diff --git a/Documentation/devicetree/bindings/dma/stericsson,dma40.yaml b/Documentation/devicetree/bindings/dma/stericsson,dma40.yaml
index 64845347f44d..1e5752b19a49 100644
--- a/Documentation/devicetree/bindings/dma/stericsson,dma40.yaml
+++ b/Documentation/devicetree/bindings/dma/stericsson,dma40.yaml
@@ -112,14 +112,23 @@ properties:
       - const: stericsson,dma40
 
   reg:
-    items:
-      - description: DMA40 memory base
-      - description: LCPA memory base
+    oneOf:
+      - items:
+          - description: DMA40 memory base
+      - items:
+          - description: DMA40 memory base
+          - description: LCPA memory base, deprecated, use eSRAM pool instead
+        deprecated: true
+
 
   reg-names:
-    items:
-      - const: base
-      - const: lcpa
+    oneOf:
+      - items:
+          - const: base
+      - items:
+          - const: base
+          - const: lcpa
+        deprecated: true
 
   interrupts:
     maxItems: 1
@@ -127,6 +136,15 @@ properties:
   clocks:
     maxItems: 1
 
+  sram:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    description: A phandle array with inner size 1 (no arg cells).
+      First phandle is the LCPA (Logical Channel Parameter Address) memory.
+      Second phandle is the  LCLA (Logical Channel Link base Address) memory.
+    maxItems: 2
+    items:
+      maxItems: 1
+
   memcpy-channels:
     $ref: /schemas/types.yaml#/definitions/uint32-array
     description: Array of u32 elements indicating which channels on the DMA
@@ -138,6 +156,7 @@ required:
   - reg
   - interrupts
   - clocks
+  - sram
   - memcpy-channels
 
 additionalProperties: false
@@ -149,8 +168,9 @@ examples:
     #include <dt-bindings/mfd/dbx500-prcmu.h>
     dma-controller@801c0000 {
         compatible = "stericsson,db8500-dma40", "stericsson,dma40";
-        reg = <0x801c0000 0x1000>, <0x40010000 0x800>;
-        reg-names = "base", "lcpa";
+        reg = <0x801c0000 0x1000>;
+        reg-names = "base";
+        sram = <&lcpa>, <&lcla>;
         interrupts = <GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>;
         #dma-cells = <3>;
         memcpy-channels = <56 57 58 59 60>;
diff --git a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
index beecfe7a1732..4ca300a42a99 100644
--- a/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
+++ b/Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml
@@ -33,6 +33,7 @@ properties:
     enum:
       - ti,am62a-dmss-bcdma-csirx
       - ti,am64-dmss-bcdma
+      - ti,j721s2-dmss-bcdma-csi
 
   reg:
     minItems: 3
@@ -151,7 +152,12 @@ allOf:
       required:
         - power-domains
 
-    else:
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: ti,am64-dmss-bcdma
+    then:
       properties:
         reg:
           minItems: 5
@@ -168,6 +174,28 @@ allOf:
         - ti,sci-rm-range-bchan
         - ti,sci-rm-range-tchan
 
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: ti,j721s2-dmss-bcdma-csi
+    then:
+      properties:
+        ti,sci-rm-range-bchan: false
+
+        reg:
+          maxItems: 4
+
+        reg-names:
+          items:
+            - const: gcfg
+            - const: rchanrt
+            - const: tchanrt
+            - const: ringrt
+
+      required:
+        - ti,sci-rm-range-tchan
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
index d6cbd95ec26d..2128f4645c98 100644
--- a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
+++ b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml
@@ -41,6 +41,9 @@ properties:
   clock-names:
     const: axi_clk
 
+  power-domains:
+    maxItems: 1
+
 required:
   - "#dma-cells"
   - compatible
@@ -48,12 +51,14 @@ required:
   - interrupts
   - clocks
   - clock-names
+  - power-domains
 
 additionalProperties: false
 
 examples:
   - |
     #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/xlnx-zynqmp-power.h>
 
     dma: dma-controller@fd4c0000 {
       compatible = "xlnx,zynqmp-dpdma";
@@ -63,6 +68,7 @@ examples:
       clocks = <&dpdma_clk>;
       clock-names = "axi_clk";
       #dma-cells = <1>;
+      power-domains = <&zynqmp_firmware PD_DP>;
     };
 
 ...
diff --git a/MAINTAINERS b/MAINTAINERS
index d204ff5eecde..b3648da1c5b2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5932,7 +5932,9 @@ S:	Orphan
 F:	drivers/mtd/nand/raw/denali*
 
 DESIGNWARE EDMA CORE IP DRIVER
-M:	Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+M:	Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
+R:	Gustavo Pimentel <gustavo.pimentel@synopsys.com>
+R:	Serge Semin <fancer.lancer@gmail.com>
 L:	dmaengine@vger.kernel.org
 S:	Maintained
 F:	drivers/dma/dw-edma/
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index f5f422f9b850..644c188d6a11 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -553,6 +553,7 @@ config STE_DMA40
 	bool "ST-Ericsson DMA40 support"
 	depends on ARCH_U8500
 	select DMA_ENGINE
+	select SRAM
 	help
 	  Support for ST-Ericsson DMA40 controller
 
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index a812b9b00e6b..fc7cdad37161 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -963,7 +963,6 @@ static int axi_dmac_probe(struct platform_device *pdev)
 	dma_dev->device_terminate_all = axi_dmac_terminate_all;
 	dma_dev->device_synchronize = axi_dmac_synchronize;
 	dma_dev->dev = &pdev->dev;
-	dma_dev->chancnt = 1;
 	dma_dev->src_addr_widths = BIT(dmac->chan.src_width);
 	dma_dev->dst_addr_widths = BIT(dmac->chan.dest_width);
 	dma_dev->directions = BIT(dmac->chan.direction);
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index 6937cc0c0b65..796b6caf0bab 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -1466,7 +1466,6 @@ static int dw_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_CYCLIC, dw->dma.cap_mask);
 
 	/* DMA capabilities */
-	dw->dma.chancnt = hdata->nr_channels;
 	dw->dma.max_burst = hdata->axi_rw_burst_len;
 	dw->dma.src_addr_widths = AXI_DMA_BUSWIDTHS;
 	dw->dma.dst_addr_widths = AXI_DMA_BUSWIDTHS;
diff --git a/drivers/dma/dw-edma/Makefile b/drivers/dma/dw-edma/Makefile
index 8d45c0d5689d..83ab58f87760 100644
--- a/drivers/dma/dw-edma/Makefile
+++ b/drivers/dma/dw-edma/Makefile
@@ -1,7 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 
 obj-$(CONFIG_DW_EDMA)		+= dw-edma.o
-dw-edma-$(CONFIG_DEBUG_FS)	:= dw-edma-v0-debugfs.o
-dw-edma-objs			:= dw-edma-core.o \
-					dw-edma-v0-core.o $(dw-edma-y)
+dw-edma-$(CONFIG_DEBUG_FS)	:= dw-edma-v0-debugfs.o	\
+				   dw-hdma-v0-debugfs.o
+dw-edma-objs			:= dw-edma-core.o	\
+				   dw-edma-v0-core.o	\
+				   dw-hdma-v0-core.o $(dw-edma-y)
 obj-$(CONFIG_DW_EDMA_PCIE)	+= dw-edma-pcie.o
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 7d2b73ef0872..68236247059d 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -18,6 +18,7 @@
 
 #include "dw-edma-core.h"
 #include "dw-edma-v0-core.h"
+#include "dw-hdma-v0-core.h"
 #include "../dmaengine.h"
 #include "../virt-dma.h"
 
