0x2000>;
+	interrupt-parent = <&tegra_agic>;
+	interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>,
+		     <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&tegra_car TEGRA210_CLK_D_AUDIO>;
+	clock-names = "d_audio";
+	#dma-cells = <1>;
+};

Documentation/devicetree/bindings/dma/qcom_bam_dma.txt

@@ -13,6 +13,8 @@ Required properties:
 - clock-names: must contain "bam_clk" entry
 - qcom,ee : indicates the active Execution Environment identifier (0-7) used in
   the secure world.
+- qcom,controlled-remotely : optional, indicates that the bam is controlled by
+  remote proccessor i.e. execution environment.
 
 Example:
 

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

@@ -13,6 +13,11 @@ Required properties:
 - chan_priority: priority of channels. 0 (default): increase from chan 0->n, 1:
   increase from chan n->0
 - block_size: Maximum block size supported by the controller
+- data-width: Maximum data width supported by hardware per AHB master
+  (in bytes, power of 2)
+
+
+Deprecated properties:
 - data_width: Maximum data width supported by hardware per AHB master
   (0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
 
@@ -38,7 +43,7 @@ Example:
 		chan_allocation_order = <1>;
 		chan_priority = <1>;
 		block_size = <0xfff>;
-		data_width = <3 3>;
+		data-width = <8 8>;
 	};
 
 DMA clients connected to the Designware DMA controller must use the format
@@ -47,8 +52,8 @@ The four cells in order are:
 
 1. A phandle pointing to the DMA controller
 2. The DMA request line number
-3. Source master for transfers on allocated channel
-4. Destination master for transfers on allocated channel
+3. Memory master for transfers on allocated channel
+4. Peripheral master for transfers on allocated channel
 
 Example:
 	

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

@@ -3,18 +3,44 @@ 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.
 
+Xilinx AXI DMA engine, it does transfers between memory and AXI4 stream
+target devices. It can be configured to have one channel or two channels.
+If configured as two channels, one is to transmit to the device and another
+is to receive from the device.
+
+Xilinx AXI CDMA engine, it does transfers between memory-mapped source
+address and a memory-mapped destination address.
+
 Required properties:
-- compatible: Should be "xlnx,axi-vdma-1.00.a"
+- compatible: Should be "xlnx,axi-vdma-1.00.a" or "xlnx,axi-dma-1.00.a" or
+	      "xlnx,axi-cdma-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.
+- xlnx,addrwidth: Should be the vdma addressing size in bits(ex: 32 bits).
+- dma-ranges: Should be as the following <dma_addr cpu_addr max_len>.
 - 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).
+- clocks: Input clock specifier. Refer to common clock bindings.
+- clock-names: List of input clocks
+	For VDMA:
+	Required elements: "s_axi_lite_aclk"
+	Optional elements: "m_axi_mm2s_aclk" "m_axi_s2mm_aclk",
+			   "m_axis_mm2s_aclk", "s_axis_s2mm_aclk"
+	For CDMA:
+	Required elements: "s_axi_lite_aclk", "m_axi_aclk"
+	FOR AXIDMA:
+	Required elements: "s_axi_lite_aclk"
+	Optional elements: "m_axi_mm2s_aclk", "m_axi_s2mm_aclk",
+			   "m_axi_sg_aclk"
+
+Required properties for VDMA:
+- xlnx,num-fstores: Should be the number of framebuffers as configured in h/w.
 
 Optional properties:
 - xlnx,include-sg: Tells configured for Scatter-mode in
 	the hardware.
+Optional properties for VDMA:
 - xlnx,flush-fsync: Tells which channel to Flush on Frame sync.
 	It takes following values:
 	{1}, flush both channels
@@ -31,6 +57,7 @@ Required child node properties:
 Optional child node properties:
 - xlnx,include-dre: Tells hardware is configured for Data
 	Realignment Engine.
+Optional child node properties for VDMA:
 - xlnx,genlock-mode: Tells Genlock synchronization is
 	enabled/disabled in hardware.
 
@@ -41,8 +68,13 @@ axi_vdma_0: axivdma@40030000 {
 	compatible = "xlnx,axi-vdma-1.00.a";
 	#dma_cells = <1>;
 	reg = < 0x40030000 0x10000 >;
+	dma-ranges = <0x00000000 0x00000000 0x40000000>;
 	xlnx,num-fstores = <0x8>;
 	xlnx,flush-fsync = <0x1>;
+	xlnx,addrwidth = <0x20>;
+	clocks = <&clk 0>, <&clk 1>, <&clk 2>, <&clk 3>, <&clk 4>;
+	clock-names = "s_axi_lite_aclk", "m_axi_mm2s_aclk", "m_axi_s2mm_aclk",
+		      "m_axis_mm2s_aclk", "s_axis_s2mm_aclk";
 	dma-channel@40030000 {
 		compatible = "xlnx,axi-vdma-mm2s-channel";
 		interrupts = < 0 54 4 >;

MAINTAINERS

@@ -11017,10 +11017,11 @@ M:	Prashant Gaikwad <pgaikwad@nvidia.com>
 S:	Supported
 F:	drivers/clk/tegra/
 
-TEGRA DMA DRIVER
+TEGRA DMA DRIVERS
 M:	Laxman Dewangan <ldewangan@nvidia.com>
+M:	Jon Hunter <jonathanh@nvidia.com>
 S:	Supported
-F:	drivers/dma/tegra20-apb-dma.c
+F:	drivers/dma/tegra*
 
 TEGRA I2C DRIVER
 M:	Laxman Dewangan <ldewangan@nvidia.com>

arch/arc/boot/dts/abilis_tb10x.dtsi

@@ -126,7 +126,7 @@ dma@FE000000 {
 			chan_allocation_order = <0>;
 			chan_priority = <1>;
 			block_size = <0x7ff>;
-			data_width = <2>;
+			data-width = <4>;
 			clocks = <&ahb_clk>;
 			clock-names = "hclk";
 		};

arch/arm/boot/dts/bcm283x.dtsi

@@ -48,9 +48,29 @@ dma: dma@7e007000 {
 				     <1 24>,
 				     <1 25>,
 				     <1 26>,
+				     /* dma channel 11-14 share one irq */
 				     <1 27>,
+				     <1 27>,
+				     <1 27>,
+				     <1 27>,
+				     /* unused shared irq for all channels */
 				     <1 28>;
-
+			interrupt-names = "dma0",
+					  "dma1",
+					  "dma2",
+					  "dma3",
+					  "dma4",
+					  "dma5",
+					  "dma6",
+					  "dma7",
+					  "dma8",
+					  "dma9",
+					  "dma10",
+					  "dma11",
+					  "dma12",
+					  "dma13",
+					  "dma14",
+					  "dma-shared-all";
 			#dma-cells = <1>;
 			brcm,dma-channel-mask = <0x7f35>;
 		};

arch/arm/boot/dts/spear13xx.dtsi

@@ -117,7 +117,7 @@ dwdma0: dma@ea800000 {
 			chan_priority = <1>;
 			block_size = <0xfff>;
 			dma-masters = <2>;
-			data_width = <3 3>;
+			data-width = <8 8>;
 		};
 
 		dma@eb000000 {
@@ -133,7 +133,7 @@ dma@eb000000 {
 			chan_allocation_order = <1>;
 			chan_priority = <1>;
 			block_size = <0xfff>;
-			data_width = <3 3>;
+			data-width = <8 8>;
 		};
 
 		fsmc: flash@b0000000 {

arch/avr32/mach-at32ap/at32ap700x.c

@@ -1365,8 +1365,8 @@ at32_add_device_mci(unsigned int id, struct mci_platform_data *data)
 	slave->dma_dev = &dw_dmac0_device.dev;
 	slave->src_id = 0;
 	slave->dst_id = 1;
-	slave->src_master = 1;
-	slave->dst_master = 0;
+	slave->m_master = 1;
+	slave->p_master = 0;
 
 	data->dma_slave = slave;
 	data->dma_filter = at32_mci_dma_filter;
@@ -2061,16 +2061,16 @@ at32_add_device_ac97c(unsigned int id, struct ac97c_platform_data *data,
 	if (flags & AC97C_CAPTURE) {
 		rx_dws->dma_dev = &dw_dmac0_device.dev;
 		rx_dws->src_id = 3;
-		rx_dws->src_master = 0;
-		rx_dws->dst_master = 1;
+		rx_dws->m_master = 0;
+		rx_dws->p_master = 1;
 	}
 
 	/* Check if DMA slave interface for playback should be configured. */
 	if (flags & AC97C_PLAYBACK) {
 		tx_dws->dma_dev = &dw_dmac0_device.dev;
 		tx_dws->dst_id = 4;
-		tx_dws->src_master = 0;
-		tx_dws->dst_master = 1;
+		tx_dws->m_master = 0;
+		tx_dws->p_master = 1;
 	}
 
 	if (platform_device_add_data(pdev, data,
@@ -2141,8 +2141,8 @@ at32_add_device_abdac(unsigned int id, struct atmel_abdac_pdata *data)
 
 	dws->dma_dev = &dw_dmac0_device.dev;
 	dws->dst_id = 2;
-	dws->src_master = 0;
-	dws->dst_master = 1;
+	dws->m_master = 0;
+	dws->p_master = 1;
 
 	if (platform_device_add_data(pdev, data,
 				sizeof(struct atmel_abdac_pdata)))

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;
 

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.

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

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 @@ static int pl08x_probe(struct amba_device *adev, const struct amba_id *id)
 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,
 };

drivers/dma/dmaengine.c

@@ -289,7 +289,7 @@ enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
 	do {
 		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
-			pr_err("%s: timeout!\n", __func__);
+			dev_err(chan->device->dev, "%s: timeout!\n", __func__);
 			return DMA_ERROR;
 		}
 		if (status != DMA_IN_PROGRESS)
@@ -482,7 +482,8 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	device = chan->device;
 
 	/* check if the channel supports slave transactions */
-	if (!test_bit(DMA_SLAVE, device->cap_mask.bits))
+	if (!(test_bit(DMA_SLAVE, device->cap_mask.bits) ||
+	      test_bit(DMA_CYCLIC, device->cap_mask.bits)))
 		return -ENXIO;
 
