Merge remote-tracking branch 'slave-dma/next'

40 files changed, 3321 insertions, 301 deletions

diff --git a/Documentation/devicetree/bindings/dma/fsl-qdma.txt b/Documentation/devicetree/bindings/dma/fsl-qdma.txt
new file mode 100644
index 000000000000..6a0ff9059e72
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/fsl-qdma.txt
@@ -0,0 +1,57 @@
+NXP Layerscape SoC qDMA Controller
+==================================
+
+This device follows the generic DMA bindings defined in dma/dma.txt.
+
+Required properties:
+
+- compatible:		Must be one of
+			 "fsl,ls1021a-qdma": for LS1021A Board
+			 "fsl,ls1043a-qdma": for ls1043A Board
+			 "fsl,ls1046a-qdma": for ls1046A Board
+- reg:			Should contain the register's base address and length.
+- interrupts:		Should contain a reference to the interrupt used by this
+			device.
+- interrupt-names:	Should contain interrupt names:
+			 "qdma-queue0": the block0 interrupt
+			 "qdma-queue1": the block1 interrupt
+			 "qdma-queue2": the block2 interrupt
+			 "qdma-queue3": the block3 interrupt
+			 "qdma-error":  the error interrupt
+- fsl,dma-queues:	Should contain number of queues supported.
+- dma-channels:	Number of DMA channels supported
+- block-number:	the virtual block number
+- block-offset:	the offset of different virtual block
+- status-sizes:	status queue size of per virtual block
+- queue-sizes:		command queue size of per virtual block, the size number
+			based on queues
+
+Optional properties:
+
+- dma-channels:		Number of DMA channels supported by the controller.
+- big-endian:		If present registers and hardware scatter/gather descriptors
+			of the qDMA are implemented in big endian mode, otherwise in little
+			mode.
+
+Examples:
+
+	qdma: dma-controller@8390000 {
+			compatible = "fsl,ls1021a-qdma";
+			reg = <0x0 0x8388000 0x0 0x1000>, /* Controller regs */
+			      <0x0 0x8389000 0x0 0x1000>, /* Status regs */
+			      <0x0 0x838a000 0x0 0x2000>; /* Block regs */
+			interrupts = <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "qdma-error",
+				"qdma-queue0", "qdma-queue1";
+			dma-channels = <8>;
+			block-number = <2>;
+			block-offset = <0x1000>;
+			fsl,dma-queues = <2>;
+			status-sizes = <64>;
+			queue-sizes = <64 64>;
+			big-endian;
+		};
+
+DMA clients must use the format described in dma/dma.txt file.
diff --git a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
index a5a7c3f5a1e3..cdf32b2b77f9 100644
--- a/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/renesas,rcar-dmac.txt
@@ -1,6 +1,6 @@
 * Renesas R-Car (RZ/G) DMA Controller Device Tree bindings
 
-Renesas R-Car Generation 2 SoCs have multiple multi-channel DMA
+Renesas R-Car (Gen 2/3) and RZ/G SoCs have multiple multi-channel DMA
 controller instances named DMAC capable of serving multiple clients. Channels
 can be dedicated to specific clients or shared between a large number of
 clients.
@@ -20,6 +20,7 @@ Required Properties:
 		- "renesas,dmac-r8a7744" (RZ/G1N)
 		- "renesas,dmac-r8a7745" (RZ/G1E)
 		- "renesas,dmac-r8a77470" (RZ/G1C)
+		- "renesas,dmac-r8a774a1" (RZ/G2M)
 		- "renesas,dmac-r8a7790" (R-Car H2)
 		- "renesas,dmac-r8a7791" (R-Car M2-W)
 		- "renesas,dmac-r8a7792" (R-Car V2H)
diff --git a/Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt b/Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt
index 1743017bd948..5e2c7e84c43e 100644
--- a/Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/renesas,usb-dmac.txt
@@ -6,6 +6,8 @@ Required Properties:
 	  - "renesas,r8a7743-usb-dmac" (RZ/G1M)
 	  - "renesas,r8a7744-usb-dmac" (RZ/G1N)
 	  - "renesas,r8a7745-usb-dmac" (RZ/G1E)
+	  - "renesas,r8a77470-usb-dmac" (RZ/G1C)
+	  - "renesas,r8a774a1-usb-dmac" (RZ/G2M)
 	  - "renesas,r8a7790-usb-dmac" (R-Car H2)
 	  - "renesas,r8a7791-usb-dmac" (R-Car M2-W)
 	  - "renesas,r8a7793-usb-dmac" (R-Car M2-N)
diff --git a/Documentation/devicetree/bindings/dma/snps-dma.txt b/Documentation/devicetree/bindings/dma/snps-dma.txt
index 39e2b26be344..db757df7057d 100644
--- a/Documentation/devicetree/bindings/dma/snps-dma.txt
+++ b/Documentation/devicetree/bindings/dma/snps-dma.txt
@@ -27,6 +27,10 @@ Optional properties:
   general purpose DMA channel allocator. False if not passed.
 - multi-block: Multi block transfers supported by hardware. Array property with
   one cell per channel. 0: not supported, 1 (default): supported.
+- snps,dma-protection-control: AHB HPROT[3:1] protection setting.
+  The default value is 0 (for non-cacheable, non-buffered,
+  unprivileged data access).
+  Refer to include/dt-bindings/dma/dw-dmac.h for possible values.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/dma/uniphier-mio-dmac.txt b/Documentation/devicetree/bindings/dma/uniphier-mio-dmac.txt
new file mode 100644
index 000000000000..b12388dc7eac
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/uniphier-mio-dmac.txt
@@ -0,0 +1,25 @@
+UniPhier Media IO DMA controller
+
+This works as an external DMA engine for SD/eMMC controllers etc.
+found in UniPhier LD4, Pro4, sLD8 SoCs.
+
+Required properties:
+- compatible: should be "socionext,uniphier-mio-dmac".
+- reg: offset and length of the register set for the device.
+- interrupts: a list of interrupt specifiers associated with the DMA channels.
+- clocks: a single clock specifier.
+- #dma-cells: should be <1>. The single cell represents the channel index.
+
+Example:
+	dmac: dma-controller@5a000000 {
+		compatible = "socionext,uniphier-mio-dmac";
+		reg = <0x5a000000 0x1000>;
+		interrupts = <0 68 4>, <0 68 4>, <0 69 4>, <0 70 4>,
+			     <0 71 4>, <0 72 4>, <0 73 4>, <0 74 4>;
+		clocks = <&mio_clk 7>;
+		#dma-cells = <1>;
+	};
+
+Note:
+In the example above, "interrupts = <0 68 4>, <0 68 4>, ..." is not a typo.
+The first two channels share a single interrupt line.
diff --git a/MAINTAINERS b/MAINTAINERS
index 7f9ecdb12f07..a75257a5ac4b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2269,6 +2269,7 @@ F:	arch/arm/mm/cache-uniphier.c
 F:	arch/arm64/boot/dts/socionext/uniphier*
 F:	drivers/bus/uniphier-system-bus.c
 F:	drivers/clk/uniphier/
+F:	drivers/dmaengine/uniphier-mdmac.c
 F:	drivers/gpio/gpio-uniphier.c
 F:	drivers/i2c/busses/i2c-uniphier*
 F:	drivers/irqchip/irq-uniphier-aidet.c
@@ -14596,9 +14597,11 @@ SYNOPSYS DESIGNWARE DMAC DRIVER
 M:	Viresh Kumar <vireshk@kernel.org>
 R:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
+F:	Documentation/devicetree/bindings/dma/snps-dma.txt
+F:	drivers/dma/dw/
+F:	include/dt-bindings/dma/dw-dmac.h
 F:	include/linux/dma/dw.h
 F:	include/linux/platform_data/dma-dw.h
-F:	drivers/dma/dw/
 
 SYNOPSYS DESIGNWARE ENTERPRISE ETHERNET DRIVER
 M:	Jose Abreu <Jose.Abreu@synopsys.com>
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index de511db021cc..0b1dfb5bf2d9 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -218,6 +218,20 @@ config FSL_EDMA
 	  multiplexing capability for DMA request sources(slot).
 	  This module can be found on Freescale Vybrid and LS-1 SoCs.
 
+config FSL_QDMA
+       tristate "NXP Layerscape qDMA engine support"
+       depends on ARM || ARM64
+       select DMA_ENGINE
+       select DMA_VIRTUAL_CHANNELS
+       select DMA_ENGINE_RAID
+       select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+       help
+         Support the NXP Layerscape qDMA engine with command queue and legacy mode.
+         Channel virtualization is supported through enqueuing of DMA jobs to,
+         or dequeuing DMA jobs from, different work queues.
+         This module can be found on NXP Layerscape SoCs.
+	  The qdma driver only work on  SoCs with a DPAA hardware block.
+
 config FSL_RAID
         tristate "Freescale RAID engine Support"
         depends on FSL_SOC && !ASYNC_TX_ENABLE_CHANNEL_SWITCH
@@ -587,6 +601,17 @@ config TIMB_DMA
 	help
 	  Enable support for the Timberdale FPGA DMA engine.
 
+config UNIPHIER_MDMAC
+	tristate "UniPhier MIO DMAC"
+	depends on ARCH_UNIPHIER || COMPILE_TEST
+	depends on OF
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the MIO DMAC (Media I/O DMA controller) on the
+	  UniPhier platform.  This DMA controller is used as the external
+	  DMA engine of the SD/eMMC controllers of the LD4, Pro4, sLD8 SoCs.
+
 config XGENE_DMA
 	tristate "APM X-Gene DMA support"
 	depends on ARCH_XGENE || COMPILE_TEST
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 7fcc4d8e336d..6126e1c3a875 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_FSL_EDMA) += fsl-edma.o fsl-edma-common.o
 obj-$(CONFIG_MCF_EDMA) += mcf-edma.o fsl-edma-common.o
+obj-$(CONFIG_FSL_QDMA) += fsl-qdma.o
 obj-$(CONFIG_FSL_RAID) += fsl_raid.o
 obj-$(CONFIG_HSU_DMA) += hsu/
 obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o
@@ -70,6 +71,7 @@ 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-$(CONFIG_UNIPHIER_MDMAC) += uniphier-mdmac.o
 obj-$(CONFIG_XGENE_DMA) += xgene-dma.o
 obj-$(CONFIG_ZX_DMA) += zx_dma.o
 obj-$(CONFIG_ST_FDMA) += st_fdma.o
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index cad55ab80d41..1a44c8086d77 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * BCM2835 DMA engine support
  *
@@ -18,16 +19,6 @@
  *
  *	MARVELL MMP Peripheral DMA Driver
  *	Copyright 2012 Marvell International Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * 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/dmaengine.h>
 #include <linux/dma-mapping.h>
@@ -1056,4 +1047,4 @@ module_platform_driver(bcm2835_dma_driver);
 MODULE_ALIAS("platform:bcm2835-dma");
 MODULE_DESCRIPTION("BCM2835 DMA engine driver");
 MODULE_AUTHOR("Florian Meier <florian.meier@koalo.de>");
-MODULE_LICENSE("GPL v2");
+MODULE_LICENSE("GPL");
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index eebaba3d9e78..b69d66e44052 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1802,13 +1802,10 @@ static struct dma_chan *coh901318_xlate(struct of_phandle_args *dma_spec,
 static int coh901318_config(struct coh901318_chan *cohc,
 			    struct coh901318_params *param)
 {
-	unsigned long flags;
 	const struct coh901318_params *p;
 	int channel = cohc->id;
 	void __iomem *virtbase = cohc->base->virtbase;
 
-	spin_lock_irqsave(&cohc->lock, flags);
-
 	if (param)
 		p = param;
 	else
@@ -1828,8 +1825,6 @@ static int coh901318_config(struct coh901318_chan *cohc,
 	coh901318_set_conf(cohc, p->config);
 	coh901318_set_ctrl(cohc, p->ctrl_lli_last);
 
-	spin_unlock_irqrestore(&cohc->lock, flags);
-
 	return 0;
 }
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index aa1712beb0cc..28deaa084257 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -507,9 +507,22 @@ static int dmatest_func(void *data)
 	} else
 		goto err_thread_type;
 
+	/* Check if buffer count fits into map count variable (u8) */
+	if ((src_cnt + dst_cnt) >= 255) {
+		pr_err("too many buffers (%d of 255 supported)\n",
+		       src_cnt + dst_cnt);
+		goto err_free_coefs;
+	}
+
+	if (1 << align > params->buf_size) {
+		pr_err("%u-byte buffer too small for %d-byte alignment\n",
+		       params->buf_size, 1 << align);
+		goto err_free_coefs;
+	}
+
 	thread->srcs = kcalloc(src_cnt + 1, sizeof(u8 *), GFP_KERNEL);
 	if (!thread->srcs)
-		goto err_srcs;
+		goto err_free_coefs;
 
 	thread->usrcs = kcalloc(src_cnt + 1, sizeof(u8 *), GFP_KERNEL);
 	if (!thread->usrcs)
@@ -576,19 +589,6 @@ static int dmatest_func(void *data)
 
 		total_tests++;
 
-		/* Check if buffer count fits into map count variable (u8) */
-		if ((src_cnt + dst_cnt) >= 255) {
-			pr_err("too many buffers (%d of 255 supported)\n",
-			       src_cnt + dst_cnt);
-			break;
-		}
-
-		if (1 << align > params->buf_size) {
-			pr_err("%u-byte buffer too small for %d-byte alignment\n",
-			       params->buf_size, 1 << align);
-			break;
-		}
-
 		if (params->norandom)
 			len = params->buf_size;
 		else
@@ -721,14 +721,14 @@ static int dmatest_func(void *data)
 
 		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 
+		dmaengine_unmap_put(um);
+
 		if (!done->done) {
-			dmaengine_unmap_put(um);
 			result("test timed out", total_tests, src_off, dst_off,
 			       len, 0);
 			failed_tests++;
 			continue;
 		} else if (status != DMA_COMPLETE) {
-			dmaengine_unmap_put(um);
 			result(status == DMA_ERROR ?
 			       "completion error status" :
 			       "completion busy status", total_tests, src_off,
@@ -737,8 +737,6 @@ static int dmatest_func(void *data)
 			continue;
 		}
 
-		dmaengine_unmap_put(um);
-
 		if (params->noverify) {
 			verbose_result("test passed", total_tests, src_off,
 				       dst_off, len, 0);
@@ -802,7 +800,7 @@ err_srcbuf:
 	kfree(thread->usrcs);
 err_usrcs:
 	kfree(thread->srcs);
-err_srcs:
+err_free_coefs:
 	kfree(pq_coefs);
 err_thread_type:
 	pr_info("%s: summary %u tests, %u failures %llu iops %llu KB/s (%d)\n",
@@ -812,7 +810,7 @@ err_thread_type:
 
 	/* terminate all transfers on specified channels */
 	if (ret || failed_tests)
-		dmaengine_terminate_all(chan);
+		dmaengine_terminate_sync(chan);
 
 	thread->done = true;
 	wake_up(&thread_wait);
@@ -836,7 +834,7 @@ static void dmatest_cleanup_channel(struct dmatest_chan *dtc)
 	}
 
 	/* terminate all transfers on specified channels */
-	dmaengine_terminate_all(dtc->chan);
+	dmaengine_terminate_sync(dtc->chan);
 
 	kfree(dtc);
 }
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 1fc488e90f36..dc053e62f894 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -160,12 +160,14 @@ static void dwc_initialize_chan_idma32(struct dw_dma_chan *dwc)
 
 static void dwc_initialize_chan_dw(struct dw_dma_chan *dwc)
 {
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 	u32 cfghi = DWC_CFGH_FIFO_MODE;
 	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
 	bool hs_polarity = dwc->dws.hs_polarity;
 
 	cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id);
 	cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id);
+	cfghi |= DWC_CFGH_PROTCTL(dw->pdata->protctl);
 
 	/* Set polarity of handshake interface */
 	cfglo |= hs_polarity ? DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL : 0;
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index f01b2c173fa6..31ff8113c3de 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -162,6 +162,12 @@ dw_dma_parse_dt(struct platform_device *pdev)
 			pdata->multi_block[tmp] = 1;
 	}
 
+	if (!of_property_read_u32(np, "snps,dma-protection-control", &tmp)) {
+		if (tmp > CHAN_PROTCTL_MASK)
+			return NULL;
+		pdata->protctl = tmp;
+	}
+
 	return pdata;
 }
 #else
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 09e7dfdbb790..646c9c960c07 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -200,6 +200,10 @@ enum dw_dma_msize {
 #define DWC_CFGH_FCMODE		(1 << 0)
 #define DWC_CFGH_FIFO_MODE	(1 << 1)
 #define DWC_CFGH_PROTCTL(x)	((x) << 2)
+#define DWC_CFGH_PROTCTL_DATA	(0 << 2)	/* data access - always set */
+#define DWC_CFGH_PROTCTL_PRIV	(1 << 2)	/* privileged -> AHB HPROT[1] */
+#define DWC_CFGH_PROTCTL_BUFFER	(2 << 2)	/* bufferable -> AHB HPROT[2] */
+#define DWC_CFGH_PROTCTL_CACHE	(4 << 2)	/* cacheable  -> AHB HPROT[3] */
 #define DWC_CFGH_DS_UPD_EN	(1 << 5)
 #define DWC_CFGH_SS_UPD_EN	(1 << 6)
 #define DWC_CFGH_SRC_PER(x)	((x) << 7)
diff --git a/drivers/dma/ep93xx_dma.c b/drivers/dma/ep93xx_dma.c
index f674eb5fbbef..594a88f4f99c 100644
--- a/drivers/dma/ep93xx_dma.c
+++ b/drivers/dma/ep93xx_dma.c
@@ -997,7 +997,7 @@ ep93xx_dma_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest,
 	for (offset = 0; offset < len; offset += bytes) {
 		desc = ep93xx_dma_desc_get(edmac);
 		if (!desc) {
-			dev_warn(chan2dev(edmac), "couln't get descriptor\n");
+			dev_warn(chan2dev(edmac), "couldn't get descriptor\n");
 			goto fail;
 		}
 
@@ -1069,7 +1069,7 @@ ep93xx_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 		desc = ep93xx_dma_desc_get(edmac);
 		if (!desc) {
-			dev_warn(chan2dev(edmac), "couln't get descriptor\n");
+			dev_warn(chan2dev(edmac), "couldn't get descriptor\n");
 			goto fail;
 		}
 
@@ -1149,7 +1149,7 @@ ep93xx_dma_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t dma_addr,
 	for (offset = 0; offset < buf_len; offset += period_len) {
 		desc = ep93xx_dma_desc_get(edmac);
 		if (!desc) {
-			dev_warn(chan2dev(edmac), "couln't get descriptor\n");
+			dev_warn(chan2dev(edmac), "couldn't get descriptor\n");
 			goto fail;
 		}
 