@@ -183,6 +184,7 @@ static void vchan_free_desc(struct virt_dma_desc *vdesc)
 
 static int dw_edma_start_transfer(struct dw_edma_chan *chan)
 {
+	struct dw_edma *dw = chan->dw;
 	struct dw_edma_chunk *child;
 	struct dw_edma_desc *desc;
 	struct virt_dma_desc *vd;
@@ -200,7 +202,7 @@ static int dw_edma_start_transfer(struct dw_edma_chan *chan)
 	if (!child)
 		return 0;
 
-	dw_edma_v0_core_start(child, !desc->xfer_sz);
+	dw_edma_core_start(dw, child, !desc->xfer_sz);
 	desc->xfer_sz += child->ll_region.sz;
 	dw_edma_free_burst(child);
 	list_del(&child->list);
@@ -287,7 +289,7 @@ static int dw_edma_device_terminate_all(struct dma_chan *dchan)
 		chan->configured = false;
 	} else if (chan->status == EDMA_ST_IDLE) {
 		chan->configured = false;
-	} else if (dw_edma_v0_core_ch_status(chan) == DMA_COMPLETE) {
+	} else if (dw_edma_core_ch_status(chan) == DMA_COMPLETE) {
 		/*
 		 * The channel is in a false BUSY state, probably didn't
 		 * receive or lost an interrupt
@@ -599,8 +601,6 @@ static void dw_edma_done_interrupt(struct dw_edma_chan *chan)
 	struct virt_dma_desc *vd;
 	unsigned long flags;
 
-	dw_edma_v0_core_clear_done_int(chan);
-
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	vd = vchan_next_desc(&chan->vc);
 	if (vd) {
@@ -641,8 +641,6 @@ static void dw_edma_abort_interrupt(struct dw_edma_chan *chan)
 	struct virt_dma_desc *vd;
 	unsigned long flags;
 
-	dw_edma_v0_core_clear_abort_int(chan);
-
 	spin_lock_irqsave(&chan->vc.lock, flags);
 	vd = vchan_next_desc(&chan->vc);
 	if (vd) {
@@ -654,63 +652,32 @@ static void dw_edma_abort_interrupt(struct dw_edma_chan *chan)
 	chan->status = EDMA_ST_IDLE;
 }
 
-static irqreturn_t dw_edma_interrupt(int irq, void *data, bool write)
-{
-	struct dw_edma_irq *dw_irq = data;
-	struct dw_edma *dw = dw_irq->dw;
-	unsigned long total, pos, val;
-	unsigned long off;
-	u32 mask;
-
-	if (write) {
-		total = dw->wr_ch_cnt;
-		off = 0;
-		mask = dw_irq->wr_mask;
-	} else {
-		total = dw->rd_ch_cnt;
-		off = dw->wr_ch_cnt;
-		mask = dw_irq->rd_mask;
-	}
-
-	val = dw_edma_v0_core_status_done_int(dw, write ?
-							  EDMA_DIR_WRITE :
-							  EDMA_DIR_READ);
-	val &= mask;
-	for_each_set_bit(pos, &val, total) {
-		struct dw_edma_chan *chan = &dw->chan[pos + off];
-
-		dw_edma_done_interrupt(chan);
-	}
-
-	val = dw_edma_v0_core_status_abort_int(dw, write ?
-							   EDMA_DIR_WRITE :
-							   EDMA_DIR_READ);
-	val &= mask;
-	for_each_set_bit(pos, &val, total) {
-		struct dw_edma_chan *chan = &dw->chan[pos + off];
-
-		dw_edma_abort_interrupt(chan);
-	}
-
-	return IRQ_HANDLED;
-}
-
 static inline irqreturn_t dw_edma_interrupt_write(int irq, void *data)
 {
-	return dw_edma_interrupt(irq, data, true);
+	struct dw_edma_irq *dw_irq = data;
+
+	return dw_edma_core_handle_int(dw_irq, EDMA_DIR_WRITE,
+				       dw_edma_done_interrupt,
+				       dw_edma_abort_interrupt);
 }
 
 static inline irqreturn_t dw_edma_interrupt_read(int irq, void *data)
 {
-	return dw_edma_interrupt(irq, data, false);
+	struct dw_edma_irq *dw_irq = data;
+
+	return dw_edma_core_handle_int(dw_irq, EDMA_DIR_READ,
+				       dw_edma_done_interrupt,
+				       dw_edma_abort_interrupt);
 }
 
 static irqreturn_t dw_edma_interrupt_common(int irq, void *data)
 {
-	dw_edma_interrupt(irq, data, true);
-	dw_edma_interrupt(irq, data, false);
+	irqreturn_t ret = IRQ_NONE;
 
-	return IRQ_HANDLED;
+	ret |= dw_edma_interrupt_write(irq, data);
+	ret |= dw_edma_interrupt_read(irq, data);
+
+	return ret;
 }
 
 static int dw_edma_alloc_chan_resources(struct dma_chan *dchan)
@@ -811,7 +778,7 @@ static int dw_edma_channel_setup(struct dw_edma *dw, u32 wr_alloc, u32 rd_alloc)
 
 		vchan_init(&chan->vc, dma);
 
-		dw_edma_v0_core_device_config(chan);
+		dw_edma_core_ch_config(chan);
 	}
 
 	/* Set DMA channel capabilities */
@@ -956,14 +923,19 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 
 	dw->chip = chip;
 
+	if (dw->chip->mf == EDMA_MF_HDMA_NATIVE)
+		dw_hdma_v0_core_register(dw);
+	else
+		dw_edma_v0_core_register(dw);
+
 	raw_spin_lock_init(&dw->lock);
 
 	dw->wr_ch_cnt = min_t(u16, chip->ll_wr_cnt,
-			      dw_edma_v0_core_ch_count(dw, EDMA_DIR_WRITE));
+			      dw_edma_core_ch_count(dw, EDMA_DIR_WRITE));
 	dw->wr_ch_cnt = min_t(u16, dw->wr_ch_cnt, EDMA_MAX_WR_CH);
 
 	dw->rd_ch_cnt = min_t(u16, chip->ll_rd_cnt,
-			      dw_edma_v0_core_ch_count(dw, EDMA_DIR_READ));
+			      dw_edma_core_ch_count(dw, EDMA_DIR_READ));
 	dw->rd_ch_cnt = min_t(u16, dw->rd_ch_cnt, EDMA_MAX_RD_CH);
 
 	if (!dw->wr_ch_cnt && !dw->rd_ch_cnt)
@@ -982,7 +954,7 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 		 dev_name(chip->dev));
 
 	/* Disable eDMA, only to establish the ideal initial conditions */
-	dw_edma_v0_core_off(dw);
+	dw_edma_core_off(dw);
 
 	/* Request IRQs */
 	err = dw_edma_irq_request(dw, &wr_alloc, &rd_alloc);
@@ -995,7 +967,7 @@ int dw_edma_probe(struct dw_edma_chip *chip)
 		goto err_irq_free;
 
 	/* Turn debugfs on */
-	dw_edma_v0_core_debugfs_on(dw);
+	dw_edma_core_debugfs_on(dw);
 
 	chip->dw = dw;
 
@@ -1021,7 +993,7 @@ int dw_edma_remove(struct dw_edma_chip *chip)
 		return -ENODEV;
 
 	/* Disable eDMA */
-	dw_edma_v0_core_off(dw);
+	dw_edma_core_off(dw);
 