 	/*
@@ -518,7 +519,7 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 	struct dma_chan *chan;
 
 	if (mask && !__dma_device_satisfies_mask(dev, mask)) {
-		pr_debug("%s: wrong capabilities\n", __func__);
+		dev_dbg(dev->dev, "%s: wrong capabilities\n", __func__);
 		return NULL;
 	}
 	/* devices with multiple channels need special handling as we need to
@@ -533,12 +534,12 @@ static struct dma_chan *private_candidate(const dma_cap_mask_t *mask,
 
 	list_for_each_entry(chan, &dev->channels, device_node) {
 		if (chan->client_count) {
-			pr_debug("%s: %s busy\n",
+			dev_dbg(dev->dev, "%s: %s busy\n",
 				 __func__, dma_chan_name(chan));
 			continue;
 		}
 		if (fn && !fn(chan, fn_param)) {
-			pr_debug("%s: %s filter said false\n",
+			dev_dbg(dev->dev, "%s: %s filter said false\n",
 				 __func__, dma_chan_name(chan));
 			continue;
 		}
@@ -567,11 +568,12 @@ static struct dma_chan *find_candidate(struct dma_device *device,
 
 		if (err) {
 			if (err == -ENODEV) {
-				pr_debug("%s: %s module removed\n", __func__,
-					 dma_chan_name(chan));
+				dev_dbg(device->dev, "%s: %s module removed\n",
+					__func__, dma_chan_name(chan));
 				list_del_rcu(&device->global_node);
 			} else
-				pr_debug("%s: failed to get %s: (%d)\n",
+				dev_dbg(device->dev,
+					"%s: failed to get %s: (%d)\n",
 					 __func__, dma_chan_name(chan), err);
 
 			if (--device->privatecnt == 0)
@@ -602,7 +604,8 @@ struct dma_chan *dma_get_slave_channel(struct dma_chan *chan)
 		device->privatecnt++;
 		err = dma_chan_get(chan);
 		if (err) {
-			pr_debug("%s: failed to get %s: (%d)\n",
+			dev_dbg(chan->device->dev,
+				"%s: failed to get %s: (%d)\n",
 				__func__, dma_chan_name(chan), err);
 			chan = NULL;
 			if (--device->privatecnt == 0)
@@ -814,7 +817,8 @@ void dmaengine_get(void)
 				list_del_rcu(&device->global_node);
 				break;
 			} else if (err)
-				pr_debug("%s: failed to get %s: (%d)\n",
+				dev_dbg(chan->device->dev,
+					"%s: failed to get %s: (%d)\n",
 					__func__, dma_chan_name(chan), err);
 		}
 	}
@@ -862,12 +866,12 @@ static bool device_has_all_tx_types(struct dma_device *device)
 		return false;
 	#endif
 
-	#if defined(CONFIG_ASYNC_MEMCPY) || defined(CONFIG_ASYNC_MEMCPY_MODULE)
+	#if IS_ENABLED(CONFIG_ASYNC_MEMCPY)
 	if (!dma_has_cap(DMA_MEMCPY, device->cap_mask))
 		return false;
 	#endif
 
-	#if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE)
+	#if IS_ENABLED(CONFIG_ASYNC_XOR)
 	if (!dma_has_cap(DMA_XOR, device->cap_mask))
 		return false;
 
@@ -877,7 +881,7 @@ static bool device_has_all_tx_types(struct dma_device *device)
 	#endif
 	#endif
 
-	#if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE)
+	#if IS_ENABLED(CONFIG_ASYNC_PQ)
 	if (!dma_has_cap(DMA_PQ, device->cap_mask))
 		return false;
 
@@ -1222,7 +1226,8 @@ dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
 
 	while (tx->cookie == -EBUSY) {
 		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
-			pr_err("%s timeout waiting for descriptor submission\n",
+			dev_err(tx->chan->device->dev,
+				"%s timeout waiting for descriptor submission\n",
 				__func__);
 			return DMA_ERROR;
 		}

drivers/dma/dw/pci.c

@@ -17,8 +17,8 @@
 
 static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 {
+	const struct dw_dma_platform_data *pdata = (void *)pid->driver_data;
 	struct dw_dma_chip *chip;
-	struct dw_dma_platform_data *pdata = (void *)pid->driver_data;
 	int ret;
 
 	ret = pcim_enable_device(pdev);
@@ -49,8 +49,9 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 	chip->dev = &pdev->dev;
 	chip->regs = pcim_iomap_table(pdev)[0];
 	chip->irq = pdev->irq;
+	chip->pdata = pdata;
 
-	ret = dw_dma_probe(chip, pdata);
+	ret = dw_dma_probe(chip);
 	if (ret)
 		return ret;
 

drivers/dma/dw/platform.c

@@ -42,13 +42,13 @@ static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
 
 	slave.src_id = dma_spec->args[0];
 	slave.dst_id = dma_spec->args[0];
-	slave.src_master = dma_spec->args[1];
-	slave.dst_master = dma_spec->args[2];
+	slave.m_master = dma_spec->args[1];
+	slave.p_master = dma_spec->args[2];
 
 	if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS ||
 		    slave.dst_id >= DW_DMA_MAX_NR_REQUESTS ||
-		    slave.src_master >= dw->nr_masters ||
-		    slave.dst_master >= dw->nr_masters))
+		    slave.m_master >= dw->pdata->nr_masters ||
+		    slave.p_master >= dw->pdata->nr_masters))
 		return NULL;
 
 	dma_cap_zero(cap);
@@ -66,8 +66,8 @@ static bool dw_dma_acpi_filter(struct dma_chan *chan, void *param)
 		.dma_dev = dma_spec->dev,
 		.src_id = dma_spec->slave_id,
 		.dst_id = dma_spec->slave_id,
-		.src_master = 1,
-		.dst_master = 0,
+		.m_master = 0,
+		.p_master = 1,
 	};
 
 	return dw_dma_filter(chan, &slave);
@@ -103,6 +103,7 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct dw_dma_platform_data *pdata;
 	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS];
+	u32 nr_masters;
 	u32 nr_channels;
 
 	if (!np) {
@@ -110,6 +111,11 @@ dw_dma_parse_dt(struct platform_device *pdev)
 		return NULL;
 	}
 
+	if (of_property_read_u32(np, "dma-masters", &nr_masters))
+		return NULL;
+	if (nr_masters < 1 || nr_masters > DW_DMA_MAX_NR_MASTERS)
+		return NULL;
+
 	if (of_property_read_u32(np, "dma-channels", &nr_channels))
 		return NULL;
 
@@ -117,6 +123,7 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	if (!pdata)
 		return NULL;
 
+	pdata->nr_masters = nr_masters;
 	pdata->nr_channels = nr_channels;
 
 	if (of_property_read_bool(np, "is_private"))
@@ -131,17 +138,13 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	if (!of_property_read_u32(np, "block_size", &tmp))
 		pdata->block_size = tmp;
 
-	if (!of_property_read_u32(np, "dma-masters", &tmp)) {
-		if (tmp > DW_DMA_MAX_NR_MASTERS)
-			return NULL;
-
-		pdata->nr_masters = tmp;
-	}
-
-	if (!of_property_read_u32_array(np, "data_width", arr,
-				pdata->nr_masters))
-		for (tmp = 0; tmp < pdata->nr_masters; tmp++)
+	if (!of_property_read_u32_array(np, "data-width", arr, nr_masters)) {
+		for (tmp = 0; tmp < nr_masters; tmp++)
 			pdata->data_width[tmp] = arr[tmp];
+	} else if (!of_property_read_u32_array(np, "data_width", arr, nr_masters)) {
+		for (tmp = 0; tmp < nr_masters; tmp++)
+			pdata->data_width[tmp] = BIT(arr[tmp] & 0x07);
+	}
 
 	return pdata;
 }
@@ -158,7 +161,7 @@ static int dw_probe(struct platform_device *pdev)
 	struct dw_dma_chip *chip;
 	struct device *dev = &pdev->dev;
 	struct resource *mem;
-	struct dw_dma_platform_data *pdata;
+	const struct dw_dma_platform_data *pdata;
 	int err;
 
 	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
@@ -183,6 +186,7 @@ static int dw_probe(struct platform_device *pdev)
 		pdata = dw_dma_parse_dt(pdev);
 
 	chip->dev = dev;
+	chip->pdata = pdata;
 
 	chip->clk = devm_clk_get(chip->dev, "hclk");
 	if (IS_ERR(chip->clk))
@@ -193,7 +197,7 @@ static int dw_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(&pdev->dev);
 
-	err = dw_dma_probe(chip, pdata);
+	err = dw_dma_probe(chip);
 	if (err)
 		goto err_dw_dma_probe;
 

drivers/dma/dw/regs.h

@@ -114,10 +114,6 @@ struct dw_dma_regs {
 #define dma_writel_native writel
 #endif
 
-/* To access the registers in early stage of probe */
-#define dma_read_byaddr(addr, name) \
-	dma_readl_native((addr) + offsetof(struct dw_dma_regs, name))
-
 /* Bitfields in DW_PARAMS */
 #define DW_PARAMS_NR_CHAN	8		/* number of channels */
 #define DW_PARAMS_NR_MASTER	11		/* number of AHB masters */
@@ -143,6 +139,10 @@ enum dw_dma_msize {
 	DW_DMA_MSIZE_256,
 };
 
+/* Bitfields in LLP */
+#define DWC_LLP_LMS(x)		((x) & 3)	/* list master select */
+#define DWC_LLP_LOC(x)		((x) & ~3)	/* next lli */
+
 /* Bitfields in CTL_LO */
 #define DWC_CTLL_INT_EN		(1 << 0)	/* irqs enabled? */
 #define DWC_CTLL_DST_WIDTH(n)	((n)<<1)	/* bytes per element */
@@ -216,6 +216,8 @@ enum dw_dma_msize {
 enum dw_dmac_flags {
 	DW_DMA_IS_CYCLIC = 0,
 	DW_DMA_IS_SOFT_LLP = 1,
+	DW_DMA_IS_PAUSED = 2,
+	DW_DMA_IS_INITIALIZED = 3,
 };
 
 struct dw_dma_chan {
@@ -224,8 +226,6 @@ struct dw_dma_chan {
 	u8				mask;
 	u8				priority;
 	enum dma_transfer_direction	direction;
-	bool				paused;
-	bool				initialized;
 
 	/* software emulation of the LLP transfers */
 	struct list_head	*tx_node_active;
@@ -236,8 +236,6 @@ struct dw_dma_chan {
 	unsigned long		flags;
 	struct list_head	active_list;
 	struct list_head	queue;
-	struct list_head	free_list;
-	u32			residue;
 	struct dw_cyclic_desc	*cdesc;
 
 	unsigned int		descs_allocated;
@@ -249,8 +247,8 @@ struct dw_dma_chan {
 	/* custom slave configuration */
 	u8			src_id;
 	u8			dst_id;
-	u8			src_master;
-	u8			dst_master;
+	u8			m_master;
+	u8			p_master;
 
 	/* configuration passed via .device_config */
 	struct dma_slave_config dma_sconfig;
@@ -283,9 +281,8 @@ struct dw_dma {
 	u8			all_chan_mask;
 	u8			in_use;
 
-	/* hardware configuration */
-	unsigned char		nr_masters;
-	unsigned char		data_width[DW_DMA_MAX_NR_MASTERS];
+	/* platform data */
+	struct dw_dma_platform_data	*pdata;
 };
 
 static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
@@ -308,32 +305,51 @@ static inline struct dw_dma *to_dw_dma(struct dma_device *ddev)
 	return container_of(ddev, struct dw_dma, dma);
 }
 
+#ifdef CONFIG_DW_DMAC_BIG_ENDIAN_IO
+typedef __be32 __dw32;
+#else
+typedef __le32 __dw32;
+#endif
+
 /* LLI == Linked List Item; a.k.a. DMA block descriptor */
 struct dw_lli {
 	/* values that are not changed by hardware */
-	u32		sar;
-	u32		dar;
-	u32		llp;		/* chain to next lli */
-	u32		ctllo;
+	__dw32		sar;
+	__dw32		dar;
+	__dw32		llp;		/* chain to next lli */
+	__dw32		ctllo;
 	/* values that may get written back: */
-	u32		ctlhi;
+	__dw32		ctlhi;
 	/* sstat and dstat can snapshot peripheral register state.
 	 * silicon config may discard either or both...
 	 */
-	u32		sstat;
-	u32		dstat;
+	__dw32		sstat;
+	__dw32		dstat;
 };
 
 struct dw_desc {
 	/* FIRST values the hardware uses */
 	struct dw_lli			lli;
 