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
new file mode 100644
index 000000000000..c18e3492090b
--- /dev/null
+++ b/drivers/dma/fsl-qdma.c
@@ -0,0 +1,1258 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright 2014-2015 Freescale
+// Copyright 2018 NXP
+
+/*
+ * Driver for NXP Layerscape Queue Direct Memory Access Controller
+ *
+ * Author:
+ *  Wen He <wen.he_1@nxp.com>
+ *  Jiaheng Fan <jiaheng.fan@nxp.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/of_dma.h>
+#include <linux/dma-mapping.h>
+
+#include "virt-dma.h"
+#include "fsldma.h"
+
+/* Register related definition */
+#define FSL_QDMA_DMR			0x0
+#define FSL_QDMA_DSR			0x4
+#define FSL_QDMA_DEIER			0xe00
+#define FSL_QDMA_DEDR			0xe04
+#define FSL_QDMA_DECFDW0R		0xe10
+#define FSL_QDMA_DECFDW1R		0xe14
+#define FSL_QDMA_DECFDW2R		0xe18
+#define FSL_QDMA_DECFDW3R		0xe1c
+#define FSL_QDMA_DECFQIDR		0xe30
+#define FSL_QDMA_DECBR			0xe34
+
+#define FSL_QDMA_BCQMR(x)		(0xc0 + 0x100 * (x))
+#define FSL_QDMA_BCQSR(x)		(0xc4 + 0x100 * (x))
+#define FSL_QDMA_BCQEDPA_SADDR(x)	(0xc8 + 0x100 * (x))
+#define FSL_QDMA_BCQDPA_SADDR(x)	(0xcc + 0x100 * (x))
+#define FSL_QDMA_BCQEEPA_SADDR(x)	(0xd0 + 0x100 * (x))
+#define FSL_QDMA_BCQEPA_SADDR(x)	(0xd4 + 0x100 * (x))
+#define FSL_QDMA_BCQIER(x)		(0xe0 + 0x100 * (x))
+#define FSL_QDMA_BCQIDR(x)		(0xe4 + 0x100 * (x))
+
+#define FSL_QDMA_SQDPAR			0x80c
+#define FSL_QDMA_SQEPAR			0x814
+#define FSL_QDMA_BSQMR			0x800
+#define FSL_QDMA_BSQSR			0x804
+#define FSL_QDMA_BSQICR			0x828
+#define FSL_QDMA_CQMR			0xa00
+#define FSL_QDMA_CQDSCR1		0xa08
+#define FSL_QDMA_CQDSCR2                0xa0c
+#define FSL_QDMA_CQIER			0xa10
+#define FSL_QDMA_CQEDR			0xa14
+#define FSL_QDMA_SQCCMR			0xa20
+
+/* Registers for bit and genmask */
+#define FSL_QDMA_CQIDR_SQT		BIT(15)
+#define QDMA_CCDF_FOTMAT		BIT(29)
+#define QDMA_CCDF_SER			BIT(30)
+#define QDMA_SG_FIN			BIT(30)
+#define QDMA_SG_LEN_MASK		GENMASK(29, 0)
+#define QDMA_CCDF_MASK			GENMASK(28, 20)
+
+#define FSL_QDMA_DEDR_CLEAR		GENMASK(31, 0)
+#define FSL_QDMA_BCQIDR_CLEAR		GENMASK(31, 0)
+#define FSL_QDMA_DEIER_CLEAR		GENMASK(31, 0)
+
+#define FSL_QDMA_BCQIER_CQTIE		BIT(15)
+#define FSL_QDMA_BCQIER_CQPEIE		BIT(23)
+#define FSL_QDMA_BSQICR_ICEN		BIT(31)
+
+#define FSL_QDMA_BSQICR_ICST(x)		((x) << 16)
+#define FSL_QDMA_CQIER_MEIE		BIT(31)
+#define FSL_QDMA_CQIER_TEIE		BIT(0)
+#define FSL_QDMA_SQCCMR_ENTER_WM	BIT(21)
+
+#define FSL_QDMA_BCQMR_EN		BIT(31)
+#define FSL_QDMA_BCQMR_EI		BIT(30)
+#define FSL_QDMA_BCQMR_CD_THLD(x)	((x) << 20)
+#define FSL_QDMA_BCQMR_CQ_SIZE(x)	((x) << 16)
+
+#define FSL_QDMA_BCQSR_QF		BIT(16)
+#define FSL_QDMA_BCQSR_XOFF		BIT(0)
+
+#define FSL_QDMA_BSQMR_EN		BIT(31)
+#define FSL_QDMA_BSQMR_DI		BIT(30)
+#define FSL_QDMA_BSQMR_CQ_SIZE(x)	((x) << 16)
+
+#define FSL_QDMA_BSQSR_QE		BIT(17)
+
+#define FSL_QDMA_DMR_DQD		BIT(30)
+#define FSL_QDMA_DSR_DB		BIT(31)
+
+/* Size related definition */
+#define FSL_QDMA_QUEUE_MAX		8
+#define FSL_QDMA_COMMAND_BUFFER_SIZE	64
+#define FSL_QDMA_DESCRIPTOR_BUFFER_SIZE 32
+#define FSL_QDMA_CIRCULAR_DESC_SIZE_MIN	64
+#define FSL_QDMA_CIRCULAR_DESC_SIZE_MAX	16384
+#define FSL_QDMA_QUEUE_NUM_MAX		8
+
+/* Field definition for CMD */
+#define FSL_QDMA_CMD_RWTTYPE		0x4
+#define FSL_QDMA_CMD_LWC                0x2
+#define FSL_QDMA_CMD_RWTTYPE_OFFSET	28
+#define FSL_QDMA_CMD_NS_OFFSET		27
+#define FSL_QDMA_CMD_DQOS_OFFSET	24
+#define FSL_QDMA_CMD_WTHROTL_OFFSET	20
+#define FSL_QDMA_CMD_DSEN_OFFSET	19
+#define FSL_QDMA_CMD_LWC_OFFSET		16
+
+/* Field definition for Descriptor offset */
+#define QDMA_CCDF_STATUS		20
+#define QDMA_CCDF_OFFSET		20
+
+/* Field definition for safe loop count*/
+#define FSL_QDMA_HALT_COUNT		1500
+#define FSL_QDMA_MAX_SIZE		16385
+#define	FSL_QDMA_COMP_TIMEOUT		1000
+#define FSL_COMMAND_QUEUE_OVERFLLOW	10
+
+#define FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma_engine, x)			\
+	(((fsl_qdma_engine)->block_offset) * (x))
+
+/**
+ * struct fsl_qdma_format - This is the struct holding describing compound
+ *			    descriptor format with qDMA.
+ * @status:		    Command status and enqueue status notification.
+ * @cfg:		    Frame offset and frame format.
+ * @addr_lo:		    Holding the compound descriptor of the lower
+ *			    32-bits address in memory 40-bit address.
+ * @addr_hi:		    Same as above member, but point high 8-bits in
+ *			    memory 40-bit address.
+ * @__reserved1:	    Reserved field.
+ * @cfg8b_w1:		    Compound descriptor command queue origin produced
+ *			    by qDMA and dynamic debug field.
+ * @data		    Pointer to the memory 40-bit address, describes DMA
+ *			    source information and DMA destination information.
+ */
+struct fsl_qdma_format {
+	__le32 status;
+	__le32 cfg;
+	union {
+		struct {
+			__le32 addr_lo;
+			u8 addr_hi;
+			u8 __reserved1[2];
+			u8 cfg8b_w1;
+		} __packed;
+		__le64 data;
+	};
+} __packed;
+
+/* qDMA status notification pre information */
+struct fsl_pre_status {
+	u64 addr;
+	u8 queue;
+};
+
+static DEFINE_PER_CPU(struct fsl_pre_status, pre);
+
+struct fsl_qdma_chan {
+	struct virt_dma_chan		vchan;
+	struct virt_dma_desc		vdesc;
+	enum dma_status			status;
+	struct fsl_qdma_engine		*qdma;
+	struct fsl_qdma_queue		*queue;
+};
+
+struct fsl_qdma_queue {
+	struct fsl_qdma_format	*virt_head;
+	struct fsl_qdma_format	*virt_tail;
+	struct list_head	comp_used;
+	struct list_head	comp_free;
+	struct dma_pool		*comp_pool;
+	struct dma_pool		*desc_pool;
+	spinlock_t		queue_lock;
+	dma_addr_t		bus_addr;
+	u32                     n_cq;
+	u32			id;
+	struct fsl_qdma_format	*cq;
+	void __iomem		*block_base;
+};
+
+struct fsl_qdma_comp {
+	dma_addr_t              bus_addr;
+	dma_addr_t              desc_bus_addr;
+	struct fsl_qdma_format	*virt_addr;
+	struct fsl_qdma_format	*desc_virt_addr;
+	struct fsl_qdma_chan	*qchan;
+	struct virt_dma_desc    vdesc;
+	struct list_head	list;
+};
+
+struct fsl_qdma_engine {
+	struct dma_device	dma_dev;
+	void __iomem		*ctrl_base;
+	void __iomem            *status_base;
+	void __iomem		*block_base;
+	u32			n_chans;
+	u32			n_queues;
+	struct mutex            fsl_qdma_mutex;
+	int			error_irq;
+	int			*queue_irq;
+	u32			feature;
+	struct fsl_qdma_queue	*queue;
+	struct fsl_qdma_queue	**status;
+	struct fsl_qdma_chan	*chans;
+	int			block_number;
+	int			block_offset;
+	int			irq_base;
+	int			desc_allocated;
+
+};
+
+static inline u64
+qdma_ccdf_addr_get64(const struct fsl_qdma_format *ccdf)
+{
+	return le64_to_cpu(ccdf->data) & (U64_MAX >> 24);
+}
+
+static inline void
+qdma_desc_addr_set64(struct fsl_qdma_format *ccdf, u64 addr)
+{
+	ccdf->addr_hi = upper_32_bits(addr);
+	ccdf->addr_lo = cpu_to_le32(lower_32_bits(addr));
+}
+
+static inline u8
+qdma_ccdf_get_queue(const struct fsl_qdma_format *ccdf)
+{
+	return ccdf->cfg8b_w1 & U8_MAX;
+}
+
+static inline int
+qdma_ccdf_get_offset(const struct fsl_qdma_format *ccdf)
+{
+	return (le32_to_cpu(ccdf->cfg) & QDMA_CCDF_MASK) >> QDMA_CCDF_OFFSET;
+}
+
+static inline void
+qdma_ccdf_set_format(struct fsl_qdma_format *ccdf, int offset)
+{
+	ccdf->cfg = cpu_to_le32(QDMA_CCDF_FOTMAT | offset);
+}
+
+static inline int
+qdma_ccdf_get_status(const struct fsl_qdma_format *ccdf)
+{
+	return (le32_to_cpu(ccdf->status) & QDMA_CCDF_MASK) >> QDMA_CCDF_STATUS;
+}
+
+static inline void
+qdma_ccdf_set_ser(struct fsl_qdma_format *ccdf, int status)
+{
+	ccdf->status = cpu_to_le32(QDMA_CCDF_SER | status);
+}
+
+static inline void qdma_csgf_set_len(struct fsl_qdma_format *csgf, int len)
+{
+	csgf->cfg = cpu_to_le32(len & QDMA_SG_LEN_MASK);
+}
+
+static inline void qdma_csgf_set_f(struct fsl_qdma_format *csgf, int len)
+{
+	csgf->cfg = cpu_to_le32(QDMA_SG_FIN | (len & QDMA_SG_LEN_MASK));
+}
+
+static u32 qdma_readl(struct fsl_qdma_engine *qdma, void __iomem *addr)
+{
+	return FSL_DMA_IN(qdma, addr, 32);
+}
+
+static void qdma_writel(struct fsl_qdma_engine *qdma, u32 val,
+			void __iomem *addr)
+{
+	FSL_DMA_OUT(qdma, addr, val, 32);
+}
+
+static struct fsl_qdma_chan *to_fsl_qdma_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct fsl_qdma_chan, vchan.chan);
+}
+
+static struct fsl_qdma_comp *to_fsl_qdma_comp(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct fsl_qdma_comp, vdesc);
+}
+
+static void fsl_qdma_free_chan_resources(struct dma_chan *chan)
+{
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	struct fsl_qdma_engine *fsl_qdma = fsl_chan->qdma;
+	struct fsl_qdma_comp *comp_temp, *_comp_temp;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+
+	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
+
+	if (!fsl_queue->comp_pool && !fsl_queue->comp_pool)
+		return;
+
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &fsl_queue->comp_used,	list) {
+		dma_pool_free(fsl_queue->comp_pool,
+			      comp_temp->virt_addr,
+			      comp_temp->bus_addr);
+		dma_pool_free(fsl_queue->desc_pool,
+			      comp_temp->desc_virt_addr,
+			      comp_temp->desc_bus_addr);
+		list_del(&comp_temp->list);
+		kfree(comp_temp);
+	}
+
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &fsl_queue->comp_free, list) {
+		dma_pool_free(fsl_queue->comp_pool,
+			      comp_temp->virt_addr,
+			      comp_temp->bus_addr);
+		dma_pool_free(fsl_queue->desc_pool,
+			      comp_temp->desc_virt_addr,
+			      comp_temp->desc_bus_addr);
+		list_del(&comp_temp->list);
+		kfree(comp_temp);
+	}
+
+	dma_pool_destroy(fsl_queue->comp_pool);
+	dma_pool_destroy(fsl_queue->desc_pool);
+
+	fsl_qdma->desc_allocated--;
+	fsl_queue->comp_pool = NULL;
+	fsl_queue->desc_pool = NULL;
+}
+
+static void fsl_qdma_comp_fill_memcpy(struct fsl_qdma_comp *fsl_comp,
+				      dma_addr_t dst, dma_addr_t src, u32 len)
+{
+	struct fsl_qdma_format *sdf, *ddf;
+	struct fsl_qdma_format *ccdf, *csgf_desc, *csgf_src, *csgf_dest;
+
+	ccdf = fsl_comp->virt_addr;
+	csgf_desc = fsl_comp->virt_addr + 1;
+	csgf_src = fsl_comp->virt_addr + 2;
+	csgf_dest = fsl_comp->virt_addr + 3;
+	sdf = fsl_comp->desc_virt_addr;
+	ddf = fsl_comp->desc_virt_addr + 1;
+
+	memset(fsl_comp->virt_addr, 0, FSL_QDMA_COMMAND_BUFFER_SIZE);
+	memset(fsl_comp->desc_virt_addr, 0, FSL_QDMA_DESCRIPTOR_BUFFER_SIZE);
+	/* Head Command Descriptor(Frame Descriptor) */
+	qdma_desc_addr_set64(ccdf, fsl_comp->bus_addr + 16);
+	qdma_ccdf_set_format(ccdf, qdma_ccdf_get_offset(ccdf));
+	qdma_ccdf_set_ser(ccdf, qdma_ccdf_get_status(ccdf));
+	/* Status notification is enqueued to status queue. */
+	/* Compound Command Descriptor(Frame List Table) */
+	qdma_desc_addr_set64(csgf_desc, fsl_comp->desc_bus_addr);
+	/* It must be 32 as Compound S/G Descriptor */
+	qdma_csgf_set_len(csgf_desc, 32);
+	qdma_desc_addr_set64(csgf_src, src);
+	qdma_csgf_set_len(csgf_src, len);
+	qdma_desc_addr_set64(csgf_dest, dst);
+	qdma_csgf_set_len(csgf_dest, len);
+	/* This entry is the last entry. */
+	qdma_csgf_set_f(csgf_dest, len);
+	/* Descriptor Buffer */
+	sdf->data =
+		cpu_to_le64(FSL_QDMA_CMD_RWTTYPE <<
+			    FSL_QDMA_CMD_RWTTYPE_OFFSET);
+	ddf->data =
+		cpu_to_le64(FSL_QDMA_CMD_RWTTYPE <<
+			    FSL_QDMA_CMD_RWTTYPE_OFFSET);
+	ddf->data |=
+		cpu_to_le64(FSL_QDMA_CMD_LWC << FSL_QDMA_CMD_LWC_OFFSET);
+}
+
+/*
+ * Pre-request full command descriptor for enqueue.
+ */
+static int fsl_qdma_pre_request_enqueue_desc(struct fsl_qdma_queue *queue)
+{
+	int i;
+	struct fsl_qdma_comp *comp_temp, *_comp_temp;
+
+	for (i = 0; i < queue->n_cq + FSL_COMMAND_QUEUE_OVERFLLOW; i++) {
+		comp_temp = kzalloc(sizeof(*comp_temp), GFP_KERNEL);
+		if (!comp_temp)
+			goto err_alloc;
+		comp_temp->virt_addr =
+			dma_pool_alloc(queue->comp_pool, GFP_KERNEL,
+				       &comp_temp->bus_addr);
+		if (!comp_temp->virt_addr)
+			goto err_dma_alloc;
+
+		comp_temp->desc_virt_addr =
+			dma_pool_alloc(queue->desc_pool, GFP_KERNEL,
+				       &comp_temp->desc_bus_addr);
+		if (!comp_temp->desc_virt_addr)
+			goto err_desc_dma_alloc;
+
+		list_add_tail(&comp_temp->list, &queue->comp_free);
+	}
+
+	return 0;
+
+err_desc_dma_alloc:
+	dma_pool_free(queue->comp_pool, comp_temp->virt_addr,
+		      comp_temp->bus_addr);
+
+err_dma_alloc:
+	kfree(comp_temp);
+
+err_alloc:
+	list_for_each_entry_safe(comp_temp, _comp_temp,
+				 &queue->comp_free, list) {
+		if (comp_temp->virt_addr)
+			dma_pool_free(queue->comp_pool,
+				      comp_temp->virt_addr,
+				      comp_temp->bus_addr);
+		if (comp_temp->desc_virt_addr)
+			dma_pool_free(queue->desc_pool,
+				      comp_temp->desc_virt_addr,
+				      comp_temp->desc_bus_addr);
+
+		list_del(&comp_temp->list);
+		kfree(comp_temp);
+	}
+
+	return -ENOMEM;
+}
+
+/*
+ * Request a command descriptor for enqueue.
+ */
+static struct fsl_qdma_comp
+*fsl_qdma_request_enqueue_desc(struct fsl_qdma_chan *fsl_chan)
+{
+	unsigned long flags;
+	struct fsl_qdma_comp *comp_temp;
+	int timeout = FSL_QDMA_COMP_TIMEOUT;
+	struct fsl_qdma_queue *queue = fsl_chan->queue;
+
+	while (timeout--) {
+		spin_lock_irqsave(&queue->queue_lock, flags);
+		if (!list_empty(&queue->comp_free)) {
+			comp_temp = list_first_entry(&queue->comp_free,
+						     struct fsl_qdma_comp,
+						     list);
+			list_del(&comp_temp->list);
+
+			spin_unlock_irqrestore(&queue->queue_lock, flags);
+			comp_temp->qchan = fsl_chan;
+			return comp_temp;
+		}
+		spin_unlock_irqrestore(&queue->queue_lock, flags);
+		udelay(1);
+	}
+
+	return NULL;
+}
+
+static struct fsl_qdma_queue
+*fsl_qdma_alloc_queue_resources(struct platform_device *pdev,
+				struct fsl_qdma_engine *fsl_qdma)
+{
+	int ret, len, i, j;
+	int queue_num, block_number;
+	unsigned int queue_size[FSL_QDMA_QUEUE_MAX];
+	struct fsl_qdma_queue *queue_head, *queue_temp;
+
+	queue_num = fsl_qdma->n_queues;
+	block_number = fsl_qdma->block_number;
+
+	if (queue_num > FSL_QDMA_QUEUE_MAX)
+		queue_num = FSL_QDMA_QUEUE_MAX;
+	len = sizeof(*queue_head) * queue_num * block_number;
+	queue_head = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!queue_head)
+		return NULL;
+
+	ret = device_property_read_u32_array(&pdev->dev, "queue-sizes",
+					     queue_size, queue_num);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get queue-sizes.\n");
+		return NULL;
+	}
+	for (j = 0; j < block_number; j++) {
+		for (i = 0; i < queue_num; i++) {
+			if (queue_size[i] > FSL_QDMA_CIRCULAR_DESC_SIZE_MAX ||
+			    queue_size[i] < FSL_QDMA_CIRCULAR_DESC_SIZE_MIN) {
+				dev_err(&pdev->dev,
+					"Get wrong queue-sizes.\n");
+				return NULL;
+			}
+			queue_temp = queue_head + i + (j * queue_num);
+
+			queue_temp->cq =
+			dma_alloc_coherent(&pdev->dev,
+					   sizeof(struct fsl_qdma_format) *
+					   queue_size[i],
+					   &queue_temp->bus_addr,
+					   GFP_KERNEL);
+			if (!queue_temp->cq)
+				return NULL;
+			queue_temp->block_base = fsl_qdma->block_base +
+				FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+			queue_temp->n_cq = queue_size[i];
+			queue_temp->id = i;
+			queue_temp->virt_head = queue_temp->cq;
+			queue_temp->virt_tail = queue_temp->cq;
+			/*
+			 * List for queue command buffer
+			 */
+			INIT_LIST_HEAD(&queue_temp->comp_used);
+			spin_lock_init(&queue_temp->queue_lock);
+		}
+	}
+	return queue_head;
+}
+
+static struct fsl_qdma_queue
+*fsl_qdma_prep_status_queue(struct platform_device *pdev)
+{
+	int ret;
+	unsigned int status_size;
+	struct fsl_qdma_queue *status_head;
+	struct device_node *np = pdev->dev.of_node;
+
+	ret = of_property_read_u32(np, "status-sizes", &status_size);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get status-sizes.\n");
+		return NULL;
+	}
+	if (status_size > FSL_QDMA_CIRCULAR_DESC_SIZE_MAX ||
+	    status_size < FSL_QDMA_CIRCULAR_DESC_SIZE_MIN) {
+		dev_err(&pdev->dev, "Get wrong status_size.\n");
+		return NULL;
+	}
+	status_head = devm_kzalloc(&pdev->dev,
+				   sizeof(*status_head), GFP_KERNEL);
+	if (!status_head)
+		return NULL;
+
+	/*
+	 * Buffer for queue command
+	 */
+	status_head->cq = dma_alloc_coherent(&pdev->dev,
+					     sizeof(struct fsl_qdma_format) *
+					     status_size,
+					     &status_head->bus_addr,
+					     GFP_KERNEL);
+	if (!status_head->cq) {
+		devm_kfree(&pdev->dev, status_head);
+		return NULL;
+	}
+	status_head->n_cq = status_size;
+	status_head->virt_head = status_head->cq;
+	status_head->virt_tail = status_head->cq;
+	status_head->comp_pool = NULL;
+
+	return status_head;
+}
+
+static int fsl_qdma_halt(struct fsl_qdma_engine *fsl_qdma)
+{
+	u32 reg;
+	int i, j, count = FSL_QDMA_HALT_COUNT;
+	void __iomem *block, *ctrl = fsl_qdma->ctrl_base;
+
+	/* Disable the command queue and wait for idle state. */
+	reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+	reg |= FSL_QDMA_DMR_DQD;
+	qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+	for (j = 0; j < fsl_qdma->block_number; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+		for (i = 0; i < FSL_QDMA_QUEUE_NUM_MAX; i++)
+			qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BCQMR(i));
+	}
+	while (1) {
+		reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DSR);
+		if (!(reg & FSL_QDMA_DSR_DB))
+			break;
+		if (count-- < 0)
+			return -EBUSY;
+		udelay(100);
+	}
+
+	for (j = 0; j < fsl_qdma->block_number; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+
+		/* Disable status queue. */
+		qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BSQMR);
+
+		/*
+		 * clear the command queue interrupt detect register for
+		 * all queues.
+		 */
+		qdma_writel(fsl_qdma, FSL_QDMA_BCQIDR_CLEAR,
+			    block + FSL_QDMA_BCQIDR(0));
+	}
+
+	return 0;
+}
+
+static int
+fsl_qdma_queue_transfer_complete(struct fsl_qdma_engine *fsl_qdma,
+				 void *block,
+				 int id)
+{
+	bool duplicate;
+	u32 reg, i, count;
+	struct fsl_qdma_queue *temp_queue;
+	struct fsl_qdma_format *status_addr;
+	struct fsl_qdma_comp *fsl_comp = NULL;
+	struct fsl_qdma_queue *fsl_queue = fsl_qdma->queue;
+	struct fsl_qdma_queue *fsl_status = fsl_qdma->status[id];
+
+	count = FSL_QDMA_MAX_SIZE;
+
+	while (count--) {
+		duplicate = 0;
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQSR);
+		if (reg & FSL_QDMA_BSQSR_QE)
+			return 0;
+
+		status_addr = fsl_status->virt_head;
+
+		if (qdma_ccdf_get_queue(status_addr) ==
+		   __this_cpu_read(pre.queue) &&
+			qdma_ccdf_addr_get64(status_addr) ==
+			__this_cpu_read(pre.addr))