 	/* Free irqs */
 	for (i = (dw->nr_irqs - 1); i >= 0; i--)
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
index 0ab2b6dba880..71894b9e0b15 100644
--- a/drivers/dma/dw-edma/dw-edma-core.h
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -111,6 +111,21 @@ struct dw_edma {
 	raw_spinlock_t			lock;		/* Only for legacy */
 
 	struct dw_edma_chip             *chip;
+
+	const struct dw_edma_core_ops	*core;
+};
+
+typedef void (*dw_edma_handler_t)(struct dw_edma_chan *);
+
+struct dw_edma_core_ops {
+	void (*off)(struct dw_edma *dw);
+	u16 (*ch_count)(struct dw_edma *dw, enum dw_edma_dir dir);
+	enum dma_status (*ch_status)(struct dw_edma_chan *chan);
+	irqreturn_t (*handle_int)(struct dw_edma_irq *dw_irq, enum dw_edma_dir dir,
+				  dw_edma_handler_t done, dw_edma_handler_t abort);
+	void (*start)(struct dw_edma_chunk *chunk, bool first);
+	void (*ch_config)(struct dw_edma_chan *chan);
+	void (*debugfs_on)(struct dw_edma *dw);
 };
 
 struct dw_edma_sg {
@@ -148,4 +163,47 @@ struct dw_edma_chan *dchan2dw_edma_chan(struct dma_chan *dchan)
 	return vc2dw_edma_chan(to_virt_chan(dchan));
 }
 
+static inline
+void dw_edma_core_off(struct dw_edma *dw)
+{
+	dw->core->off(dw);
+}
+
+static inline
+u16 dw_edma_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
+{
+	return dw->core->ch_count(dw, dir);
+}
+
+static inline
+enum dma_status dw_edma_core_ch_status(struct dw_edma_chan *chan)
+{
+	return chan->dw->core->ch_status(chan);
+}
+
+static inline irqreturn_t
+dw_edma_core_handle_int(struct dw_edma_irq *dw_irq, enum dw_edma_dir dir,
+			dw_edma_handler_t done, dw_edma_handler_t abort)
+{
+	return dw_irq->dw->core->handle_int(dw_irq, dir, done, abort);
+}
+
+static inline
+void dw_edma_core_start(struct dw_edma *dw, struct dw_edma_chunk *chunk, bool first)
+{
+	dw->core->start(chunk, first);
+}
+
+static inline
+void dw_edma_core_ch_config(struct dw_edma_chan *chan)
+{
+	chan->dw->core->ch_config(chan);
+}
+
+static inline
+void dw_edma_core_debugfs_on(struct dw_edma *dw)
+{
+	dw->core->debugfs_on(dw);
+}
+
 #endif /* _DW_EDMA_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index 2b40f2b44f5e..1c6043751dc9 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -109,7 +109,7 @@ static u64 dw_edma_pcie_address(struct device *dev, phys_addr_t cpu_addr)
 	return region.start;
 }
 
-static const struct dw_edma_core_ops dw_edma_pcie_core_ops = {
+static const struct dw_edma_plat_ops dw_edma_pcie_plat_ops = {
 	.irq_vector = dw_edma_pcie_irq_vector,
 	.pci_address = dw_edma_pcie_address,
 };
@@ -225,7 +225,7 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 
 	chip->mf = vsec_data.mf;
 	chip->nr_irqs = nr_irqs;
-	chip->ops = &dw_edma_pcie_core_ops;
+	chip->ops = &dw_edma_pcie_plat_ops;
 
 	chip->ll_wr_cnt = vsec_data.wr_ch_cnt;
 	chip->ll_rd_cnt = vsec_data.rd_ch_cnt;
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index 32f834a3848a..b38786f0ad79 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/bitfield.h>
-
+#include <linux/irqreturn.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "dw-edma-core.h"
@@ -160,7 +160,7 @@ static inline u32 readl_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 	readl_ch(dw, dir, ch, &(__dw_ch_regs(dw, dir, ch)->name))
 
 /* eDMA management callbacks */
-void dw_edma_v0_core_off(struct dw_edma *dw)
+static void dw_edma_v0_core_off(struct dw_edma *dw)
 {
 	SET_BOTH_32(dw, int_mask,
 		    EDMA_V0_DONE_INT_MASK | EDMA_V0_ABORT_INT_MASK);
@@ -169,7 +169,7 @@ void dw_edma_v0_core_off(struct dw_edma *dw)
 	SET_BOTH_32(dw, engine_en, 0);
 }
 
-u16 dw_edma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
+static u16 dw_edma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
 {
 	u32 num_ch;
 
@@ -186,7 +186,7 @@ u16 dw_edma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
 	return (u16)num_ch;
 }
 
-enum dma_status dw_edma_v0_core_ch_status(struct dw_edma_chan *chan)
+static enum dma_status dw_edma_v0_core_ch_status(struct dw_edma_chan *chan)
 {
 	struct dw_edma *dw = chan->dw;
 	u32 tmp;
@@ -202,7 +202,7 @@ enum dma_status dw_edma_v0_core_ch_status(struct dw_edma_chan *chan)
 		return DMA_ERROR;
 }
 
-void dw_edma_v0_core_clear_done_int(struct dw_edma_chan *chan)
+static void dw_edma_v0_core_clear_done_int(struct dw_edma_chan *chan)
 {
 	struct dw_edma *dw = chan->dw;
 
@@ -210,7 +210,7 @@ void dw_edma_v0_core_clear_done_int(struct dw_edma_chan *chan)
 		  FIELD_PREP(EDMA_V0_DONE_INT_MASK, BIT(chan->id)));
 }
 
-void dw_edma_v0_core_clear_abort_int(struct dw_edma_chan *chan)
+static void dw_edma_v0_core_clear_abort_int(struct dw_edma_chan *chan)
 {
 	struct dw_edma *dw = chan->dw;
 
@@ -218,18 +218,64 @@ void dw_edma_v0_core_clear_abort_int(struct dw_edma_chan *chan)
 		  FIELD_PREP(EDMA_V0_ABORT_INT_MASK, BIT(chan->id)));
 }
 
-u32 dw_edma_v0_core_status_done_int(struct dw_edma *dw, enum dw_edma_dir dir)
+static u32 dw_edma_v0_core_status_done_int(struct dw_edma *dw, enum dw_edma_dir dir)
 {
 	return FIELD_GET(EDMA_V0_DONE_INT_MASK,
 			 GET_RW_32(dw, dir, int_status));
 }
 
-u32 dw_edma_v0_core_status_abort_int(struct dw_edma *dw, enum dw_edma_dir dir)
+static u32 dw_edma_v0_core_status_abort_int(struct dw_edma *dw, enum dw_edma_dir dir)
 {
 	return FIELD_GET(EDMA_V0_ABORT_INT_MASK,
 			 GET_RW_32(dw, dir, int_status));
 }
 
+static irqreturn_t
+dw_edma_v0_core_handle_int(struct dw_edma_irq *dw_irq, enum dw_edma_dir dir,
+			   dw_edma_handler_t done, dw_edma_handler_t abort)
+{
+	struct dw_edma *dw = dw_irq->dw;
+	unsigned long total, pos, val;
+	irqreturn_t ret = IRQ_NONE;
+	struct dw_edma_chan *chan;
+	unsigned long off;
+	u32 mask;
+
+	if (dir == EDMA_DIR_WRITE) {
+		total = dw->wr_ch_cnt;
+		off = 0;
+		mask = dw_irq->wr_mask;
+	} else {
+		total = dw->rd_ch_cnt;
+		off = dw->wr_ch_cnt;
+		mask = dw_irq->rd_mask;
+	}
+
+	val = dw_edma_v0_core_status_done_int(dw, dir);
+	val &= mask;
+	for_each_set_bit(pos, &val, total) {
+		chan = &dw->chan[pos + off];
+
+		dw_edma_v0_core_clear_done_int(chan);
+		done(chan);
+
+		ret = IRQ_HANDLED;
+	}
+
+	val = dw_edma_v0_core_status_abort_int(dw, dir);
+	val &= mask;
+	for_each_set_bit(pos, &val, total) {
+		chan = &dw->chan[pos + off];
+
+		dw_edma_v0_core_clear_abort_int(chan);
+		abort(chan);
+
+		ret = IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
 static void dw_edma_v0_write_ll_data(struct dw_edma_chunk *chunk, int i,
 				     u32 control, u32 size, u64 sar, u64 dar)
 {
@@ -300,7 +346,7 @@ static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 	dw_edma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
 }
 