+#ifdef CONFIG_DW_DMAC_BIG_ENDIAN_IO
+#define lli_set(d, reg, v)		((d)->lli.reg |= cpu_to_be32(v))
+#define lli_clear(d, reg, v)		((d)->lli.reg &= ~cpu_to_be32(v))
+#define lli_read(d, reg)		be32_to_cpu((d)->lli.reg)
+#define lli_write(d, reg, v)		((d)->lli.reg = cpu_to_be32(v))
+#else
+#define lli_set(d, reg, v)		((d)->lli.reg |= cpu_to_le32(v))
+#define lli_clear(d, reg, v)		((d)->lli.reg &= ~cpu_to_le32(v))
+#define lli_read(d, reg)		le32_to_cpu((d)->lli.reg)
+#define lli_write(d, reg, v)		((d)->lli.reg = cpu_to_le32(v))
+#endif
+
 	/* THEN values for driver housekeeping */
 	struct list_head		desc_node;
 	struct list_head		tx_list;
 	struct dma_async_tx_descriptor	txd;
 	size_t				len;
 	size_t				total_len;
+	u32				residue;
 };
 
 #define to_dw_desc(h)	list_entry(h, struct dw_desc, desc_node)

drivers/dma/edma.c

@@ -1537,8 +1537,17 @@ static irqreturn_t dma_ccerr_handler(int irq, void *data)
 
 	dev_vdbg(ecc->dev, "dma_ccerr_handler\n");
 
-	if (!edma_error_pending(ecc))
+	if (!edma_error_pending(ecc)) {
+		/*
+		 * The registers indicate no pending error event but the irq
+		 * handler has been called.
+		 * Ask eDMA to re-evaluate the error registers.
+		 */
+		dev_err(ecc->dev, "%s: Error interrupt without error event!\n",
+			__func__);
+		edma_write(ecc, EDMA_EEVAL, 1);
 		return IRQ_NONE;
+	}
 
 	while (1) {
 		/* Event missed register(s) */

drivers/dma/fsldma.c

@@ -462,13 +462,12 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(struct fsldma_chan *chan)
 	struct fsl_desc_sw *desc;
 	dma_addr_t pdesc;
 
-	desc = dma_pool_alloc(chan->desc_pool, GFP_ATOMIC, &pdesc);
+	desc = dma_pool_zalloc(chan->desc_pool, GFP_ATOMIC, &pdesc);
 	if (!desc) {
 		chan_dbg(chan, "out of memory for link descriptor\n");
 		return NULL;
 	}
 
-	memset(desc, 0, sizeof(*desc));
 	INIT_LIST_HEAD(&desc->tx_list);
 	dma_async_tx_descriptor_init(&desc->async_tx, &chan->common);
 	desc->async_tx.tx_submit = fsl_dma_tx_submit;

drivers/dma/hsu/hsu.c

@@ -77,8 +77,8 @@ static void hsu_dma_chan_start(struct hsu_dma_chan *hsuc)
 	hsu_chan_writel(hsuc, HSU_CH_MTSR, mtsr);
 
 	/* Set descriptors */
-	count = (desc->nents - desc->active) % HSU_DMA_CHAN_NR_DESC;
-	for (i = 0; i < count; i++) {
+	count = desc->nents - desc->active;
+	for (i = 0; i < count && i < HSU_DMA_CHAN_NR_DESC; i++) {
 		hsu_chan_writel(hsuc, HSU_CH_DxSAR(i), desc->sg[i].addr);
 		hsu_chan_writel(hsuc, HSU_CH_DxTSR(i), desc->sg[i].len);
 
@@ -160,7 +160,7 @@ irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr)
 		return IRQ_NONE;
 
 	/* Timeout IRQ, need wait some time, see Errata 2 */
-	if (hsuc->direction == DMA_DEV_TO_MEM && (sr & HSU_CH_SR_DESCTO_ANY))
+	if (sr & HSU_CH_SR_DESCTO_ANY)
 		udelay(2);
 
 	sr &= ~HSU_CH_SR_DESCTO_ANY;
@@ -420,6 +420,8 @@ int hsu_dma_probe(struct hsu_dma_chip *chip)
 
 	hsu->dma.dev = chip->dev;
 
+	dma_set_max_seg_size(hsu->dma.dev, HSU_CH_DxTSR_MASK);
+
 	ret = dma_async_device_register(&hsu->dma);
 	if (ret)
 		return ret;

drivers/dma/hsu/hsu.h

@@ -58,6 +58,10 @@
 #define HSU_CH_DCR_CHEI		BIT(23)
 #define HSU_CH_DCR_CHTOI(x)	BIT(24 + (x))
 
+/* Bits in HSU_CH_DxTSR */
+#define HSU_CH_DxTSR_MASK	GENMASK(15, 0)
+#define HSU_CH_DxTSR_TSR(x)	((x) & HSU_CH_DxTSR_MASK)
+
 struct hsu_dma_sg {
 	dma_addr_t addr;
 	unsigned int len;

drivers/dma/ioat/init.c

@@ -690,12 +690,11 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	/* allocate a completion writeback area */
 	/* doing 2 32bit writes to mmio since 1 64b write doesn't work */
 	ioat_chan->completion =
-		dma_pool_alloc(ioat_chan->ioat_dma->completion_pool,
+		dma_pool_zalloc(ioat_chan->ioat_dma->completion_pool,
 				GFP_KERNEL, &ioat_chan->completion_dma);
 	if (!ioat_chan->completion)
 		return -ENOMEM;
 
-	memset(ioat_chan->completion, 0, sizeof(*ioat_chan->completion));
 	writel(((u64)ioat_chan->completion_dma) & 0x00000000FFFFFFFF,
 	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
 	writel(((u64)ioat_chan->completion_dma) >> 32,
@@ -1074,6 +1073,7 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca)
 	struct ioatdma_chan *ioat_chan;
 	bool is_raid_device = false;
 	int err;
+	u16 val16;
 
 	dma = &ioat_dma->dma_dev;
 	dma->device_prep_dma_memcpy = ioat_dma_prep_memcpy_lock;
@@ -1173,6 +1173,17 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca)
 	if (dca)
 		ioat_dma->dca = ioat_dca_init(pdev, ioat_dma->reg_base);
 
+	/* disable relaxed ordering */
+	err = pcie_capability_read_word(pdev, IOAT_DEVCTRL_OFFSET, &val16);
+	if (err)
+		return err;
+
+	/* clear relaxed ordering enable */
+	val16 &= ~IOAT_DEVCTRL_ROE;
+	err = pcie_capability_write_word(pdev, IOAT_DEVCTRL_OFFSET, val16);
+	if (err)
+		return err;
+
 	return 0;
 }
 

drivers/dma/ioat/registers.h

@@ -26,6 +26,13 @@
 #define IOAT_PCI_CHANERR_INT_OFFSET		0x180
 #define IOAT_PCI_CHANERRMASK_INT_OFFSET		0x184
 
+/* PCIe config registers */
+
+/* EXPCAPID + N */
+#define IOAT_DEVCTRL_OFFSET			0x8
+/* relaxed ordering enable */
+#define IOAT_DEVCTRL_ROE			0x10
+
 /* MMIO Device Registers */
 #define IOAT_CHANCNT_OFFSET			0x00	/*  8-bit */
 

drivers/dma/mmp_pdma.c

@@ -364,13 +364,12 @@ mmp_pdma_alloc_descriptor(struct mmp_pdma_chan *chan)
 	struct mmp_pdma_desc_sw *desc;
 	dma_addr_t pdesc;
 
-	desc = dma_pool_alloc(chan->desc_pool, GFP_ATOMIC, &pdesc);
+	desc = dma_pool_zalloc(chan->desc_pool, GFP_ATOMIC, &pdesc);
 	if (!desc) {
 		dev_err(chan->dev, "out of memory for link descriptor\n");
 		return NULL;
 	}
 
-	memset(desc, 0, sizeof(*desc));
 	INIT_LIST_HEAD(&desc->tx_list);
 	dma_async_tx_descriptor_init(&desc->async_tx, &chan->chan);
 	/* each desc has submit */

drivers/dma/mpc512x_dma.c

@@ -3,6 +3,7 @@
  * Copyright (C) Semihalf 2009
  * Copyright (C) Ilya Yanok, Emcraft Systems 2010
  * Copyright (C) Alexander Popov, Promcontroller 2014
+ * Copyright (C) Mario Six, Guntermann & Drunck GmbH, 2016
  *
  * Written by Piotr Ziecik <kosmo@semihalf.com>. Hardware description
  * (defines, structures and comments) was taken from MPC5121 DMA driver
@@ -26,18 +27,19 @@
  */
 
 /*
- * MPC512x and MPC8308 DMA driver. It supports
- * memory to memory data transfers (tested using dmatest module) and
- * data transfers between memory and peripheral I/O memory
- * by means of slave scatter/gather with these limitations:
- *  - chunked transfers (described by s/g lists with more than one item)
- *     are refused as long as proper support for scatter/gather is missing;
- *  - transfers on MPC8308 always start from software as this SoC appears
- *     not to have external request lines for peripheral flow control;
- *  - only peripheral devices with 4-byte FIFO access register are supported;
- *  - minimal memory <-> I/O memory transfer chunk is 4 bytes and consequently
- *     source and destination addresses must be 4-byte aligned
- *     and transfer size must be aligned on (4 * maxburst) boundary;
+ * MPC512x and MPC8308 DMA driver. It supports memory to memory data transfers
+ * (tested using dmatest module) and data transfers between memory and
+ * peripheral I/O memory by means of slave scatter/gather with these
+ * limitations:
+ *  - chunked transfers (described by s/g lists with more than one item) are
+ *     refused as long as proper support for scatter/gather is missing
+ *  - transfers on MPC8308 always start from software as this SoC does not have
+ *     external request lines for peripheral flow control
+ *  - memory <-> I/O memory transfer chunks of sizes of 1, 2, 4, 16 (for
+ *     MPC512x), and 32 bytes are supported, and, consequently, source
+ *     addresses and destination addresses must be aligned accordingly;
+ *     furthermore, for MPC512x SoCs, the transfer size must be aligned on
+ *     (chunk size * maxburst)
  */
 
 #include <linux/module.h>
@@ -213,8 +215,10 @@ struct mpc_dma_chan {
 	/* Settings for access to peripheral FIFO */
 	dma_addr_t			src_per_paddr;
 	u32				src_tcd_nunits;
+	u8				swidth;
 	dma_addr_t			dst_per_paddr;
 	u32				dst_tcd_nunits;
+	u8				dwidth;
 
 	/* Lock for this structure */
 	spinlock_t			lock;
@@ -247,6 +251,7 @@ static inline struct mpc_dma_chan *dma_chan_to_mpc_dma_chan(struct dma_chan *c)
 static inline struct mpc_dma *dma_chan_to_mpc_dma(struct dma_chan *c)
 {
 	struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(c);
+
 	return container_of(mchan, struct mpc_dma, channels[c->chan_id]);
 }
 
