Merge branch 'topic/renesas' into for-linus
diff --git a/Documentation/devicetree/bindings/dma/owl-dma.txt b/Documentation/devicetree/bindings/dma/owl-dma.txt
new file mode 100644
index 0000000..03e9bb1
--- /dev/null
+++ b/Documentation/devicetree/bindings/dma/owl-dma.txt
@@ -0,0 +1,47 @@
+* Actions Semi Owl SoCs DMA controller
+
+This binding follows the generic DMA bindings defined in dma.txt.
+
+Required properties:
+- compatible: Should be "actions,s900-dma".
+- reg: Should contain DMA registers location and length.
+- interrupts: Should contain 4 interrupts shared by all channel.
+- #dma-cells: Must be <1>. Used to represent the number of integer
+              cells in the dmas property of client device.
+- dma-channels: Physical channels supported.
+- dma-requests: Number of DMA request signals supported by the controller.
+                Refer to Documentation/devicetree/bindings/dma/dma.txt
+- clocks: Phandle and Specifier of the clock feeding the DMA controller.
+
+Example:
+
+Controller:
+                dma: dma-controller@e0260000 {
+                        compatible = "actions,s900-dma";
+                        reg = <0x0 0xe0260000 0x0 0x1000>;
+                        interrupts = <GIC_SPI 57 IRQ_TYPE_LEVEL_HIGH>,
+                                     <GIC_SPI 58 IRQ_TYPE_LEVEL_HIGH>,
+                                     <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>,
+                                     <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>;
+                        #dma-cells = <1>;
+                        dma-channels = <12>;
+                        dma-requests = <46>;
+                        clocks = <&clock CLK_DMAC>;
+                };
+
+Client:
+
+DMA clients connected to the Actions Semi Owl SoCs DMA controller must
+use the format described in the dma.txt file, using a two-cell specifier
+for each channel.
+
+The two cells in order are:
+1. A phandle pointing to the DMA controller.
+2. The channel id.
+
+uart5: serial@e012a000 {
+        ...
+        dma-names = "tx", "rx";
+        dmas = <&dma 26>, <&dma 27>;
+        ...
+};
diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt
index 7c1bb3d..43681ca 100644
--- a/Documentation/driver-model/devres.txt
+++ b/Documentation/driver-model/devres.txt
@@ -240,6 +240,7 @@
   devm_of_clk_add_hw_provider()
 
 DMA
+  dmaenginem_async_device_register()
   dmam_alloc_coherent()
   dmam_alloc_attrs()
   dmam_declare_coherent_memory()
diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 56bd612..80dc567 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -42,6 +42,8 @@ static struct page *pq_scribble_page;
 #define P(b, d) (b[d-2])
 #define Q(b, d) (b[d-1])
 
+#define MAX_DISKS 255
+
 /**
  * do_async_gen_syndrome - asynchronously calculate P and/or Q
  */
@@ -184,7 +186,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dmaengine_unmap_data *unmap = NULL;
 
-	BUG_ON(disks > 255 || !(P(blocks, disks) || Q(blocks, disks)));
+	BUG_ON(disks > MAX_DISKS || !(P(blocks, disks) || Q(blocks, disks)));
 
 	if (device)
 		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
@@ -196,7 +198,7 @@ async_gen_syndrome(struct page **blocks, unsigned int offset, int disks,
 	    is_dma_pq_aligned(device, offset, 0, len)) {
 		struct dma_async_tx_descriptor *tx;
 		enum dma_ctrl_flags dma_flags = 0;
-		unsigned char coefs[src_cnt];
+		unsigned char coefs[MAX_DISKS];
 		int i, j;
 
 		/* run the p+q asynchronously */
@@ -299,11 +301,11 @@ async_syndrome_val(struct page **blocks, unsigned int offset, int disks,
 	struct dma_chan *chan = pq_val_chan(submit, blocks, disks, len);
 	struct dma_device *device = chan ? chan->device : NULL;
 	struct dma_async_tx_descriptor *tx;
-	unsigned char coefs[disks-2];
+	unsigned char coefs[MAX_DISKS];
 	enum dma_ctrl_flags dma_flags = submit->cb_fn ? DMA_PREP_INTERRUPT : 0;
 	struct dmaengine_unmap_data *unmap = NULL;
 
-	BUG_ON(disks < 4);
+	BUG_ON(disks < 4 || disks > MAX_DISKS);
 
 	if (device)
 		unmap = dmaengine_get_unmap_data(device->dev, disks, GFP_NOWAIT);
diff --git a/crypto/async_tx/raid6test.c b/crypto/async_tx/raid6test.c
index dad95f4..a5edaab 100644
--- a/crypto/async_tx/raid6test.c
+++ b/crypto/async_tx/raid6test.c
@@ -81,11 +81,13 @@ static void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, stru
 			init_async_submit(&submit, 0, NULL, NULL, NULL, addr_conv);
 			tx = async_gen_syndrome(ptrs, 0, disks, bytes, &submit);
 		} else {
-			struct page *blocks[disks];
+			struct page *blocks[NDISKS];
 			struct page *dest;
 			int count = 0;
 			int i;
 
+			BUG_ON(disks > NDISKS);
+
 			/* data+Q failure.  Reconstruct data from P,
 			 * then rebuild syndrome
 			 */
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index ca1680a..92a278e 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -413,6 +413,14 @@
 	help
 	  Support for "Type-AXI" NBPF DMA IPs from Renesas
 
+config OWL_DMA
+	tristate "Actions Semi Owl SoCs DMA support"
+	depends on ARCH_ACTIONS
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Enable support for the Actions Semi Owl SoCs DMA controller.
+
 config PCH_DMA
 	tristate "Intel EG20T PCH / LAPIS Semicon IOH(ML7213/ML7223/ML7831) DMA"
 	depends on PCI && (X86_32 || COMPILE_TEST)
diff --git a/drivers/dma/Makefile b/drivers/dma/Makefile
index 203a99d..c91702d 100644
--- a/drivers/dma/Makefile
+++ b/drivers/dma/Makefile
@@ -52,6 +52,7 @@
 obj-$(CONFIG_MXS_DMA) += mxs-dma.o
 obj-$(CONFIG_MX3_IPU) += ipu/
 obj-$(CONFIG_NBPFAXI_DMA) += nbpfaxi.o
+obj-$(CONFIG_OWL_DMA) += owl-dma.o
 obj-$(CONFIG_PCH_DMA) += pch_dma.o
 obj-$(CONFIG_PL330_DMA) += pl330.o
 obj-$(CONFIG_PPC_BESTCOMM) += bestcomm/
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 08ba847..272bed6 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -500,12 +500,8 @@ int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
 	caps->max_burst = device->max_burst;
 	caps->residue_granularity = device->residue_granularity;
 	caps->descriptor_reuse = device->descriptor_reuse;
-
-	/*
-	 * Some devices implement only pause (e.g. to get residuum) but no
-	 * resume. However cmd_pause is advertised as pause AND resume.
-	 */
-	caps->cmd_pause = !!(device->device_pause && device->device_resume);
+	caps->cmd_pause = !!device->device_pause;
+	caps->cmd_resume = !!device->device_resume;
 	caps->cmd_terminate = !!device->device_terminate_all;
 