-void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
+static void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
 	struct dw_edma *dw = chan->dw;
@@ -371,7 +417,7 @@ void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 		  FIELD_PREP(EDMA_V0_DOORBELL_CH_MASK, chan->id));
 }
 
-int dw_edma_v0_core_device_config(struct dw_edma_chan *chan)
+static void dw_edma_v0_core_ch_config(struct dw_edma_chan *chan)
 {
 	struct dw_edma *dw = chan->dw;
 	u32 tmp = 0;
@@ -438,12 +484,25 @@ int dw_edma_v0_core_device_config(struct dw_edma_chan *chan)
 		SET_RW_32(dw, chan->dir, ch67_imwr_data, tmp);
 		break;
 	}
-
-	return 0;
 }
 
 /* eDMA debugfs callbacks */
-void dw_edma_v0_core_debugfs_on(struct dw_edma *dw)
+static void dw_edma_v0_core_debugfs_on(struct dw_edma *dw)
 {
 	dw_edma_v0_debugfs_on(dw);
 }
+
+static const struct dw_edma_core_ops dw_edma_v0_core = {
+	.off = dw_edma_v0_core_off,
+	.ch_count = dw_edma_v0_core_ch_count,
+	.ch_status = dw_edma_v0_core_ch_status,
+	.handle_int = dw_edma_v0_core_handle_int,
+	.start = dw_edma_v0_core_start,
+	.ch_config = dw_edma_v0_core_ch_config,
+	.debugfs_on = dw_edma_v0_core_debugfs_on,
+};
+
+void dw_edma_v0_core_register(struct dw_edma *dw)
+{
+	dw->core = &dw_edma_v0_core;
+}
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.h b/drivers/dma/dw-edma/dw-edma-v0-core.h
index ab96a1f48080..04a882222f99 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.h
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.h
@@ -11,17 +11,7 @@
 
 #include <linux/dma/edma.h>
 
-/* eDMA management callbacks */
-void dw_edma_v0_core_off(struct dw_edma *chan);
-u16 dw_edma_v0_core_ch_count(struct dw_edma *chan, enum dw_edma_dir dir);
-enum dma_status dw_edma_v0_core_ch_status(struct dw_edma_chan *chan);
-void dw_edma_v0_core_clear_done_int(struct dw_edma_chan *chan);
-void dw_edma_v0_core_clear_abort_int(struct dw_edma_chan *chan);
-u32 dw_edma_v0_core_status_done_int(struct dw_edma *chan, enum dw_edma_dir dir);
-u32 dw_edma_v0_core_status_abort_int(struct dw_edma *chan, enum dw_edma_dir dir);
-void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first);
-int dw_edma_v0_core_device_config(struct dw_edma_chan *chan);
-/* eDMA debug fs callbacks */
-void dw_edma_v0_core_debugfs_on(struct dw_edma *dw);
+/* eDMA core register */
+void dw_edma_v0_core_register(struct dw_edma *dw);
 