+			duplicate = 1;
+		i = qdma_ccdf_get_queue(status_addr) +
+			id * fsl_qdma->n_queues;
+		__this_cpu_write(pre.addr, qdma_ccdf_addr_get64(status_addr));
+		__this_cpu_write(pre.queue, qdma_ccdf_get_queue(status_addr));
+		temp_queue = fsl_queue + i;
+
+		spin_lock(&temp_queue->queue_lock);
+		if (list_empty(&temp_queue->comp_used)) {
+			if (!duplicate) {
+				spin_unlock(&temp_queue->queue_lock);
+				return -EAGAIN;
+			}
+		} else {
+			fsl_comp = list_first_entry(&temp_queue->comp_used,
+						    struct fsl_qdma_comp, list);
+			if (fsl_comp->bus_addr + 16 !=
+				__this_cpu_read(pre.addr)) {
+				if (!duplicate) {
+					spin_unlock(&temp_queue->queue_lock);
+					return -EAGAIN;
+				}
+			}
+		}
+
+		if (duplicate) {
+			reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+			reg |= FSL_QDMA_BSQMR_DI;
+			qdma_desc_addr_set64(status_addr, 0x0);
+			fsl_status->virt_head++;
+			if (fsl_status->virt_head == fsl_status->cq
+						   + fsl_status->n_cq)
+				fsl_status->virt_head = fsl_status->cq;
+			qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+			spin_unlock(&temp_queue->queue_lock);
+			continue;
+		}
+		list_del(&fsl_comp->list);
+
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+		reg |= FSL_QDMA_BSQMR_DI;
+		qdma_desc_addr_set64(status_addr, 0x0);
+		fsl_status->virt_head++;
+		if (fsl_status->virt_head == fsl_status->cq + fsl_status->n_cq)
+			fsl_status->virt_head = fsl_status->cq;
+		qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+		spin_unlock(&temp_queue->queue_lock);
+
+		spin_lock(&fsl_comp->qchan->vchan.lock);
+		vchan_cookie_complete(&fsl_comp->vdesc);
+		fsl_comp->qchan->status = DMA_COMPLETE;
+		spin_unlock(&fsl_comp->qchan->vchan.lock);
+	}
+
+	return 0;
+}
+
+static irqreturn_t fsl_qdma_error_handler(int irq, void *dev_id)
+{
+	unsigned int intr;
+	struct fsl_qdma_engine *fsl_qdma = dev_id;
+	void __iomem *status = fsl_qdma->status_base;
+
+	intr = qdma_readl(fsl_qdma, status + FSL_QDMA_DEDR);
+
+	if (intr) {
+		dev_err(fsl_qdma->dma_dev.dev, "DMA transaction error!\n");
+		return IRQ_NONE;
+	}
+
+	qdma_writel(fsl_qdma, FSL_QDMA_DEDR_CLEAR, status + FSL_QDMA_DEDR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t fsl_qdma_queue_handler(int irq, void *dev_id)
+{
+	int id;
+	unsigned int intr, reg;
+	struct fsl_qdma_engine *fsl_qdma = dev_id;
+	void __iomem *block, *ctrl = fsl_qdma->ctrl_base;
+
+	id = irq - fsl_qdma->irq_base;
+	if (id < 0 && id > fsl_qdma->block_number) {
+		dev_err(fsl_qdma->dma_dev.dev,
+			"irq %d is wrong irq_base is %d\n",
+			irq, fsl_qdma->irq_base);
+	}
+
+	block = fsl_qdma->block_base +
+		FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, id);
+
+	intr = qdma_readl(fsl_qdma, block + FSL_QDMA_BCQIDR(0));
+
+	if ((intr & FSL_QDMA_CQIDR_SQT) != 0)
+		intr = fsl_qdma_queue_transfer_complete(fsl_qdma, block, id);
+
+	if (intr != 0) {
+		reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+		reg |= FSL_QDMA_DMR_DQD;
+		qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+		qdma_writel(fsl_qdma, 0, block + FSL_QDMA_BCQIER(0));
+		dev_err(fsl_qdma->dma_dev.dev, "QDMA: status err!\n");
+	}
+
+	/* Clear all detected events and interrupts. */
+	qdma_writel(fsl_qdma, FSL_QDMA_BCQIDR_CLEAR,
+		    block + FSL_QDMA_BCQIDR(0));
+
+	return IRQ_HANDLED;
+}
+
+static int
+fsl_qdma_irq_init(struct platform_device *pdev,
+		  struct fsl_qdma_engine *fsl_qdma)
+{
+	int i;
+	int cpu;
+	int ret;
+	char irq_name[20];
+
+	fsl_qdma->error_irq =
+		platform_get_irq_byname(pdev, "qdma-error");
+	if (fsl_qdma->error_irq < 0) {
+		dev_err(&pdev->dev, "Can't get qdma controller irq.\n");
+		return fsl_qdma->error_irq;
+	}
+
+	ret = devm_request_irq(&pdev->dev, fsl_qdma->error_irq,
+			       fsl_qdma_error_handler, 0,
+			       "qDMA error", fsl_qdma);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't register qDMA controller IRQ.\n");
+		return  ret;
+	}
+
+	for (i = 0; i < fsl_qdma->block_number; i++) {
+		sprintf(irq_name, "qdma-queue%d", i);
+		fsl_qdma->queue_irq[i] =
+				platform_get_irq_byname(pdev, irq_name);
+
+		if (fsl_qdma->queue_irq[i] < 0) {
+			dev_err(&pdev->dev,
+				"Can't get qdma queue %d irq.\n", i);
+			return fsl_qdma->queue_irq[i];
+		}
+
+		ret = devm_request_irq(&pdev->dev,
+				       fsl_qdma->queue_irq[i],
+				       fsl_qdma_queue_handler,
+				       0,
+				       "qDMA queue",
+				       fsl_qdma);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"Can't register qDMA queue IRQ.\n");
+			return  ret;
+		}
+
+		cpu = i % num_online_cpus();
+		ret = irq_set_affinity_hint(fsl_qdma->queue_irq[i],
+					    get_cpu_mask(cpu));
+		if (ret) {
+			dev_err(&pdev->dev,
+				"Can't set cpu %d affinity to IRQ %d.\n",
+				cpu,
+				fsl_qdma->queue_irq[i]);
+			return  ret;
+		}
+	}
+
+	return 0;
+}
+
+static void fsl_qdma_irq_exit(struct platform_device *pdev,
+			      struct fsl_qdma_engine *fsl_qdma)
+{
+	int i;
+
+	devm_free_irq(&pdev->dev, fsl_qdma->error_irq, fsl_qdma);
+	for (i = 0; i < fsl_qdma->block_number; i++)
+		devm_free_irq(&pdev->dev, fsl_qdma->queue_irq[i], fsl_qdma);
+}
+
+static int fsl_qdma_reg_init(struct fsl_qdma_engine *fsl_qdma)
+{
+	u32 reg;
+	int i, j, ret;
+	struct fsl_qdma_queue *temp;
+	void __iomem *status = fsl_qdma->status_base;
+	void __iomem *block, *ctrl = fsl_qdma->ctrl_base;
+	struct fsl_qdma_queue *fsl_queue = fsl_qdma->queue;
+
+	/* Try to halt the qDMA engine first. */
+	ret = fsl_qdma_halt(fsl_qdma);
+	if (ret) {
+		dev_err(fsl_qdma->dma_dev.dev, "DMA halt failed!");
+		return ret;
+	}
+
+	for (i = 0; i < fsl_qdma->block_number; i++) {
+		/*
+		 * Clear the command queue interrupt detect register for
+		 * all queues.
+		 */
+
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, i);
+		qdma_writel(fsl_qdma, FSL_QDMA_BCQIDR_CLEAR,
+			    block + FSL_QDMA_BCQIDR(0));
+	}
+
+	for (j = 0; j < fsl_qdma->block_number; j++) {
+		block = fsl_qdma->block_base +
+			FSL_QDMA_BLOCK_BASE_OFFSET(fsl_qdma, j);
+		for (i = 0; i < fsl_qdma->n_queues; i++) {
+			temp = fsl_queue + i + (j * fsl_qdma->n_queues);
+			/*
+			 * Initialize Command Queue registers to
+			 * point to the first
+			 * command descriptor in memory.
+			 * Dequeue Pointer Address Registers
+			 * Enqueue Pointer Address Registers
+			 */
+
+			qdma_writel(fsl_qdma, temp->bus_addr,
+				    block + FSL_QDMA_BCQDPA_SADDR(i));
+			qdma_writel(fsl_qdma, temp->bus_addr,
+				    block + FSL_QDMA_BCQEPA_SADDR(i));
+
+			/* Initialize the queue mode. */
+			reg = FSL_QDMA_BCQMR_EN;
+			reg |= FSL_QDMA_BCQMR_CD_THLD(ilog2(temp->n_cq) - 4);
+			reg |= FSL_QDMA_BCQMR_CQ_SIZE(ilog2(temp->n_cq) - 6);
+			qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BCQMR(i));
+		}
+
+		/*
+		 * Workaround for erratum: ERR010812.
+		 * We must enable XOFF to avoid the enqueue rejection occurs.
+		 * Setting SQCCMR ENTER_WM to 0x20.
+		 */
+
+		qdma_writel(fsl_qdma, FSL_QDMA_SQCCMR_ENTER_WM,
+			    block + FSL_QDMA_SQCCMR);
+
+		/*
+		 * Initialize status queue registers to point to the first
+		 * command descriptor in memory.
+		 * Dequeue Pointer Address Registers
+		 * Enqueue Pointer Address Registers
+		 */
+
+		qdma_writel(fsl_qdma, fsl_qdma->status[j]->bus_addr,
+			    block + FSL_QDMA_SQEPAR);
+		qdma_writel(fsl_qdma, fsl_qdma->status[j]->bus_addr,
+			    block + FSL_QDMA_SQDPAR);
+		/* Initialize status queue interrupt. */
+		qdma_writel(fsl_qdma, FSL_QDMA_BCQIER_CQTIE,
+			    block + FSL_QDMA_BCQIER(0));
+		qdma_writel(fsl_qdma, FSL_QDMA_BSQICR_ICEN |
+				   FSL_QDMA_BSQICR_ICST(5) | 0x8000,
+				   block + FSL_QDMA_BSQICR);
+		qdma_writel(fsl_qdma, FSL_QDMA_CQIER_MEIE |
+				   FSL_QDMA_CQIER_TEIE,
+				   block + FSL_QDMA_CQIER);
+
+		/* Initialize the status queue mode. */
+		reg = FSL_QDMA_BSQMR_EN;
+		reg |= FSL_QDMA_BSQMR_CQ_SIZE(ilog2
+			(fsl_qdma->status[j]->n_cq) - 6);
+
+		qdma_writel(fsl_qdma, reg, block + FSL_QDMA_BSQMR);
+		reg = qdma_readl(fsl_qdma, block + FSL_QDMA_BSQMR);
+	}
+
+	/* Initialize controller interrupt register. */
+	qdma_writel(fsl_qdma, FSL_QDMA_DEDR_CLEAR, status + FSL_QDMA_DEDR);
+	qdma_writel(fsl_qdma, FSL_QDMA_DEIER_CLEAR, status + FSL_QDMA_DEIER);
+
+	reg = qdma_readl(fsl_qdma, ctrl + FSL_QDMA_DMR);
+	reg &= ~FSL_QDMA_DMR_DQD;
+	qdma_writel(fsl_qdma, reg, ctrl + FSL_QDMA_DMR);
+
+	return 0;
+}
+
+static struct dma_async_tx_descriptor *
+fsl_qdma_prep_memcpy(struct dma_chan *chan, dma_addr_t dst,
+		     dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct fsl_qdma_comp *fsl_comp;
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+
+	fsl_comp = fsl_qdma_request_enqueue_desc(fsl_chan);
+
+	if (!fsl_comp)
+		return NULL;
+
+	fsl_qdma_comp_fill_memcpy(fsl_comp, dst, src, len);
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_comp->vdesc, flags);
+}
+
+static void fsl_qdma_enqueue_desc(struct fsl_qdma_chan *fsl_chan)
+{
+	u32 reg;
+	struct virt_dma_desc *vdesc;
+	struct fsl_qdma_comp *fsl_comp;
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+	void __iomem *block = fsl_queue->block_base;
+
+	reg = qdma_readl(fsl_chan->qdma, block + FSL_QDMA_BCQSR(fsl_queue->id));
+	if (reg & (FSL_QDMA_BCQSR_QF | FSL_QDMA_BCQSR_XOFF))
+		return;
+	vdesc = vchan_next_desc(&fsl_chan->vchan);
+	if (!vdesc)
+		return;
+	list_del(&vdesc->node);
+	fsl_comp = to_fsl_qdma_comp(vdesc);
+
+	memcpy(fsl_queue->virt_head++,
+	       fsl_comp->virt_addr, sizeof(struct fsl_qdma_format));
+	if (fsl_queue->virt_head == fsl_queue->cq + fsl_queue->n_cq)
+		fsl_queue->virt_head = fsl_queue->cq;
+
+	list_add_tail(&fsl_comp->list, &fsl_queue->comp_used);
+	barrier();
+	reg = qdma_readl(fsl_chan->qdma, block + FSL_QDMA_BCQMR(fsl_queue->id));
+	reg |= FSL_QDMA_BCQMR_EI;
+	qdma_writel(fsl_chan->qdma, reg, block + FSL_QDMA_BCQMR(fsl_queue->id));
+	fsl_chan->status = DMA_IN_PROGRESS;
+}
+
+static void fsl_qdma_free_desc(struct virt_dma_desc *vdesc)
+{
+	unsigned long flags;
+	struct fsl_qdma_comp *fsl_comp;
+	struct fsl_qdma_queue *fsl_queue;
+
+	fsl_comp = to_fsl_qdma_comp(vdesc);
+	fsl_queue = fsl_comp->qchan->queue;
+
+	spin_lock_irqsave(&fsl_queue->queue_lock, flags);
+	list_add_tail(&fsl_comp->list, &fsl_queue->comp_free);
+	spin_unlock_irqrestore(&fsl_queue->queue_lock, flags);
+}
+
+static void fsl_qdma_issue_pending(struct dma_chan *chan)
+{
+	unsigned long flags;
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+
+	spin_lock_irqsave(&fsl_queue->queue_lock, flags);
+	spin_lock(&fsl_chan->vchan.lock);
+	if (vchan_issue_pending(&fsl_chan->vchan))
+		fsl_qdma_enqueue_desc(fsl_chan);
+	spin_unlock(&fsl_chan->vchan.lock);
+	spin_unlock_irqrestore(&fsl_queue->queue_lock, flags);
+}
+
+static void fsl_qdma_synchronize(struct dma_chan *chan)
+{
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+
+	vchan_synchronize(&fsl_chan->vchan);
+}
+
+static int fsl_qdma_terminate_all(struct dma_chan *chan)
+{
+	LIST_HEAD(head);
+	unsigned long flags;
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+
+	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
+	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
+	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
+	return 0;
+}
+
+static int fsl_qdma_alloc_chan_resources(struct dma_chan *chan)
+{
+	int ret;
+	struct fsl_qdma_chan *fsl_chan = to_fsl_qdma_chan(chan);
+	struct fsl_qdma_engine *fsl_qdma = fsl_chan->qdma;
+	struct fsl_qdma_queue *fsl_queue = fsl_chan->queue;
+
+	if (fsl_queue->comp_pool && fsl_queue->desc_pool)
+		return fsl_qdma->desc_allocated;
+
+	INIT_LIST_HEAD(&fsl_queue->comp_free);
+
+	/*
+	 * The dma pool for queue command buffer
+	 */
+	fsl_queue->comp_pool =
+	dma_pool_create("comp_pool",
+			chan->device->dev,
+			FSL_QDMA_COMMAND_BUFFER_SIZE,
+			64, 0);
+	if (!fsl_queue->comp_pool)
+		return -ENOMEM;
+
+	/*
+	 * The dma pool for Descriptor(SD/DD) buffer
+	 */
+	fsl_queue->desc_pool =
+	dma_pool_create("desc_pool",
+			chan->device->dev,
+			FSL_QDMA_DESCRIPTOR_BUFFER_SIZE,
+			32, 0);
+	if (!fsl_queue->desc_pool)
+		goto err_desc_pool;
+
+	ret = fsl_qdma_pre_request_enqueue_desc(fsl_queue);
+	if (ret) {
+		dev_err(chan->device->dev,
+			"failed to alloc dma buffer for S/G descriptor\n");
+		goto err_mem;
+	}
+
+	fsl_qdma->desc_allocated++;
+	return fsl_qdma->desc_allocated;
+
+err_mem:
+	dma_pool_destroy(fsl_queue->desc_pool);
+err_desc_pool:
+	dma_pool_destroy(fsl_queue->comp_pool);
+	return -ENOMEM;
+}
+
+static int fsl_qdma_probe(struct platform_device *pdev)
+{
+	int ret, i;
+	int blk_num, blk_off;
+	u32 len, chans, queues;
+	struct resource *res;
+	struct fsl_qdma_chan *fsl_chan;
+	struct fsl_qdma_engine *fsl_qdma;
+	struct device_node *np = pdev->dev.of_node;
+
+	ret = of_property_read_u32(np, "dma-channels", &chans);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get dma-channels.\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "block-offset", &blk_off);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get block-offset.\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "block-number", &blk_num);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get block-number.\n");
+		return ret;
+	}
+
+	blk_num = min_t(int, blk_num, num_online_cpus());
+
+	len = sizeof(*fsl_qdma);
+	fsl_qdma = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma)
+		return -ENOMEM;
+
+	len = sizeof(*fsl_chan) * chans;
+	fsl_qdma->chans = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma->chans)
+		return -ENOMEM;
+
+	len = sizeof(struct fsl_qdma_queue *) * blk_num;
+	fsl_qdma->status = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma->status)
+		return -ENOMEM;
+
+	len = sizeof(int) * blk_num;
+	fsl_qdma->queue_irq = devm_kzalloc(&pdev->dev, len, GFP_KERNEL);
+	if (!fsl_qdma->queue_irq)
+		return -ENOMEM;
+
+	ret = of_property_read_u32(np, "fsl,dma-queues", &queues);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't get queues.\n");
+		return ret;
+	}
+
+	fsl_qdma->desc_allocated = 0;
+	fsl_qdma->n_chans = chans;
+	fsl_qdma->n_queues = queues;
+	fsl_qdma->block_number = blk_num;
+	fsl_qdma->block_offset = blk_off;
+
+	mutex_init(&fsl_qdma->fsl_qdma_mutex);
+
+	for (i = 0; i < fsl_qdma->block_number; i++) {
+		fsl_qdma->status[i] = fsl_qdma_prep_status_queue(pdev);
+		if (!fsl_qdma->status[i])
+			return -ENOMEM;
+	}
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	fsl_qdma->ctrl_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->ctrl_base))
+		return PTR_ERR(fsl_qdma->ctrl_base);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	fsl_qdma->status_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->status_base))
+		return PTR_ERR(fsl_qdma->status_base);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+	fsl_qdma->block_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(fsl_qdma->block_base))
+		return PTR_ERR(fsl_qdma->block_base);
+	fsl_qdma->queue = fsl_qdma_alloc_queue_resources(pdev, fsl_qdma);
+	if (!fsl_qdma->queue)
+		return -ENOMEM;
+
+	ret = fsl_qdma_irq_init(pdev, fsl_qdma);
+	if (ret)
+		return ret;
+
+	fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0");
+	fsl_qdma->feature = of_property_read_bool(np, "big-endian");
+	INIT_LIST_HEAD(&fsl_qdma->dma_dev.channels);
+
+	for (i = 0; i < fsl_qdma->n_chans; i++) {
+		struct fsl_qdma_chan *fsl_chan = &fsl_qdma->chans[i];
+
+		fsl_chan->qdma = fsl_qdma;
+		fsl_chan->queue = fsl_qdma->queue + i % (fsl_qdma->n_queues *
+							fsl_qdma->block_number);
+		fsl_chan->vchan.desc_free = fsl_qdma_free_desc;
+		vchan_init(&fsl_chan->vchan, &fsl_qdma->dma_dev);
+	}
+
+	dma_cap_set(DMA_MEMCPY, fsl_qdma->dma_dev.cap_mask);
+
+	fsl_qdma->dma_dev.dev = &pdev->dev;
+	fsl_qdma->dma_dev.device_free_chan_resources =
+		fsl_qdma_free_chan_resources;
+	fsl_qdma->dma_dev.device_alloc_chan_resources =
+		fsl_qdma_alloc_chan_resources;
+	fsl_qdma->dma_dev.device_tx_status = dma_cookie_status;
+	fsl_qdma->dma_dev.device_prep_dma_memcpy = fsl_qdma_prep_memcpy;
+	fsl_qdma->dma_dev.device_issue_pending = fsl_qdma_issue_pending;
+	fsl_qdma->dma_dev.device_synchronize = fsl_qdma_synchronize;
+	fsl_qdma->dma_dev.device_terminate_all = fsl_qdma_terminate_all;
+
+	dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+
+	platform_set_drvdata(pdev, fsl_qdma);
+
+	ret = dma_async_device_register(&fsl_qdma->dma_dev);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"Can't register NXP Layerscape qDMA engine.\n");
+		return ret;
+	}
+
+	ret = fsl_qdma_reg_init(fsl_qdma);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't Initialize the qDMA engine.\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void fsl_qdma_cleanup_vchan(struct dma_device *dmadev)
+{
+	struct fsl_qdma_chan *chan, *_chan;
+
+	list_for_each_entry_safe(chan, _chan,
+				 &dmadev->channels, vchan.chan.device_node) {
+		list_del(&chan->vchan.chan.device_node);
+		tasklet_kill(&chan->vchan.task);
+	}
+}
+
+static int fsl_qdma_remove(struct platform_device *pdev)
+{
+	int i;
+	struct fsl_qdma_queue *status;
+	struct device_node *np = pdev->dev.of_node;
+	struct fsl_qdma_engine *fsl_qdma = platform_get_drvdata(pdev);
+
+	fsl_qdma_irq_exit(pdev, fsl_qdma);
+	fsl_qdma_cleanup_vchan(&fsl_qdma->dma_dev);
+	of_dma_controller_free(np);
+	dma_async_device_unregister(&fsl_qdma->dma_dev);
+
+	for (i = 0; i < fsl_qdma->block_number; i++) {
+		status = fsl_qdma->status[i];
+		dma_free_coherent(&pdev->dev, sizeof(struct fsl_qdma_format) *
+				status->n_cq, status->cq, status->bus_addr);
+	}
+	return 0;
+}
+
+static const struct of_device_id fsl_qdma_dt_ids[] = {
+	{ .compatible = "fsl,ls1021a-qdma", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, fsl_qdma_dt_ids);
+
+static struct platform_driver fsl_qdma_driver = {
+	.driver		= {
+		.name	= "fsl-qdma",
+		.of_match_table = fsl_qdma_dt_ids,
+	},
+	.probe          = fsl_qdma_probe,
+	.remove		= fsl_qdma_remove,
+};
+
+module_platform_driver(fsl_qdma_driver);
+
+MODULE_ALIAS("platform:fsl-qdma");
+MODULE_DESCRIPTION("NXP Layerscape qDMA engine driver");
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 9d360a3fbae3..1e38e6b94006 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -53,42 +53,42 @@ static const char msg_ld_oom[] = "No free memory for link descriptor";
 