 	return 0;
@@ -774,8 +770,14 @@ struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask)
 		return ERR_PTR(-ENODEV);
 
 	chan = __dma_request_channel(mask, NULL, NULL);
-	if (!chan)
-		chan = ERR_PTR(-ENODEV);
+	if (!chan) {
+		mutex_lock(&dma_list_mutex);
+		if (list_empty(&dma_device_list))
+			chan = ERR_PTR(-EPROBE_DEFER);
+		else
+			chan = ERR_PTR(-ENODEV);
+		mutex_unlock(&dma_list_mutex);
+	}
 
 	return chan;
 }
@@ -1139,6 +1141,41 @@ void dma_async_device_unregister(struct dma_device *device)
 }
 EXPORT_SYMBOL(dma_async_device_unregister);
 
+static void dmam_device_release(struct device *dev, void *res)
+{
+	struct dma_device *device;
+
+	device = *(struct dma_device **)res;
+	dma_async_device_unregister(device);
+}
+
+/**
+ * dmaenginem_async_device_register - registers DMA devices found
+ * @device: &dma_device
+ *
+ * The operation is managed and will be undone on driver detach.
+ */
+int dmaenginem_async_device_register(struct dma_device *device)
+{
+	void *p;
+	int ret;
+
+	p = devres_alloc(dmam_device_release, sizeof(void *), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	ret = dma_async_device_register(device);
+	if (!ret) {
+		*(struct dma_device **)p = device;
+		devres_add(device->dev, p);
+	} else {
+		devres_free(p);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(dmaenginem_async_device_register);
+
 struct dmaengine_unmap_pool {
 	struct kmem_cache *cache;
 	const char *name;
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index 29d04ca..202ffa9 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -413,6 +413,13 @@ static void hsu_dma_free_chan_resources(struct dma_chan *chan)
 	vchan_free_chan_resources(to_virt_chan(chan));
 }
 
+static void hsu_dma_synchronize(struct dma_chan *chan)
+{
+	struct hsu_dma_chan *hsuc = to_hsu_dma_chan(chan);
+
+	vchan_synchronize(&hsuc->vchan);
+}
+
 int hsu_dma_probe(struct hsu_dma_chip *chip)
 {
 	struct hsu_dma *hsu;
@@ -459,6 +466,7 @@ int hsu_dma_probe(struct hsu_dma_chip *chip)
 	hsu->dma.device_pause = hsu_dma_pause;
 	hsu->dma.device_resume = hsu_dma_resume;
 	hsu->dma.device_terminate_all = hsu_dma_terminate_all;
+	hsu->dma.device_synchronize = hsu_dma_synchronize;
 
 	hsu->dma.src_addr_widths = HSU_DMA_BUSWIDTHS;
 	hsu->dma.dst_addr_widths = HSU_DMA_BUSWIDTHS;
diff --git a/drivers/dma/idma64.c b/drivers/dma/idma64.c
index e5c9112..1fbf9cb 100644
--- a/drivers/dma/idma64.c
+++ b/drivers/dma/idma64.c
@@ -496,6 +496,13 @@ static int idma64_terminate_all(struct dma_chan *chan)
 	return 0;
 }
 
+static void idma64_synchronize(struct dma_chan *chan)
+{
+	struct idma64_chan *idma64c = to_idma64_chan(chan);
+
+	vchan_synchronize(&idma64c->vchan);
+}
+
 static int idma64_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct idma64_chan *idma64c = to_idma64_chan(chan);
@@ -583,6 +590,7 @@ static int idma64_probe(struct idma64_chip *chip)
 	idma64->dma.device_pause = idma64_pause;
 	idma64->dma.device_resume = idma64_resume;
 	idma64->dma.device_terminate_all = idma64_terminate_all;
+	idma64->dma.device_synchronize = idma64_synchronize;
 
 	idma64->dma.src_addr_widths = IDMA64_BUSWIDTHS;
 	idma64->dma.dst_addr_widths = IDMA64_BUSWIDTHS;
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 8b5b23a..23fb2fa 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -688,6 +688,12 @@ static void ioat_restart_channel(struct ioatdma_chan *ioat_chan)
 {
 	u64 phys_complete;
 
+	/* set the completion address register again */
+	writel(lower_32_bits(ioat_chan->completion_dma),
+	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_LOW);
+	writel(upper_32_bits(ioat_chan->completion_dma),
+	       ioat_chan->reg_base + IOAT_CHANCMP_OFFSET_HIGH);
+
 	ioat_quiesce(ioat_chan, 0);
 	if (ioat_cleanup_preamble(ioat_chan, &phys_complete))
 		__cleanup(ioat_chan, phys_complete);
diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c
index 68dd797..b76cb17 100644
--- a/drivers/dma/mic_x100_dma.c
+++ b/drivers/dma/mic_x100_dma.c
@@ -470,11 +470,6 @@ static void mic_dma_chan_destroy(struct mic_dma_chan *ch)
 	mic_dma_chan_mask_intr(ch);
 }
 
-static void mic_dma_unregister_dma_device(struct mic_dma_device *mic_dma_dev)
-{
-	dma_async_device_unregister(&mic_dma_dev->dma_dev);
-}
-
 static int mic_dma_setup_irq(struct mic_dma_chan *ch)
 {
 	ch->cookie =
@@ -630,7 +625,7 @@ static int mic_dma_register_dma_device(struct mic_dma_device *mic_dma_dev,
 		list_add_tail(&mic_dma_dev->mic_ch[i].api_ch.device_node,
 			      &mic_dma_dev->dma_dev.channels);
 	}
-	return dma_async_device_register(&mic_dma_dev->dma_dev);
+	return dmaenginem_async_device_register(&mic_dma_dev->dma_dev);
 }
 
 /*
@@ -678,7 +673,6 @@ static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev,
 
 static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev)
 {
-	mic_dma_unregister_dma_device(mic_dma_dev);
 	mic_dma_uninit(mic_dma_dev);
 	kfree(mic_dma_dev);
 }
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index c6589cc..8dc0aa4 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -174,6 +174,7 @@ struct mv_xor_v2_device {
 	int desc_size;
 	unsigned int npendings;
 	unsigned int hw_queue_idx;
+	struct msi_desc *msi_desc;
 };
 