 #endif /* _DW_EDMA_V0_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
new file mode 100644
index 000000000000..00b735a0202a
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 core
+ */
+
+#include <linux/bitfield.h>
+#include <linux/irqreturn.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
+
+#include "dw-edma-core.h"
+#include "dw-hdma-v0-core.h"
+#include "dw-hdma-v0-regs.h"
+#include "dw-hdma-v0-debugfs.h"
+
+enum dw_hdma_control {
+	DW_HDMA_V0_CB					= BIT(0),
+	DW_HDMA_V0_TCB					= BIT(1),
+	DW_HDMA_V0_LLP					= BIT(2),
+	DW_HDMA_V0_LIE					= BIT(3),
+	DW_HDMA_V0_RIE					= BIT(4),
+	DW_HDMA_V0_CCS					= BIT(8),
+	DW_HDMA_V0_LLE					= BIT(9),
+};
+
+static inline struct dw_hdma_v0_regs __iomem *__dw_regs(struct dw_edma *dw)
+{
+	return dw->chip->reg_base;
+}
+
+static inline struct dw_hdma_v0_ch_regs __iomem *
+__dw_ch_regs(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch)
+{
+	if (dir == EDMA_DIR_WRITE)
+		return &(__dw_regs(dw)->ch[ch].wr);
+	else
+		return &(__dw_regs(dw)->ch[ch].rd);
+}
+
+#define SET_CH_32(dw, dir, ch, name, value) \
+	writel(value, &(__dw_ch_regs(dw, dir, ch)->name))
+
+#define GET_CH_32(dw, dir, ch, name) \
+	readl(&(__dw_ch_regs(dw, dir, ch)->name))
+
+#define SET_BOTH_CH_32(dw, ch, name, value) \
+	do {					\
+		writel(value, &(__dw_ch_regs(dw, EDMA_DIR_WRITE, ch)->name));	\
+		writel(value, &(__dw_ch_regs(dw, EDMA_DIR_READ, ch)->name));	\
+	} while (0)
+
+/* HDMA management callbacks */
+static void dw_hdma_v0_core_off(struct dw_edma *dw)
+{
+	int id;
+
+	for (id = 0; id < HDMA_V0_MAX_NR_CH; id++) {
+		SET_BOTH_CH_32(dw, id, int_setup,
+			       HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+		SET_BOTH_CH_32(dw, id, int_clear,
+			       HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
+		SET_BOTH_CH_32(dw, id, ch_en, 0);
+	}
+}
+
+static u16 dw_hdma_v0_core_ch_count(struct dw_edma *dw, enum dw_edma_dir dir)
+{
+	u32 num_ch = 0;
+	int id;
+
+	for (id = 0; id < HDMA_V0_MAX_NR_CH; id++) {
+		if (GET_CH_32(dw, id, dir, ch_en) & BIT(0))
+			num_ch++;
+	}
+
+	if (num_ch > HDMA_V0_MAX_NR_CH)
+		num_ch = HDMA_V0_MAX_NR_CH;
+
+	return (u16)num_ch;
+}
+
+static enum dma_status dw_hdma_v0_core_ch_status(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+	u32 tmp;
+
+	tmp = FIELD_GET(HDMA_V0_CH_STATUS_MASK,
+			GET_CH_32(dw, chan->id, chan->dir, ch_stat));
+
+	if (tmp == 1)
+		return DMA_IN_PROGRESS;
+	else if (tmp == 3)
+		return DMA_COMPLETE;
+	else
+		return DMA_ERROR;
+}
+
+static void dw_hdma_v0_core_clear_done_int(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	SET_CH_32(dw, chan->dir, chan->id, int_clear, HDMA_V0_STOP_INT_MASK);
+}
+
+static void dw_hdma_v0_core_clear_abort_int(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	SET_CH_32(dw, chan->dir, chan->id, int_clear, HDMA_V0_ABORT_INT_MASK);
+}
+
+static u32 dw_hdma_v0_core_status_int(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	return GET_CH_32(dw, chan->dir, chan->id, int_stat);
+}
+
+static irqreturn_t
+dw_hdma_v0_core_handle_int(struct dw_edma_irq *dw_irq, enum dw_edma_dir dir,
+			   dw_edma_handler_t done, dw_edma_handler_t abort)
+{
+	struct dw_edma *dw = dw_irq->dw;
+	unsigned long total, pos, val;
+	irqreturn_t ret = IRQ_NONE;
+	struct dw_edma_chan *chan;
+	unsigned long off, mask;
+
+	if (dir == EDMA_DIR_WRITE) {
+		total = dw->wr_ch_cnt;
+		off = 0;
+		mask = dw_irq->wr_mask;
+	} else {
+		total = dw->rd_ch_cnt;
+		off = dw->wr_ch_cnt;
+		mask = dw_irq->rd_mask;
+	}
+
+	for_each_set_bit(pos, &mask, total) {
+		chan = &dw->chan[pos + off];
+
+		val = dw_hdma_v0_core_status_int(chan);
+		if (FIELD_GET(HDMA_V0_STOP_INT_MASK, val)) {
+			dw_hdma_v0_core_clear_done_int(chan);
+			done(chan);
+
+			ret = IRQ_HANDLED;
+		}
+
+		if (FIELD_GET(HDMA_V0_ABORT_INT_MASK, val)) {
+			dw_hdma_v0_core_clear_abort_int(chan);
+			abort(chan);
+
+			ret = IRQ_HANDLED;
+		}
+	}
+
+	return ret;
+}
+
+static void dw_hdma_v0_write_ll_data(struct dw_edma_chunk *chunk, int i,
+				     u32 control, u32 size, u64 sar, u64 dar)
+{
+	ptrdiff_t ofs = i * sizeof(struct dw_hdma_v0_lli);
+
+	if (chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		struct dw_hdma_v0_lli *lli = chunk->ll_region.vaddr.mem + ofs;
+
+		lli->control = control;
+		lli->transfer_size = size;
+		lli->sar.reg = sar;
+		lli->dar.reg = dar;
+	} else {
+		struct dw_hdma_v0_lli __iomem *lli = chunk->ll_region.vaddr.io + ofs;
+
+		writel(control, &lli->control);
+		writel(size, &lli->transfer_size);
+		writeq(sar, &lli->sar.reg);
+		writeq(dar, &lli->dar.reg);
+	}
+}
+
+static void dw_hdma_v0_write_ll_link(struct dw_edma_chunk *chunk,
+				     int i, u32 control, u64 pointer)
+{
+	ptrdiff_t ofs = i * sizeof(struct dw_hdma_v0_lli);
+
+	if (chunk->chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		struct dw_hdma_v0_llp *llp = chunk->ll_region.vaddr.mem + ofs;
+
+		llp->control = control;
+		llp->llp.reg = pointer;
+	} else {
+		struct dw_hdma_v0_llp __iomem *llp = chunk->ll_region.vaddr.io + ofs;
+
+		writel(control, &llp->control);
+		writeq(pointer, &llp->llp.reg);
+	}
+}
+
+static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
+{
+	struct dw_edma_burst *child;
+	struct dw_edma_chan *chan = chunk->chan;
+	u32 control = 0, i = 0;
+	int j;
+
+	if (chunk->cb)
+		control = DW_HDMA_V0_CB;
+
+	j = chunk->bursts_alloc;
+	list_for_each_entry(child, &chunk->burst->list, list) {
+		j--;
+		if (!j) {
+			control |= DW_HDMA_V0_LIE;
+			if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+				control |= DW_HDMA_V0_RIE;
+		}
+
+		dw_hdma_v0_write_ll_data(chunk, i++, control, child->sz,
+					 child->sar, child->dar);
+	}
+
+	control = DW_HDMA_V0_LLP | DW_HDMA_V0_TCB;
+	if (!chunk->cb)
+		control |= DW_HDMA_V0_CB;
+
+	dw_hdma_v0_write_ll_link(chunk, i, control, chunk->ll_region.paddr);
+}
+
+static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
+{
+	struct dw_edma_chan *chan = chunk->chan;
+	struct dw_edma *dw = chan->dw;
+	u32 tmp;
+
+	dw_hdma_v0_core_write_chunk(chunk);
+
+	if (first) {
+		/* Enable engine */
+		SET_CH_32(dw, chan->dir, chan->id, ch_en, BIT(0));
+		/* Interrupt enable&unmask - done, abort */
+		tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) |
+		      HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK |
+		      HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_STOP_INT_EN;
+		SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp);
+		/* Channel control */
+		SET_CH_32(dw, chan->dir, chan->id, control1, HDMA_V0_LINKLIST_EN);
+		/* Linked list */
+		/* llp is not aligned on 64bit -> keep 32bit accesses */
+		SET_CH_32(dw, chan->dir, chan->id, llp.lsb,
+			  lower_32_bits(chunk->ll_region.paddr));
+		SET_CH_32(dw, chan->dir, chan->id, llp.msb,
+			  upper_32_bits(chunk->ll_region.paddr));
+	}
+	/* Set consumer cycle */
+	SET_CH_32(dw, chan->dir, chan->id, cycle_sync,
+		  HDMA_V0_CONSUMER_CYCLE_STAT | HDMA_V0_CONSUMER_CYCLE_BIT);
+	/* Doorbell */
+	SET_CH_32(dw, chan->dir, chan->id, doorbell, HDMA_V0_DOORBELL_START);
+}
+
+static void dw_hdma_v0_core_ch_config(struct dw_edma_chan *chan)
+{
+	struct dw_edma *dw = chan->dw;
+
+	/* MSI done addr - low, high */
+	SET_CH_32(dw, chan->dir, chan->id, msi_stop.lsb, chan->msi.address_lo);
+	SET_CH_32(dw, chan->dir, chan->id, msi_stop.msb, chan->msi.address_hi);
+	/* MSI abort addr - low, high */
+	SET_CH_32(dw, chan->dir, chan->id, msi_abort.lsb, chan->msi.address_lo);
+	SET_CH_32(dw, chan->dir, chan->id, msi_abort.msb, chan->msi.address_hi);
+	/* config MSI data */
+	SET_CH_32(dw, chan->dir, chan->id, msi_msgdata, chan->msi.data);
+}
+
+/* HDMA debugfs callbacks */
+static void dw_hdma_v0_core_debugfs_on(struct dw_edma *dw)
+{
+	dw_hdma_v0_debugfs_on(dw);
+}
+
+static const struct dw_edma_core_ops dw_hdma_v0_core = {
+	.off = dw_hdma_v0_core_off,
+	.ch_count = dw_hdma_v0_core_ch_count,
+	.ch_status = dw_hdma_v0_core_ch_status,
+	.handle_int = dw_hdma_v0_core_handle_int,
+	.start = dw_hdma_v0_core_start,
+	.ch_config = dw_hdma_v0_core_ch_config,
+	.debugfs_on = dw_hdma_v0_core_debugfs_on,
+};
+
+void dw_hdma_v0_core_register(struct dw_edma *dw)
+{
+	dw->core = &dw_hdma_v0_core;
+}
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.h b/drivers/dma/dw-edma/dw-hdma-v0-core.h
new file mode 100644
index 000000000000..c373b4f0bd8a
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-core.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 core
+ *
+ * Author: Cai Huoqing <cai.huoqing@linux.dev>
+ */
+
+#ifndef _DW_HDMA_V0_CORE_H
+#define _DW_HDMA_V0_CORE_H
+
+#include <linux/dma/edma.h>
+
+/* HDMA core register */
+void dw_hdma_v0_core_register(struct dw_edma *dw);
+
+#endif /* _DW_HDMA_V0_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
new file mode 100644
index 000000000000..520c81978b08