 static void set_sr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->sr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->sr, val, 32);
 }
 
 static u32 get_sr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->sr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->sr, 32);
 }
 
 static void set_mr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->mr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->mr, val, 32);
 }
 
 static u32 get_mr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->mr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->mr, 32);
 }
 
 static void set_cdar(struct fsldma_chan *chan, dma_addr_t addr)
 {
-	DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
+	FSL_DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
 }
 
 static dma_addr_t get_cdar(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
+	return FSL_DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
 }
 
 static void set_bcr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->bcr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->bcr, val, 32);
 }
 
 static u32 get_bcr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->bcr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->bcr, 32);
 }
 
 /*
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 4787d485dd76..88db939c04a1 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -196,39 +196,62 @@ struct fsldma_chan {
 #define to_fsl_desc(lh) container_of(lh, struct fsl_desc_sw, node)
 #define tx_to_fsl_desc(tx) container_of(tx, struct fsl_desc_sw, async_tx)
 
+#ifdef	CONFIG_PPC
+#define fsl_ioread32(p)		in_le32(p)
+#define fsl_ioread32be(p)	in_be32(p)
+#define fsl_iowrite32(v, p)	out_le32(p, v)
+#define fsl_iowrite32be(v, p)	out_be32(p, v)
+
 #ifndef __powerpc64__
-static u64 in_be64(const u64 __iomem *addr)
+static u64 fsl_ioread64(const u64 __iomem *addr)
 {
-	return ((u64)in_be32((u32 __iomem *)addr) << 32) |
-		(in_be32((u32 __iomem *)addr + 1));
+	u32 fsl_addr = lower_32_bits(addr);
+	u64 fsl_addr_hi = (u64)in_le32((u32 *)(fsl_addr + 1)) << 32;
+
+	return fsl_addr_hi | in_le32((u32 *)fsl_addr);
 }
 
-static void out_be64(u64 __iomem *addr, u64 val)
+static void fsl_iowrite64(u64 val, u64 __iomem *addr)
 {
-	out_be32((u32 __iomem *)addr, val >> 32);
-	out_be32((u32 __iomem *)addr + 1, (u32)val);
+	out_le32((u32 __iomem *)addr + 1, val >> 32);
+	out_le32((u32 __iomem *)addr, (u32)val);
 }
 
-/* There is no asm instructions for 64 bits reverse loads and stores */
-static u64 in_le64(const u64 __iomem *addr)
+static u64 fsl_ioread64be(const u64 __iomem *addr)
 {
-	return ((u64)in_le32((u32 __iomem *)addr + 1) << 32) |
-		(in_le32((u32 __iomem *)addr));
+	u32 fsl_addr = lower_32_bits(addr);
+	u64 fsl_addr_hi = (u64)in_be32((u32 *)fsl_addr) << 32;
+
+	return fsl_addr_hi | in_be32((u32 *)(fsl_addr + 1));
 }
 
-static void out_le64(u64 __iomem *addr, u64 val)
+static void fsl_iowrite64be(u64 val, u64 __iomem *addr)
 {
-	out_le32((u32 __iomem *)addr + 1, val >> 32);
-	out_le32((u32 __iomem *)addr, (u32)val);
+	out_be32((u32 __iomem *)addr, val >> 32);
+	out_be32((u32 __iomem *)addr + 1, (u32)val);
 }
 #endif
+#endif
 
-#define DMA_IN(fsl_chan, addr, width)					\
-		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\
-			in_be##width(addr) : in_le##width(addr))
-#define DMA_OUT(fsl_chan, addr, val, width)				\
-		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\
-			out_be##width(addr, val) : out_le##width(addr, val))
+#if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
+#define fsl_ioread32(p)		ioread32(p)
+#define fsl_ioread32be(p)	ioread32be(p)
+#define fsl_iowrite32(v, p)	iowrite32(v, p)
+#define fsl_iowrite32be(v, p)	iowrite32be(v, p)
+#define fsl_ioread64(p)		ioread64(p)
+#define fsl_ioread64be(p)	ioread64be(p)
+#define fsl_iowrite64(v, p)	iowrite64(v, p)
+#define fsl_iowrite64be(v, p)	iowrite64be(v, p)
+#endif
+
+#define FSL_DMA_IN(fsl_dma, addr, width)			\
+		(((fsl_dma)->feature & FSL_DMA_BIG_ENDIAN) ?	\
+			fsl_ioread##width##be(addr) : fsl_ioread##width(addr))
+
+#define FSL_DMA_OUT(fsl_dma, addr, val, width)			\
+		(((fsl_dma)->feature & FSL_DMA_BIG_ENDIAN) ?	\
+			fsl_iowrite##width##be(val, addr) : fsl_iowrite	\
+		##width(val, addr))
 
 #define DMA_TO_CPU(fsl_chan, d, width)					\
 		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index cb1b44d78a1f..a2b0a0e71168 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -335,6 +335,7 @@ struct sdma_desc {
  * @sdma:		pointer to the SDMA engine for this channel
  * @channel:		the channel number, matches dmaengine chan_id + 1
  * @direction:		transfer type. Needed for setting SDMA script
+ * @slave_config	Slave configuration
  * @peripheral_type:	Peripheral type. Needed for setting SDMA script
  * @event_id0:		aka dma request line
  * @event_id1:		for channels that use 2 events
@@ -362,6 +363,7 @@ struct sdma_channel {
 	struct sdma_engine		*sdma;
 	unsigned int			channel;
 	enum dma_transfer_direction		direction;
+	struct dma_slave_config		slave_config;
 	enum sdma_peripheral_type	peripheral_type;
 	unsigned int			event_id0;
 	unsigned int			event_id1;
@@ -440,6 +442,10 @@ struct sdma_engine {
 	struct sdma_buffer_descriptor	*bd0;
 };
 
+static int sdma_config_write(struct dma_chan *chan,
+		       struct dma_slave_config *dmaengine_cfg,
+		       enum dma_transfer_direction direction);
+
 static struct sdma_driver_data sdma_imx31 = {
 	.chnenbl0 = SDMA_CHNENBL0_IMX31,
 	.num_events = 32,
@@ -671,9 +677,7 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size,
 	int ret;
 	unsigned long flags;
 
-	buf_virt = dma_alloc_coherent(NULL,
-			size,
-			&buf_phys, GFP_KERNEL);
+	buf_virt = dma_alloc_coherent(NULL, size, &buf_phys, GFP_KERNEL);
 	if (!buf_virt) {
 		return -ENOMEM;
 	}
@@ -1122,18 +1126,6 @@ static int sdma_config_channel(struct dma_chan *chan)
 	sdmac->shp_addr = 0;
 	sdmac->per_addr = 0;
 
-	if (sdmac->event_id0) {
-		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
-			return -EINVAL;
-		sdma_event_enable(sdmac, sdmac->event_id0);
-	}
-
-	if (sdmac->event_id1) {
-		if (sdmac->event_id1 >= sdmac->sdma->drvdata->num_events)
-			return -EINVAL;
-		sdma_event_enable(sdmac, sdmac->event_id1);
-	}
-
 	switch (sdmac->peripheral_type) {
 	case IMX_DMATYPE_DSP:
 		sdma_config_ownership(sdmac, false, true, true);
@@ -1431,6 +1423,8 @@ static struct dma_async_tx_descriptor *sdma_prep_slave_sg(
 	struct scatterlist *sg;
 	struct sdma_desc *desc;
 
+	sdma_config_write(chan, &sdmac->slave_config, direction);
+
 	desc = sdma_transfer_init(sdmac, direction, sg_len);
 	if (!desc)
 		goto err_out;
@@ -1515,6 +1509,8 @@ static struct dma_async_tx_descriptor *sdma_prep_dma_cyclic(
 
 	dev_dbg(sdma->dev, "%s channel: %d\n", __func__, channel);
 
+	sdma_config_write(chan, &sdmac->slave_config, direction);
+
 	desc = sdma_transfer_init(sdmac, direction, num_periods);
 	if (!desc)
 		goto err_out;
@@ -1570,17 +1566,18 @@ err_out:
 	return NULL;
 }
 
-static int sdma_config(struct dma_chan *chan,
-		       struct dma_slave_config *dmaengine_cfg)
+static int sdma_config_write(struct dma_chan *chan,
+		       struct dma_slave_config *dmaengine_cfg,
+		       enum dma_transfer_direction direction)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
 
-	if (dmaengine_cfg->direction == DMA_DEV_TO_MEM) {
+	if (direction == DMA_DEV_TO_MEM) {
 		sdmac->per_address = dmaengine_cfg->src_addr;
 		sdmac->watermark_level = dmaengine_cfg->src_maxburst *
 			dmaengine_cfg->src_addr_width;
 		sdmac->word_size = dmaengine_cfg->src_addr_width;
-	} else if (dmaengine_cfg->direction == DMA_DEV_TO_DEV) {
+	} else if (direction == DMA_DEV_TO_DEV) {
 		sdmac->per_address2 = dmaengine_cfg->src_addr;
 		sdmac->per_address = dmaengine_cfg->dst_addr;
 		sdmac->watermark_level = dmaengine_cfg->src_maxburst &
@@ -1594,10 +1591,33 @@ static int sdma_config(struct dma_chan *chan,
 			dmaengine_cfg->dst_addr_width;
 		sdmac->word_size = dmaengine_cfg->dst_addr_width;
 	}
-	sdmac->direction = dmaengine_cfg->direction;
+	sdmac->direction = direction;
 	return sdma_config_channel(chan);
 }
 