 /**
@@ -588,11 +589,9 @@ static void mv_xor_v2_tasklet(unsigned long data)
 			 */
 			dma_cookie_complete(&next_pending_sw_desc->async_tx);
 
-			if (next_pending_sw_desc->async_tx.callback)
-				next_pending_sw_desc->async_tx.callback(
-				next_pending_sw_desc->async_tx.callback_param);
-
 			dma_descriptor_unmap(&next_pending_sw_desc->async_tx);
+			dmaengine_desc_get_callback_invoke(
+					&next_pending_sw_desc->async_tx, NULL);
 		}
 
 		dma_run_dependencies(&next_pending_sw_desc->async_tx);
@@ -643,9 +642,9 @@ static int mv_xor_v2_descq_init(struct mv_xor_v2_device *xor_dev)
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_SIZE_OFF);
 
 	/* write the DESQ address to the DMA enngine*/
-	writel(xor_dev->hw_desq & 0xFFFFFFFF,
+	writel(lower_32_bits(xor_dev->hw_desq),
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_BALR_OFF);
-	writel((xor_dev->hw_desq & 0xFFFF00000000) >> 32,
+	writel(upper_32_bits(xor_dev->hw_desq),
 	       xor_dev->dma_base + MV_XOR_V2_DMA_DESQ_BAHR_OFF);
 
 	/*
@@ -780,6 +779,7 @@ static int mv_xor_v2_probe(struct platform_device *pdev)
 	msi_desc = first_msi_entry(&pdev->dev);
 	if (!msi_desc)
 		goto free_msi_irqs;
+	xor_dev->msi_desc = msi_desc;
 
 	ret = devm_request_irq(&pdev->dev, msi_desc->irq,
 			       mv_xor_v2_interrupt_handler, 0,
@@ -897,8 +897,12 @@ static int mv_xor_v2_remove(struct platform_device *pdev)
 			  xor_dev->desc_size * MV_XOR_V2_DESC_NUM,
 			  xor_dev->hw_desq_virt, xor_dev->hw_desq);
 
+	devm_free_irq(&pdev->dev, xor_dev->msi_desc->irq, xor_dev);
+
 	platform_msi_domain_free_irqs(&pdev->dev);
 
+	tasklet_kill(&xor_dev->irq_tasklet);
+
 	clk_disable_unprepare(xor_dev->clk);
 
 	return 0;
diff --git a/drivers/dma/nbpfaxi.c b/drivers/dma/nbpfaxi.c
index 2f9974d..8c7b2e8 100644
--- a/drivers/dma/nbpfaxi.c
+++ b/drivers/dma/nbpfaxi.c
@@ -479,6 +479,7 @@ static size_t nbpf_xfer_size(struct nbpf_device *nbpf,
 