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 debugfs
+ *
+ * Author: Cai Huoqing <cai.huoqing@linux.dev>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/bitfield.h>
+
+#include "dw-hdma-v0-debugfs.h"
+#include "dw-hdma-v0-regs.h"
+#include "dw-edma-core.h"
+
+#define REGS_ADDR(dw, name)						       \
+	({								       \
+		struct dw_hdma_v0_regs __iomem *__regs = (dw)->chip->reg_base; \
+									       \
+		(void __iomem *)&__regs->name;				       \
+	})
+
+#define REGS_CH_ADDR(dw, name, _dir, _ch)				       \
+	({								       \
+		struct dw_hdma_v0_ch_regs __iomem *__ch_regs;		       \
+									       \
+		if (_dir == EDMA_DIR_READ)				       \
+			__ch_regs = REGS_ADDR(dw, ch[_ch].rd);		       \
+		else							       \
+			__ch_regs = REGS_ADDR(dw, ch[_ch].wr);		       \
+									       \
+		(void __iomem *)&__ch_regs->name;			       \
+	})
+
+#define CTX_REGISTER(dw, name, dir, ch) \
+	{#name, REGS_CH_ADDR(dw, name, dir, ch)}
+
+#define WRITE_STR				"write"
+#define READ_STR				"read"
+#define CHANNEL_STR				"channel"
+#define REGISTERS_STR				"registers"
+
+struct dw_hdma_debugfs_entry {
+	const char				*name;
+	void __iomem				*reg;
+};
+
+static int dw_hdma_debugfs_u32_get(void *data, u64 *val)
+{
+	struct dw_hdma_debugfs_entry *entry = data;
+	void __iomem *reg = entry->reg;
+
+	*val = readl(reg);
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_x32, dw_hdma_debugfs_u32_get, NULL, "0x%08llx\n");
+
+static void dw_hdma_debugfs_create_x32(struct dw_edma *dw,
+				       const struct dw_hdma_debugfs_entry ini[],
+				       int nr_entries, struct dentry *dent)
+{
+	struct dw_hdma_debugfs_entry *entries;
+	int i;
+
+	entries = devm_kcalloc(dw->chip->dev, nr_entries, sizeof(*entries),
+			       GFP_KERNEL);
+	if (!entries)
+		return;
+
+	for (i = 0; i < nr_entries; i++) {
+		entries[i] = ini[i];
+
+		debugfs_create_file_unsafe(entries[i].name, 0444, dent,
+					   &entries[i], &fops_x32);
+	}
+}
+
+static void dw_hdma_debugfs_regs_ch(struct dw_edma *dw, enum dw_edma_dir dir,
+				    u16 ch, struct dentry *dent)
+{
+	const struct dw_hdma_debugfs_entry debugfs_regs[] = {
+		CTX_REGISTER(dw, ch_en, dir, ch),
+		CTX_REGISTER(dw, doorbell, dir, ch),
+		CTX_REGISTER(dw, prefetch, dir, ch),
+		CTX_REGISTER(dw, handshake, dir, ch),
+		CTX_REGISTER(dw, llp.lsb, dir, ch),
+		CTX_REGISTER(dw, llp.msb, dir, ch),
+		CTX_REGISTER(dw, cycle_sync, dir, ch),
+		CTX_REGISTER(dw, transfer_size, dir, ch),
+		CTX_REGISTER(dw, sar.lsb, dir, ch),
+		CTX_REGISTER(dw, sar.msb, dir, ch),
+		CTX_REGISTER(dw, dar.lsb, dir, ch),
+		CTX_REGISTER(dw, dar.msb, dir, ch),
+		CTX_REGISTER(dw, watermark_en, dir, ch),
+		CTX_REGISTER(dw, control1, dir, ch),
+		CTX_REGISTER(dw, func_num, dir, ch),
+		CTX_REGISTER(dw, qos, dir, ch),
+		CTX_REGISTER(dw, ch_stat, dir, ch),
+		CTX_REGISTER(dw, int_stat, dir, ch),
+		CTX_REGISTER(dw, int_setup, dir, ch),
+		CTX_REGISTER(dw, int_clear, dir, ch),
+		CTX_REGISTER(dw, msi_stop.lsb, dir, ch),
+		CTX_REGISTER(dw, msi_stop.msb, dir, ch),
+		CTX_REGISTER(dw, msi_watermark.lsb, dir, ch),
+		CTX_REGISTER(dw, msi_watermark.msb, dir, ch),
+		CTX_REGISTER(dw, msi_abort.lsb, dir, ch),
+		CTX_REGISTER(dw, msi_abort.msb, dir, ch),
+		CTX_REGISTER(dw, msi_msgdata, dir, ch),
+	};
+	int nr_entries = ARRAY_SIZE(debugfs_regs);
+
+	dw_hdma_debugfs_create_x32(dw, debugfs_regs, nr_entries, dent);
+}
+
+static void dw_hdma_debugfs_regs_wr(struct dw_edma *dw, struct dentry *dent)
+{
+	struct dentry *regs_dent, *ch_dent;
+	char name[16];
+	int i;
+
+	regs_dent = debugfs_create_dir(WRITE_STR, dent);
+
+	for (i = 0; i < dw->wr_ch_cnt; i++) {
+		snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
+
+		ch_dent = debugfs_create_dir(name, regs_dent);
+
+		dw_hdma_debugfs_regs_ch(dw, EDMA_DIR_WRITE, i, ch_dent);
+	}
+}
+
+static void dw_hdma_debugfs_regs_rd(struct dw_edma *dw, struct dentry *dent)
+{
+	struct dentry *regs_dent, *ch_dent;
+	char name[16];
+	int i;
+
+	regs_dent = debugfs_create_dir(READ_STR, dent);
+
+	for (i = 0; i < dw->rd_ch_cnt; i++) {
+		snprintf(name, sizeof(name), "%s:%d", CHANNEL_STR, i);
+
+		ch_dent = debugfs_create_dir(name, regs_dent);
+
+		dw_hdma_debugfs_regs_ch(dw, EDMA_DIR_READ, i, ch_dent);
+	}
+}
+
+static void dw_hdma_debugfs_regs(struct dw_edma *dw)
+{
+	struct dentry *regs_dent;
+
+	regs_dent = debugfs_create_dir(REGISTERS_STR, dw->dma.dbg_dev_root);
+
+	dw_hdma_debugfs_regs_wr(dw, regs_dent);
+	dw_hdma_debugfs_regs_rd(dw, regs_dent);
+}
+
+void dw_hdma_v0_debugfs_on(struct dw_edma *dw)
+{
+	if (!debugfs_initialized())
+		return;
+
+	debugfs_create_u32("mf", 0444, dw->dma.dbg_dev_root, &dw->chip->mf);
+	debugfs_create_u16("wr_ch_cnt", 0444, dw->dma.dbg_dev_root, &dw->wr_ch_cnt);
+	debugfs_create_u16("rd_ch_cnt", 0444, dw->dma.dbg_dev_root, &dw->rd_ch_cnt);
+
+	dw_hdma_debugfs_regs(dw);
+}
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-debugfs.h b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.h
new file mode 100644
index 000000000000..e6842c83777d
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-debugfs.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 debugfs
+ *
+ * Author: Cai Huoqing <cai.huoqing@linux.dev>
+ */
+
+#ifndef _DW_HDMA_V0_DEBUG_FS_H
+#define _DW_HDMA_V0_DEBUG_FS_H
+
+#include <linux/dma/edma.h>
+
+#ifdef CONFIG_DEBUG_FS
+void dw_hdma_v0_debugfs_on(struct dw_edma *dw);
+#else
+static inline void dw_hdma_v0_debugfs_on(struct dw_edma *dw)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* _DW_HDMA_V0_DEBUG_FS_H */
diff --git a/drivers/dma/dw-edma/dw-hdma-v0-regs.h b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
new file mode 100644
index 000000000000..a974abdf8aaf
--- /dev/null
+++ b/drivers/dma/dw-edma/dw-hdma-v0-regs.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Cai Huoqing
+ * Synopsys DesignWare HDMA v0 reg
+ *
+ * Author: Cai Huoqing <cai.huoqing@linux.dev>
+ */
+
+#ifndef _DW_HDMA_V0_REGS_H
+#define _DW_HDMA_V0_REGS_H
+
+#include <linux/dmaengine.h>
+
+#define HDMA_V0_MAX_NR_CH			8
+#define HDMA_V0_LOCAL_ABORT_INT_EN		BIT(6)
+#define HDMA_V0_REMOTE_ABORT_INT_EN		BIT(5)
+#define HDMA_V0_LOCAL_STOP_INT_EN		BIT(4)
+#define HDMA_V0_REMOTEL_STOP_INT_EN		BIT(3)
+#define HDMA_V0_ABORT_INT_MASK			BIT(2)
+#define HDMA_V0_STOP_INT_MASK			BIT(0)
+#define HDMA_V0_LINKLIST_EN			BIT(0)
+#define HDMA_V0_CONSUMER_CYCLE_STAT		BIT(1)
+#define HDMA_V0_CONSUMER_CYCLE_BIT		BIT(0)
+#define HDMA_V0_DOORBELL_START			BIT(0)
+#define HDMA_V0_CH_STATUS_MASK			GENMASK(1, 0)
+
+struct dw_hdma_v0_ch_regs {
+	u32 ch_en;				/* 0x0000 */
+	u32 doorbell;				/* 0x0004 */
+	u32 prefetch;				/* 0x0008 */
+	u32 handshake;				/* 0x000c */
+	union {
+		u64 reg;			/* 0x0010..0x0014 */
+		struct {
+			u32 lsb;		/* 0x0010 */
+			u32 msb;		/* 0x0014 */
+		};
+	} llp;
+	u32 cycle_sync;				/* 0x0018 */
+	u32 transfer_size;			/* 0x001c */
+	union {
+		u64 reg;			/* 0x0020..0x0024 */
+		struct {
+			u32 lsb;		/* 0x0020 */
+			u32 msb;		/* 0x0024 */
+		};
+	} sar;
+	union {
+		u64 reg;			/* 0x0028..0x002c */
+		struct {
+			u32 lsb;		/* 0x0028 */
+			u32 msb;		/* 0x002c */
+		};
+	} dar;
+	u32 watermark_en;			/* 0x0030 */
+	u32 control1;				/* 0x0034 */
+	u32 func_num;				/* 0x0038 */
+	u32 qos;				/* 0x003c */
+	u32 padding_1[16];			/* 0x0040..0x007c */
+	u32 ch_stat;				/* 0x0080 */
+	u32 int_stat;				/* 0x0084 */
+	u32 int_setup;				/* 0x0088 */
+	u32 int_clear;				/* 0x008c */
+	union {
+		u64 reg;			/* 0x0090..0x0094 */
+		struct {
+			u32 lsb;		/* 0x0090 */
+			u32 msb;		/* 0x0094 */
+		};
+	} msi_stop;
+	union {
+		u64 reg;			/* 0x0098..0x009c */
+		struct {
+			u32 lsb;		/* 0x0098 */
+			u32 msb;		/* 0x009c */
+		};
+	} msi_watermark;
+	union {
+		u64 reg;			/* 0x00a0..0x00a4 */
+		struct {
+			u32 lsb;		/* 0x00a0 */
+			u32 msb;		/* 0x00a4 */
+		};
+	} msi_abort;
+	u32 msi_msgdata;			/* 0x00a8 */
+	u32 padding_2[21];			/* 0x00ac..0x00fc */
+} __packed;
+
+struct dw_hdma_v0_ch {
+	struct dw_hdma_v0_ch_regs wr;		/* 0x0000 */
+	struct dw_hdma_v0_ch_regs rd;		/* 0x0100 */
+} __packed;
+
+struct dw_hdma_v0_regs {
+	struct dw_hdma_v0_ch ch[HDMA_V0_MAX_NR_CH];	/* 0x0000..0x0fa8 */
+} __packed;
+
+struct dw_hdma_v0_lli {
+	u32 control;
+	u32 transfer_size;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} sar;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} dar;
+} __packed;
+
+struct dw_hdma_v0_llp {
+	u32 control;
+	u32 reserved;
+	union {
+		u64 reg;
+		struct {
+			u32 lsb;
+			u32 msb;
+		};
+	} llp;
+} __packed;
+
+#endif /* _DW_HDMA_V0_REGS_H */
diff --git a/drivers/dma/plx_dma.c b/drivers/dma/plx_dma.c
index 12725fa1655f..34b6416c3287 100644
--- a/drivers/dma/plx_dma.c
+++ b/drivers/dma/plx_dma.c
@@ -517,7 +517,6 @@ static int plx_dma_create(struct pci_dev *pdev)
 	plxdev->bar = pcim_iomap_table(pdev)[0];
 