@@ -446,20 +451,15 @@ static void mpc_dma_tasklet(unsigned long data)
 		if (es & MPC_DMA_DMAES_SAE)
 			dev_err(mdma->dma.dev, "- Source Address Error\n");
 		if (es & MPC_DMA_DMAES_SOE)
-			dev_err(mdma->dma.dev, "- Source Offset"
-						" Configuration Error\n");
+			dev_err(mdma->dma.dev, "- Source Offset Configuration Error\n");
 		if (es & MPC_DMA_DMAES_DAE)
-			dev_err(mdma->dma.dev, "- Destination Address"
-								" Error\n");
+			dev_err(mdma->dma.dev, "- Destination Address Error\n");
 		if (es & MPC_DMA_DMAES_DOE)
-			dev_err(mdma->dma.dev, "- Destination Offset"
-						" Configuration Error\n");
+			dev_err(mdma->dma.dev, "- Destination Offset Configuration Error\n");
 		if (es & MPC_DMA_DMAES_NCE)
-			dev_err(mdma->dma.dev, "- NBytes/Citter"
-						" Configuration Error\n");
+			dev_err(mdma->dma.dev, "- NBytes/Citter Configuration Error\n");
 		if (es & MPC_DMA_DMAES_SGE)
-			dev_err(mdma->dma.dev, "- Scatter/Gather"
-						" Configuration Error\n");
+			dev_err(mdma->dma.dev, "- Scatter/Gather Configuration Error\n");
 		if (es & MPC_DMA_DMAES_SBE)
 			dev_err(mdma->dma.dev, "- Source Bus Error\n");
 		if (es & MPC_DMA_DMAES_DBE)
@@ -518,8 +518,8 @@ static int mpc_dma_alloc_chan_resources(struct dma_chan *chan)
 	for (i = 0; i < MPC_DMA_DESCRIPTORS; i++) {
 		mdesc = kzalloc(sizeof(struct mpc_dma_desc), GFP_KERNEL);
 		if (!mdesc) {
-			dev_notice(mdma->dma.dev, "Memory allocation error. "
-					"Allocated only %u descriptors\n", i);
+			dev_notice(mdma->dma.dev,
+				"Memory allocation error. Allocated only %u descriptors\n", i);
 			break;
 		}
 
@@ -684,6 +684,15 @@ mpc_dma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst, dma_addr_t src,
 	return &mdesc->desc;
 }
 
+inline u8 buswidth_to_dmatsize(u8 buswidth)
+{
+	u8 res;
+
+	for (res = 0; buswidth > 1; buswidth /= 2)
+		res++;
+	return res;
+}
+
 static struct dma_async_tx_descriptor *
 mpc_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
@@ -742,26 +751,40 @@ mpc_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 		memset(tcd, 0, sizeof(struct mpc_dma_tcd));
 
-		if (!IS_ALIGNED(sg_dma_address(sg), 4))
-			goto err_prep;
-
 		if (direction == DMA_DEV_TO_MEM) {
 			tcd->saddr = per_paddr;
 			tcd->daddr = sg_dma_address(sg);
+
+			if (!IS_ALIGNED(sg_dma_address(sg), mchan->dwidth))
+				goto err_prep;
+
 			tcd->soff = 0;
-			tcd->doff = 4;
+			tcd->doff = mchan->dwidth;
 		} else {
 			tcd->saddr = sg_dma_address(sg);
 			tcd->daddr = per_paddr;
-			tcd->soff = 4;
+
+			if (!IS_ALIGNED(sg_dma_address(sg), mchan->swidth))
+				goto err_prep;
+
+			tcd->soff = mchan->swidth;
 			tcd->doff = 0;
 		}
 
-		tcd->ssize = MPC_DMA_TSIZE_4;
-		tcd->dsize = MPC_DMA_TSIZE_4;
+		tcd->ssize = buswidth_to_dmatsize(mchan->swidth);
+		tcd->dsize = buswidth_to_dmatsize(mchan->dwidth);
 
+		if (mdma->is_mpc8308) {
+			tcd->nbytes = sg_dma_len(sg);
+			if (!IS_ALIGNED(tcd->nbytes, mchan->swidth))
+				goto err_prep;
+
+			/* No major loops for MPC8303 */
+			tcd->biter = 1;
+			tcd->citer = 1;
+		} else {
 			len = sg_dma_len(sg);
-		tcd->nbytes = tcd_nunits * 4;
+			tcd->nbytes = tcd_nunits * tcd->ssize;
 			if (!IS_ALIGNED(len, tcd->nbytes))
 				goto err_prep;
 
@@ -775,6 +798,7 @@ mpc_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 			tcd->biter_linkch = iter >> 9;
 			tcd->citer = tcd->biter;
 			tcd->citer_linkch = tcd->biter_linkch;
+		}
 
 		tcd->e_sg = 0;
 		tcd->d_req = 1;
@@ -796,40 +820,62 @@ mpc_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	return NULL;
 }
 
+inline bool is_buswidth_valid(u8 buswidth, bool is_mpc8308)
+{
+	switch (buswidth) {
+	case 16:
+		if (is_mpc8308)
+			return false;
+	case 1:
+	case 2:
+	case 4:
+	case 32:
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
 static int mpc_dma_device_config(struct dma_chan *chan,
 				 struct dma_slave_config *cfg)
 {
 	struct mpc_dma_chan *mchan = dma_chan_to_mpc_dma_chan(chan);
+	struct mpc_dma *mdma = dma_chan_to_mpc_dma(&mchan->chan);
 	unsigned long flags;
 
 	/*
 	 * Software constraints:
-	 *  - only transfers between a peripheral device and
-	 *     memory are supported;
-	 *  - only peripheral devices with 4-byte FIFO access register
-	 *     are supported;
-	 *  - minimal transfer chunk is 4 bytes and consequently
-	 *     source and destination addresses must be 4-byte aligned
-	 *     and transfer size must be aligned on (4 * maxburst)
-	 *     boundary;
-	 *  - during the transfer RAM address is being incremented by
-	 *     the size of minimal transfer chunk;
-	 *  - peripheral port's address is constant during the transfer.
+	 *  - only transfers between a peripheral device and memory are
+	 *     supported
+	 *  - transfer chunk sizes of 1, 2, 4, 16 (for MPC512x), and 32 bytes
+	 *     are supported, and, consequently, source addresses and
+	 *     destination addresses; must be aligned accordingly; furthermore,
+	 *     for MPC512x SoCs, the transfer size must be aligned on (chunk
+	 *     size * maxburst)
+	 *  - during the transfer, the RAM address is incremented by the size
+	 *     of transfer chunk
+	 *  - the peripheral port's address is constant during the transfer.
 	 */
 
-	if (cfg->src_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES ||
-	    cfg->dst_addr_width != DMA_SLAVE_BUSWIDTH_4_BYTES ||
-	    !IS_ALIGNED(cfg->src_addr, 4) ||
-	    !IS_ALIGNED(cfg->dst_addr, 4)) {
+	if (!IS_ALIGNED(cfg->src_addr, cfg->src_addr_width) ||
+	    !IS_ALIGNED(cfg->dst_addr, cfg->dst_addr_width)) {
 		return -EINVAL;
 	}
 
+	if (!is_buswidth_valid(cfg->src_addr_width, mdma->is_mpc8308) ||
+	    !is_buswidth_valid(cfg->dst_addr_width, mdma->is_mpc8308))
+		return -EINVAL;
+
 	spin_lock_irqsave(&mchan->lock, flags);
 
 	mchan->src_per_paddr = cfg->src_addr;
 	mchan->src_tcd_nunits = cfg->src_maxburst;
+	mchan->swidth = cfg->src_addr_width;
 	mchan->dst_per_paddr = cfg->dst_addr;
 	mchan->dst_tcd_nunits = cfg->dst_maxburst;
+	mchan->dwidth = cfg->dst_addr_width;
 
 	/* Apply defaults */
 	if (mchan->src_tcd_nunits == 0)
@@ -875,7 +921,6 @@ static int mpc_dma_probe(struct platform_device *op)
 
 	mdma = devm_kzalloc(dev, sizeof(struct mpc_dma), GFP_KERNEL);
 	if (!mdma) {
-		dev_err(dev, "Memory exhausted!\n");
 		retval = -ENOMEM;
 		goto err;
 	}
@@ -999,7 +1044,8 @@ static int mpc_dma_probe(struct platform_device *op)
 		out_be32(&mdma->regs->dmaerrl, 0xFFFF);
 	} else {
 		out_be32(&mdma->regs->dmacr, MPC_DMA_DMACR_EDCG |
-					MPC_DMA_DMACR_ERGA | MPC_DMA_DMACR_ERCA);
+						MPC_DMA_DMACR_ERGA |
+						MPC_DMA_DMACR_ERCA);
 
 		/* Disable hardware DMA requests */
 		out_be32(&mdma->regs->dmaerqh, 0);

drivers/dma/mv_xor.c

@@ -31,6 +31,12 @@
 #include "dmaengine.h"
 #include "mv_xor.h"
 
+enum mv_xor_type {
+	XOR_ORION,
+	XOR_ARMADA_38X,
+	XOR_ARMADA_37XX,
+};
+
 enum mv_xor_mode {
 	XOR_MODE_IN_REG,
 	XOR_MODE_IN_DESC,
@@ -477,7 +483,7 @@ mv_xor_prep_dma_xor(struct dma_chan *chan, dma_addr_t dest, dma_addr_t *src,
 	BUG_ON(len > MV_XOR_MAX_BYTE_COUNT);
 
 	dev_dbg(mv_chan_to_devp(mv_chan),
-		"%s src_cnt: %d len: %u dest %pad flags: %ld\n",
+		"%s src_cnt: %d len: %zu dest %pad flags: %ld\n",
 		__func__, src_cnt, len, &dest, flags);
 
 	sw_desc = mv_chan_alloc_slot(mv_chan);
@@ -933,7 +939,7 @@ static int mv_xor_channel_remove(struct mv_xor_chan *mv_chan)
 static struct mv_xor_chan *
 mv_xor_channel_add(struct mv_xor_device *xordev,
 		   struct platform_device *pdev,
-		   int idx, dma_cap_mask_t cap_mask, int irq, int op_in_desc)
+		   int idx, dma_cap_mask_t cap_mask, int irq)
 {
 	int ret = 0;
 	struct mv_xor_chan *mv_chan;
@@ -945,7 +951,10 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 
 	mv_chan->idx = idx;
 	mv_chan->irq = irq;
-	mv_chan->op_in_desc = op_in_desc;
+	if (xordev->xor_type == XOR_ORION)
+		mv_chan->op_in_desc = XOR_MODE_IN_REG;
+	else
+		mv_chan->op_in_desc = XOR_MODE_IN_DESC;
 
 	dma_dev = &mv_chan->dmadev;
 
@@ -1085,6 +1094,33 @@ mv_xor_conf_mbus_windows(struct mv_xor_device *xordev,
 	writel(0, base + WINDOW_OVERRIDE_CTRL(1));
 }
 