 	default:
 		pr_warn("%s(): invalid bus width %u\n", __func__, width);
+		/* fall through */
 	case DMA_SLAVE_BUSWIDTH_1_BYTE:
 		size = burst;
 	}
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
new file mode 100644
index 0000000..7812a63
--- /dev/null
+++ b/drivers/dma/owl-dma.c
@@ -0,0 +1,971 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Actions Semi Owl SoCs DMA driver
+//
+// Copyright (c) 2014 Actions Semi Inc.
+// Author: David Liu <liuwei@actions-semi.com>
+//
+// Copyright (c) 2018 Linaro Ltd.
+// Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include "virt-dma.h"
+
+#define OWL_DMA_FRAME_MAX_LENGTH		0xfffff
+
+/* Global DMA Controller Registers */
+#define OWL_DMA_IRQ_PD0				0x00
+#define OWL_DMA_IRQ_PD1				0x04
+#define OWL_DMA_IRQ_PD2				0x08
+#define OWL_DMA_IRQ_PD3				0x0C
+#define OWL_DMA_IRQ_EN0				0x10
+#define OWL_DMA_IRQ_EN1				0x14
+#define OWL_DMA_IRQ_EN2				0x18
+#define OWL_DMA_IRQ_EN3				0x1C
+#define OWL_DMA_SECURE_ACCESS_CTL		0x20
+#define OWL_DMA_NIC_QOS				0x24
+#define OWL_DMA_DBGSEL				0x28
+#define OWL_DMA_IDLE_STAT			0x2C
+
+/* Channel Registers */
+#define OWL_DMA_CHAN_BASE(i)			(0x100 + (i) * 0x100)
+#define OWL_DMAX_MODE				0x00
+#define OWL_DMAX_SOURCE				0x04
+#define OWL_DMAX_DESTINATION			0x08
+#define OWL_DMAX_FRAME_LEN			0x0C
+#define OWL_DMAX_FRAME_CNT			0x10
+#define OWL_DMAX_REMAIN_FRAME_CNT		0x14
+#define OWL_DMAX_REMAIN_CNT			0x18
+#define OWL_DMAX_SOURCE_STRIDE			0x1C
+#define OWL_DMAX_DESTINATION_STRIDE		0x20
+#define OWL_DMAX_START				0x24
+#define OWL_DMAX_PAUSE				0x28
+#define OWL_DMAX_CHAINED_CTL			0x2C
+#define OWL_DMAX_CONSTANT			0x30
+#define OWL_DMAX_LINKLIST_CTL			0x34
+#define OWL_DMAX_NEXT_DESCRIPTOR		0x38
+#define OWL_DMAX_CURRENT_DESCRIPTOR_NUM		0x3C
+#define OWL_DMAX_INT_CTL			0x40
+#define OWL_DMAX_INT_STATUS			0x44
+#define OWL_DMAX_CURRENT_SOURCE_POINTER		0x48
+#define OWL_DMAX_CURRENT_DESTINATION_POINTER	0x4C
+
+/* OWL_DMAX_MODE Bits */
+#define OWL_DMA_MODE_TS(x)			(((x) & GENMASK(5, 0)) << 0)
+#define OWL_DMA_MODE_ST(x)			(((x) & GENMASK(1, 0)) << 8)
+#define	OWL_DMA_MODE_ST_DEV			OWL_DMA_MODE_ST(0)
+#define	OWL_DMA_MODE_ST_DCU			OWL_DMA_MODE_ST(2)
+#define	OWL_DMA_MODE_ST_SRAM			OWL_DMA_MODE_ST(3)
+#define OWL_DMA_MODE_DT(x)			(((x) & GENMASK(1, 0)) << 10)
+#define	OWL_DMA_MODE_DT_DEV			OWL_DMA_MODE_DT(0)
+#define	OWL_DMA_MODE_DT_DCU			OWL_DMA_MODE_DT(2)
+#define	OWL_DMA_MODE_DT_SRAM			OWL_DMA_MODE_DT(3)
+#define OWL_DMA_MODE_SAM(x)			(((x) & GENMASK(1, 0)) << 16)
+#define	OWL_DMA_MODE_SAM_CONST			OWL_DMA_MODE_SAM(0)
+#define	OWL_DMA_MODE_SAM_INC			OWL_DMA_MODE_SAM(1)
+#define	OWL_DMA_MODE_SAM_STRIDE			OWL_DMA_MODE_SAM(2)
+#define OWL_DMA_MODE_DAM(x)			(((x) & GENMASK(1, 0)) << 18)
+#define	OWL_DMA_MODE_DAM_CONST			OWL_DMA_MODE_DAM(0)
+#define	OWL_DMA_MODE_DAM_INC			OWL_DMA_MODE_DAM(1)
+#define	OWL_DMA_MODE_DAM_STRIDE			OWL_DMA_MODE_DAM(2)
+#define OWL_DMA_MODE_PW(x)			(((x) & GENMASK(2, 0)) << 20)
+#define OWL_DMA_MODE_CB				BIT(23)
+#define OWL_DMA_MODE_NDDBW(x)			(((x) & 0x1) << 28)
+#define	OWL_DMA_MODE_NDDBW_32BIT		OWL_DMA_MODE_NDDBW(0)
+#define	OWL_DMA_MODE_NDDBW_8BIT			OWL_DMA_MODE_NDDBW(1)
+#define OWL_DMA_MODE_CFE			BIT(29)
+#define OWL_DMA_MODE_LME			BIT(30)
+#define OWL_DMA_MODE_CME			BIT(31)
+
+/* OWL_DMAX_LINKLIST_CTL Bits */
+#define OWL_DMA_LLC_SAV(x)			(((x) & GENMASK(1, 0)) << 8)
+#define	OWL_DMA_LLC_SAV_INC			OWL_DMA_LLC_SAV(0)
+#define	OWL_DMA_LLC_SAV_LOAD_NEXT		OWL_DMA_LLC_SAV(1)
+#define	OWL_DMA_LLC_SAV_LOAD_PREV		OWL_DMA_LLC_SAV(2)
+#define OWL_DMA_LLC_DAV(x)			(((x) & GENMASK(1, 0)) << 10)
+#define	OWL_DMA_LLC_DAV_INC			OWL_DMA_LLC_DAV(0)
+#define	OWL_DMA_LLC_DAV_LOAD_NEXT		OWL_DMA_LLC_DAV(1)
+#define	OWL_DMA_LLC_DAV_LOAD_PREV		OWL_DMA_LLC_DAV(2)
+#define OWL_DMA_LLC_SUSPEND			BIT(16)
+
+/* OWL_DMAX_INT_CTL Bits */
+#define OWL_DMA_INTCTL_BLOCK			BIT(0)
+#define OWL_DMA_INTCTL_SUPER_BLOCK		BIT(1)
+#define OWL_DMA_INTCTL_FRAME			BIT(2)
+#define OWL_DMA_INTCTL_HALF_FRAME		BIT(3)
+#define OWL_DMA_INTCTL_LAST_FRAME		BIT(4)
+
+/* OWL_DMAX_INT_STATUS Bits */
+#define OWL_DMA_INTSTAT_BLOCK			BIT(0)
+#define OWL_DMA_INTSTAT_SUPER_BLOCK		BIT(1)
+#define OWL_DMA_INTSTAT_FRAME			BIT(2)
+#define OWL_DMA_INTSTAT_HALF_FRAME		BIT(3)
+#define OWL_DMA_INTSTAT_LAST_FRAME		BIT(4)
+
+/* Pack shift and newshift in a single word */
+#define BIT_FIELD(val, width, shift, newshift)	\
+		((((val) >> (shift)) & ((BIT(width)) - 1)) << (newshift))
+
+/**
+ * struct owl_dma_lli_hw - Hardware link list for dma transfer
+ * @next_lli: physical address of the next link list
+ * @saddr: source physical address
+ * @daddr: destination physical address
+ * @flen: frame length
+ * @fcnt: frame count
+ * @src_stride: source stride
+ * @dst_stride: destination stride
+ * @ctrla: dma_mode and linklist ctrl config
+ * @ctrlb: interrupt config
+ * @const_num: data for constant fill
+ */
+struct owl_dma_lli_hw {
+	u32	next_lli;
+	u32	saddr;
+	u32	daddr;
+	u32	flen:20;
+	u32	fcnt:12;
+	u32	src_stride;
+	u32	dst_stride;
+	u32	ctrla;
+	u32	ctrlb;
+	u32	const_num;
+};
+
+/**
+ * struct owl_dma_lli - Link list for dma transfer
+ * @hw: hardware link list
+ * @phys: physical address of hardware link list
+ * @node: node for txd's lli_list
+ */
+struct owl_dma_lli {
+	struct  owl_dma_lli_hw	hw;
+	dma_addr_t		phys;
+	struct list_head	node;
+};
+
+/**
+ * struct owl_dma_txd - Wrapper for struct dma_async_tx_descriptor