 	dma = &plxdev->dma_dev;
-	dma->chancnt = 1;
 	INIT_LIST_HEAD(&dma->channels);
 	dma_cap_set(DMA_MEMCPY, dma->cap_mask);
 	dma->copy_align = DMAENGINE_ALIGN_1_BYTE;
diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig
index 3f926a653bd8..ace75d7b835a 100644
--- a/drivers/dma/qcom/Kconfig
+++ b/drivers/dma/qcom/Kconfig
@@ -45,6 +45,7 @@ config QCOM_HIDMA_MGMT
 
 config QCOM_HIDMA
 	tristate "Qualcomm Technologies HIDMA Channel support"
+	depends on HAS_IOMEM
 	select DMA_ENGINE
 	help
 	  Enable support for the Qualcomm Technologies HIDMA controller.
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index 1e47d27e1f81..4c3eb972039d 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -1272,7 +1272,15 @@ static int bam_dma_probe(struct platform_device *pdev)
 	bdev->powered_remotely = of_property_read_bool(pdev->dev.of_node,
 						"qcom,powered-remotely");
 
-	if (bdev->controlled_remotely || bdev->powered_remotely) {
+	if (bdev->controlled_remotely || bdev->powered_remotely)
+		bdev->bamclk = devm_clk_get_optional(bdev->dev, "bam_clk");
+	else
+		bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk");
+
+	if (IS_ERR(bdev->bamclk))
+		return PTR_ERR(bdev->bamclk);
+
+	if (!bdev->bamclk) {
 		ret = of_property_read_u32(pdev->dev.of_node, "num-channels",
 					   &bdev->num_channels);
 		if (ret)
@@ -1284,14 +1292,6 @@ static int bam_dma_probe(struct platform_device *pdev)
 			dev_err(bdev->dev, "num-ees unspecified in dt\n");
 	}
 