+static void
+mv_xor_conf_mbus_windows_a3700(struct mv_xor_device *xordev)
+{
+	void __iomem *base = xordev->xor_high_base;
+	u32 win_enable = 0;
+	int i;
+
+	for (i = 0; i < 8; i++) {
+		writel(0, base + WINDOW_BASE(i));
+		writel(0, base + WINDOW_SIZE(i));
+		if (i < 4)
+			writel(0, base + WINDOW_REMAP_HIGH(i));
+	}
+	/*
+	 * For Armada3700 open default 4GB Mbus window. The dram
+	 * related configuration are done at AXIS level.
+	 */
+	writel(0xffff0000, base + WINDOW_SIZE(0));
+	win_enable |= 1;
+	win_enable |= 3 << 16;
+
+	writel(win_enable, base + WINDOW_BAR_ENABLE(0));
+	writel(win_enable, base + WINDOW_BAR_ENABLE(1));
+	writel(0, base + WINDOW_OVERRIDE_CTRL(0));
+	writel(0, base + WINDOW_OVERRIDE_CTRL(1));
+}
+
 /*
  * Since this XOR driver is basically used only for RAID5, we don't
  * need to care about synchronizing ->suspend with DMA activity,
@@ -1129,6 +1165,11 @@ static int mv_xor_resume(struct platform_device *dev)
 			       XOR_INTR_MASK(mv_chan));
 	}
 
+	if (xordev->xor_type == XOR_ARMADA_37XX) {
+		mv_xor_conf_mbus_windows_a3700(xordev);
+		return 0;
+	}
+
 	dram = mv_mbus_dram_info();
 	if (dram)
 		mv_xor_conf_mbus_windows(xordev, dram);
@@ -1137,8 +1178,9 @@ static int mv_xor_resume(struct platform_device *dev)
 }
 
 static const struct of_device_id mv_xor_dt_ids[] = {
-	{ .compatible = "marvell,orion-xor", .data = (void *)XOR_MODE_IN_REG },
-	{ .compatible = "marvell,armada-380-xor", .data = (void *)XOR_MODE_IN_DESC },
+	{ .compatible = "marvell,orion-xor", .data = (void *)XOR_ORION },
+	{ .compatible = "marvell,armada-380-xor", .data = (void *)XOR_ARMADA_38X },
+	{ .compatible = "marvell,armada-3700-xor", .data = (void *)XOR_ARMADA_37XX },
 	{},
 };
 
@@ -1152,7 +1194,6 @@ static int mv_xor_probe(struct platform_device *pdev)
 	struct resource *res;
 	unsigned int max_engines, max_channels;
 	int i, ret;
-	int op_in_desc;
 
 	dev_notice(&pdev->dev, "Marvell shared XOR driver\n");
 
@@ -1180,12 +1221,30 @@ static int mv_xor_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, xordev);
 
+
+	/*
+	 * We need to know which type of XOR device we use before
+	 * setting up. In non-dt case it can only be the legacy one.
+	 */
+	xordev->xor_type = XOR_ORION;
+	if (pdev->dev.of_node) {
+		const struct of_device_id *of_id =
+			of_match_device(mv_xor_dt_ids,
+					&pdev->dev);
+
+		xordev->xor_type = (uintptr_t)of_id->data;
+	}
+
 	/*
 	 * (Re-)program MBUS remapping windows if we are asked to.
 	 */
+	if (xordev->xor_type == XOR_ARMADA_37XX) {
+		mv_xor_conf_mbus_windows_a3700(xordev);
+	} else {
 		dram = mv_mbus_dram_info();
 		if (dram)
 			mv_xor_conf_mbus_windows(xordev, dram);
+	}
 
 	/* Not all platforms can gate the clock, so it is not
 	 * an error if the clock does not exists.
@@ -1199,9 +1258,13 @@ static int mv_xor_probe(struct platform_device *pdev)
 	 * order for async_tx to perform well. So we limit the number
 	 * of engines and channels so that we take into account this
 	 * constraint. Note that we also want to use channels from
-	 * separate engines when possible.
+	 * separate engines when possible.  For dual-CPU Armada 3700
+	 * SoC with single XOR engine allow using its both channels.
 	 */
 	max_engines = num_present_cpus();
+	if (xordev->xor_type == XOR_ARMADA_37XX)
+		max_channels =	num_present_cpus();
+	else
 		max_channels = min_t(unsigned int,
 				     MV_XOR_MAX_CHANNELS,
 				     DIV_ROUND_UP(num_present_cpus(), 2));
@@ -1212,15 +1275,11 @@ static int mv_xor_probe(struct platform_device *pdev)
 	if (pdev->dev.of_node) {
 		struct device_node *np;
 		int i = 0;
-		const struct of_device_id *of_id =
-			of_match_device(mv_xor_dt_ids,
-					&pdev->dev);
 
 		for_each_child_of_node(pdev->dev.of_node, np) {
 			struct mv_xor_chan *chan;
 			dma_cap_mask_t cap_mask;
 			int irq;
-			op_in_desc = (int)of_id->data;
 
 			if (i >= max_channels)
 				continue;
@@ -1237,7 +1296,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 			}
 
 			chan = mv_xor_channel_add(xordev, pdev, i,
-						  cap_mask, irq, op_in_desc);
+						  cap_mask, irq);
 			if (IS_ERR(chan)) {
 				ret = PTR_ERR(chan);
 				irq_dispose_mapping(irq);
@@ -1266,8 +1325,7 @@ static int mv_xor_probe(struct platform_device *pdev)
 			}
 
 			chan = mv_xor_channel_add(xordev, pdev, i,
-						  cd->cap_mask, irq,
-						  XOR_MODE_IN_REG);
+						  cd->cap_mask, irq);
 			if (IS_ERR(chan)) {
 				ret = PTR_ERR(chan);
 				goto err_channel_add;

drivers/dma/mv_xor.h

@@ -85,6 +85,7 @@ struct mv_xor_device {
 	void __iomem	     *xor_high_base;
 	struct clk	     *clk;
 	struct mv_xor_chan   *channels[MV_XOR_MAX_CHANNELS];
+	int		     xor_type;
 };
 
 /**

drivers/dma/of-dma.c

@@ -240,8 +240,9 @@ struct dma_chan *of_dma_request_slave_channel(struct device_node *np,
 	struct of_phandle_args	dma_spec;
 	struct of_dma		*ofdma;
 	struct dma_chan		*chan;
-	int			count, i;
+	int			count, i, start;
 	int			ret_no_channel = -ENODEV;
+	static atomic_t		last_index;
 
 	if (!np || !name) {
 		pr_err("%s: not enough information provided\n", __func__);
@@ -259,8 +260,15 @@ struct dma_chan *of_dma_request_slave_channel(struct device_node *np,
 		return ERR_PTR(-ENODEV);
 	}
 
+	/*
+	 * approximate an average distribution across multiple
+	 * entries with the same name
+	 */
+	start = atomic_inc_return(&last_index);
 	for (i = 0; i < count; i++) {
-		if (of_dma_match_channel(np, name, i, &dma_spec))
+		if (of_dma_match_channel(np, name,
+					 (i + start) % count,
+					 &dma_spec))
 			continue;
 
 		mutex_lock(&of_dma_lock);

drivers/dma/pxa_dma.c

@@ -117,6 +117,7 @@ struct pxad_chan {
 	/* protected by vc->lock */
 	struct pxad_phy		*phy;
 	struct dma_pool		*desc_pool;	/* Descriptors pool */
+	dma_cookie_t		bus_error;
 };
 
 struct pxad_device {
@@ -563,6 +564,7 @@ static void pxad_launch_chan(struct pxad_chan *chan,
 			return;
 		}
 	}
+	chan->bus_error = 0;
 
 	/*
 	 * Program the descriptor's address into the DMA controller,
@@ -666,6 +668,7 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id)
 	struct virt_dma_desc *vd, *tmp;
 	unsigned int dcsr;
 	unsigned long flags;
+	dma_cookie_t last_started = 0;
 
 	BUG_ON(!chan);
 
@@ -678,6 +681,7 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id)
 		dev_dbg(&chan->vc.chan.dev->device,
 			"%s(): checking txd %p[%x]: completed=%d\n",
 			__func__, vd, vd->tx.cookie, is_desc_completed(vd));
+		last_started = vd->tx.cookie;
 		if (to_pxad_sw_desc(vd)->cyclic) {
 			vchan_cyclic_callback(vd);
 			break;
@@ -690,7 +694,12 @@ static irqreturn_t pxad_chan_handler(int irq, void *dev_id)
 		}
 	}
 
-	if (dcsr & PXA_DCSR_STOPSTATE) {
+	if (dcsr & PXA_DCSR_BUSERR) {
+		chan->bus_error = last_started;
+		phy_disable(phy);
+	}
+
+	if (!chan->bus_error && dcsr & PXA_DCSR_STOPSTATE) {
 		dev_dbg(&chan->vc.chan.dev->device,
 		"%s(): channel stopped, submitted_empty=%d issued_empty=%d",
 			__func__,
@@ -1249,6 +1258,9 @@ static enum dma_status pxad_tx_status(struct dma_chan *dchan,
 	struct pxad_chan *chan = to_pxad_chan(dchan);
 	enum dma_status ret;
 
+	if (cookie == chan->bus_error)
+		return DMA_ERROR;
+
 	ret = dma_cookie_status(dchan, cookie, txstate);
 	if (likely(txstate && (ret != DMA_ERROR)))
 		dma_set_residue(txstate, pxad_residue(chan, cookie));
@@ -1321,7 +1333,7 @@ static int pxad_init_phys(struct platform_device *op,
 	return 0;
 }
 
-static const struct of_device_id const pxad_dt_ids[] = {
+static const struct of_device_id pxad_dt_ids[] = {
 	{ .compatible = "marvell,pdma-1.0", },
 	{}
 };

drivers/dma/qcom/Makefile

 obj-$(CONFIG_QCOM_BAM_DMA) += bam_dma.o
 obj-$(CONFIG_QCOM_HIDMA_MGMT) += hdma_mgmt.o
 hdma_mgmt-objs	 := hidma_mgmt.o hidma_mgmt_sys.o
+obj-$(CONFIG_QCOM_HIDMA) +=  hdma.o
+hdma-objs        := hidma_ll.o hidma.o hidma_dbg.o

drivers/dma/qcom/bam_dma.c

@@ -342,7 +342,7 @@ static const struct reg_offset_data bam_v1_7_reg_info[] = {
 
 #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)
+#define BAM_FIFO_SIZE	(SZ_32K - 8)
 
 struct bam_chan {
 	struct virt_dma_chan vc;
@@ -387,6 +387,7 @@ struct bam_device {
 
 	/* execution environment ID, from DT */
 	u32 ee;
+	bool controlled_remotely;
 
 	const struct reg_offset_data *layout;
 
@@ -458,7 +459,7 @@ static void bam_chan_init_hw(struct bam_chan *bchan,
 	 */
 	writel_relaxed(ALIGN(bchan->fifo_phys, sizeof(struct bam_desc_hw)),
 			bam_addr(bdev, bchan->id, BAM_P_DESC_FIFO_ADDR));
-	writel_relaxed(BAM_DESC_FIFO_SIZE,
+	writel_relaxed(BAM_FIFO_SIZE,
 			bam_addr(bdev, bchan->id, BAM_P_FIFO_SIZES));
 
 	/* enable the per pipe interrupts, enable EOT, ERR, and INT irqs */
@@ -604,7 +605,7 @@ static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan,
 
 	/* 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);
+		num_alloc += DIV_ROUND_UP(sg_dma_len(sg), BAM_FIFO_SIZE);
 