+ * @vd: virtual DMA descriptor
+ * @lli_list: link list of lli nodes
+ */
+struct owl_dma_txd {
+	struct virt_dma_desc	vd;
+	struct list_head	lli_list;
+};
+
+/**
+ * struct owl_dma_pchan - Holder for the physical channels
+ * @id: physical index to this channel
+ * @base: virtual memory base for the dma channel
+ * @vchan: the virtual channel currently being served by this physical channel
+ * @lock: a lock to use when altering an instance of this struct
+ */
+struct owl_dma_pchan {
+	u32			id;
+	void __iomem		*base;
+	struct owl_dma_vchan	*vchan;
+	spinlock_t		lock;
+};
+
+/**
+ * struct owl_dma_pchan - Wrapper for DMA ENGINE channel
+ * @vc: wrappped virtual channel
+ * @pchan: the physical channel utilized by this channel
+ * @txd: active transaction on this channel
+ */
+struct owl_dma_vchan {
+	struct virt_dma_chan	vc;
+	struct owl_dma_pchan	*pchan;
+	struct owl_dma_txd	*txd;
+};
+
+/**
+ * struct owl_dma - Holder for the Owl DMA controller
+ * @dma: dma engine for this instance
+ * @base: virtual memory base for the DMA controller
+ * @clk: clock for the DMA controller
+ * @lock: a lock to use when change DMA controller global register
+ * @lli_pool: a pool for the LLI descriptors
+ * @nr_pchans: the number of physical channels
+ * @pchans: array of data for the physical channels
+ * @nr_vchans: the number of physical channels
+ * @vchans: array of data for the physical channels
+ */
+struct owl_dma {
+	struct dma_device	dma;
+	void __iomem		*base;
+	struct clk		*clk;
+	spinlock_t		lock;
+	struct dma_pool		*lli_pool;
+	int			irq;
+
+	unsigned int		nr_pchans;
+	struct owl_dma_pchan	*pchans;
+
+	unsigned int		nr_vchans;
+	struct owl_dma_vchan	*vchans;
+};
+
+static void pchan_update(struct owl_dma_pchan *pchan, u32 reg,
+			 u32 val, bool state)
+{
+	u32 regval;
+
+	regval = readl(pchan->base + reg);
+
+	if (state)
+		regval |= val;
+	else
+		regval &= ~val;
+
+	writel(val, pchan->base + reg);
+}
+
+static void pchan_writel(struct owl_dma_pchan *pchan, u32 reg, u32 data)
+{
+	writel(data, pchan->base + reg);
+}
+
+static u32 pchan_readl(struct owl_dma_pchan *pchan, u32 reg)
+{
+	return readl(pchan->base + reg);
+}
+
+static void dma_update(struct owl_dma *od, u32 reg, u32 val, bool state)
+{
+	u32 regval;
+
+	regval = readl(od->base + reg);
+
+	if (state)
+		regval |= val;
+	else
+		regval &= ~val;
+
+	writel(val, od->base + reg);
+}
+
+static void dma_writel(struct owl_dma *od, u32 reg, u32 data)
+{
+	writel(data, od->base + reg);
+}
+
+static u32 dma_readl(struct owl_dma *od, u32 reg)
+{
+	return readl(od->base + reg);
+}
+
+static inline struct owl_dma *to_owl_dma(struct dma_device *dd)
+{
+	return container_of(dd, struct owl_dma, dma);
+}
+
+static struct device *chan2dev(struct dma_chan *chan)
+{
+	return &chan->dev->device;
+}
+
+static inline struct owl_dma_vchan *to_owl_vchan(struct dma_chan *chan)
+{
+	return container_of(chan, struct owl_dma_vchan, vc.chan);
+}
+
+static inline struct owl_dma_txd *to_owl_txd(struct dma_async_tx_descriptor *tx)
+{
+	return container_of(tx, struct owl_dma_txd, vd.tx);
+}
+
+static inline u32 llc_hw_ctrla(u32 mode, u32 llc_ctl)
+{
+	u32 ctl;
+
+	ctl = BIT_FIELD(mode, 4, 28, 28) |
+	      BIT_FIELD(mode, 8, 16, 20) |
+	      BIT_FIELD(mode, 4, 8, 16) |
+	      BIT_FIELD(mode, 6, 0, 10) |
+	      BIT_FIELD(llc_ctl, 2, 10, 8) |
+	      BIT_FIELD(llc_ctl, 2, 8, 6);
+
+	return ctl;
+}
+
+static inline u32 llc_hw_ctrlb(u32 int_ctl)
+{
+	u32 ctl;
+
+	ctl = BIT_FIELD(int_ctl, 7, 0, 18);
+
+	return ctl;
+}
+
+static void owl_dma_free_lli(struct owl_dma *od,
+			     struct owl_dma_lli *lli)
+{
+	list_del(&lli->node);
+	dma_pool_free(od->lli_pool, lli, lli->phys);
+}
+
+static struct owl_dma_lli *owl_dma_alloc_lli(struct owl_dma *od)
+{
+	struct owl_dma_lli *lli;
+	dma_addr_t phys;
+
+	lli = dma_pool_alloc(od->lli_pool, GFP_NOWAIT, &phys);
+	if (!lli)
+		return NULL;
+
+	INIT_LIST_HEAD(&lli->node);
+	lli->phys = phys;
+
+	return lli;
+}
+
+static struct owl_dma_lli *owl_dma_add_lli(struct owl_dma_txd *txd,
+					   struct owl_dma_lli *prev,
+					   struct owl_dma_lli *next)
+{
+	list_add_tail(&next->node, &txd->lli_list);
+
+	if (prev) {
+		prev->hw.next_lli = next->phys;
+		prev->hw.ctrla |= llc_hw_ctrla(OWL_DMA_MODE_LME, 0);
+	}
+
+	return next;
+}
+
+static inline int owl_dma_cfg_lli(struct owl_dma_vchan *vchan,
+				  struct owl_dma_lli *lli,
+				  dma_addr_t src, dma_addr_t dst,
+				  u32 len, enum dma_transfer_direction dir)
+{
+	struct owl_dma_lli_hw *hw = &lli->hw;
+	u32 mode;
+
+	mode = OWL_DMA_MODE_PW(0);
+
+	switch (dir) {
+	case DMA_MEM_TO_MEM:
+		mode |= OWL_DMA_MODE_TS(0) | OWL_DMA_MODE_ST_DCU |
+			OWL_DMA_MODE_DT_DCU | OWL_DMA_MODE_SAM_INC |
+			OWL_DMA_MODE_DAM_INC;
+
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	hw->next_lli = 0; /* One link list by default */
+	hw->saddr = src;
+	hw->daddr = dst;
+
+	hw->fcnt = 1; /* Frame count fixed as 1 */
+	hw->flen = len; /* Max frame length is 1MB */
+	hw->src_stride = 0;
+	hw->dst_stride = 0;
+	hw->ctrla = llc_hw_ctrla(mode,
+				 OWL_DMA_LLC_SAV_LOAD_NEXT |
+				 OWL_DMA_LLC_DAV_LOAD_NEXT);
+
+	hw->ctrlb = llc_hw_ctrlb(OWL_DMA_INTCTL_SUPER_BLOCK);
+
+	return 0;
+}
+
+static struct owl_dma_pchan *owl_dma_get_pchan(struct owl_dma *od,
+					       struct owl_dma_vchan *vchan)
+{
+	struct owl_dma_pchan *pchan = NULL;
+	unsigned long flags;
+	int i;
+
+	for (i = 0; i < od->nr_pchans; i++) {