+static int sdma_config(struct dma_chan *chan,
+		       struct dma_slave_config *dmaengine_cfg)
+{
+	struct sdma_channel *sdmac = to_sdma_chan(chan);
+
+	memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
+
+	/* Set ENBLn earlier to make sure dma request triggered after that */
+	if (sdmac->event_id0) {
+		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
+			return -EINVAL;
+		sdma_event_enable(sdmac, sdmac->event_id0);
+	}
+
+	if (sdmac->event_id1) {
+		if (sdmac->event_id1 >= sdmac->sdma->drvdata->num_events)
+			return -EINVAL;
+		sdma_event_enable(sdmac, sdmac->event_id1);
+	}
+
+	return 0;
+}
+
 static enum dma_status sdma_tx_status(struct dma_chan *chan,
 				      dma_cookie_t cookie,
 				      struct dma_tx_state *txstate)
diff --git a/drivers/dma/mediatek/Kconfig b/drivers/dma/mediatek/Kconfig
index 27bac0bba09e..680fc0572d87 100644
--- a/drivers/dma/mediatek/Kconfig
+++ b/drivers/dma/mediatek/Kconfig
@@ -11,3 +11,16 @@ config MTK_HSDMA
 	  This controller provides the channels which is dedicated to
 	  memory-to-memory transfer to offload from CPU through ring-
 	  based descriptor management.
+
+config MTK_CQDMA
+	tristate "MediaTek Command-Queue DMA controller support"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+	help
+	  Enable support for Command-Queue DMA controller on MediaTek
+	  SoCs.
+
+	  This controller provides the channels which is dedicated to
+	  memory-to-memory transfer to offload from CPU.
diff --git a/drivers/dma/mediatek/Makefile b/drivers/dma/mediatek/Makefile
index 6e778f842f01..41bb3815f636 100644
--- a/drivers/dma/mediatek/Makefile
+++ b/drivers/dma/mediatek/Makefile
@@ -1 +1,2 @@
 obj-$(CONFIG_MTK_HSDMA) += mtk-hsdma.o
+obj-$(CONFIG_MTK_CQDMA) += mtk-cqdma.o
diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c
new file mode 100644
index 000000000000..131f3974740d
--- /dev/null
+++ b/drivers/dma/mediatek/mtk-cqdma.c
@@ -0,0 +1,951 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018-2019 MediaTek Inc.
+
+/*
+ * Driver for MediaTek Command-Queue DMA Controller
+ *
+ * Author: Shun-Chih Yu <shun-chih.yu@mediatek.com>
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/iopoll.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
+
+#include "../virt-dma.h"
+
+#define MTK_CQDMA_USEC_POLL		10
+#define MTK_CQDMA_TIMEOUT_POLL		1000
+#define MTK_CQDMA_DMA_BUSWIDTHS		BIT(DMA_SLAVE_BUSWIDTH_4_BYTES)
+#define MTK_CQDMA_ALIGN_SIZE		1
+
+/* The default number of virtual channel */
+#define MTK_CQDMA_NR_VCHANS		32
+
+/* The default number of physical channel */
+#define MTK_CQDMA_NR_PCHANS		3
+
+/* Registers for underlying dma manipulation */
+#define MTK_CQDMA_INT_FLAG		0x0
+#define MTK_CQDMA_INT_EN		0x4
+#define MTK_CQDMA_EN			0x8
+#define MTK_CQDMA_RESET			0xc
+#define MTK_CQDMA_FLUSH			0x14
+#define MTK_CQDMA_SRC			0x1c
+#define MTK_CQDMA_DST			0x20
+#define MTK_CQDMA_LEN1			0x24
+#define MTK_CQDMA_LEN2			0x28
+#define MTK_CQDMA_SRC2			0x60
+#define MTK_CQDMA_DST2			0x64
+
+/* Registers setting */
+#define MTK_CQDMA_EN_BIT		BIT(0)
+#define MTK_CQDMA_INT_FLAG_BIT		BIT(0)
+#define MTK_CQDMA_INT_EN_BIT		BIT(0)
+#define MTK_CQDMA_FLUSH_BIT		BIT(0)
+
+#define MTK_CQDMA_WARM_RST_BIT		BIT(0)
+#define MTK_CQDMA_HARD_RST_BIT		BIT(1)
+
+#define MTK_CQDMA_MAX_LEN		GENMASK(27, 0)
+#define MTK_CQDMA_ADDR_LIMIT		GENMASK(31, 0)
+#define MTK_CQDMA_ADDR2_SHFIT		(32)
+
+/**
+ * struct mtk_cqdma_vdesc - The struct holding info describing virtual
+ *                         descriptor (CVD)
+ * @vd:                    An instance for struct virt_dma_desc
+ * @len:                   The total data size device wants to move
+ * @residue:               The remaining data size device will move
+ * @dest:                  The destination address device wants to move to
+ * @src:                   The source address device wants to move from
+ * @ch:                    The pointer to the corresponding dma channel
+ * @node:                  The lise_head struct to build link-list for VDs
+ * @parent:                The pointer to the parent CVD
+ */
+struct mtk_cqdma_vdesc {
+	struct virt_dma_desc vd;
+	size_t len;
+	size_t residue;
+	dma_addr_t dest;
+	dma_addr_t src;
+	struct dma_chan *ch;
+
+	struct list_head node;
+	struct mtk_cqdma_vdesc *parent;
+};
+
+/**
+ * struct mtk_cqdma_pchan - The struct holding info describing physical
+ *                         channel (PC)
+ * @queue:                 Queue for the PDs issued to this PC
+ * @base:                  The mapped register I/O base of this PC
+ * @irq:                   The IRQ that this PC are using
+ * @refcnt:                Track how many VCs are using this PC
+ * @tasklet:               Tasklet for this PC
+ * @lock:                  Lock protect agaisting multiple VCs access PC
+ */
+struct mtk_cqdma_pchan {
+	struct list_head queue;
+	void __iomem *base;
+	u32 irq;
+
+	refcount_t refcnt;
+
+	struct tasklet_struct tasklet;
+
+	/* lock to protect PC */
+	spinlock_t lock;
+};
+
+/**
+ * struct mtk_cqdma_vchan - The struct holding info describing virtual
+ *                         channel (VC)
+ * @vc:                    An instance for struct virt_dma_chan
+ * @pc:                    The pointer to the underlying PC
+ * @issue_completion:	   The wait for all issued descriptors completited
+ * @issue_synchronize:	   Bool indicating channel synchronization starts
+ */
+struct mtk_cqdma_vchan {
+	struct virt_dma_chan vc;
+	struct mtk_cqdma_pchan *pc;
+	struct completion issue_completion;
+	bool issue_synchronize;
+};
+
+/**
+ * struct mtk_cqdma_device - The struct holding info describing CQDMA
+ *                          device
+ * @ddev:                   An instance for struct dma_device
+ * @clk:                    The clock that device internal is using
+ * @dma_requests:           The number of VCs the device supports to
+ * @dma_channels:           The number of PCs the device supports to
+ * @vc:                     The pointer to all available VCs
+ * @pc:                     The pointer to all the underlying PCs
+ */
+struct mtk_cqdma_device {
+	struct dma_device ddev;
+	struct clk *clk;
+
+	u32 dma_requests;
+	u32 dma_channels;
+	struct mtk_cqdma_vchan *vc;
+	struct mtk_cqdma_pchan **pc;
+};
+
+static struct mtk_cqdma_device *to_cqdma_dev(struct dma_chan *chan)
+{
+	return container_of(chan->device, struct mtk_cqdma_device, ddev);
+}
+
+static struct mtk_cqdma_vchan *to_cqdma_vchan(struct dma_chan *chan)
+{
+	return container_of(chan, struct mtk_cqdma_vchan, vc.chan);
+}
+
+static struct mtk_cqdma_vdesc *to_cqdma_vdesc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct mtk_cqdma_vdesc, vd);
+}
+
+static struct device *cqdma2dev(struct mtk_cqdma_device *cqdma)
+{
+	return cqdma->ddev.dev;
+}
+
+static u32 mtk_dma_read(struct mtk_cqdma_pchan *pc, u32 reg)
+{
+	return readl(pc->base + reg);
+}
+
+static void mtk_dma_write(struct mtk_cqdma_pchan *pc, u32 reg, u32 val)
+{
+	writel_relaxed(val, pc->base + reg);
+}
+
+static void mtk_dma_rmw(struct mtk_cqdma_pchan *pc, u32 reg,
+			u32 mask, u32 set)
+{
+	u32 val;
+
+	val = mtk_dma_read(pc, reg);
+	val &= ~mask;
+	val |= set;
+	mtk_dma_write(pc, reg, val);
+}
+
+static void mtk_dma_set(struct mtk_cqdma_pchan *pc, u32 reg, u32 val)
+{
+	mtk_dma_rmw(pc, reg, 0, val);
+}
+
+static void mtk_dma_clr(struct mtk_cqdma_pchan *pc, u32 reg, u32 val)
+{
+	mtk_dma_rmw(pc, reg, val, 0);
+}
+
+static void mtk_cqdma_vdesc_free(struct virt_dma_desc *vd)
+{
+	kfree(to_cqdma_vdesc(vd));
+}
+
+static int mtk_cqdma_poll_engine_done(struct mtk_cqdma_pchan *pc, bool atomic)
+{
+	u32 status = 0;
+
+	if (!atomic)
+		return readl_poll_timeout(pc->base + MTK_CQDMA_EN,
+					  status,
+					  !(status & MTK_CQDMA_EN_BIT),
+					  MTK_CQDMA_USEC_POLL,
+					  MTK_CQDMA_TIMEOUT_POLL);
+
+	return readl_poll_timeout_atomic(pc->base + MTK_CQDMA_EN,
+					 status,
+					 !(status & MTK_CQDMA_EN_BIT),
+					 MTK_CQDMA_USEC_POLL,
+					 MTK_CQDMA_TIMEOUT_POLL);
+}
+
+static int mtk_cqdma_hard_reset(struct mtk_cqdma_pchan *pc)
+{
+	mtk_dma_set(pc, MTK_CQDMA_RESET, MTK_CQDMA_HARD_RST_BIT);
+	mtk_dma_clr(pc, MTK_CQDMA_RESET, MTK_CQDMA_HARD_RST_BIT);
+
+	return mtk_cqdma_poll_engine_done(pc, false);
+}
+
+static void mtk_cqdma_start(struct mtk_cqdma_pchan *pc,
+			    struct mtk_cqdma_vdesc *cvd)
+{
+	/* wait for the previous transaction done */
+	if (mtk_cqdma_poll_engine_done(pc, true) < 0)
+		dev_err(cqdma2dev(to_cqdma_dev(cvd->ch)), "cqdma wait transaction timeout\n");
+
+	/* warm reset the dma engine for the new transaction */
+	mtk_dma_set(pc, MTK_CQDMA_RESET, MTK_CQDMA_WARM_RST_BIT);
+	if (mtk_cqdma_poll_engine_done(pc, true) < 0)
+		dev_err(cqdma2dev(to_cqdma_dev(cvd->ch)), "cqdma warm reset timeout\n");
+
+	/* setup the source */
+	mtk_dma_set(pc, MTK_CQDMA_SRC, cvd->src & MTK_CQDMA_ADDR_LIMIT);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	mtk_dma_set(pc, MTK_CQDMA_SRC2, cvd->src >> MTK_CQDMA_ADDR2_SHFIT);
+#else
+	mtk_dma_set(pc, MTK_CQDMA_SRC2, 0);
+#endif
+
+	/* setup the destination */
+	mtk_dma_set(pc, MTK_CQDMA_DST, cvd->dest & MTK_CQDMA_ADDR_LIMIT);
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	mtk_dma_set(pc, MTK_CQDMA_DST2, cvd->dest >> MTK_CQDMA_ADDR2_SHFIT);
+#else
+	mtk_dma_set(pc, MTK_CQDMA_SRC2, 0);
+#endif
+
+	/* setup the length */
+	mtk_dma_set(pc, MTK_CQDMA_LEN1, cvd->len);
+
+	/* start dma engine */
+	mtk_dma_set(pc, MTK_CQDMA_EN, MTK_CQDMA_EN_BIT);
+}
+
+static void mtk_cqdma_issue_vchan_pending(struct mtk_cqdma_vchan *cvc)
+{
+	struct virt_dma_desc *vd, *vd2;
+	struct mtk_cqdma_pchan *pc = cvc->pc;
+	struct mtk_cqdma_vdesc *cvd;
+	bool trigger_engine = false;
+
+	lockdep_assert_held(&cvc->vc.lock);
+	lockdep_assert_held(&pc->lock);
+
+	list_for_each_entry_safe(vd, vd2, &cvc->vc.desc_issued, node) {
+		/* need to trigger dma engine if PC's queue is empty */
+		if (list_empty(&pc->queue))
+			trigger_engine = true;
+
+		cvd = to_cqdma_vdesc(vd);
+
+		/* add VD into PC's queue */
+		list_add_tail(&cvd->node, &pc->queue);
+
+		/* start the dma engine */
+		if (trigger_engine)
+			mtk_cqdma_start(pc, cvd);
+
+		/* remove VD from list desc_issued */
+		list_del(&vd->node);
+	}
+}
+
+/*
+ * return true if this VC is active,
+ * meaning that there are VDs under processing by the PC
+ */
+static bool mtk_cqdma_is_vchan_active(struct mtk_cqdma_vchan *cvc)
+{
+	struct mtk_cqdma_vdesc *cvd;
+
+	list_for_each_entry(cvd, &cvc->pc->queue, node)
+		if (cvc == to_cqdma_vchan(cvd->ch))
+			return true;
+
+	return false;
+}
+
+/*
+ * return the pointer of the CVD that is just consumed by the PC
+ */
+static struct mtk_cqdma_vdesc
+*mtk_cqdma_consume_work_queue(struct mtk_cqdma_pchan *pc)
+{
+	struct mtk_cqdma_vchan *cvc;
+	struct mtk_cqdma_vdesc *cvd, *ret = NULL;
+
+	/* consume a CVD from PC's queue */
+	cvd = list_first_entry_or_null(&pc->queue,
+				       struct mtk_cqdma_vdesc, node);
+	if (unlikely(!cvd || !cvd->parent))
+		return NULL;
+
+	cvc = to_cqdma_vchan(cvd->ch);
+	ret = cvd;
+
+	/* update residue of the parent CVD */
+	cvd->parent->residue -= cvd->len;
+
+	/* delete CVD from PC's queue */
+	list_del(&cvd->node);
+
+	spin_lock(&cvc->vc.lock);
+
+	/* check whether all the child CVDs completed */
+	if (!cvd->parent->residue) {
+		/* add the parent VD into list desc_completed */
+		vchan_cookie_complete(&cvd->parent->vd);
+
+		/* setup completion if this VC is under synchronization */
+		if (cvc->issue_synchronize && !mtk_cqdma_is_vchan_active(cvc)) {
+			complete(&cvc->issue_completion);
+			cvc->issue_synchronize = false;
+		}
+	}
+
+	spin_unlock(&cvc->vc.lock);
+
+	/* start transaction for next CVD in the queue */
+	cvd = list_first_entry_or_null(&pc->queue,
+				       struct mtk_cqdma_vdesc, node);
+	if (cvd)
+		mtk_cqdma_start(pc, cvd);
+
+	return ret;
+}
+
+static void mtk_cqdma_tasklet_cb(unsigned long data)
+{
+	struct mtk_cqdma_pchan *pc = (struct mtk_cqdma_pchan *)data;
+	struct mtk_cqdma_vdesc *cvd = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pc->lock, flags);
+	/* consume the queue */
+	cvd = mtk_cqdma_consume_work_queue(pc);
+	spin_unlock_irqrestore(&pc->lock, flags);
+
+	/* submit the next CVD */
+	if (cvd) {
+		dma_run_dependencies(&cvd->vd.tx);
+
+		/*
+		 * free child CVD after completion.
+		 * the parent CVD would be freeed with desc_free by user.
+		 */
+		if (cvd->parent != cvd)
+			kfree(cvd);
+	}
+
+	/* re-enable interrupt before leaving tasklet */
+	enable_irq(pc->irq);
+}
+
+static irqreturn_t mtk_cqdma_irq(int irq, void *devid)
+{
+	struct mtk_cqdma_device *cqdma = devid;
+	irqreturn_t ret = IRQ_NONE;
+	bool schedule_tasklet = false;
+	u32 i;
+
+	/* clear interrupt flags for each PC */
+	for (i = 0; i < cqdma->dma_channels; ++i, schedule_tasklet = false) {
+		spin_lock(&cqdma->pc[i]->lock);
+		if (mtk_dma_read(cqdma->pc[i],
+				 MTK_CQDMA_INT_FLAG) & MTK_CQDMA_INT_FLAG_BIT) {
+			/* clear interrupt */
+			mtk_dma_clr(cqdma->pc[i], MTK_CQDMA_INT_FLAG,
+				    MTK_CQDMA_INT_FLAG_BIT);
+
+			schedule_tasklet = true;
+			ret = IRQ_HANDLED;
+		}
+		spin_unlock(&cqdma->pc[i]->lock);
+
+		if (schedule_tasklet) {
+			/* disable interrupt */
+			disable_irq_nosync(cqdma->pc[i]->irq);
+
+			/* schedule the tasklet to handle the transactions */
+			tasklet_schedule(&cqdma->pc[i]->tasklet);
+		}
+	}
+
+	return ret;
+}
+
+static struct virt_dma_desc *mtk_cqdma_find_active_desc(struct dma_chan *c,
+							dma_cookie_t cookie)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cvc->pc->lock, flags);
+	list_for_each_entry(vd, &cvc->pc->queue, node)
+		if (vd->tx.cookie == cookie) {
+			spin_unlock_irqrestore(&cvc->pc->lock, flags);
+			return vd;
+		}
+	spin_unlock_irqrestore(&cvc->pc->lock, flags);
+
+	list_for_each_entry(vd, &cvc->vc.desc_issued, node)
+		if (vd->tx.cookie == cookie)
+			return vd;
+
+	return NULL;
+}
+
+static enum dma_status mtk_cqdma_tx_status(struct dma_chan *c,
+					   dma_cookie_t cookie,
+					   struct dma_tx_state *txstate)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	struct mtk_cqdma_vdesc *cvd;
+	struct virt_dma_desc *vd;
+	enum dma_status ret;
+	unsigned long flags;
+	size_t bytes = 0;
+
+	ret = dma_cookie_status(c, cookie, txstate);
+	if (ret == DMA_COMPLETE || !txstate)
+		return ret;
+
+	spin_lock_irqsave(&cvc->vc.lock, flags);
+	vd = mtk_cqdma_find_active_desc(c, cookie);
+	spin_unlock_irqrestore(&cvc->vc.lock, flags);
+
+	if (vd) {
+		cvd = to_cqdma_vdesc(vd);
+		bytes = cvd->residue;
+	}
+
+	dma_set_residue(txstate, bytes);
+
+	return ret;
+}
+
+static void mtk_cqdma_issue_pending(struct dma_chan *c)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	unsigned long pc_flags;
+	unsigned long vc_flags;
+
+	/* acquire PC's lock before VS's lock for lock dependency in tasklet */
+	spin_lock_irqsave(&cvc->pc->lock, pc_flags);
+	spin_lock_irqsave(&cvc->vc.lock, vc_flags);
+
+	if (vchan_issue_pending(&cvc->vc))
+		mtk_cqdma_issue_vchan_pending(cvc);
+
+	spin_unlock_irqrestore(&cvc->vc.lock, vc_flags);
+	spin_unlock_irqrestore(&cvc->pc->lock, pc_flags);
+}
+
+static struct dma_async_tx_descriptor *
+mtk_cqdma_prep_dma_memcpy(struct dma_chan *c, dma_addr_t dest,
+			  dma_addr_t src, size_t len, unsigned long flags)
+{
+	struct mtk_cqdma_vdesc **cvd;
+	struct dma_async_tx_descriptor *tx = NULL, *prev_tx = NULL;
+	size_t i, tlen, nr_vd;
+
+	/*
+	 * In the case that trsanction length is larger than the
+	 * DMA engine supports, a single memcpy transaction needs
+	 * to be separated into several DMA transactions.
+	 * Each DMA transaction would be described by a CVD,
+	 * and the first one is referred as the parent CVD,
+	 * while the others are child CVDs.
+	 * The parent CVD's tx descriptor is the only tx descriptor
+	 * returned to the DMA user, and it should not be completed
+	 * until all the child CVDs completed.
+	 */
+	nr_vd = DIV_ROUND_UP(len, MTK_CQDMA_MAX_LEN);
+	cvd = kcalloc(nr_vd, sizeof(*cvd), GFP_NOWAIT);
+	if (!cvd)
+		return NULL;
+
+	for (i = 0; i < nr_vd; ++i) {
+		cvd[i] = kzalloc(sizeof(*cvd[i]), GFP_NOWAIT);
+		if (!cvd[i]) {
+			for (; i > 0; --i)
+				kfree(cvd[i - 1]);
+			return NULL;
+		}
+
+		/* setup dma channel */
+		cvd[i]->ch = c;
+
+		/* setup sourece, destination, and length */
+		tlen = (len > MTK_CQDMA_MAX_LEN) ? MTK_CQDMA_MAX_LEN : len;
+		cvd[i]->len = tlen;
+		cvd[i]->src = src;
+		cvd[i]->dest = dest;
+
+		/* setup tx descriptor */
+		tx = vchan_tx_prep(to_virt_chan(c), &cvd[i]->vd, flags);
+		tx->next = NULL;
+
+		if (!i) {
+			cvd[0]->residue = len;
+		} else {
+			prev_tx->next = tx;
+			cvd[i]->residue = tlen;
+		}
+
+		cvd[i]->parent = cvd[0];
+
+		/* update the src, dest, len, prev_tx for the next CVD */
+		src += tlen;
+		dest += tlen;
+		len -= tlen;
+		prev_tx = tx;
+	}
+
+	return &cvd[0]->vd.tx;
+}
+
+static void mtk_cqdma_free_inactive_desc(struct dma_chan *c)
+{
+	struct virt_dma_chan *vc = to_virt_chan(c);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	/*
+	 * set desc_allocated, desc_submitted,
+	 * and desc_issued as the candicates to be freed
+	 */
+	spin_lock_irqsave(&vc->lock, flags);
+	list_splice_tail_init(&vc->desc_allocated, &head);
+	list_splice_tail_init(&vc->desc_submitted, &head);
+	list_splice_tail_init(&vc->desc_issued, &head);
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	/* free descriptor lists */
+	vchan_dma_desc_free_list(vc, &head);
+}
+
+static void mtk_cqdma_free_active_desc(struct dma_chan *c)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	bool sync_needed = false;
+	unsigned long pc_flags;
+	unsigned long vc_flags;
+
+	/* acquire PC's lock first due to lock dependency in dma ISR */
+	spin_lock_irqsave(&cvc->pc->lock, pc_flags);
+	spin_lock_irqsave(&cvc->vc.lock, vc_flags);
+
+	/* synchronization is required if this VC is active */
+	if (mtk_cqdma_is_vchan_active(cvc)) {
+		cvc->issue_synchronize = true;
+		sync_needed = true;
+	}
+
+	spin_unlock_irqrestore(&cvc->vc.lock, vc_flags);
+	spin_unlock_irqrestore(&cvc->pc->lock, pc_flags);
+
+	/* waiting for the completion of this VC */
+	if (sync_needed)
+		wait_for_completion(&cvc->issue_completion);
+
+	/* free all descriptors in list desc_completed */
+	vchan_synchronize(&cvc->vc);
+
+	WARN_ONCE(!list_empty(&cvc->vc.desc_completed),
+		  "Desc pending still in list desc_completed\n");
+}
+
+static int mtk_cqdma_terminate_all(struct dma_chan *c)
+{
+	/* free descriptors not processed yet by hardware */
+	mtk_cqdma_free_inactive_desc(c);
+
+	/* free descriptors being processed by hardware */
+	mtk_cqdma_free_active_desc(c);
+
+	return 0;
+}
+
+static int mtk_cqdma_alloc_chan_resources(struct dma_chan *c)
+{
+	struct mtk_cqdma_device *cqdma = to_cqdma_dev(c);
+	struct mtk_cqdma_vchan *vc = to_cqdma_vchan(c);
+	struct mtk_cqdma_pchan *pc = NULL;
+	u32 i, min_refcnt = U32_MAX, refcnt;
+	unsigned long flags;
+
+	/* allocate PC with the minimun refcount */
+	for (i = 0; i < cqdma->dma_channels; ++i) {
+		refcnt = refcount_read(&cqdma->pc[i]->refcnt);
+		if (refcnt < min_refcnt) {
+			pc = cqdma->pc[i];
+			min_refcnt = refcnt;
+		}
+	}
+
+	if (!pc)
+		return -ENOSPC;
+
+	spin_lock_irqsave(&pc->lock, flags);
+
+	if (!refcount_read(&pc->refcnt)) {
+		/* allocate PC when the refcount is zero */
+		mtk_cqdma_hard_reset(pc);
+
+		/* enable interrupt for this PC */
+		mtk_dma_set(pc, MTK_CQDMA_INT_EN, MTK_CQDMA_INT_EN_BIT);
+
+		/*
+		 * refcount_inc would complain increment on 0; use-after-free.
+		 * Thus, we need to explicitly set it as 1 initially.
+		 */
+		refcount_set(&pc->refcnt, 1);
+	} else {
+		refcount_inc(&pc->refcnt);
+	}
+
+	spin_unlock_irqrestore(&pc->lock, flags);
+
+	vc->pc = pc;
+
+	return 0;
+}
+
+static void mtk_cqdma_free_chan_resources(struct dma_chan *c)
+{
+	struct mtk_cqdma_vchan *cvc = to_cqdma_vchan(c);
+	unsigned long flags;
+
+	/* free all descriptors in all lists on the VC */
+	mtk_cqdma_terminate_all(c);
+
+	spin_lock_irqsave(&cvc->pc->lock, flags);
+
+	/* PC is not freed until there is no VC mapped to it */
+	if (refcount_dec_and_test(&cvc->pc->refcnt)) {
+		/* start the flush operation and stop the engine */
+		mtk_dma_set(cvc->pc, MTK_CQDMA_FLUSH, MTK_CQDMA_FLUSH_BIT);
+
+		/* wait for the completion of flush operation */
+		if (mtk_cqdma_poll_engine_done(cvc->pc, false) < 0)
+			dev_err(cqdma2dev(to_cqdma_dev(c)), "cqdma flush timeout\n");
+
+		/* clear the flush bit and interrupt flag */
+		mtk_dma_clr(cvc->pc, MTK_CQDMA_FLUSH, MTK_CQDMA_FLUSH_BIT);
+		mtk_dma_clr(cvc->pc, MTK_CQDMA_INT_FLAG,
+			    MTK_CQDMA_INT_FLAG_BIT);
+
+		/* disable interrupt for this PC */
+		mtk_dma_clr(cvc->pc, MTK_CQDMA_INT_EN, MTK_CQDMA_INT_EN_BIT);
+	}
+
+	spin_unlock_irqrestore(&cvc->pc->lock, flags);
+}
+
+static int mtk_cqdma_hw_init(struct mtk_cqdma_device *cqdma)
+{
+	unsigned long flags;
+	int err;
+	u32 i;
+
+	pm_runtime_enable(cqdma2dev(cqdma));
+	pm_runtime_get_sync(cqdma2dev(cqdma));
+
+	err = clk_prepare_enable(cqdma->clk);
+
+	if (err) {
+		pm_runtime_put_sync(cqdma2dev(cqdma));
+		pm_runtime_disable(cqdma2dev(cqdma));
+		return err;
+	}
+
+	/* reset all PCs */
+	for (i = 0; i < cqdma->dma_channels; ++i) {
+		spin_lock_irqsave(&cqdma->pc[i]->lock, flags);
+		if (mtk_cqdma_hard_reset(cqdma->pc[i]) < 0) {
+			dev_err(cqdma2dev(cqdma), "cqdma hard reset timeout\n");
+			spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags);
+
+			clk_disable_unprepare(cqdma->clk);
+			pm_runtime_put_sync(cqdma2dev(cqdma));
+			pm_runtime_disable(cqdma2dev(cqdma));
+			return -EINVAL;
+		}
+		spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags);
+	}
+
+	return 0;
+}
+
+static void mtk_cqdma_hw_deinit(struct mtk_cqdma_device *cqdma)
+{
+	unsigned long flags;
+	u32 i;
+
+	/* reset all PCs */
+	for (i = 0; i < cqdma->dma_channels; ++i) {
+		spin_lock_irqsave(&cqdma->pc[i]->lock, flags);
+		if (mtk_cqdma_hard_reset(cqdma->pc[i]) < 0)
+			dev_err(cqdma2dev(cqdma), "cqdma hard reset timeout\n");
+		spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags);
+	}
+
+	clk_disable_unprepare(cqdma->clk);
+
+	pm_runtime_put_sync(cqdma2dev(cqdma));
+	pm_runtime_disable(cqdma2dev(cqdma));
+}
+
+static const struct of_device_id mtk_cqdma_match[] = {
+	{ .compatible = "mediatek,mt6765-cqdma" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, mtk_cqdma_match);
+
+static int mtk_cqdma_probe(struct platform_device *pdev)
+{
+	struct mtk_cqdma_device *cqdma;
+	struct mtk_cqdma_vchan *vc;
+	struct dma_device *dd;
+	struct resource *res;
+	int err;
+	u32 i;
+
+	cqdma = devm_kzalloc(&pdev->dev, sizeof(*cqdma), GFP_KERNEL);
+	if (!cqdma)
+		return -ENOMEM;
+
+	dd = &cqdma->ddev;
+
+	cqdma->clk = devm_clk_get(&pdev->dev, "cqdma");
+	if (IS_ERR(cqdma->clk)) {
+		dev_err(&pdev->dev, "No clock for %s\n",
+			dev_name(&pdev->dev));
+		return PTR_ERR(cqdma->clk);
+	}
+
+	dma_cap_set(DMA_MEMCPY, dd->cap_mask);
+
+	dd->copy_align = MTK_CQDMA_ALIGN_SIZE;
+	dd->device_alloc_chan_resources = mtk_cqdma_alloc_chan_resources;
+	dd->device_free_chan_resources = mtk_cqdma_free_chan_resources;
+	dd->device_tx_status = mtk_cqdma_tx_status;
+	dd->device_issue_pending = mtk_cqdma_issue_pending;
+	dd->device_prep_dma_memcpy = mtk_cqdma_prep_dma_memcpy;
+	dd->device_terminate_all = mtk_cqdma_terminate_all;
+	dd->src_addr_widths = MTK_CQDMA_DMA_BUSWIDTHS;
+	dd->dst_addr_widths = MTK_CQDMA_DMA_BUSWIDTHS;
+	dd->directions = BIT(DMA_MEM_TO_MEM);
+	dd->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	dd->dev = &pdev->dev;
+	INIT_LIST_HEAD(&dd->channels);
+
+	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
+						      "dma-requests",
+						      &cqdma->dma_requests)) {
+		dev_info(&pdev->dev,
+			 "Using %u as missing dma-requests property\n",
+			 MTK_CQDMA_NR_VCHANS);
+
+		cqdma->dma_requests = MTK_CQDMA_NR_VCHANS;
+	}
+
+	if (pdev->dev.of_node && of_property_read_u32(pdev->dev.of_node,
+						      "dma-channels",
+						      &cqdma->dma_channels)) {
+		dev_info(&pdev->dev,
+			 "Using %u as missing dma-channels property\n",
+			 MTK_CQDMA_NR_PCHANS);
+
+		cqdma->dma_channels = MTK_CQDMA_NR_PCHANS;
+	}
+
+	cqdma->pc = devm_kcalloc(&pdev->dev, cqdma->dma_channels,
+				 sizeof(*cqdma->pc), GFP_KERNEL);
+	if (!cqdma->pc)
+		return -ENOMEM;
+
+	/* initialization for PCs */
+	for (i = 0; i < cqdma->dma_channels; ++i) {
+		cqdma->pc[i] = devm_kcalloc(&pdev->dev, 1,
+					    sizeof(**cqdma->pc), GFP_KERNEL);
+		if (!cqdma->pc[i])
+			return -ENOMEM;
+
+		INIT_LIST_HEAD(&cqdma->pc[i]->queue);
+		spin_lock_init(&cqdma->pc[i]->lock);
+		refcount_set(&cqdma->pc[i]->refcnt, 0);
+
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+		if (!res) {
+			dev_err(&pdev->dev, "No mem resource for %s\n",
+				dev_name(&pdev->dev));
+			return -EINVAL;
+		}
+
+		cqdma->pc[i]->base = devm_ioremap_resource(&pdev->dev, res);
+		if (IS_ERR(cqdma->pc[i]->base))
+			return PTR_ERR(cqdma->pc[i]->base);
+
+		/* allocate IRQ resource */
+		res = platform_get_resource(pdev, IORESOURCE_IRQ, i);
+		if (!res) {
+			dev_err(&pdev->dev, "No irq resource for %s\n",
+				dev_name(&pdev->dev));
+			return -EINVAL;
+		}
+		cqdma->pc[i]->irq = res->start;
+
+		err = devm_request_irq(&pdev->dev, cqdma->pc[i]->irq,
+				       mtk_cqdma_irq, 0, dev_name(&pdev->dev),
+				       cqdma);
+		if (err) {
+			dev_err(&pdev->dev,
+				"request_irq failed with err %d\n", err);
+			return -EINVAL;
+		}
+	}
+
+	/* allocate resource for VCs */
+	cqdma->vc = devm_kcalloc(&pdev->dev, cqdma->dma_requests,
+				 sizeof(*cqdma->vc), GFP_KERNEL);
+	if (!cqdma->vc)
+		return -ENOMEM;
+
+	for (i = 0; i < cqdma->dma_requests; i++) {
+		vc = &cqdma->vc[i];
+		vc->vc.desc_free = mtk_cqdma_vdesc_free;
+		vchan_init(&vc->vc, dd);
+		init_completion(&vc->issue_completion);
+	}
+
+	err = dma_async_device_register(dd);
+	if (err)
+		return err;
+
+	err = of_dma_controller_register(pdev->dev.of_node,
+					 of_dma_xlate_by_chan_id, cqdma);
+	if (err) {
+		dev_err(&pdev->dev,
+			"MediaTek CQDMA OF registration failed %d\n", err);
+		goto err_unregister;
+	}
+
+	err = mtk_cqdma_hw_init(cqdma);
+	if (err) {
+		dev_err(&pdev->dev,
+			"MediaTek CQDMA HW initialization failed %d\n", err);
+		goto err_unregister;
+	}
+
+	platform_set_drvdata(pdev, cqdma);
+
+	/* initialize tasklet for each PC */
+	for (i = 0; i < cqdma->dma_channels; ++i)
+		tasklet_init(&cqdma->pc[i]->tasklet, mtk_cqdma_tasklet_cb,
+			     (unsigned long)cqdma->pc[i]);
+
+	dev_info(&pdev->dev, "MediaTek CQDMA driver registered\n");
+
+	return 0;
+
+err_unregister:
+	dma_async_device_unregister(dd);
+
+	return err;
+}
+
+static int mtk_cqdma_remove(struct platform_device *pdev)
+{
+	struct mtk_cqdma_device *cqdma = platform_get_drvdata(pdev);
+	struct mtk_cqdma_vchan *vc;
+	unsigned long flags;
+	int i;
+
+	/* kill VC task */
+	for (i = 0; i < cqdma->dma_requests; i++) {
+		vc = &cqdma->vc[i];
+
+		list_del(&vc->vc.chan.device_node);
+		tasklet_kill(&vc->vc.task);
+	}
+
+	/* disable interrupt */
+	for (i = 0; i < cqdma->dma_channels; i++) {
+		spin_lock_irqsave(&cqdma->pc[i]->lock, flags);
+		mtk_dma_clr(cqdma->pc[i], MTK_CQDMA_INT_EN,
+			    MTK_CQDMA_INT_EN_BIT);
+		spin_unlock_irqrestore(&cqdma->pc[i]->lock, flags);
+
+		/* Waits for any pending IRQ handlers to complete */
+		synchronize_irq(cqdma->pc[i]->irq);
+
+		tasklet_kill(&cqdma->pc[i]->tasklet);
+	}
+
+	/* disable hardware */
+	mtk_cqdma_hw_deinit(cqdma);
+
+	dma_async_device_unregister(&cqdma->ddev);
+	of_dma_controller_free(pdev->dev.of_node);
+
+	return 0;
+}
+
+static struct platform_driver mtk_cqdma_driver = {
+	.probe = mtk_cqdma_probe,
+	.remove = mtk_cqdma_remove,
+	.driver = {
+		.name           = KBUILD_MODNAME,
+		.of_match_table = mtk_cqdma_match,
+	},
+};
+module_platform_driver(mtk_cqdma_driver);
+
+MODULE_DESCRIPTION("MediaTek CQDMA Controller Driver");
+MODULE_AUTHOR("Shun-Chih Yu <shun-chih.yu@mediatek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index eb3a1f42ab06..334bab92d26d 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -96,6 +96,7 @@ struct mmp_pdma_chan {
 	struct dma_async_tx_descriptor desc;
 	struct mmp_pdma_phy *phy;
 	enum dma_transfer_direction dir;
+	struct dma_slave_config slave_config;
 
 	struct mmp_pdma_desc_sw *cyclic_first;	/* first desc_sw if channel
 						 * is in cyclic mode */
@@ -140,6 +141,10 @@ struct mmp_pdma_device {
 #define to_mmp_pdma_dev(dmadev)					\
 	container_of(dmadev, struct mmp_pdma_device, device)
 