 	/* allocate enough room to accomodate the number of entries */
 	async_desc = kzalloc(sizeof(*async_desc) +
@@ -635,10 +636,10 @@ static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan,
 			desc->addr = cpu_to_le32(sg_dma_address(sg) +
 						 curr_offset);
 
-			if (remainder > BAM_MAX_DATA_SIZE) {
-				desc->size = cpu_to_le16(BAM_MAX_DATA_SIZE);
-				remainder -= BAM_MAX_DATA_SIZE;
-				curr_offset += BAM_MAX_DATA_SIZE;
+			if (remainder > BAM_FIFO_SIZE) {
+				desc->size = cpu_to_le16(BAM_FIFO_SIZE);
+				remainder -= BAM_FIFO_SIZE;
+				curr_offset += BAM_FIFO_SIZE;
 			} else {
 				desc->size = cpu_to_le16(remainder);
 				remainder = 0;
@@ -801,13 +802,17 @@ static irqreturn_t bam_dma_irq(int irq, void *data)
 	if (srcs & P_IRQ)
 		tasklet_schedule(&bdev->task);
 
-	if (srcs & BAM_IRQ)
+	if (srcs & BAM_IRQ) {
 		clr_mask = readl_relaxed(bam_addr(bdev, 0, BAM_IRQ_STTS));
 
-	/* don't allow reorder of the various accesses to the BAM registers */
+		/*
+		 * don't allow reorder of the various accesses to the BAM
+		 * registers
+		 */
 		mb();
 
 		writel_relaxed(clr_mask, bam_addr(bdev, 0, BAM_IRQ_CLR));
+	}
 
 	return IRQ_HANDLED;
 }
@@ -1038,6 +1043,9 @@ static int bam_init(struct bam_device *bdev)
 	val = readl_relaxed(bam_addr(bdev, 0, BAM_NUM_PIPES));
 	bdev->num_channels = val & BAM_NUM_PIPES_MASK;
 
+	if (bdev->controlled_remotely)
+		return 0;
+
 	/* s/w reset bam */
 	/* after reset all pipes are disabled and idle */
 	val = readl_relaxed(bam_addr(bdev, 0, BAM_CTRL));
@@ -1125,6 +1133,9 @@ static int bam_dma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	bdev->controlled_remotely = of_property_read_bool(pdev->dev.of_node,
+						"qcom,controlled-remotely");
+
 	bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk");
 	if (IS_ERR(bdev->bamclk))
 		return PTR_ERR(bdev->bamclk);
@@ -1163,7 +1174,7 @@ static int bam_dma_probe(struct platform_device *pdev)
 	/* 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);
+	ret = dma_set_max_seg_size(bdev->common.dev, BAM_FIFO_SIZE);
 	if (ret) {
 		dev_err(bdev->dev, "cannot set maximum segment size\n");
 		goto err_bam_channel_exit;
@@ -1234,6 +1245,9 @@ static int bam_dma_remove(struct platform_device *pdev)
 		bam_dma_terminate_all(&bdev->channels[i].vc.chan);
 		tasklet_kill(&bdev->channels[i].vc.task);
 
+		if (!bdev->channels[i].fifo_virt)
+			continue;
+
 		dma_free_wc(bdev->dev, BAM_DESC_FIFO_SIZE,
 			    bdev->channels[i].fifo_virt,
 			    bdev->channels[i].fifo_phys);

drivers/dma/qcom/hidma.c

 /*
  * Qualcomm Technologies HIDMA DMA engine interface
  *
- * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2015-2016, 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
@@ -404,7 +404,7 @@ static int hidma_terminate_channel(struct dma_chan *chan)
 	spin_unlock_irqrestore(&mchan->lock, irqflags);
 
 	/* this suspends the existing transfer */
-	rc = hidma_ll_pause(dmadev->lldev);
+	rc = hidma_ll_disable(dmadev->lldev);
 	if (rc) {
 		dev_err(dmadev->ddev.dev, "channel did not pause\n");
 		goto out;
@@ -427,7 +427,7 @@ static int hidma_terminate_channel(struct dma_chan *chan)
 		list_move(&mdesc->node, &mchan->free);
 	}
 
-	rc = hidma_ll_resume(dmadev->lldev);
+	rc = hidma_ll_enable(dmadev->lldev);
 out:
 	pm_runtime_mark_last_busy(dmadev->ddev.dev);
 	pm_runtime_put_autosuspend(dmadev->ddev.dev);
@@ -488,7 +488,7 @@ static int hidma_pause(struct dma_chan *chan)
 	dmadev = to_hidma_dev(mchan->chan.device);
 	if (!mchan->paused) {
 		pm_runtime_get_sync(dmadev->ddev.dev);
-		if (hidma_ll_pause(dmadev->lldev))
+		if (hidma_ll_disable(dmadev->lldev))
 			dev_warn(dmadev->ddev.dev, "channel did not stop\n");
 		mchan->paused = true;
 		pm_runtime_mark_last_busy(dmadev->ddev.dev);
@@ -507,7 +507,7 @@ static int hidma_resume(struct dma_chan *chan)
 	dmadev = to_hidma_dev(mchan->chan.device);
 	if (mchan->paused) {
 		pm_runtime_get_sync(dmadev->ddev.dev);
-		rc = hidma_ll_resume(dmadev->lldev);
+		rc = hidma_ll_enable(dmadev->lldev);
 		if (!rc)
 			mchan->paused = false;
 		else
@@ -530,6 +530,43 @@ static irqreturn_t hidma_chirq_handler(int chirq, void *arg)
 	return hidma_ll_inthandler(chirq, lldev);
 }
 
+static ssize_t hidma_show_values(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct hidma_dev *mdev = platform_get_drvdata(pdev);
+
+	buf[0] = 0;
+
+	if (strcmp(attr->attr.name, "chid") == 0)
+		sprintf(buf, "%d\n", mdev->chidx);
+
+	return strlen(buf);
+}
+
+static int hidma_create_sysfs_entry(struct hidma_dev *dev, char *name,
+				    int mode)
+{
+	struct device_attribute *attrs;
+	char *name_copy;
+
+	attrs = devm_kmalloc(dev->ddev.dev, sizeof(struct device_attribute),
+			     GFP_KERNEL);
+	if (!attrs)
+		return -ENOMEM;
+
+	name_copy = devm_kstrdup(dev->ddev.dev, name, GFP_KERNEL);
+	if (!name_copy)
+		return -ENOMEM;
+
+	attrs->attr.name = name_copy;
+	attrs->attr.mode = mode;
+	attrs->show = hidma_show_values;
+	sysfs_attr_init(&attrs->attr);
+
+	return device_create_file(dev->ddev.dev, attrs);
+}
+
 static int hidma_probe(struct platform_device *pdev)
 {
 	struct hidma_dev *dmadev;
@@ -644,6 +681,8 @@ static int hidma_probe(struct platform_device *pdev)
 
 	dmadev->irq = chirq;
 	tasklet_init(&dmadev->task, hidma_issue_task, (unsigned long)dmadev);
+	hidma_debug_init(dmadev);
+	hidma_create_sysfs_entry(dmadev, "chid", S_IRUGO);
 	dev_info(&pdev->dev, "HI-DMA engine driver registration complete\n");
 	platform_set_drvdata(pdev, dmadev);
 	pm_runtime_mark_last_busy(dmadev->ddev.dev);
@@ -651,6 +690,7 @@ static int hidma_probe(struct platform_device *pdev)
 	return 0;
 
 uninit:
+	hidma_debug_uninit(dmadev);
 	hidma_ll_uninit(dmadev->lldev);
 dmafree:
 	if (dmadev)
@@ -668,6 +708,7 @@ static int hidma_remove(struct platform_device *pdev)
 	pm_runtime_get_sync(dmadev->ddev.dev);
 	dma_async_device_unregister(&dmadev->ddev);
 	devm_free_irq(dmadev->ddev.dev, dmadev->irq, dmadev->lldev);
+	hidma_debug_uninit(dmadev);
 	hidma_ll_uninit(dmadev->lldev);
 	hidma_free(dmadev);
 
@@ -689,7 +730,6 @@ static const struct of_device_id hidma_match[] = {
 	{.compatible = "qcom,hidma-1.0",},
 	{},
 };
-
 MODULE_DEVICE_TABLE(of, hidma_match);
 
 static struct platform_driver hidma_driver = {

drivers/dma/qcom/hidma.h

 /*
  * Qualcomm Technologies HIDMA data structures
  *
- * Copyright (c) 2014, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2014-2016, 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
@@ -20,32 +20,29 @@
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
 
-#define TRE_SIZE			32 /* each TRE is 32 bytes  */
-#define TRE_CFG_IDX			0
-#define TRE_LEN_IDX			1
-#define TRE_SRC_LOW_IDX		2
-#define TRE_SRC_HI_IDX			3
-#define TRE_DEST_LOW_IDX		4
-#define TRE_DEST_HI_IDX		5
-
-struct hidma_tx_status {
-	u8 err_info;			/* error record in this transfer    */
-	u8 err_code;			/* completion code		    */
-};
+#define HIDMA_TRE_SIZE			32 /* each TRE is 32 bytes  */
+#define HIDMA_TRE_CFG_IDX		0
+#define HIDMA_TRE_LEN_IDX		1
+#define HIDMA_TRE_SRC_LOW_IDX		2
+#define HIDMA_TRE_SRC_HI_IDX		3
+#define HIDMA_TRE_DEST_LOW_IDX		4
+#define HIDMA_TRE_DEST_HI_IDX		5
 
 struct hidma_tre {
 	atomic_t allocated;		/* if this channel is allocated	    */
 	bool queued;			/* flag whether this is pending     */
 	u16 status;			/* status			    */
-	u32 chidx;			/* index of the tre		    */
+	u32 idx;			/* index of the tre		    */
 	u32 dma_sig;			/* signature of the tre		    */
 	const char *dev_name;		/* name of the device		    */
 	void (*callback)(void *data);	/* requester callback		    */
 	void *data;			/* Data associated with this channel*/
 	struct hidma_lldev *lldev;	/* lldma device pointer		    */
-	u32 tre_local[TRE_SIZE / sizeof(u32) + 1]; /* TRE local copy        */
+	u32 tre_local[HIDMA_TRE_SIZE / sizeof(u32) + 1]; /* TRE local copy  */
 	u32 tre_index;			/* the offset where this was written*/
 	u32 int_flags;			/* interrupt flags		    */
+	u8 err_info;			/* error record in this transfer    */
+	u8 err_code;			/* completion code		    */
 };
 
 struct hidma_lldev {
@@ -61,22 +58,21 @@ struct hidma_lldev {
 	void __iomem *evca;		/* Event Channel address          */
 	struct hidma_tre
 		**pending_tre_list;	/* Pointers to pending TREs	  */
-	struct hidma_tx_status
-		*tx_status_list;	/* Pointers to pending TREs status*/
 	s32 pending_tre_count;		/* Number of TREs pending	  */
 
 	void *tre_ring;			/* TRE ring			  */
-	dma_addr_t tre_ring_handle;	/* TRE ring to be shared with HW  */
+	dma_addr_t tre_dma;		/* TRE ring to be shared with HW  */
 	u32 tre_ring_size;		/* Byte size of the ring	  */
 	u32 tre_processed_off;		/* last processed TRE		  */
 