+		pchan = &od->pchans[i];
+
+		spin_lock_irqsave(&pchan->lock, flags);
+		if (!pchan->vchan) {
+			pchan->vchan = vchan;
+			spin_unlock_irqrestore(&pchan->lock, flags);
+			break;
+		}
+
+		spin_unlock_irqrestore(&pchan->lock, flags);
+	}
+
+	return pchan;
+}
+
+static int owl_dma_pchan_busy(struct owl_dma *od, struct owl_dma_pchan *pchan)
+{
+	unsigned int val;
+
+	val = dma_readl(od, OWL_DMA_IDLE_STAT);
+
+	return !(val & (1 << pchan->id));
+}
+
+static void owl_dma_terminate_pchan(struct owl_dma *od,
+				    struct owl_dma_pchan *pchan)
+{
+	unsigned long flags;
+	u32 irq_pd;
+
+	pchan_writel(pchan, OWL_DMAX_START, 0);
+	pchan_update(pchan, OWL_DMAX_INT_STATUS, 0xff, false);
+
+	spin_lock_irqsave(&od->lock, flags);
+	dma_update(od, OWL_DMA_IRQ_EN0, (1 << pchan->id), false);
+
+	irq_pd = dma_readl(od, OWL_DMA_IRQ_PD0);
+	if (irq_pd & (1 << pchan->id)) {
+		dev_warn(od->dma.dev,
+			 "terminating pchan %d that still has pending irq\n",
+			 pchan->id);
+		dma_writel(od, OWL_DMA_IRQ_PD0, (1 << pchan->id));
+	}
+
+	pchan->vchan = NULL;
+
+	spin_unlock_irqrestore(&od->lock, flags);
+}
+
+static int owl_dma_start_next_txd(struct owl_dma_vchan *vchan)
+{
+	struct owl_dma *od = to_owl_dma(vchan->vc.chan.device);
+	struct virt_dma_desc *vd = vchan_next_desc(&vchan->vc);
+	struct owl_dma_pchan *pchan = vchan->pchan;
+	struct owl_dma_txd *txd = to_owl_txd(&vd->tx);
+	struct owl_dma_lli *lli;
+	unsigned long flags;
+	u32 int_ctl;
+
+	list_del(&vd->node);
+
+	vchan->txd = txd;
+
+	/* Wait for channel inactive */
+	while (owl_dma_pchan_busy(od, pchan))
+		cpu_relax();
+
+	lli = list_first_entry(&txd->lli_list,
+			       struct owl_dma_lli, node);
+
+	int_ctl = OWL_DMA_INTCTL_SUPER_BLOCK;
+
+	pchan_writel(pchan, OWL_DMAX_MODE, OWL_DMA_MODE_LME);
+	pchan_writel(pchan, OWL_DMAX_LINKLIST_CTL,
+		     OWL_DMA_LLC_SAV_LOAD_NEXT | OWL_DMA_LLC_DAV_LOAD_NEXT);
+	pchan_writel(pchan, OWL_DMAX_NEXT_DESCRIPTOR, lli->phys);
+	pchan_writel(pchan, OWL_DMAX_INT_CTL, int_ctl);
+
+	/* Clear IRQ status for this pchan */
+	pchan_update(pchan, OWL_DMAX_INT_STATUS, 0xff, false);
+
+	spin_lock_irqsave(&od->lock, flags);
+
+	dma_update(od, OWL_DMA_IRQ_EN0, (1 << pchan->id), true);
+
+	spin_unlock_irqrestore(&od->lock, flags);
+
+	dev_dbg(chan2dev(&vchan->vc.chan), "starting pchan %d\n", pchan->id);
+
+	/* Start DMA transfer for this pchan */
+	pchan_writel(pchan, OWL_DMAX_START, 0x1);
+
+	return 0;
+}
+
+static void owl_dma_phy_free(struct owl_dma *od, struct owl_dma_vchan *vchan)
+{
+	/* Ensure that the physical channel is stopped */
+	owl_dma_terminate_pchan(od, vchan->pchan);
+
+	vchan->pchan = NULL;
+}
+
+static irqreturn_t owl_dma_interrupt(int irq, void *dev_id)
+{
+	struct owl_dma *od = dev_id;
+	struct owl_dma_vchan *vchan;
+	struct owl_dma_pchan *pchan;
+	unsigned long pending;
+	int i;
+	unsigned int global_irq_pending, chan_irq_pending;
+
+	spin_lock(&od->lock);
+
+	pending = dma_readl(od, OWL_DMA_IRQ_PD0);
+
+	/* Clear IRQ status for each pchan */
+	for_each_set_bit(i, &pending, od->nr_pchans) {
+		pchan = &od->pchans[i];
+		pchan_update(pchan, OWL_DMAX_INT_STATUS, 0xff, false);
+	}
+
+	/* Clear pending IRQ */
+	dma_writel(od, OWL_DMA_IRQ_PD0, pending);
+
+	/* Check missed pending IRQ */
+	for (i = 0; i < od->nr_pchans; i++) {
+		pchan = &od->pchans[i];
+		chan_irq_pending = pchan_readl(pchan, OWL_DMAX_INT_CTL) &
+				   pchan_readl(pchan, OWL_DMAX_INT_STATUS);
+
+		/* Dummy read to ensure OWL_DMA_IRQ_PD0 value is updated */
+		dma_readl(od, OWL_DMA_IRQ_PD0);
+
+		global_irq_pending = dma_readl(od, OWL_DMA_IRQ_PD0);
+
+		if (chan_irq_pending && !(global_irq_pending & BIT(i)))	{
+			dev_dbg(od->dma.dev,
+				"global and channel IRQ pending match err\n");
+
+			/* Clear IRQ status for this pchan */
+			pchan_update(pchan, OWL_DMAX_INT_STATUS,
+				     0xff, false);
+
+			/* Update global IRQ pending */
+			pending |= BIT(i);
+		}
+	}
+
+	spin_unlock(&od->lock);
+
+	for_each_set_bit(i, &pending, od->nr_pchans) {
+		struct owl_dma_txd *txd;
+
+		pchan = &od->pchans[i];
+
+		vchan = pchan->vchan;
+		if (!vchan) {
+			dev_warn(od->dma.dev, "no vchan attached on pchan %d\n",
+				 pchan->id);
+			continue;
+		}
+
+		spin_lock(&vchan->vc.lock);
+
+		txd = vchan->txd;
+		if (txd) {
+			vchan->txd = NULL;
+
+			vchan_cookie_complete(&txd->vd);
+
+			/*
+			 * Start the next descriptor (if any),
+			 * otherwise free this channel.
+			 */
+			if (vchan_next_desc(&vchan->vc))
+				owl_dma_start_next_txd(vchan);
+			else
+				owl_dma_phy_free(od, vchan);
+		}
+
+		spin_unlock(&vchan->vc.lock);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void owl_dma_free_txd(struct owl_dma *od, struct owl_dma_txd *txd)
+{
+	struct owl_dma_lli *lli, *_lli;
+
+	if (unlikely(!txd))
+		return;
+
+	list_for_each_entry_safe(lli, _lli, &txd->lli_list, node)
+		owl_dma_free_lli(od, lli);
+
+	kfree(txd);
+}
+
+static void owl_dma_desc_free(struct virt_dma_desc *vd)
+{
+	struct owl_dma *od = to_owl_dma(vd->tx.chan->device);
+	struct owl_dma_txd *txd = to_owl_txd(&vd->tx);
+
+	owl_dma_free_txd(od, txd);
+}
+
+static int owl_dma_terminate_all(struct dma_chan *chan)
+{
+	struct owl_dma *od = to_owl_dma(chan->device);
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+
+	if (vchan->pchan)
+		owl_dma_phy_free(od, vchan);
+
+	if (vchan->txd) {
+		owl_dma_desc_free(&vchan->txd->vd);
+		vchan->txd = NULL;
+	}
+
+	vchan_get_all_descriptors(&vchan->vc, &head);