+static int mmp_pdma_config_write(struct dma_chan *dchan,
+			   struct dma_slave_config *cfg,
+			   enum dma_transfer_direction direction);
+
 static void set_desc(struct mmp_pdma_phy *phy, dma_addr_t addr)
 {
 	u32 reg = (phy->idx << 4) + DDADR;
@@ -537,6 +542,8 @@ mmp_pdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
 
 	chan->byte_align = false;
 
+	mmp_pdma_config_write(dchan, &chan->slave_config, dir);
+
 	for_each_sg(sgl, sg, sg_len, i) {
 		addr = sg_dma_address(sg);
 		avail = sg_dma_len(sgl);
@@ -619,6 +626,7 @@ mmp_pdma_prep_dma_cyclic(struct dma_chan *dchan,
 		return NULL;
 
 	chan = to_mmp_pdma_chan(dchan);
+	mmp_pdma_config_write(dchan, &chan->slave_config, direction);
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
@@ -684,8 +692,9 @@ fail:
 	return NULL;
 }
 
-static int mmp_pdma_config(struct dma_chan *dchan,
-			   struct dma_slave_config *cfg)
+static int mmp_pdma_config_write(struct dma_chan *dchan,
+			   struct dma_slave_config *cfg,
+			   enum dma_transfer_direction direction)
 {
 	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
 	u32 maxburst = 0, addr = 0;
@@ -694,12 +703,12 @@ static int mmp_pdma_config(struct dma_chan *dchan,
 	if (!dchan)
 		return -EINVAL;
 
-	if (cfg->direction == DMA_DEV_TO_MEM) {
+	if (direction == DMA_DEV_TO_MEM) {
 		chan->dcmd = DCMD_INCTRGADDR | DCMD_FLOWSRC;
 		maxburst = cfg->src_maxburst;
 		width = cfg->src_addr_width;
 		addr = cfg->src_addr;
-	} else if (cfg->direction == DMA_MEM_TO_DEV) {
+	} else if (direction == DMA_MEM_TO_DEV) {
 		chan->dcmd = DCMD_INCSRCADDR | DCMD_FLOWTRG;
 		maxburst = cfg->dst_maxburst;
 		width = cfg->dst_addr_width;
@@ -720,7 +729,7 @@ static int mmp_pdma_config(struct dma_chan *dchan,
 	else if (maxburst == 32)
 		chan->dcmd |= DCMD_BURST32;
 
-	chan->dir = cfg->direction;
+	chan->dir = direction;
 	chan->dev_addr = addr;
 	/* FIXME: drivers should be ported over to use the filter
 	 * function. Once that's done, the following two lines can
@@ -732,6 +741,15 @@ static int mmp_pdma_config(struct dma_chan *dchan,
 	return 0;
 }
 
+static int mmp_pdma_config(struct dma_chan *dchan,
+			   struct dma_slave_config *cfg)
+{
+	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
+
+	memcpy(&chan->slave_config, cfg, sizeof(*cfg));
+	return 0;
+}
+
 static int mmp_pdma_terminate_all(struct dma_chan *dchan)
 {
 	struct mmp_pdma_chan *chan = to_mmp_pdma_chan(dchan);
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 88750a34e859..cff1b143fff5 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -448,6 +448,7 @@ struct dma_pl330_chan {
 	/* DMA-mapped view of the FIFO; may differ if an IOMMU is present */
 	dma_addr_t fifo_dma;
 	enum dma_data_direction dir;
+	struct dma_slave_config slave_config;
 
 	/* for cyclic capability */
 	bool cyclic;
@@ -542,6 +543,10 @@ struct _xfer_spec {
 	struct dma_pl330_desc *desc;
 };
 
+static int pl330_config_write(struct dma_chan *chan,
+			struct dma_slave_config *slave_config,
+			enum dma_transfer_direction direction);
+
 static inline bool _queue_full(struct pl330_thread *thrd)
 {
 	return thrd->req[0].desc != NULL && thrd->req[1].desc != NULL;
@@ -2220,20 +2225,21 @@ static int fixup_burst_len(int max_burst_len, int quirks)
 		return max_burst_len;
 }
 
-static int pl330_config(struct dma_chan *chan,
-			struct dma_slave_config *slave_config)
+static int pl330_config_write(struct dma_chan *chan,
+			struct dma_slave_config *slave_config,
+			enum dma_transfer_direction direction)
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
 
 	pl330_unprep_slave_fifo(pch);
-	if (slave_config->direction == DMA_MEM_TO_DEV) {
+	if (direction == DMA_MEM_TO_DEV) {
 		if (slave_config->dst_addr)
 			pch->fifo_addr = slave_config->dst_addr;
 		if (slave_config->dst_addr_width)
 			pch->burst_sz = __ffs(slave_config->dst_addr_width);
 		pch->burst_len = fixup_burst_len(slave_config->dst_maxburst,
 			pch->dmac->quirks);
-	} else if (slave_config->direction == DMA_DEV_TO_MEM) {
+	} else if (direction == DMA_DEV_TO_MEM) {
 		if (slave_config->src_addr)
 			pch->fifo_addr = slave_config->src_addr;
 		if (slave_config->src_addr_width)
@@ -2245,6 +2251,16 @@ static int pl330_config(struct dma_chan *chan,
 	return 0;
 }
 
+static int pl330_config(struct dma_chan *chan,
+			struct dma_slave_config *slave_config)
+{
+	struct dma_pl330_chan *pch = to_pchan(chan);
+
+	memcpy(&pch->slave_config, slave_config, sizeof(*slave_config));
+
+	return 0;
+}
+
 static int pl330_terminate_all(struct dma_chan *chan)
 {
 	struct dma_pl330_chan *pch = to_pchan(chan);
@@ -2661,6 +2677,8 @@ static struct dma_async_tx_descriptor *pl330_prep_dma_cyclic(
 		return NULL;
 	}
 
+	pl330_config_write(chan, &pch->slave_config, direction);
+
 	if (!pl330_prep_slave_fifo(pch, direction))
 		return NULL;
 
@@ -2815,6 +2833,8 @@ pl330_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (unlikely(!pch || !sgl || !sg_len))
 		return NULL;
 
+	pl330_config_write(chan, &pch->slave_config, direction);
+
 	if (!pl330_prep_slave_fifo(pch, direction))
 		return NULL;
 
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
index b31d07c7d93c..784d5f1a473b 100644
--- a/drivers/dma/sa11x0-dma.c
+++ b/drivers/dma/sa11x0-dma.c
@@ -17,7 +17,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/sa11x0-dma.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
@@ -830,6 +829,14 @@ static const struct dma_slave_map sa11x0_dma_map[] = {
 	{ "sa11x0-ssp", "rx", "Ser4SSPRc" },
 };
 
+static bool sa11x0_dma_filter_fn(struct dma_chan *chan, void *param)
+{
+	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
+	const char *p = param;
+
+	return !strcmp(c->name, p);
+}
+
 static int sa11x0_dma_init_dmadev(struct dma_device *dmadev,
 	struct device *dev)
 {
@@ -1087,18 +1094,6 @@ static struct platform_driver sa11x0_dma_driver = {
 	.remove		= sa11x0_dma_remove,
 };
 
-bool sa11x0_dma_filter_fn(struct dma_chan *chan, void *param)
-{
-	if (chan->device->dev->driver == &sa11x0_dma_driver.driver) {
-		struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
-		const char *p = param;
-
-		return !strcmp(c->name, p);
-	}
-	return false;
-}
-EXPORT_SYMBOL(sa11x0_dma_filter_fn);
-
 static int __init sa11x0_dma_init(void)
 {
 	return platform_driver_register(&sa11x0_dma_driver);
diff --git a/drivers/dma/sh/Kconfig b/drivers/dma/sh/Kconfig
index 6e0685f1a838..4d6b02b3b1f1 100644
--- a/drivers/dma/sh/Kconfig
+++ b/drivers/dma/sh/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 #
 # DMA engine configuration for sh
 #
@@ -12,7 +13,7 @@ config RENESAS_DMA
 
 config SH_DMAE_BASE
 	bool "Renesas SuperH DMA Engine support"
-	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
+	depends on SUPERH || COMPILE_TEST
 	depends on !SUPERH || SH_DMA
 	depends on !SH_DMA_API
 	default y
@@ -30,15 +31,6 @@ config SH_DMAE
 	help
 	  Enable support for the Renesas SuperH DMA controllers.
 
-if SH_DMAE
-
-config SH_DMAE_R8A73A4
-	def_bool y
-	depends on ARCH_R8A73A4
-	depends on OF
-
-endif
-
 config RCAR_DMAC
 	tristate "Renesas R-Car Gen2 DMA Controller"
 	depends on ARCH_RENESAS || COMPILE_TEST
diff --git a/drivers/dma/sh/Makefile b/drivers/dma/sh/Makefile
index 7d7c9491ade1..42110dd57a56 100644
--- a/drivers/dma/sh/Makefile
+++ b/drivers/dma/sh/Makefile
@@ -10,7 +10,6 @@ obj-$(CONFIG_SH_DMAE_BASE) += shdma-base.o shdma-of.o
 #
 
 shdma-y := shdmac.o
-shdma-$(CONFIG_SH_DMAE_R8A73A4) += shdma-r8a73a4.o
 shdma-objs := $(shdma-y)
 obj-$(CONFIG_SH_DMAE) += shdma.o
 
diff --git a/drivers/dma/sh/shdma-r8a73a4.c b/drivers/dma/sh/shdma-r8a73a4.c
deleted file mode 100644
index ddc9a3578353..000000000000
--- a/drivers/dma/sh/shdma-r8a73a4.c
+++ /dev/null
@@ -1,74 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Renesas SuperH DMA Engine support for r8a73a4 (APE6) SoCs
- *
- * Copyright (C) 2013 Renesas Electronics, Inc.
- */
-#include <linux/sh_dma.h>
-
-#include "shdma-arm.h"
-
-static const unsigned int dma_ts_shift[] = SH_DMAE_TS_SHIFT;
-
-static const struct sh_dmae_slave_config dma_slaves[] = {
-	{
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd1,		/* MMC0 Tx */
-	}, {
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xd2,		/* MMC0 Rx */
-	}, {
-		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xe1,		/* MMC1 Tx */
-	}, {
-		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
-		.mid_rid	= 0xe2,		/* MMC1 Rx */
-	},
-};
-
-#define DMAE_CHANNEL(a, b)				\
-	{						\
-		.offset         = (a) - 0x20,		\
-		.dmars          = (a) - 0x20 + 0x40,	\
-		.chclr_bit	= (b),			\
-		.chclr_offset	= 0x80 - 0x20,		\
-	}
-
-static const struct sh_dmae_channel dma_channels[] = {
-	DMAE_CHANNEL(0x8000, 0),
-	DMAE_CHANNEL(0x8080, 1),
-	DMAE_CHANNEL(0x8100, 2),
-	DMAE_CHANNEL(0x8180, 3),
-	DMAE_CHANNEL(0x8200, 4),
-	DMAE_CHANNEL(0x8280, 5),
-	DMAE_CHANNEL(0x8300, 6),
-	DMAE_CHANNEL(0x8380, 7),
-	DMAE_CHANNEL(0x8400, 8),
-	DMAE_CHANNEL(0x8480, 9),
-	DMAE_CHANNEL(0x8500, 10),
-	DMAE_CHANNEL(0x8580, 11),
-	DMAE_CHANNEL(0x8600, 12),
-	DMAE_CHANNEL(0x8680, 13),
-	DMAE_CHANNEL(0x8700, 14),
-	DMAE_CHANNEL(0x8780, 15),
-	DMAE_CHANNEL(0x8800, 16),
-	DMAE_CHANNEL(0x8880, 17),
-	DMAE_CHANNEL(0x8900, 18),
-	DMAE_CHANNEL(0x8980, 19),
-};
-
-const struct sh_dmae_pdata r8a73a4_dma_pdata = {
-	.slave		= dma_slaves,
-	.slave_num	= ARRAY_SIZE(dma_slaves),
-	.channel	= dma_channels,
-	.channel_num	= ARRAY_SIZE(dma_channels),
-	.ts_low_shift	= TS_LOW_SHIFT,
-	.ts_low_mask	= TS_LOW_BIT << TS_LOW_SHIFT,
-	.ts_high_shift	= TS_HI_SHIFT,
-	.ts_high_mask	= TS_HI_BIT << TS_HI_SHIFT,
-	.ts_shift	= dma_ts_shift,
-	.ts_shift_num	= ARRAY_SIZE(dma_ts_shift),
-	.dmaor_init     = DMAOR_DME,
-	.chclr_present	= 1,
-	.chclr_bitwise	= 1,
-};
diff --git a/drivers/dma/sh/shdma.h b/drivers/dma/sh/shdma.h
index bfb69909bd19..9c121a4b33ad 100644
--- a/drivers/dma/sh/shdma.h
+++ b/drivers/dma/sh/shdma.h
@@ -58,11 +58,4 @@ struct sh_dmae_desc {
 #define to_sh_dev(chan) container_of(chan->shdma_chan.dma_chan.device,\
 				     struct sh_dmae_device, shdma_dev.dma_dev)
 
-#ifdef CONFIG_SH_DMAE_R8A73A4
-extern const struct sh_dmae_pdata r8a73a4_dma_pdata;
-#define r8a73a4_shdma_devid (&r8a73a4_dma_pdata)
-#else
-#define r8a73a4_shdma_devid NULL
-#endif
-
 #endif	/* __DMA_SHDMA_H */
diff --git a/drivers/dma/sh/shdmac.c b/drivers/dma/sh/shdmac.c
index 7971ea275387..5aafe548ca5f 100644
--- a/drivers/dma/sh/shdmac.c
+++ b/drivers/dma/sh/shdmac.c
@@ -665,12 +665,6 @@ static const struct shdma_ops sh_dmae_shdma_ops = {
 	.get_partial = sh_dmae_get_partial,
 };
 
-static const struct of_device_id sh_dmae_of_match[] = {
-	{.compatible = "renesas,shdma-r8a73a4", .data = r8a73a4_shdma_devid,},
-	{}
-};
-MODULE_DEVICE_TABLE(of, sh_dmae_of_match);
-
 static int sh_dmae_probe(struct platform_device *pdev)
 {
 	const enum dma_slave_buswidth widths =
@@ -915,7 +909,6 @@ static struct platform_driver sh_dmae_driver = {
 	.driver		= {
 		.pm	= &sh_dmae_pm,
 		.name	= SH_DMAE_DRV_NAME,
-		.of_match_table = sh_dmae_of_match,
 	},
 	.remove		= sh_dmae_remove,
 };
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index 38d4e4f07c66..e2f016700fcc 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -36,6 +36,8 @@
 #define SPRD_DMA_GLB_CHN_EN_STS		0x1c
 #define SPRD_DMA_GLB_DEBUG_STS		0x20
 #define SPRD_DMA_GLB_ARB_SEL_STS	0x24
+#define SPRD_DMA_GLB_2STAGE_GRP1	0x28
+#define SPRD_DMA_GLB_2STAGE_GRP2	0x2c
 #define SPRD_DMA_GLB_REQ_UID(uid)	(0x4 * ((uid) - 1))
 #define SPRD_DMA_GLB_REQ_UID_OFFSET	0x2000
 
@@ -57,6 +59,18 @@
 #define SPRD_DMA_CHN_SRC_BLK_STEP	0x38
 #define SPRD_DMA_CHN_DES_BLK_STEP	0x3c
 
+/* SPRD_DMA_GLB_2STAGE_GRP register definition */
+#define SPRD_DMA_GLB_2STAGE_EN		BIT(24)
+#define SPRD_DMA_GLB_CHN_INT_MASK	GENMASK(23, 20)
+#define SPRD_DMA_GLB_LIST_DONE_TRG	BIT(19)
+#define SPRD_DMA_GLB_TRANS_DONE_TRG	BIT(18)
+#define SPRD_DMA_GLB_BLOCK_DONE_TRG	BIT(17)
+#define SPRD_DMA_GLB_FRAG_DONE_TRG	BIT(16)
+#define SPRD_DMA_GLB_TRG_OFFSET		16
+#define SPRD_DMA_GLB_DEST_CHN_MASK	GENMASK(13, 8)
+#define SPRD_DMA_GLB_DEST_CHN_OFFSET	8
+#define SPRD_DMA_GLB_SRC_CHN_MASK	GENMASK(5, 0)
+
 /* SPRD_DMA_CHN_INTC register definition */
 #define SPRD_DMA_INT_MASK		GENMASK(4, 0)
 #define SPRD_DMA_INT_CLR_OFFSET		24
@@ -118,6 +132,10 @@
 #define SPRD_DMA_SRC_TRSF_STEP_OFFSET	0
 #define SPRD_DMA_TRSF_STEP_MASK		GENMASK(15, 0)
 
+/* define DMA channel mode & trigger mode mask */
+#define SPRD_DMA_CHN_MODE_MASK		GENMASK(7, 0)
+#define SPRD_DMA_TRG_MODE_MASK		GENMASK(7, 0)
+
 /* define the DMA transfer step type */
 #define SPRD_DMA_NONE_STEP		0
 #define SPRD_DMA_BYTE_STEP		1
@@ -159,6 +177,7 @@ struct sprd_dma_chn_hw {
 struct sprd_dma_desc {
 	struct virt_dma_desc	vd;
 	struct sprd_dma_chn_hw	chn_hw;
+	enum dma_transfer_direction dir;
 };
 
 /* dma channel description */
@@ -169,6 +188,8 @@ struct sprd_dma_chn {
 	struct dma_slave_config	slave_cfg;
 	u32			chn_num;
 	u32			dev_id;
+	enum sprd_dma_chn_mode	chn_mode;
+	enum sprd_dma_trg_mode	trg_mode;
 	struct sprd_dma_desc	*cur_desc;
 };
 
@@ -205,6 +226,16 @@ static inline struct sprd_dma_desc *to_sprd_dma_desc(struct virt_dma_desc *vd)
 	return container_of(vd, struct sprd_dma_desc, vd);
 }
 
+static void sprd_dma_glb_update(struct sprd_dma_dev *sdev, u32 reg,
+				u32 mask, u32 val)
+{
+	u32 orig = readl(sdev->glb_base + reg);
+	u32 tmp;
+
+	tmp = (orig & ~mask) | val;
+	writel(tmp, sdev->glb_base + reg);
+}
+
 static void sprd_dma_chn_update(struct sprd_dma_chn *schan, u32 reg,
 				u32 mask, u32 val)
 {
@@ -331,6 +362,17 @@ static void sprd_dma_stop_and_disable(struct sprd_dma_chn *schan)
 	sprd_dma_disable_chn(schan);
 }
 
+static unsigned long sprd_dma_get_src_addr(struct sprd_dma_chn *schan)
+{
+	unsigned long addr, addr_high;
+
+	addr = readl(schan->chn_base + SPRD_DMA_CHN_SRC_ADDR);
+	addr_high = readl(schan->chn_base + SPRD_DMA_CHN_WARP_PTR) &
+		    SPRD_DMA_HIGH_ADDR_MASK;
+
+	return addr | (addr_high << SPRD_DMA_HIGH_ADDR_OFFSET);
+}
+
 static unsigned long sprd_dma_get_dst_addr(struct sprd_dma_chn *schan)
 {
 	unsigned long addr, addr_high;
@@ -377,6 +419,49 @@ static enum sprd_dma_req_mode sprd_dma_get_req_type(struct sprd_dma_chn *schan)
 	return (frag_reg >> SPRD_DMA_REQ_MODE_OFFSET) & SPRD_DMA_REQ_MODE_MASK;
 }
 