 	void *evre_ring;		/* EVRE ring			   */
-	dma_addr_t evre_ring_handle;	/* EVRE ring to be shared with HW  */
+	dma_addr_t evre_dma;		/* EVRE ring to be shared with HW  */
 	u32 evre_ring_size;		/* Byte size of the ring	   */
 	u32 evre_processed_off;		/* last processed EVRE		   */
 
 	u32 tre_write_offset;           /* TRE write location              */
 	struct tasklet_struct task;	/* task delivering notifications   */
+	struct tasklet_struct rst_task;	/* task to reset HW                */
 	DECLARE_KFIFO_PTR(handoff_fifo,
 		struct hidma_tre *);    /* pending TREs FIFO               */
 };
@@ -145,8 +141,8 @@ enum dma_status hidma_ll_status(struct hidma_lldev *llhndl, u32 tre_ch);
 bool hidma_ll_isenabled(struct hidma_lldev *llhndl);
 void hidma_ll_queue_request(struct hidma_lldev *llhndl, u32 tre_ch);
 void hidma_ll_start(struct hidma_lldev *llhndl);
-int hidma_ll_pause(struct hidma_lldev *llhndl);
-int hidma_ll_resume(struct hidma_lldev *llhndl);
+int hidma_ll_disable(struct hidma_lldev *lldev);
+int hidma_ll_enable(struct hidma_lldev *llhndl);
 void hidma_ll_set_transfer_params(struct hidma_lldev *llhndl, u32 tre_ch,
 	dma_addr_t src, dma_addr_t dest, u32 len, u32 flags);
 int hidma_ll_setup(struct hidma_lldev *lldev);
@@ -157,4 +153,6 @@ int hidma_ll_uninit(struct hidma_lldev *llhndl);
 irqreturn_t hidma_ll_inthandler(int irq, void *arg);
 void hidma_cleanup_pending_tre(struct hidma_lldev *llhndl, u8 err_info,
 				u8 err_code);
+int hidma_debug_init(struct hidma_dev *dmadev);
+void hidma_debug_uninit(struct hidma_dev *dmadev);
 #endif

drivers/dma/qcom/hidma_dbg.c

+/*
+ * Qualcomm Technologies HIDMA debug file
+ *
+ * Copyright (c) 2015-2016, 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.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/pm_runtime.h>
+
+#include "hidma.h"
+
+static void hidma_ll_chstats(struct seq_file *s, void *llhndl, u32 tre_ch)
+{
+	struct hidma_lldev *lldev = llhndl;
+	struct hidma_tre *tre;
+	u32 length;
+	dma_addr_t src_start;
+	dma_addr_t dest_start;
+	u32 *tre_local;
+
+	if (tre_ch >= lldev->nr_tres) {
+		dev_err(lldev->dev, "invalid TRE number in chstats:%d", tre_ch);
+		return;
+	}
+	tre = &lldev->trepool[tre_ch];
+	seq_printf(s, "------Channel %d -----\n", tre_ch);
+	seq_printf(s, "allocated=%d\n", atomic_read(&tre->allocated));
+	seq_printf(s, "queued = 0x%x\n", tre->queued);
+	seq_printf(s, "err_info = 0x%x\n", tre->err_info);
+	seq_printf(s, "err_code = 0x%x\n", tre->err_code);
+	seq_printf(s, "status = 0x%x\n", tre->status);
+	seq_printf(s, "idx = 0x%x\n", tre->idx);
+	seq_printf(s, "dma_sig = 0x%x\n", tre->dma_sig);
+	seq_printf(s, "dev_name=%s\n", tre->dev_name);
+	seq_printf(s, "callback=%p\n", tre->callback);
+	seq_printf(s, "data=%p\n", tre->data);
+	seq_printf(s, "tre_index = 0x%x\n", tre->tre_index);
+
+	tre_local = &tre->tre_local[0];
+	src_start = tre_local[HIDMA_TRE_SRC_LOW_IDX];
+	src_start = ((u64) (tre_local[HIDMA_TRE_SRC_HI_IDX]) << 32) + src_start;
+	dest_start = tre_local[HIDMA_TRE_DEST_LOW_IDX];
+	dest_start += ((u64) (tre_local[HIDMA_TRE_DEST_HI_IDX]) << 32);
+	length = tre_local[HIDMA_TRE_LEN_IDX];
+
+	seq_printf(s, "src=%pap\n", &src_start);
+	seq_printf(s, "dest=%pap\n", &dest_start);
+	seq_printf(s, "length = 0x%x\n", length);
+}
+
+static void hidma_ll_devstats(struct seq_file *s, void *llhndl)
+{
+	struct hidma_lldev *lldev = llhndl;
+
+	seq_puts(s, "------Device -----\n");
+	seq_printf(s, "lldev init = 0x%x\n", lldev->initialized);
+	seq_printf(s, "trch_state = 0x%x\n", lldev->trch_state);
+	seq_printf(s, "evch_state = 0x%x\n", lldev->evch_state);
+	seq_printf(s, "chidx = 0x%x\n", lldev->chidx);
+	seq_printf(s, "nr_tres = 0x%x\n", lldev->nr_tres);
+	seq_printf(s, "trca=%p\n", lldev->trca);
+	seq_printf(s, "tre_ring=%p\n", lldev->tre_ring);
+	seq_printf(s, "tre_ring_handle=%pap\n", &lldev->tre_dma);
+	seq_printf(s, "tre_ring_size = 0x%x\n", lldev->tre_ring_size);
+	seq_printf(s, "tre_processed_off = 0x%x\n", lldev->tre_processed_off);
+	seq_printf(s, "pending_tre_count=%d\n", lldev->pending_tre_count);
+	seq_printf(s, "evca=%p\n", lldev->evca);
+	seq_printf(s, "evre_ring=%p\n", lldev->evre_ring);
+	seq_printf(s, "evre_ring_handle=%pap\n", &lldev->evre_dma);
+	seq_printf(s, "evre_ring_size = 0x%x\n", lldev->evre_ring_size);
+	seq_printf(s, "evre_processed_off = 0x%x\n", lldev->evre_processed_off);
+	seq_printf(s, "tre_write_offset = 0x%x\n", lldev->tre_write_offset);
+}
+
+/*
+ * hidma_chan_stats: display HIDMA channel statistics
+ *
+ * Display the statistics for the current HIDMA virtual channel device.
+ */
+static int hidma_chan_stats(struct seq_file *s, void *unused)
+{
+	struct hidma_chan *mchan = s->private;
+	struct hidma_desc *mdesc;
+	struct hidma_dev *dmadev = mchan->dmadev;
+
+	pm_runtime_get_sync(dmadev->ddev.dev);
+	seq_printf(s, "paused=%u\n", mchan->paused);
+	seq_printf(s, "dma_sig=%u\n", mchan->dma_sig);
+	seq_puts(s, "prepared\n");
+	list_for_each_entry(mdesc, &mchan->prepared, node)
+		hidma_ll_chstats(s, mchan->dmadev->lldev, mdesc->tre_ch);
+
+	seq_puts(s, "active\n");
+	list_for_each_entry(mdesc, &mchan->active, node)
+		hidma_ll_chstats(s, mchan->dmadev->lldev, mdesc->tre_ch);
+
+	seq_puts(s, "completed\n");
+	list_for_each_entry(mdesc, &mchan->completed, node)
+		hidma_ll_chstats(s, mchan->dmadev->lldev, mdesc->tre_ch);
+
+	hidma_ll_devstats(s, mchan->dmadev->lldev);
+	pm_runtime_mark_last_busy(dmadev->ddev.dev);
+	pm_runtime_put_autosuspend(dmadev->ddev.dev);
+	return 0;
+}
+
+/*
+ * hidma_dma_info: display HIDMA device info
+ *
+ * Display the info for the current HIDMA device.
+ */
+static int hidma_dma_info(struct seq_file *s, void *unused)
+{
+	struct hidma_dev *dmadev = s->private;
+	resource_size_t sz;
+
+	seq_printf(s, "nr_descriptors=%d\n", dmadev->nr_descriptors);
+	seq_printf(s, "dev_trca=%p\n", &dmadev->dev_trca);
+	seq_printf(s, "dev_trca_phys=%pa\n", &dmadev->trca_resource->start);
+	sz = resource_size(dmadev->trca_resource);
+	seq_printf(s, "dev_trca_size=%pa\n", &sz);
+	seq_printf(s, "dev_evca=%p\n", &dmadev->dev_evca);
+	seq_printf(s, "dev_evca_phys=%pa\n", &dmadev->evca_resource->start);
+	sz = resource_size(dmadev->evca_resource);
+	seq_printf(s, "dev_evca_size=%pa\n", &sz);
+	return 0;
+}
+
+static int hidma_chan_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hidma_chan_stats, inode->i_private);
+}
+
+static int hidma_dma_info_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hidma_dma_info, inode->i_private);
+}
+
+static const struct file_operations hidma_chan_fops = {
+	.open = hidma_chan_stats_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static const struct file_operations hidma_dma_fops = {
+	.open = hidma_dma_info_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+void hidma_debug_uninit(struct hidma_dev *dmadev)
+{
+	debugfs_remove_recursive(dmadev->debugfs);
+	debugfs_remove_recursive(dmadev->stats);
+}
+
+int hidma_debug_init(struct hidma_dev *dmadev)
+{
+	int rc = 0;
+	int chidx = 0;
+	struct list_head *position = NULL;
+
+	dmadev->debugfs = debugfs_create_dir(dev_name(dmadev->ddev.dev), NULL);
+	if (!dmadev->debugfs) {
+		rc = -ENODEV;
+		return rc;
+	}
+
+	/* walk through the virtual channel list */
+	list_for_each(position, &dmadev->ddev.channels) {
+		struct hidma_chan *chan;
+
+		chan = list_entry(position, struct hidma_chan,
+				  chan.device_node);
+		sprintf(chan->dbg_name, "chan%d", chidx);
+		chan->debugfs = debugfs_create_dir(chan->dbg_name,
+						   dmadev->debugfs);
+		if (!chan->debugfs) {
+			rc = -ENOMEM;
+			goto cleanup;
+		}
+		chan->stats = debugfs_create_file("stats", S_IRUGO,
+						  chan->debugfs, chan,
+						  &hidma_chan_fops);
+		if (!chan->stats) {
+			rc = -ENOMEM;
+			goto cleanup;
+		}
+		chidx++;
+	}
+
+	dmadev->stats = debugfs_create_file("stats", S_IRUGO,
+					    dmadev->debugfs, dmadev,
+					    &hidma_dma_fops);
+	if (!dmadev->stats) {
+		rc = -ENOMEM;
+		goto cleanup;
+	}
+
+	return 0;
+cleanup:
+	hidma_debug_uninit(dmadev);
+	return rc;
+}

drivers/dma/qcom/hidma_mgmt.c

 /*
  * Qualcomm Technologies HIDMA DMA engine Management interface
  *
- * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2015-2016, 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
@@ -17,13 +17,14 @@
 #include <linux/acpi.h>
 #include <linux/of.h>
 #include <linux/property.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 #include <linux/pm_runtime.h>
 #include <linux/bitops.h>
+#include <linux/dma-mapping.h>
 