+	vchan_dma_desc_free_list(&vchan->vc, &head);
+
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+
+	return 0;
+}
+
+static u32 owl_dma_getbytes_chan(struct owl_dma_vchan *vchan)
+{
+	struct owl_dma_pchan *pchan;
+	struct owl_dma_txd *txd;
+	struct owl_dma_lli *lli;
+	unsigned int next_lli_phy;
+	size_t bytes;
+
+	pchan = vchan->pchan;
+	txd = vchan->txd;
+
+	if (!pchan || !txd)
+		return 0;
+
+	/* Get remain count of current node in link list */
+	bytes = pchan_readl(pchan, OWL_DMAX_REMAIN_CNT);
+
+	/* Loop through the preceding nodes to get total remaining bytes */
+	if (pchan_readl(pchan, OWL_DMAX_MODE) & OWL_DMA_MODE_LME) {
+		next_lli_phy = pchan_readl(pchan, OWL_DMAX_NEXT_DESCRIPTOR);
+		list_for_each_entry(lli, &txd->lli_list, node) {
+			/* Start from the next active node */
+			if (lli->phys == next_lli_phy) {
+				list_for_each_entry(lli, &txd->lli_list, node)
+					bytes += lli->hw.flen;
+				break;
+			}
+		}
+	}
+
+	return bytes;
+}
+
+static enum dma_status owl_dma_tx_status(struct dma_chan *chan,
+					 dma_cookie_t cookie,
+					 struct dma_tx_state *state)
+{
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+	struct owl_dma_lli *lli;
+	struct virt_dma_desc *vd;
+	struct owl_dma_txd *txd;
+	enum dma_status ret;
+	unsigned long flags;
+	size_t bytes = 0;
+
+	ret = dma_cookie_status(chan, cookie, state);
+	if (ret == DMA_COMPLETE || !state)
+		return ret;
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+
+	vd = vchan_find_desc(&vchan->vc, cookie);
+	if (vd) {
+		txd = to_owl_txd(&vd->tx);
+		list_for_each_entry(lli, &txd->lli_list, node)
+			bytes += lli->hw.flen;
+	} else {
+		bytes = owl_dma_getbytes_chan(vchan);
+	}
+
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+
+	dma_set_residue(state, bytes);
+
+	return ret;
+}
+
+static void owl_dma_phy_alloc_and_start(struct owl_dma_vchan *vchan)
+{
+	struct owl_dma *od = to_owl_dma(vchan->vc.chan.device);
+	struct owl_dma_pchan *pchan;
+
+	pchan = owl_dma_get_pchan(od, vchan);
+	if (!pchan)
+		return;
+
+	dev_dbg(od->dma.dev, "allocated pchan %d\n", pchan->id);
+
+	vchan->pchan = pchan;
+	owl_dma_start_next_txd(vchan);
+}
+
+static void owl_dma_issue_pending(struct dma_chan *chan)
+{
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vchan->vc.lock, flags);
+	if (vchan_issue_pending(&vchan->vc)) {
+		if (!vchan->pchan)
+			owl_dma_phy_alloc_and_start(vchan);
+	}
+	spin_unlock_irqrestore(&vchan->vc.lock, flags);
+}
+
+static struct dma_async_tx_descriptor
+		*owl_dma_prep_memcpy(struct dma_chan *chan,
+				     dma_addr_t dst, dma_addr_t src,
+				     size_t len, unsigned long flags)
+{
+	struct owl_dma *od = to_owl_dma(chan->device);
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+	struct owl_dma_txd *txd;
+	struct owl_dma_lli *lli, *prev = NULL;
+	size_t offset, bytes;
+	int ret;
+
+	if (!len)
+		return NULL;
+
+	txd = kzalloc(sizeof(*txd), GFP_NOWAIT);
+	if (!txd)
+		return NULL;
+
+	INIT_LIST_HEAD(&txd->lli_list);
+
+	/* Process the transfer as frame by frame */
+	for (offset = 0; offset < len; offset += bytes) {
+		lli = owl_dma_alloc_lli(od);
+		if (!lli) {
+			dev_warn(chan2dev(chan), "failed to allocate lli\n");
+			goto err_txd_free;
+		}
+
+		bytes = min_t(size_t, (len - offset), OWL_DMA_FRAME_MAX_LENGTH);
+
+		ret = owl_dma_cfg_lli(vchan, lli, src + offset, dst + offset,
+				      bytes, DMA_MEM_TO_MEM);
+		if (ret) {
+			dev_warn(chan2dev(chan), "failed to config lli\n");
+			goto err_txd_free;
+		}
+
+		prev = owl_dma_add_lli(txd, prev, lli);
+	}
+
+	return vchan_tx_prep(&vchan->vc, &txd->vd, flags);
+
+err_txd_free:
+	owl_dma_free_txd(od, txd);
+	return NULL;
+}
+
+static void owl_dma_free_chan_resources(struct dma_chan *chan)
+{
+	struct owl_dma_vchan *vchan = to_owl_vchan(chan);
+
+	/* Ensure all queued descriptors are freed */
+	vchan_free_chan_resources(&vchan->vc);
+}
+
+static inline void owl_dma_free(struct owl_dma *od)
+{
+	struct owl_dma_vchan *vchan = NULL;
+	struct owl_dma_vchan *next;
+
+	list_for_each_entry_safe(vchan,
+				 next, &od->dma.channels, vc.chan.device_node) {
+		list_del(&vchan->vc.chan.device_node);
+		tasklet_kill(&vchan->vc.task);
+	}
+}
+
+static int owl_dma_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct owl_dma *od;
+	struct resource *res;
+	int ret, i, nr_channels, nr_requests;
+
+	od = devm_kzalloc(&pdev->dev, sizeof(*od), GFP_KERNEL);
+	if (!od)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+
+	od->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(od->base))
+		return PTR_ERR(od->base);
+
+	ret = of_property_read_u32(np, "dma-channels", &nr_channels);
+	if (ret) {
+		dev_err(&pdev->dev, "can't get dma-channels\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "dma-requests", &nr_requests);
+	if (ret) {
+		dev_err(&pdev->dev, "can't get dma-requests\n");
+		return ret;
+	}
+
+	dev_info(&pdev->dev, "dma-channels %d, dma-requests %d\n",
+		 nr_channels, nr_requests);
+
+	od->nr_pchans = nr_channels;
+	od->nr_vchans = nr_requests;
+
+	pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+
+	platform_set_drvdata(pdev, od);
+	spin_lock_init(&od->lock);
+
+	dma_cap_set(DMA_MEMCPY, od->dma.cap_mask);
+
+	od->dma.dev = &pdev->dev;
+	od->dma.device_free_chan_resources = owl_dma_free_chan_resources;
+	od->dma.device_tx_status = owl_dma_tx_status;
+	od->dma.device_issue_pending = owl_dma_issue_pending;
+	od->dma.device_prep_dma_memcpy = owl_dma_prep_memcpy;