+static int sprd_dma_set_2stage_config(struct sprd_dma_chn *schan)
+{
+	struct sprd_dma_dev *sdev = to_sprd_dma_dev(&schan->vc.chan);
+	u32 val, chn = schan->chn_num + 1;
+
+	switch (schan->chn_mode) {
+	case SPRD_DMA_SRC_CHN0:
+		val = chn & SPRD_DMA_GLB_SRC_CHN_MASK;
+		val |= BIT(schan->trg_mode - 1) << SPRD_DMA_GLB_TRG_OFFSET;
+		val |= SPRD_DMA_GLB_2STAGE_EN;
+		sprd_dma_glb_update(sdev, SPRD_DMA_GLB_2STAGE_GRP1, val, val);
+		break;
+
+	case SPRD_DMA_SRC_CHN1:
+		val = chn & SPRD_DMA_GLB_SRC_CHN_MASK;
+		val |= BIT(schan->trg_mode - 1) << SPRD_DMA_GLB_TRG_OFFSET;
+		val |= SPRD_DMA_GLB_2STAGE_EN;
+		sprd_dma_glb_update(sdev, SPRD_DMA_GLB_2STAGE_GRP2, val, val);
+		break;
+
+	case SPRD_DMA_DST_CHN0:
+		val = (chn << SPRD_DMA_GLB_DEST_CHN_OFFSET) &
+			SPRD_DMA_GLB_DEST_CHN_MASK;
+		val |= SPRD_DMA_GLB_2STAGE_EN;
+		sprd_dma_glb_update(sdev, SPRD_DMA_GLB_2STAGE_GRP1, val, val);
+		break;
+
+	case SPRD_DMA_DST_CHN1:
+		val = (chn << SPRD_DMA_GLB_DEST_CHN_OFFSET) &
+			SPRD_DMA_GLB_DEST_CHN_MASK;
+		val |= SPRD_DMA_GLB_2STAGE_EN;
+		sprd_dma_glb_update(sdev, SPRD_DMA_GLB_2STAGE_GRP2, val, val);
+		break;
+
+	default:
+		dev_err(sdev->dma_dev.dev, "invalid channel mode setting %d\n",
+			schan->chn_mode);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void sprd_dma_set_chn_config(struct sprd_dma_chn *schan,
 				    struct sprd_dma_desc *sdesc)
 {
@@ -411,6 +496,13 @@ static void sprd_dma_start(struct sprd_dma_chn *schan)
 	schan->cur_desc = to_sprd_dma_desc(vd);
 
 	/*
+	 * Set 2-stage configuration if the channel starts one 2-stage
+	 * transfer.
+	 */
+	if (schan->chn_mode && sprd_dma_set_2stage_config(schan))
+		return;
+
+	/*
 	 * Copy the DMA configuration from DMA descriptor to this hardware
 	 * channel.
 	 */
@@ -427,6 +519,7 @@ static void sprd_dma_stop(struct sprd_dma_chn *schan)
 	sprd_dma_stop_and_disable(schan);
 	sprd_dma_unset_uid(schan);
 	sprd_dma_clear_int(schan);
+	schan->cur_desc = NULL;
 }
 
 static bool sprd_dma_check_trans_done(struct sprd_dma_desc *sdesc,
@@ -450,7 +543,7 @@ static irqreturn_t dma_irq_handle(int irq, void *dev_id)
 	struct sprd_dma_desc *sdesc;
 	enum sprd_dma_req_mode req_type;
 	enum sprd_dma_int_type int_type;
-	bool trans_done = false;
+	bool trans_done = false, cyclic = false;
 	u32 i;
 
 	while (irq_status) {
@@ -465,13 +558,19 @@ static irqreturn_t dma_irq_handle(int irq, void *dev_id)
 
 		sdesc = schan->cur_desc;
 
-		/* Check if the dma request descriptor is done. */
-		trans_done = sprd_dma_check_trans_done(sdesc, int_type,
-						       req_type);
-		if (trans_done == true) {
-			vchan_cookie_complete(&sdesc->vd);
-			schan->cur_desc = NULL;
-			sprd_dma_start(schan);
+		/* cyclic mode schedule callback */
+		cyclic = schan->linklist.phy_addr ? true : false;
+		if (cyclic == true) {
+			vchan_cyclic_callback(&sdesc->vd);
+		} else {
+			/* Check if the dma request descriptor is done. */
+			trans_done = sprd_dma_check_trans_done(sdesc, int_type,
+							       req_type);
+			if (trans_done == true) {
+				vchan_cookie_complete(&sdesc->vd);
+				schan->cur_desc = NULL;
+				sprd_dma_start(schan);
+			}
 		}
 		spin_unlock(&schan->vc.lock);
 	}
@@ -534,7 +633,12 @@ static enum dma_status sprd_dma_tx_status(struct dma_chan *chan,
 		else
 			pos = 0;
 	} else if (schan->cur_desc && schan->cur_desc->vd.tx.cookie == cookie) {
-		pos = sprd_dma_get_dst_addr(schan);
+		struct sprd_dma_desc *sdesc = to_sprd_dma_desc(vd);
+
+		if (sdesc->dir == DMA_DEV_TO_MEM)
+			pos = sprd_dma_get_dst_addr(schan);
+		else
+			pos = sprd_dma_get_src_addr(schan);
 	} else {
 		pos = 0;
 	}
@@ -593,6 +697,7 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 {
 	struct sprd_dma_dev *sdev = to_sprd_dma_dev(chan);
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
+	enum sprd_dma_chn_mode chn_mode = schan->chn_mode;
 	u32 req_mode = (flags >> SPRD_DMA_REQ_SHIFT) & SPRD_DMA_REQ_MODE_MASK;
 	u32 int_mode = flags & SPRD_DMA_INT_MASK;
 	int src_datawidth, dst_datawidth, src_step, dst_step;
@@ -604,7 +709,16 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 			dev_err(sdev->dma_dev.dev, "invalid source step\n");
 			return src_step;
 		}
-		dst_step = SPRD_DMA_NONE_STEP;
+
+		/*
+		 * For 2-stage transfer, destination channel step can not be 0,
+		 * since destination device is AON IRAM.
+		 */
+		if (chn_mode == SPRD_DMA_DST_CHN0 ||
+		    chn_mode == SPRD_DMA_DST_CHN1)
+			dst_step = src_step;
+		else
+			dst_step = SPRD_DMA_NONE_STEP;
 	} else {
 		dst_step = sprd_dma_get_step(slave_cfg->dst_addr_width);
 		if (dst_step < 0) {
@@ -674,13 +788,11 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 
 	/* link-list configuration */
 	if (schan->linklist.phy_addr) {
-		if (sg_index == sglen - 1)
-			hw->frg_len |= SPRD_DMA_LLIST_END;
-
 		hw->cfg |= SPRD_DMA_LINKLIST_EN;
 
 		/* link-list index */
-		temp = (sg_index + 1) % sglen;
+		temp = sglen ? (sg_index + 1) % sglen : 0;
+
 		/* Next link-list configuration's physical address offset */
 		temp = temp * sizeof(*hw) + SPRD_DMA_CHN_SRC_ADDR;
 		/*
@@ -804,6 +916,8 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (!sdesc)
 		return NULL;
 
+	sdesc->dir = dir;
+
 	for_each_sg(sgl, sg, sglen, i) {
 		len = sg_dma_len(sg);
 
@@ -831,6 +945,12 @@ sprd_dma_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 		}
 	}
 
+	/* Set channel mode and trigger mode for 2-stage transfer */
+	schan->chn_mode =
+		(flags >> SPRD_DMA_CHN_MODE_SHIFT) & SPRD_DMA_CHN_MODE_MASK;
+	schan->trg_mode =
+		(flags >> SPRD_DMA_TRG_MODE_SHIFT) & SPRD_DMA_TRG_MODE_MASK;
+
 	ret = sprd_dma_fill_desc(chan, &sdesc->chn_hw, 0, 0, src, dst, len,
 				 dir, flags, slave_cfg);
 	if (ret) {
@@ -847,9 +967,6 @@ static int sprd_dma_slave_config(struct dma_chan *chan,
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
 	struct dma_slave_config *slave_cfg = &schan->slave_cfg;
 
-	if (!is_slave_direction(config->direction))
-		return -EINVAL;
-
 	memcpy(slave_cfg, config, sizeof(*config));
 	return 0;
 }
@@ -1109,4 +1226,5 @@ module_platform_driver(sprd_dma_driver);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("DMA driver for Spreadtrum");
 MODULE_AUTHOR("Baolin Wang <baolin.wang@spreadtrum.com>");
+MODULE_AUTHOR("Eric Long <eric.long@spreadtrum.com>");
 MODULE_ALIAS("platform:sprd-dma");
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index 5e328bd10c27..907ae97a3ef4 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -442,6 +442,7 @@ struct d40_base;
  * @queue: Queued jobs.
  * @prepare_queue: Prepared jobs.
  * @dma_cfg: The client configuration of this dma channel.
+ * @slave_config: DMA slave configuration.
  * @configured: whether the dma_cfg configuration is valid
  * @base: Pointer to the device instance struct.
  * @src_def_cfg: Default cfg register setting for src.
@@ -468,6 +469,7 @@ struct d40_chan {
 	struct list_head		 queue;
 	struct list_head		 prepare_queue;
 	struct stedma40_chan_cfg	 dma_cfg;
+	struct dma_slave_config		 slave_config;
 	bool				 configured;
 	struct d40_base			*base;
 	/* Default register configurations */
@@ -625,6 +627,10 @@ static void __iomem *chan_base(struct d40_chan *chan)
 #define chan_err(d40c, format, arg...)		\
 	d40_err(chan2dev(d40c), format, ## arg)
 
+static int d40_set_runtime_config_write(struct dma_chan *chan,
+				  struct dma_slave_config *config,
+				  enum dma_transfer_direction direction);
+
 static int d40_pool_lli_alloc(struct d40_chan *d40c, struct d40_desc *d40d,
 			      int lli_len)
 {
@@ -2216,6 +2222,8 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src,
 		return NULL;
 	}
 
+	d40_set_runtime_config_write(dchan, &chan->slave_config, direction);
+
 	spin_lock_irqsave(&chan->lock, flags);
 
 	desc = d40_prep_desc(chan, sg_src, sg_len, dma_flags);
@@ -2634,11 +2642,22 @@ dma40_config_to_halfchannel(struct d40_chan *d40c,
 	return 0;
 }
 
-/* Runtime reconfiguration extension */
 static int d40_set_runtime_config(struct dma_chan *chan,
 				  struct dma_slave_config *config)
 {
 	struct d40_chan *d40c = container_of(chan, struct d40_chan, chan);
+
+	memcpy(&d40c->slave_config, config, sizeof(*config));
+
+	return 0;
+}
+
+/* Runtime reconfiguration extension */
+static int d40_set_runtime_config_write(struct dma_chan *chan,
+				  struct dma_slave_config *config,
+				  enum dma_transfer_direction direction)
+{
+	struct d40_chan *d40c = container_of(chan, struct d40_chan, chan);
 	struct stedma40_chan_cfg *cfg = &d40c->dma_cfg;
 	enum dma_slave_buswidth src_addr_width, dst_addr_width;
 	dma_addr_t config_addr;
@@ -2655,7 +2674,7 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 	dst_addr_width = config->dst_addr_width;
 	dst_maxburst = config->dst_maxburst;
 
-	if (config->direction == DMA_DEV_TO_MEM) {
+	if (direction == DMA_DEV_TO_MEM) {
 		config_addr = config->src_addr;
 
 		if (cfg->dir != DMA_DEV_TO_MEM)
@@ -2671,7 +2690,7 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 		if (dst_maxburst == 0)
 			dst_maxburst = src_maxburst;
 
-	} else if (config->direction == DMA_MEM_TO_DEV) {
+	} else if (direction == DMA_MEM_TO_DEV) {
 		config_addr = config->dst_addr;
 
 		if (cfg->dir != DMA_MEM_TO_DEV)
@@ -2689,7 +2708,7 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 	} else {
 		dev_err(d40c->base->dev,
 			"unrecognized channel direction %d\n",
-			config->direction);
+			direction);
 		return -EINVAL;
 	}
 
@@ -2746,12 +2765,12 @@ static int d40_set_runtime_config(struct dma_chan *chan,
 
 	/* These settings will take precedence later */
 	d40c->runtime_addr = config_addr;
-	d40c->runtime_direction = config->direction;
+	d40c->runtime_direction = direction;
 	dev_dbg(d40c->base->dev,
 		"configured channel %s for %s, data width %d/%d, "
 		"maxburst %d/%d elements, LE, no flow control\n",
 		dma_chan_name(chan),
-		(config->direction == DMA_DEV_TO_MEM) ? "RX" : "TX",
+		(direction == DMA_DEV_TO_MEM) ? "RX" : "TX",
 		src_addr_width, dst_addr_width,
 		src_maxburst, dst_maxburst);
 
diff --git a/drivers/dma/uniphier-mdmac.c b/drivers/dma/uniphier-mdmac.c
new file mode 100644
index 000000000000..ec65a7430dc4
--- /dev/null
+++ b/drivers/dma/uniphier-mdmac.c
@@ -0,0 +1,506 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2018 Socionext Inc.
+//   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
+
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "virt-dma.h"
+
+/* registers common for all channels */
+#define UNIPHIER_MDMAC_CMD		0x000	/* issue DMA start/abort */
+#define   UNIPHIER_MDMAC_CMD_ABORT		BIT(31) /* 1: abort, 0: start */
+
+/* per-channel registers */
+#define UNIPHIER_MDMAC_CH_OFFSET	0x100
+#define UNIPHIER_MDMAC_CH_STRIDE	0x040
+
+#define UNIPHIER_MDMAC_CH_IRQ_STAT	0x010	/* current hw status (RO) */
+#define UNIPHIER_MDMAC_CH_IRQ_REQ	0x014	/* latched STAT (WOC) */
+#define UNIPHIER_MDMAC_CH_IRQ_EN	0x018	/* IRQ enable mask */
+#define UNIPHIER_MDMAC_CH_IRQ_DET	0x01c	/* REQ & EN (RO) */
+#define   UNIPHIER_MDMAC_CH_IRQ__ABORT		BIT(13)
+#define   UNIPHIER_MDMAC_CH_IRQ__DONE		BIT(1)
+#define UNIPHIER_MDMAC_CH_SRC_MODE	0x020	/* mode of source */
+#define UNIPHIER_MDMAC_CH_DEST_MODE	0x024	/* mode of destination */
+#define   UNIPHIER_MDMAC_CH_MODE__ADDR_INC	(0 << 4)
+#define   UNIPHIER_MDMAC_CH_MODE__ADDR_DEC	(1 << 4)
+#define   UNIPHIER_MDMAC_CH_MODE__ADDR_FIXED	(2 << 4)
+#define UNIPHIER_MDMAC_CH_SRC_ADDR	0x028	/* source address */
+#define UNIPHIER_MDMAC_CH_DEST_ADDR	0x02c	/* destination address */
+#define UNIPHIER_MDMAC_CH_SIZE		0x030	/* transfer bytes */
+
+#define UNIPHIER_MDMAC_SLAVE_BUSWIDTHS \
+	(BIT(DMA_SLAVE_BUSWIDTH_1_BYTE) | \
+	 BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) | \
+	 BIT(DMA_SLAVE_BUSWIDTH_3_BYTES) | \
+	 BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
+
+struct uniphier_mdmac_desc {
+	struct virt_dma_desc vd;
+	struct scatterlist *sgl;
+	unsigned int sg_len;
+	unsigned int sg_cur;
+	enum dma_transfer_direction dir;
+};
+
+struct uniphier_mdmac_chan {
+	struct virt_dma_chan vc;
+	struct uniphier_mdmac_device *mdev;
+	struct uniphier_mdmac_desc *md;
+	void __iomem *reg_ch_base;
+	unsigned int chan_id;
+};
+
+struct uniphier_mdmac_device {
+	struct dma_device ddev;
+	struct clk *clk;
+	void __iomem *reg_base;
+	struct uniphier_mdmac_chan channels[0];
+};
+
+static struct uniphier_mdmac_chan *
+to_uniphier_mdmac_chan(struct virt_dma_chan *vc)
+{
+	return container_of(vc, struct uniphier_mdmac_chan, vc);
+}
+
+static struct uniphier_mdmac_desc *
+to_uniphier_mdmac_desc(struct virt_dma_desc *vd)
+{
+	return container_of(vd, struct uniphier_mdmac_desc, vd);
+}
+
+/* mc->vc.lock must be held by caller */
+static struct uniphier_mdmac_desc *
+uniphier_mdmac_next_desc(struct uniphier_mdmac_chan *mc)
+{
+	struct virt_dma_desc *vd;
+
+	vd = vchan_next_desc(&mc->vc);
+	if (!vd) {
+		mc->md = NULL;
+		return NULL;
+	}
+
+	list_del(&vd->node);
+
+	mc->md = to_uniphier_mdmac_desc(vd);
+
+	return mc->md;
+}
+
+/* mc->vc.lock must be held by caller */
+static void uniphier_mdmac_handle(struct uniphier_mdmac_chan *mc,
+				  struct uniphier_mdmac_desc *md)
+{
+	struct uniphier_mdmac_device *mdev = mc->mdev;
+	struct scatterlist *sg;
+	u32 irq_flag = UNIPHIER_MDMAC_CH_IRQ__DONE;
+	u32 src_mode, src_addr, dest_mode, dest_addr, chunk_size;
+
+	sg = &md->sgl[md->sg_cur];
+
+	if (md->dir == DMA_MEM_TO_DEV) {
+		src_mode = UNIPHIER_MDMAC_CH_MODE__ADDR_INC;
+		src_addr = sg_dma_address(sg);
+		dest_mode = UNIPHIER_MDMAC_CH_MODE__ADDR_FIXED;
+		dest_addr = 0;
+	} else {
+		src_mode = UNIPHIER_MDMAC_CH_MODE__ADDR_FIXED;
+		src_addr = 0;
+		dest_mode = UNIPHIER_MDMAC_CH_MODE__ADDR_INC;
+		dest_addr = sg_dma_address(sg);
+	}
+
+	chunk_size = sg_dma_len(sg);
+
+	writel(src_mode, mc->reg_ch_base + UNIPHIER_MDMAC_CH_SRC_MODE);
+	writel(dest_mode, mc->reg_ch_base + UNIPHIER_MDMAC_CH_DEST_MODE);
+	writel(src_addr, mc->reg_ch_base + UNIPHIER_MDMAC_CH_SRC_ADDR);
+	writel(dest_addr, mc->reg_ch_base + UNIPHIER_MDMAC_CH_DEST_ADDR);
+	writel(chunk_size, mc->reg_ch_base + UNIPHIER_MDMAC_CH_SIZE);
+
+	/* write 1 to clear */
+	writel(irq_flag, mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_REQ);
+
+	writel(irq_flag, mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_EN);
+
+	writel(BIT(mc->chan_id), mdev->reg_base + UNIPHIER_MDMAC_CMD);
+}
+
+/* mc->vc.lock must be held by caller */
+static void uniphier_mdmac_start(struct uniphier_mdmac_chan *mc)
+{
+	struct uniphier_mdmac_desc *md;
+
+	md = uniphier_mdmac_next_desc(mc);
+	if (md)
+		uniphier_mdmac_handle(mc, md);
+}
+
+/* mc->vc.lock must be held by caller */
+static int uniphier_mdmac_abort(struct uniphier_mdmac_chan *mc)
+{
+	struct uniphier_mdmac_device *mdev = mc->mdev;
+	u32 irq_flag = UNIPHIER_MDMAC_CH_IRQ__ABORT;
+	u32 val;
+
+	/* write 1 to clear */
+	writel(irq_flag, mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_REQ);
+
+	writel(UNIPHIER_MDMAC_CMD_ABORT | BIT(mc->chan_id),
+	       mdev->reg_base + UNIPHIER_MDMAC_CMD);
+
+	/*
+	 * Abort should be accepted soon. We poll the bit here instead of
+	 * waiting for the interrupt.
+	 */
+	return readl_poll_timeout(mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_REQ,
+				  val, val & irq_flag, 0, 20);
+}
+
+static irqreturn_t uniphier_mdmac_interrupt(int irq, void *dev_id)
+{
+	struct uniphier_mdmac_chan *mc = dev_id;
+	struct uniphier_mdmac_desc *md;
+	irqreturn_t ret = IRQ_HANDLED;
+	u32 irq_stat;
+
+	spin_lock(&mc->vc.lock);
+
+	irq_stat = readl(mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_DET);
+
+	/*
+	 * Some channels share a single interrupt line. If the IRQ status is 0,
+	 * this is probably triggered by a different channel.
+	 */
+	if (!irq_stat) {
+		ret = IRQ_NONE;
+		goto out;
+	}
+
+	/* write 1 to clear */
+	writel(irq_stat, mc->reg_ch_base + UNIPHIER_MDMAC_CH_IRQ_REQ);
+
+	/*
+	 * UNIPHIER_MDMAC_CH_IRQ__DONE interrupt is asserted even when the DMA
+	 * is aborted. To distinguish the normal completion and the abort,
+	 * check mc->md. If it is NULL, we are aborting.
+	 */
+	md = mc->md;
+	if (!md)
+		goto out;
+
+	md->sg_cur++;
+
+	if (md->sg_cur >= md->sg_len) {
+		vchan_cookie_complete(&md->vd);
+		md = uniphier_mdmac_next_desc(mc);
+		if (!md)
+			goto out;
+	}
+
+	uniphier_mdmac_handle(mc, md);
+
+out:
+	spin_unlock(&mc->vc.lock);
+
+	return ret;
+}
+
+static void uniphier_mdmac_free_chan_resources(struct dma_chan *chan)
+{
+	vchan_free_chan_resources(to_virt_chan(chan));
+}
+
+static struct dma_async_tx_descriptor *
+uniphier_mdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+			     unsigned int sg_len,
+			     enum dma_transfer_direction direction,
+			     unsigned long flags, void *context)
+{
+	struct virt_dma_chan *vc = to_virt_chan(chan);
+	struct uniphier_mdmac_desc *md;
+
+	if (!is_slave_direction(direction))
+		return NULL;
+
+	md = kzalloc(sizeof(*md), GFP_NOWAIT);
+	if (!md)
+		return NULL;
+
+	md->sgl = sgl;
+	md->sg_len = sg_len;
+	md->dir = direction;
+
+	return vchan_tx_prep(vc, &md->vd, flags);
+}
+
+static int uniphier_mdmac_terminate_all(struct dma_chan *chan)
+{
+	struct virt_dma_chan *vc = to_virt_chan(chan);
+	struct uniphier_mdmac_chan *mc = to_uniphier_mdmac_chan(vc);
+	unsigned long flags;
+	int ret = 0;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&vc->lock, flags);
+
+	if (mc->md) {
+		vchan_terminate_vdesc(&mc->md->vd);
+		mc->md = NULL;
+		ret = uniphier_mdmac_abort(mc);
+	}
+	vchan_get_all_descriptors(vc, &head);
+
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	vchan_dma_desc_free_list(vc, &head);
+
+	return ret;
+}
+
+static void uniphier_mdmac_synchronize(struct dma_chan *chan)
+{
+	vchan_synchronize(to_virt_chan(chan));
+}
+
+static enum dma_status uniphier_mdmac_tx_status(struct dma_chan *chan,
+						dma_cookie_t cookie,
+						struct dma_tx_state *txstate)
+{
+	struct virt_dma_chan *vc;
+	struct virt_dma_desc *vd;
+	struct uniphier_mdmac_chan *mc;
+	struct uniphier_mdmac_desc *md = NULL;
+	enum dma_status stat;
+	unsigned long flags;
+	int i;
+
+	stat = dma_cookie_status(chan, cookie, txstate);
+	/* Return immediately if we do not need to compute the residue. */
+	if (stat == DMA_COMPLETE || !txstate)
+		return stat;
+
+	vc = to_virt_chan(chan);
+
+	spin_lock_irqsave(&vc->lock, flags);
+
+	mc = to_uniphier_mdmac_chan(vc);
+
+	if (mc->md && mc->md->vd.tx.cookie == cookie) {
+		/* residue from the on-flight chunk */
+		txstate->residue = readl(mc->reg_ch_base +
+					 UNIPHIER_MDMAC_CH_SIZE);
+		md = mc->md;
+	}
+
+	if (!md) {
+		vd = vchan_find_desc(vc, cookie);
+		if (vd)
+			md = to_uniphier_mdmac_desc(vd);
+	}
+
+	if (md) {
+		/* residue from the queued chunks */
+		for (i = md->sg_cur; i < md->sg_len; i++)
+			txstate->residue += sg_dma_len(&md->sgl[i]);
+	}
+
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	return stat;
+}
+
+static void uniphier_mdmac_issue_pending(struct dma_chan *chan)
+{
+	struct virt_dma_chan *vc = to_virt_chan(chan);
+	struct uniphier_mdmac_chan *mc = to_uniphier_mdmac_chan(vc);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vc->lock, flags);
+
+	if (vchan_issue_pending(vc) && !mc->md)
+		uniphier_mdmac_start(mc);
+
+	spin_unlock_irqrestore(&vc->lock, flags);
+}
+
+static void uniphier_mdmac_desc_free(struct virt_dma_desc *vd)
+{
+	kfree(to_uniphier_mdmac_desc(vd));
+}
+
+static int uniphier_mdmac_chan_init(struct platform_device *pdev,
+				    struct uniphier_mdmac_device *mdev,
+				    int chan_id)
+{
+	struct device *dev = &pdev->dev;
+	struct uniphier_mdmac_chan *mc = &mdev->channels[chan_id];
+	char *irq_name;
+	int irq, ret;
+
+	irq = platform_get_irq(pdev, chan_id);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "failed to get IRQ number for ch%d\n",
+			chan_id);
+		return irq;
+	}
+
+	irq_name = devm_kasprintf(dev, GFP_KERNEL, "uniphier-mio-dmac-ch%d",
+				  chan_id);
+	if (!irq_name)
+		return -ENOMEM;
+
+	ret = devm_request_irq(dev, irq, uniphier_mdmac_interrupt,
+			       IRQF_SHARED, irq_name, mc);
+	if (ret)
+		return ret;
+
+	mc->mdev = mdev;
+	mc->reg_ch_base = mdev->reg_base + UNIPHIER_MDMAC_CH_OFFSET +
+					UNIPHIER_MDMAC_CH_STRIDE * chan_id;
+	mc->chan_id = chan_id;
+	mc->vc.desc_free = uniphier_mdmac_desc_free;
+	vchan_init(&mc->vc, &mdev->ddev);
+
+	return 0;
+}
+
+static int uniphier_mdmac_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct uniphier_mdmac_device *mdev;
+	struct dma_device *ddev;
+	struct resource *res;
+	int nr_chans, ret, i;
+
+	nr_chans = platform_irq_count(pdev);
+	if (nr_chans < 0)
+		return nr_chans;
+
+	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	mdev = devm_kzalloc(dev, struct_size(mdev, channels, nr_chans),
+			    GFP_KERNEL);
+	if (!mdev)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mdev->reg_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(mdev->reg_base))
+		return PTR_ERR(mdev->reg_base);
+
+	mdev->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(mdev->clk)) {
+		dev_err(dev, "failed to get clock\n");
+		return PTR_ERR(mdev->clk);
+	}
+
+	ret = clk_prepare_enable(mdev->clk);
+	if (ret)
+		return ret;
+
+	ddev = &mdev->ddev;
+	ddev->dev = dev;
+	dma_cap_set(DMA_PRIVATE, ddev->cap_mask);
+	ddev->src_addr_widths = UNIPHIER_MDMAC_SLAVE_BUSWIDTHS;
+	ddev->dst_addr_widths = UNIPHIER_MDMAC_SLAVE_BUSWIDTHS;
+	ddev->directions = BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
+	ddev->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	ddev->device_free_chan_resources = uniphier_mdmac_free_chan_resources;
+	ddev->device_prep_slave_sg = uniphier_mdmac_prep_slave_sg;
+	ddev->device_terminate_all = uniphier_mdmac_terminate_all;
+	ddev->device_synchronize = uniphier_mdmac_synchronize;
+	ddev->device_tx_status = uniphier_mdmac_tx_status;
+	ddev->device_issue_pending = uniphier_mdmac_issue_pending;
+	INIT_LIST_HEAD(&ddev->channels);
+
+	for (i = 0; i < nr_chans; i++) {
+		ret = uniphier_mdmac_chan_init(pdev, mdev, i);
+		if (ret)
+			goto disable_clk;
+	}
+
+	ret = dma_async_device_register(ddev);
+	if (ret)
+		goto disable_clk;
+
+	ret = of_dma_controller_register(dev->of_node, of_dma_xlate_by_chan_id,
+					 ddev);
+	if (ret)
+		goto unregister_dmac;
+
+	platform_set_drvdata(pdev, mdev);
+
+	return 0;
+
+unregister_dmac:
+	dma_async_device_unregister(ddev);
+disable_clk:
+	clk_disable_unprepare(mdev->clk);
+
+	return ret;
+}
+
+static int uniphier_mdmac_remove(struct platform_device *pdev)
+{
+	struct uniphier_mdmac_device *mdev = platform_get_drvdata(pdev);
+	struct dma_chan *chan;
+	int ret;
+
+	/*
+	 * Before reaching here, almost all descriptors have been freed by the
+	 * ->device_free_chan_resources() hook. However, each channel might
+	 * be still holding one descriptor that was on-flight at that moment.
+	 * Terminate it to make sure this hardware is no longer running. Then,
+	 * free the channel resources once again to avoid memory leak.
+	 */
+	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
+		ret = dmaengine_terminate_sync(chan);
+		if (ret)
+			return ret;
+		uniphier_mdmac_free_chan_resources(chan);
+	}
+
+	of_dma_controller_free(pdev->dev.of_node);
+	dma_async_device_unregister(&mdev->ddev);
+	clk_disable_unprepare(mdev->clk);
+
+	return 0;
+}
+
+static const struct of_device_id uniphier_mdmac_match[] = {
+	{ .compatible = "socionext,uniphier-mio-dmac" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, uniphier_mdmac_match);
+
+static struct platform_driver uniphier_mdmac_driver = {
+	.probe = uniphier_mdmac_probe,
+	.remove = uniphier_mdmac_remove,
+	.driver = {
+		.name = "uniphier-mio-dmac",
+		.of_match_table = uniphier_mdmac_match,
+	},
+};
+module_platform_driver(uniphier_mdmac_driver);
+
+MODULE_AUTHOR("Masahiro Yamada <yamada.masahiro@socionext.com>");
+MODULE_DESCRIPTION("UniPhier MIO DMAC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index c12442312595..02880963092f 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -190,6 +190,8 @@
 /* AXI CDMA Specific Masks */
 #define XILINX_CDMA_CR_SGMODE          BIT(3)
 