 #include "hidma_mgmt.h"
 
@@ -298,5 +299,109 @@ static struct platform_driver hidma_mgmt_driver = {
 	},
 };
 
-module_platform_driver(hidma_mgmt_driver);
+#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ)
+static int object_counter;
+
+static int __init hidma_mgmt_of_populate_channels(struct device_node *np)
+{
+	struct platform_device *pdev_parent = of_find_device_by_node(np);
+	struct platform_device_info pdevinfo;
+	struct of_phandle_args out_irq;
+	struct device_node *child;
+	struct resource *res;
+	const __be32 *cell;
+	int ret = 0, size, i, num;
+	u64 addr, addr_size;
+
+	for_each_available_child_of_node(np, child) {
+		struct resource *res_iter;
+		struct platform_device *new_pdev;
+
+		cell = of_get_property(child, "reg", &size);
+		if (!cell) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		size /= sizeof(*cell);
+		num = size /
+			(of_n_addr_cells(child) + of_n_size_cells(child)) + 1;
+
+		/* allocate a resource array */
+		res = kcalloc(num, sizeof(*res), GFP_KERNEL);
+		if (!res) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		/* read each reg value */
+		i = 0;
+		res_iter = res;
+		while (i < size) {
+			addr = of_read_number(&cell[i],
+					      of_n_addr_cells(child));
+			i += of_n_addr_cells(child);
+
+			addr_size = of_read_number(&cell[i],
+						   of_n_size_cells(child));
+			i += of_n_size_cells(child);
+
+			res_iter->start = addr;
+			res_iter->end = res_iter->start + addr_size - 1;
+			res_iter->flags = IORESOURCE_MEM;
+			res_iter++;
+		}
+
+		ret = of_irq_parse_one(child, 0, &out_irq);
+		if (ret)
+			goto out;
+
+		res_iter->start = irq_create_of_mapping(&out_irq);
+		res_iter->name = "hidma event irq";
+		res_iter->flags = IORESOURCE_IRQ;
+
+		memset(&pdevinfo, 0, sizeof(pdevinfo));
+		pdevinfo.fwnode = &child->fwnode;
+		pdevinfo.parent = pdev_parent ? &pdev_parent->dev : NULL;
+		pdevinfo.name = child->name;
+		pdevinfo.id = object_counter++;
+		pdevinfo.res = res;
+		pdevinfo.num_res = num;
+		pdevinfo.data = NULL;
+		pdevinfo.size_data = 0;
+		pdevinfo.dma_mask = DMA_BIT_MASK(64);
+		new_pdev = platform_device_register_full(&pdevinfo);
+		if (!new_pdev) {
+			ret = -ENODEV;
+			goto out;
+		}
+		of_dma_configure(&new_pdev->dev, child);
+
+		kfree(res);
+		res = NULL;
+	}
+out:
+	kfree(res);
+
+	return ret;
+}
+#endif
+
+static int __init hidma_mgmt_init(void)
+{
+#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ)
+	struct device_node *child;
+
+	for (child = of_find_matching_node(NULL, hidma_mgmt_match); child;
+	     child = of_find_matching_node(child, hidma_mgmt_match)) {
+		/* device tree based firmware here */
+		hidma_mgmt_of_populate_channels(child);
+		of_node_put(child);
+	}
+#endif
+	platform_driver_register(&hidma_mgmt_driver);
+
+	return 0;
+}
+module_init(hidma_mgmt_init);
 MODULE_LICENSE("GPL v2");

drivers/dma/tegra20-apb-dma.c

@@ -54,6 +54,7 @@
 #define TEGRA_APBDMA_CSR_ONCE			BIT(27)
 #define TEGRA_APBDMA_CSR_FLOW			BIT(21)
 #define TEGRA_APBDMA_CSR_REQ_SEL_SHIFT		16
+#define TEGRA_APBDMA_CSR_REQ_SEL_MASK		0x1F
 #define TEGRA_APBDMA_CSR_WCOUNT_MASK		0xFFFC
 
 /* STATUS register */
@@ -114,6 +115,8 @@
 /* Channel base address offset from APBDMA base address */
 #define TEGRA_APBDMA_CHANNEL_BASE_ADD_OFFSET	0x1000
 
+#define TEGRA_APBDMA_SLAVE_ID_INVALID	(TEGRA_APBDMA_CSR_REQ_SEL_MASK + 1)
+
 struct tegra_dma;
 
 /*
@@ -353,8 +356,11 @@ static int tegra_dma_slave_config(struct dma_chan *dc,
 	}
 
 	memcpy(&tdc->dma_sconfig, sconfig, sizeof(*sconfig));
-	if (!tdc->slave_id)
+	if (tdc->slave_id == TEGRA_APBDMA_SLAVE_ID_INVALID) {
+		if (sconfig->slave_id > TEGRA_APBDMA_CSR_REQ_SEL_MASK)
+			return -EINVAL;
 		tdc->slave_id = sconfig->slave_id;
+	}
 	tdc->config_init = true;
 	return 0;
 }
@@ -1236,7 +1242,7 @@ static void tegra_dma_free_chan_resources(struct dma_chan *dc)
 	}
 	pm_runtime_put(tdma->dev);
 
-	tdc->slave_id = 0;
+	tdc->slave_id = TEGRA_APBDMA_SLAVE_ID_INVALID;
 }
 
 static struct dma_chan *tegra_dma_of_xlate(struct of_phandle_args *dma_spec,
@@ -1246,6 +1252,11 @@ static struct dma_chan *tegra_dma_of_xlate(struct of_phandle_args *dma_spec,
 	struct dma_chan *chan;
 	struct tegra_dma_channel *tdc;
 
+	if (dma_spec->args[0] > TEGRA_APBDMA_CSR_REQ_SEL_MASK) {
+		dev_err(tdma->dev, "Invalid slave id: %d\n", dma_spec->args[0]);
+		return NULL;
+	}
+
 	chan = dma_get_any_slave_channel(&tdma->dma_dev);
 	if (!chan)
 		return NULL;
@@ -1389,6 +1400,7 @@ static int tegra_dma_probe(struct platform_device *pdev)
 				&tdma->dma_dev.channels);
 		tdc->tdma = tdma;
 		tdc->id = i;
+		tdc->slave_id = TEGRA_APBDMA_SLAVE_ID_INVALID;
 
 		tasklet_init(&tdc->tasklet, tegra_dma_tasklet,
 				(unsigned long)tdc);

drivers/spi/spi-pxa2xx-pci.c

@@ -144,16 +144,16 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
 		struct dw_dma_slave *slave = c->tx_param;
 
 		slave->dma_dev = &dma_dev->dev;
-		slave->src_master = 1;
-		slave->dst_master = 0;
+		slave->m_master = 0;
+		slave->p_master = 1;
 	}
 
 	if (c->rx_param) {
 		struct dw_dma_slave *slave = c->rx_param;
 
 		slave->dma_dev = &dma_dev->dev;
-		slave->src_master = 1;
-		slave->dst_master = 0;
+		slave->m_master = 0;
+		slave->p_master = 1;
 	}
 
 	spi_pdata.dma_filter = lpss_dma_filter;

drivers/tty/serial/8250/8250_pci.c

@@ -1454,13 +1454,13 @@ byt_serial_setup(struct serial_private *priv,
 		return -EINVAL;
 	}
 
-	rx_param->src_master = 1;
-	rx_param->dst_master = 0;
+	rx_param->m_master = 0;
+	rx_param->p_master = 1;
 
 	dma->rxconf.src_maxburst = 16;
 
-	tx_param->src_master = 1;
-	tx_param->dst_master = 0;
+	tx_param->m_master = 0;
+	tx_param->p_master = 1;
 
 	dma->txconf.dst_maxburst = 16;
 

include/linux/amba/pl08x.h

@@ -86,7 +86,7 @@ struct pl08x_channel_data {
  * @mem_buses: buses which memory can be accessed from: PL08X_AHB1 | PL08X_AHB2
  */
 struct pl08x_platform_data {
-	const struct pl08x_channel_data *slave_channels;
+	struct pl08x_channel_data *slave_channels;
 	unsigned int num_slave_channels;
 	struct pl08x_channel_data memcpy_channel;
 	int (*get_xfer_signal)(const struct pl08x_channel_data *);

include/linux/dma/dw.h

@@ -27,6 +27,7 @@ struct dw_dma;
  * @regs:		memory mapped I/O space
  * @clk:		hclk clock
  * @dw:			struct dw_dma that is filed by dw_dma_probe()
+ * @pdata:		pointer to platform data
  */
 struct dw_dma_chip {
 	struct device	*dev;
@@ -34,10 +35,12 @@ struct dw_dma_chip {
 	void __iomem	*regs;
 	struct clk	*clk;
 	struct dw_dma	*dw;
+
+	const struct dw_dma_platform_data	*pdata;
 };
 
 /* Export to the platform drivers */
-int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata);
+int dw_dma_probe(struct dw_dma_chip *chip);
 int dw_dma_remove(struct dw_dma_chip *chip);
 
 /* DMA API extensions */

include/linux/dma/xilinx_dma.h

@@ -41,6 +41,20 @@ struct xilinx_vdma_config {
 	int ext_fsync;
 };
 
+/**
+ * enum xdma_ip_type: DMA IP type.
+ *
+ * XDMA_TYPE_AXIDMA: Axi dma ip.
+ * XDMA_TYPE_CDMA: Axi cdma ip.
+ * XDMA_TYPE_VDMA: Axi vdma ip.
+ *
+ */
+enum xdma_ip_type {
+	XDMA_TYPE_AXIDMA = 0,
+	XDMA_TYPE_CDMA,
+	XDMA_TYPE_VDMA,
+};
+
 int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
 					struct xilinx_vdma_config *cfg);
 

include/linux/platform_data/dma-dw.h

@@ -21,15 +21,15 @@
  * @dma_dev:	required DMA master device
  * @src_id:	src request line
  * @dst_id:	dst request line
- * @src_master: src master for transfers on allocated channel.
- * @dst_master: dest master for transfers on allocated channel.
+ * @m_master:	memory master for transfers on allocated channel
+ * @p_master:	peripheral master for transfers on allocated channel
  */
 struct dw_dma_slave {
 	struct device		*dma_dev;
 	u8			src_id;
 	u8			dst_id;
-	u8			src_master;
-	u8			dst_master;
+	u8			m_master;
+	u8			p_master;
 };
 
 /**
@@ -43,7 +43,7 @@ struct dw_dma_slave {
  * @block_size: Maximum block size supported by the controller
  * @nr_masters: Number of AHB masters supported by the controller
  * @data_width: Maximum data width supported by hardware per AHB master
- *		(0 - 8bits, 1 - 16bits, ..., 5 - 256bits)
+ *		(in bytes, power of 2)
  */
 struct dw_dma_platform_data {
 	unsigned int	nr_channels;
@@ -55,7 +55,7 @@ struct dw_dma_platform_data {
 #define CHAN_PRIORITY_ASCENDING		0	/* chan0 highest */
 #define CHAN_PRIORITY_DESCENDING	1	/* chan7 highest */
 	unsigned char	chan_priority;
-	unsigned short	block_size;
+	unsigned int	block_size;
 	unsigned char	nr_masters;
 	unsigned char	data_width[DW_DMA_MAX_NR_MASTERS];
 };