+	od->dma.device_terminate_all = owl_dma_terminate_all;
+	od->dma.src_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	od->dma.dst_addr_widths = BIT(DMA_SLAVE_BUSWIDTH_4_BYTES);
+	od->dma.directions = BIT(DMA_MEM_TO_MEM);
+	od->dma.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+
+	INIT_LIST_HEAD(&od->dma.channels);
+
+	od->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(od->clk)) {
+		dev_err(&pdev->dev, "unable to get clock\n");
+		return PTR_ERR(od->clk);
+	}
+
+	/*
+	 * Eventhough the DMA controller is capable of generating 4
+	 * IRQ's for DMA priority feature, we only use 1 IRQ for
+	 * simplification.
+	 */
+	od->irq = platform_get_irq(pdev, 0);
+	ret = devm_request_irq(&pdev->dev, od->irq, owl_dma_interrupt, 0,
+			       dev_name(&pdev->dev), od);
+	if (ret) {
+		dev_err(&pdev->dev, "unable to request IRQ\n");
+		return ret;
+	}
+
+	/* Init physical channel */
+	od->pchans = devm_kcalloc(&pdev->dev, od->nr_pchans,
+				  sizeof(struct owl_dma_pchan), GFP_KERNEL);
+	if (!od->pchans)
+		return -ENOMEM;
+
+	for (i = 0; i < od->nr_pchans; i++) {
+		struct owl_dma_pchan *pchan = &od->pchans[i];
+
+		pchan->id = i;
+		pchan->base = od->base + OWL_DMA_CHAN_BASE(i);
+	}
+
+	/* Init virtual channel */
+	od->vchans = devm_kcalloc(&pdev->dev, od->nr_vchans,
+				  sizeof(struct owl_dma_vchan), GFP_KERNEL);
+	if (!od->vchans)
+		return -ENOMEM;
+
+	for (i = 0; i < od->nr_vchans; i++) {
+		struct owl_dma_vchan *vchan = &od->vchans[i];
+
+		vchan->vc.desc_free = owl_dma_desc_free;
+		vchan_init(&vchan->vc, &od->dma);
+	}
+
+	/* Create a pool of consistent memory blocks for hardware descriptors */
+	od->lli_pool = dma_pool_create(dev_name(od->dma.dev), od->dma.dev,
+				       sizeof(struct owl_dma_lli),
+				       __alignof__(struct owl_dma_lli),
+				       0);
+	if (!od->lli_pool) {
+		dev_err(&pdev->dev, "unable to allocate DMA descriptor pool\n");
+		return -ENOMEM;
+	}
+
+	clk_prepare_enable(od->clk);
+
+	ret = dma_async_device_register(&od->dma);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register DMA engine device\n");
+		goto err_pool_free;
+	}
+
+	return 0;
+
+err_pool_free:
+	clk_disable_unprepare(od->clk);
+	dma_pool_destroy(od->lli_pool);
+
+	return ret;
+}
+
+static int owl_dma_remove(struct platform_device *pdev)
+{
+	struct owl_dma *od = platform_get_drvdata(pdev);
+
+	dma_async_device_unregister(&od->dma);
+
+	/* Mask all interrupts for this execution environment */
+	dma_writel(od, OWL_DMA_IRQ_EN0, 0x0);
+
+	/* Make sure we won't have any further interrupts */
+	devm_free_irq(od->dma.dev, od->irq, od);
+
+	owl_dma_free(od);
+
+	clk_disable_unprepare(od->clk);
+
+	return 0;
+}
+
+static const struct of_device_id owl_dma_match[] = {
+	{ .compatible = "actions,s900-dma", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, owl_dma_match);
+
+static struct platform_driver owl_dma_driver = {
+	.probe	= owl_dma_probe,
+	.remove	= owl_dma_remove,
+	.driver = {
+		.name = "dma-owl",
+		.of_match_table = of_match_ptr(owl_dma_match),
+	},
+};
+
+static int owl_dma_init(void)
+{
+	return platform_driver_register(&owl_dma_driver);
+}
+subsys_initcall(owl_dma_init);
+
+static void __exit owl_dma_exit(void)
+{
+	platform_driver_unregister(&owl_dma_driver);
+}
+module_exit(owl_dma_exit);
+
+MODULE_AUTHOR("David Liu <liuwei@actions-semi.com>");
+MODULE_AUTHOR("Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>");
+MODULE_DESCRIPTION("Actions Semi Owl SoCs DMA driver");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 861be5c..d49ec5c 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -415,7 +415,9 @@ enum dma_residue_granularity {
  *	each type, the dma controller should set BIT(<TYPE>) and same
  *	should be checked by controller as well
  * @max_burst: max burst capability per-transfer
- * @cmd_pause: true, if pause and thereby resume is supported
+ * @cmd_pause: true, if pause is supported (i.e. for reading residue or
+ *	       for resume later)
+ * @cmd_resume: true, if resume is supported
  * @cmd_terminate: true, if terminate cmd is supported
  * @residue_granularity: granularity of the reported transfer residue
  * @descriptor_reuse: if a descriptor can be reused by client and
@@ -427,6 +429,7 @@ struct dma_slave_caps {
 	u32 directions;
 	u32 max_burst;
 	bool cmd_pause;
+	bool cmd_resume;
 	bool cmd_terminate;
 	enum dma_residue_granularity residue_granularity;
 	bool descriptor_reuse;
@@ -1403,6 +1406,7 @@ static inline int dmaengine_desc_free(struct dma_async_tx_descriptor *desc)
 /* --- DMA device --- */
 
 int dma_async_device_register(struct dma_device *device);
+int dmaenginem_async_device_register(struct dma_device *device);
 void dma_async_device_unregister(struct dma_device *device);
 void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
 struct dma_chan *dma_get_slave_channel(struct dma_chan *chan);
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 56a541b..76c46d7 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -156,7 +156,7 @@ static int dmaengine_pcm_set_runtime_hwparams(struct snd_pcm_substream *substrea
 
 	ret = dma_get_slave_caps(chan, &dma_caps);
 	if (ret == 0) {
-		if (dma_caps.cmd_pause)
+		if (dma_caps.cmd_pause && dma_caps.cmd_resume)
 			hw.info |= SNDRV_PCM_INFO_PAUSE | SNDRV_PCM_INFO_RESUME;
 		if (dma_caps.residue_granularity <= DMA_RESIDUE_GRANULARITY_SEGMENT)
 			hw.info |= SNDRV_PCM_INFO_BATCH;