+#define xilinx_prep_dma_addr_t(addr)	\
+	((dma_addr_t)((u64)addr##_##msb << 32 | (addr)))
 /**
  * struct xilinx_vdma_desc_hw - Hardware Descriptor
  * @next_desc: Next Descriptor Pointer @0x00
@@ -887,6 +889,24 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 				chan->id);
 			return -ENOMEM;
 		}
+		/*
+		 * For cyclic DMA mode we need to program the tail Descriptor
+		 * register with a value which is not a part of the BD chain
+		 * so allocating a desc segment during channel allocation for
+		 * programming tail descriptor.
+		 */
+		chan->cyclic_seg_v = dma_zalloc_coherent(chan->dev,
+					sizeof(*chan->cyclic_seg_v),
+					&chan->cyclic_seg_p, GFP_KERNEL);
+		if (!chan->cyclic_seg_v) {
+			dev_err(chan->dev,
+				"unable to allocate desc segment for cyclic DMA\n");
+			dma_free_coherent(chan->dev, sizeof(*chan->seg_v) *
+				XILINX_DMA_NUM_DESCS, chan->seg_v,
+				chan->seg_p);
+			return -ENOMEM;
+		}
+		chan->cyclic_seg_v->phys = chan->cyclic_seg_p;
 
 		for (i = 0; i < XILINX_DMA_NUM_DESCS; i++) {
 			chan->seg_v[i].hw.next_desc =
@@ -922,24 +942,6 @@ static int xilinx_dma_alloc_chan_resources(struct dma_chan *dchan)
 		return -ENOMEM;
 	}
 
-	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
-		/*
-		 * For cyclic DMA mode we need to program the tail Descriptor
-		 * register with a value which is not a part of the BD chain
-		 * so allocating a desc segment during channel allocation for
-		 * programming tail descriptor.
-		 */
-		chan->cyclic_seg_v = dma_zalloc_coherent(chan->dev,
-					sizeof(*chan->cyclic_seg_v),
-					&chan->cyclic_seg_p, GFP_KERNEL);
-		if (!chan->cyclic_seg_v) {
-			dev_err(chan->dev,
-				"unable to allocate desc segment for cyclic DMA\n");
-			return -ENOMEM;
-		}
-		chan->cyclic_seg_v->phys = chan->cyclic_seg_p;
-	}
-
 	dma_cookie_init(dchan);
 
 	if (chan->xdev->dma_config->dmatype == XDMA_TYPE_AXIDMA) {
@@ -1245,8 +1247,10 @@ static void xilinx_cdma_start_transfer(struct xilinx_dma_chan *chan)
 
 		hw = &segment->hw;
 
-		xilinx_write(chan, XILINX_CDMA_REG_SRCADDR, hw->src_addr);
-		xilinx_write(chan, XILINX_CDMA_REG_DSTADDR, hw->dest_addr);
+		xilinx_write(chan, XILINX_CDMA_REG_SRCADDR,
+			     xilinx_prep_dma_addr_t(hw->src_addr));
+		xilinx_write(chan, XILINX_CDMA_REG_DSTADDR,
+			     xilinx_prep_dma_addr_t(hw->dest_addr));
 
 		/* Start the transfer */
 		dma_ctrl_write(chan, XILINX_DMA_REG_BTT,
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index c74a88b65039..8db51750ce93 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -163,7 +163,7 @@ struct zynqmp_dma_desc_ll {
 	u32 ctrl;
 	u64 nxtdscraddr;
 	u64 rsvd;
-}; __aligned(64)
+};
 
 /**
  * struct zynqmp_dma_desc_sw - Per Transaction structure
@@ -375,9 +375,10 @@ static dma_cookie_t zynqmp_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct zynqmp_dma_chan *chan = to_chan(tx->chan);
 	struct zynqmp_dma_desc_sw *desc, *new;
 	dma_cookie_t cookie;
+	unsigned long irqflags;
 
 	new = tx_to_desc(tx);
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	cookie = dma_cookie_assign(tx);
 
 	if (!list_empty(&chan->pending_list)) {
@@ -393,7 +394,7 @@ static dma_cookie_t zynqmp_dma_tx_submit(struct dma_async_tx_descriptor *tx)
 	}
 
 	list_add_tail(&new->node, &chan->pending_list);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	return cookie;
 }
@@ -408,12 +409,13 @@ static struct zynqmp_dma_desc_sw *
 zynqmp_dma_get_descriptor(struct zynqmp_dma_chan *chan)
 {
 	struct zynqmp_dma_desc_sw *desc;
+	unsigned long irqflags;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	desc = list_first_entry(&chan->free_list,
 				struct zynqmp_dma_desc_sw, node);
 	list_del(&desc->node);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	INIT_LIST_HEAD(&desc->tx_list);
 	/* Clear the src and dst descriptor memory */
@@ -643,10 +645,11 @@ static void zynqmp_dma_complete_descriptor(struct zynqmp_dma_chan *chan)
 static void zynqmp_dma_issue_pending(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
+	unsigned long irqflags;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	zynqmp_dma_start_transfer(chan);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 }
 
 /**
@@ -667,10 +670,11 @@ static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan)
 static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
+	unsigned long irqflags;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	zynqmp_dma_free_descriptors(chan);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 	dma_free_coherent(chan->dev,
 		(2 * ZYNQMP_DMA_DESC_SIZE(chan) * ZYNQMP_DMA_NUM_DESCS),
 		chan->desc_pool_v, chan->desc_pool_p);
@@ -743,8 +747,9 @@ static void zynqmp_dma_do_tasklet(unsigned long data)
 {
 	struct zynqmp_dma_chan *chan = (struct zynqmp_dma_chan *)data;
 	u32 count;
+	unsigned long irqflags;
 
-	spin_lock(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 
 	if (chan->err) {
 		zynqmp_dma_reset(chan);
@@ -764,7 +769,7 @@ static void zynqmp_dma_do_tasklet(unsigned long data)
 		zynqmp_dma_start_transfer(chan);
 
 unlock:
-	spin_unlock(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 }
 
 /**
@@ -776,11 +781,12 @@ unlock:
 static int zynqmp_dma_device_terminate_all(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
+	unsigned long irqflags;
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS);
 	zynqmp_dma_free_descriptors(chan);
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	return 0;
 }
@@ -804,19 +810,20 @@ static struct dma_async_tx_descriptor *zynqmp_dma_prep_memcpy(
 	void *desc = NULL, *prev = NULL;
 	size_t copy;
 	u32 desc_cnt;
+	unsigned long irqflags;
 
 	chan = to_chan(dchan);
 
 	desc_cnt = DIV_ROUND_UP(len, ZYNQMP_DMA_MAX_TRANS_LEN);
 
-	spin_lock_bh(&chan->lock);
+	spin_lock_irqsave(&chan->lock, irqflags);
 	if (desc_cnt > chan->desc_free_cnt) {
-		spin_unlock_bh(&chan->lock);
+		spin_unlock_irqrestore(&chan->lock, irqflags);
 		dev_dbg(chan->dev, "chan %p descs are not available\n", chan);
 		return NULL;
 	}
 	chan->desc_free_cnt = chan->desc_free_cnt - desc_cnt;
-	spin_unlock_bh(&chan->lock);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	do {
 		/* Allocate and populate the descriptor */
diff --git a/include/dt-bindings/dma/dw-dmac.h b/include/dt-bindings/dma/dw-dmac.h
new file mode 100644
index 000000000000..d1ca705c95b3
--- /dev/null
+++ b/include/dt-bindings/dma/dw-dmac.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+
+#ifndef __DT_BINDINGS_DMA_DW_DMAC_H__
+#define __DT_BINDINGS_DMA_DW_DMAC_H__
+
+/*
+ * Protection Control bits provide protection against illegal transactions.
+ * The protection bits[0:2] are one-to-one mapped to AHB HPROT[3:1] signals.
+ */
+#define DW_DMAC_HPROT1_PRIVILEGED_MODE	(1 << 0)	/* Privileged Mode */
+#define DW_DMAC_HPROT2_BUFFERABLE	(1 << 1)	/* DMA is bufferable */
+#define DW_DMAC_HPROT3_CACHEABLE	(1 << 2)	/* DMA is cacheable */
+
+#endif /* __DT_BINDINGS_DMA_DW_DMAC_H__ */
diff --git a/include/linux/dma/sprd-dma.h b/include/linux/dma/sprd-dma.h
index b42b80e52cc2..ab82df64682a 100644
--- a/include/linux/dma/sprd-dma.h
+++ b/include/linux/dma/sprd-dma.h
@@ -3,9 +3,65 @@
 #ifndef _SPRD_DMA_H_
 #define _SPRD_DMA_H_
 
-#define SPRD_DMA_REQ_SHIFT 16
-#define SPRD_DMA_FLAGS(req_mode, int_type) \
-	((req_mode) << SPRD_DMA_REQ_SHIFT | (int_type))
+#define SPRD_DMA_REQ_SHIFT	8
+#define SPRD_DMA_TRG_MODE_SHIFT	16
+#define SPRD_DMA_CHN_MODE_SHIFT	24
+#define SPRD_DMA_FLAGS(chn_mode, trg_mode, req_mode, int_type) \
+	((chn_mode) << SPRD_DMA_CHN_MODE_SHIFT | \
+	(trg_mode) << SPRD_DMA_TRG_MODE_SHIFT | \
+	(req_mode) << SPRD_DMA_REQ_SHIFT | (int_type))
+
+/*
+ * The Spreadtrum DMA controller supports channel 2-stage tansfer, that means
+ * we can request 2 dma channels, one for source channel, and another one for
+ * destination channel. Each channel is independent, and has its own
+ * configurations. Once the source channel's transaction is done, it will
+ * trigger the destination channel's transaction automatically by hardware
+ * signal.
+ *
+ * To support 2-stage tansfer, we must configure the channel mode and trigger
+ * mode as below definition.
+ */
+
+/*
+ * enum sprd_dma_chn_mode: define the DMA channel mode for 2-stage transfer
+ * @SPRD_DMA_CHN_MODE_NONE: No channel mode setting which means channel doesn't
+ * support the 2-stage transfer.
+ * @SPRD_DMA_SRC_CHN0: Channel used as source channel 0.
+ * @SPRD_DMA_SRC_CHN1: Channel used as source channel 1.
+ * @SPRD_DMA_DST_CHN0: Channel used as destination channel 0.
+ * @SPRD_DMA_DST_CHN1: Channel used as destination channel 1.
+ *
+ * Now the DMA controller can supports 2 groups 2-stage transfer.
+ */
+enum sprd_dma_chn_mode {
+	SPRD_DMA_CHN_MODE_NONE,
+	SPRD_DMA_SRC_CHN0,
+	SPRD_DMA_SRC_CHN1,
+	SPRD_DMA_DST_CHN0,
+	SPRD_DMA_DST_CHN1,
+};
+
+/*
+ * enum sprd_dma_trg_mode: define the DMA channel trigger mode for 2-stage
+ * transfer
+ * @SPRD_DMA_NO_TRG: No trigger setting.
+ * @SPRD_DMA_FRAG_DONE_TRG: Trigger the transaction of destination channel
+ * automatically once the source channel's fragment request is done.
+ * @SPRD_DMA_BLOCK_DONE_TRG: Trigger the transaction of destination channel
+ * automatically once the source channel's block request is done.
+ * @SPRD_DMA_TRANS_DONE_TRG: Trigger the transaction of destination channel
+ * automatically once the source channel's transfer request is done.
+ * @SPRD_DMA_LIST_DONE_TRG: Trigger the transaction of destination channel
+ * automatically once the source channel's link-list request is done.
+ */
+enum sprd_dma_trg_mode {
+	SPRD_DMA_NO_TRG,
+	SPRD_DMA_FRAG_DONE_TRG,
+	SPRD_DMA_BLOCK_DONE_TRG,
+	SPRD_DMA_TRANS_DONE_TRG,
+	SPRD_DMA_LIST_DONE_TRG,
+};
 
 /*
  * enum sprd_dma_req_mode: define the DMA request mode
diff --git a/include/linux/platform_data/dma-dw.h b/include/linux/platform_data/dma-dw.h
index 896cb71a382c..1a1d58ebffbf 100644
--- a/include/linux/platform_data/dma-dw.h
+++ b/include/linux/platform_data/dma-dw.h
@@ -49,6 +49,7 @@ struct dw_dma_slave {
  * @data_width: Maximum data width supported by hardware per AHB master
  *		(in bytes, power of 2)
  * @multi_block: Multi block transfers supported by hardware per channel.
+ * @protctl: Protection control signals setting per channel.
  */
 struct dw_dma_platform_data {
 	unsigned int	nr_channels;
@@ -65,6 +66,11 @@ struct dw_dma_platform_data {
 	unsigned char	nr_masters;
 	unsigned char	data_width[DW_DMA_MAX_NR_MASTERS];
 	unsigned char	multi_block[DW_DMA_MAX_NR_CHANNELS];
+#define CHAN_PROTCTL_PRIVILEGED		BIT(0)
+#define CHAN_PROTCTL_BUFFERABLE		BIT(1)
+#define CHAN_PROTCTL_CACHEABLE		BIT(2)
+#define CHAN_PROTCTL_MASK		GENMASK(2, 0)
+	unsigned char	protctl;
 };
 
 #endif /* _PLATFORM_DATA_DMA_DW_H */
diff --git a/include/linux/sa11x0-dma.h b/include/linux/sa11x0-dma.h
deleted file mode 100644
index 65839a58b8e5..000000000000
--- a/include/linux/sa11x0-dma.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * SA11x0 DMA Engine support
- *
- * Copyright (C) 2012 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#ifndef __LINUX_SA11X0_DMA_H
-#define __LINUX_SA11X0_DMA_H
-
-struct dma_chan;
-
-#if defined(CONFIG_DMA_SA11X0) || defined(CONFIG_DMA_SA11X0_MODULE)
-bool sa11x0_dma_filter_fn(struct dma_chan *, void *);
-#else
-static inline bool sa11x0_dma_filter_fn(struct dma_chan *c, void *d)
-{
-	return false;
-}
-#endif
-
-#endif
diff --git a/include/linux/shdma-base.h b/include/linux/shdma-base.h
index d927647e6350..6dfd05ef5c2d 100644
--- a/include/linux/shdma-base.h
+++ b/include/linux/shdma-base.h
@@ -1,4 +1,5 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * Dmaengine driver base library for DMA controllers, found on SH-based SoCs
  *
  * extracted from shdma.c and headers
@@ -7,10 +8,6 @@
  * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
  * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
  * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
- *
- * This is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
  */
 
 #ifndef SHDMA_BASE_H