-	if (bdev->controlled_remotely || bdev->powered_remotely)
-		bdev->bamclk = devm_clk_get_optional(bdev->dev, "bam_clk");
-	else
-		bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk");
-
-	if (IS_ERR(bdev->bamclk))
-		return PTR_ERR(bdev->bamclk);
-
 	ret = clk_prepare_enable(bdev->bamclk);
 	if (ret) {
 		dev_err(bdev->dev, "failed to prepare/enable clock\n");
diff --git a/drivers/dma/qcom/hidma.c b/drivers/dma/qcom/hidma.c
index 04d1c33afc12..344525c3a32f 100644
--- a/drivers/dma/qcom/hidma.c
+++ b/drivers/dma/qcom/hidma.c
@@ -214,7 +214,6 @@ static int hidma_chan_init(struct hidma_dev *dmadev, u32 dma_sig)
 
 	spin_lock_init(&mchan->lock);
 	list_add_tail(&mchan->chan.device_node, &ddev->channels);
-	dmadev->ddev.chancnt++;
 	return 0;
 }
 
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index 474d3ba8ec9f..2b639adb48ba 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -1169,7 +1169,6 @@ static int sprd_dma_probe(struct platform_device *pdev)
 
 	dma_cap_set(DMA_MEMCPY, sdev->dma_dev.cap_mask);
 	sdev->total_chns = chn_count;
-	sdev->dma_dev.chancnt = chn_count;
 	INIT_LIST_HEAD(&sdev->dma_dev.channels);
 	INIT_LIST_HEAD(&sdev->dma_dev.global_node);
 	sdev->dma_dev.dev = &pdev->dev;
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index f093e08c23b1..825001bde42c 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -19,14 +19,43 @@
 #include <linux/pm_runtime.h>
 #include <linux/err.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/of_dma.h>
 #include <linux/amba/bus.h>
 #include <linux/regulator/consumer.h>
-#include <linux/platform_data/dma-ste-dma40.h>
 
 #include "dmaengine.h"
+#include "ste_dma40.h"
 #include "ste_dma40_ll.h"
 
+/**
+ * struct stedma40_platform_data - Configuration struct for the dma device.
+ *
+ * @dev_tx: mapping between destination event line and io address
+ * @dev_rx: mapping between source event line and io address
+ * @disabled_channels: A vector, ending with -1, that marks physical channels
+ * that are for different reasons not available for the driver.
+ * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW
+ * which avoids HW bug that exists in some versions of the controller.
+ * SoftLLI introduces relink overhead that could impact performace for
+ * certain use cases.
+ * @num_of_soft_lli_chans: The number of channels that needs to be configured
+ * to use SoftLLI.
+ * @use_esram_lcla: flag for mapping the lcla into esram region
+ * @num_of_memcpy_chans: The number of channels reserved for memcpy.
+ * @num_of_phy_chans: The number of physical channels implemented in HW.
+ * 0 means reading the number of channels from DMA HW but this is only valid
+ * for 'multiple of 4' channels, like 8.
+ */
+struct stedma40_platform_data {
+	int				 disabled_channels[STEDMA40_MAX_PHYS];
+	int				*soft_lli_chans;
+	int				 num_of_soft_lli_chans;
+	bool				 use_esram_lcla;
+	int				 num_of_memcpy_chans;
+	int				 num_of_phy_chans;
+};
+
 #define D40_NAME "dma40"
 
 #define D40_PHY_CHAN -1
@@ -107,7 +136,7 @@ static const struct stedma40_chan_cfg dma40_memcpy_conf_log = {
 };
 
 /**
- * enum 40_command - The different commands and/or statuses.
+ * enum d40_command - The different commands and/or statuses.
  *
  * @D40_DMA_STOP: DMA channel command STOP or status STOPPED,
  * @D40_DMA_RUN: The DMA channel is RUNNING of the command RUN.
@@ -525,8 +554,6 @@ struct d40_gen_dmac {
  * @virtbase: The virtual base address of the DMA's register.
  * @rev: silicon revision detected.
  * @clk: Pointer to the DMA clock structure.
- * @phy_start: Physical memory start of the DMA registers.
- * @phy_size: Size of the DMA register map.
  * @irq: The IRQ number.
  * @num_memcpy_chans: The number of channels used for memcpy (mem-to-mem
  * transfers).
@@ -570,8 +597,6 @@ struct d40_base {
 	void __iomem			 *virtbase;
 	u8				  rev:4;
 	struct clk			 *clk;
-	phys_addr_t			  phy_start;
-	resource_size_t			  phy_size;
 	int				  irq;
 	int				  num_memcpy_chans;
 	int				  num_phy_chans;
@@ -2268,7 +2293,7 @@ d40_prep_sg(struct dma_chan *dchan, struct scatterlist *sg_src,
 	return NULL;
 }
 
-bool stedma40_filter(struct dma_chan *chan, void *data)
+static bool stedma40_filter(struct dma_chan *chan, void *data)
 {
 	struct stedma40_chan_cfg *info = data;
 	struct d40_chan *d40c =
@@ -2287,7 +2312,6 @@ bool stedma40_filter(struct dma_chan *chan, void *data)
 
 	return err == 0;
 }
-EXPORT_SYMBOL(stedma40_filter);
 
 static void __d40_set_prio_rt(struct d40_chan *d40c, int dev_type, bool src)
 {
@@ -3100,64 +3124,57 @@ static int __init d40_phy_res_init(struct d40_base *base)
 	return num_phy_chans_avail;
 }
 
-static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
+/* Called from the registered devm action */
+static void d40_drop_kmem_cache_action(void *d)
+{
+	struct kmem_cache *desc_slab = d;
+
+	kmem_cache_destroy(desc_slab);
+}
+
+static int __init d40_hw_detect_init(struct platform_device *pdev,
+				     struct d40_base **retbase)
 {
 	struct stedma40_platform_data *plat_data = dev_get_platdata(&pdev->dev);
+	struct device *dev = &pdev->dev;
 	struct clk *clk;
 	void __iomem *virtbase;
-	struct resource *res;
 	struct d40_base *base;
 	int num_log_chans;
 	int num_phy_chans;
 	int num_memcpy_chans;
-	int clk_ret = -EINVAL;
 	int i;
 	u32 pid;
 	u32 cid;
 	u8 rev;
+	int ret;
 
-	clk = clk_get(&pdev->dev, NULL);
-	if (IS_ERR(clk)) {
-		d40_err(&pdev->dev, "No matching clock found\n");
-		goto check_prepare_enabled;
-	}
-
-	clk_ret = clk_prepare_enable(clk);
-	if (clk_ret) {
-		d40_err(&pdev->dev, "Failed to prepare/enable clock\n");
-		goto disable_unprepare;
-	}
+	clk = devm_clk_get_enabled(dev, NULL);
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
 
 	/* Get IO for DMAC base address */
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "base");
-	if (!res)
-		goto disable_unprepare;
-
-	if (request_mem_region(res->start, resource_size(res),
-			       D40_NAME " I/O base") == NULL)
-		goto release_region;
-
-	virtbase = ioremap(res->start, resource_size(res));
-	if (!virtbase)
-		goto release_region;
+	virtbase = devm_platform_ioremap_resource_byname(pdev, "base");
+	if (IS_ERR(virtbase))
+		return PTR_ERR(virtbase);
 
 	/* This is just a regular AMBA PrimeCell ID actually */
 	for (pid = 0, i = 0; i < 4; i++)
-		pid |= (readl(virtbase + resource_size(res) - 0x20 + 4 * i)
+		pid |= (readl(virtbase + SZ_4K - 0x20 + 4 * i)
 			& 255) << (i * 8);
 	for (cid = 0, i = 0; i < 4; i++)
-		cid |= (readl(virtbase + resource_size(res) - 0x10 + 4 * i)
+		cid |= (readl(virtbase + SZ_4K - 0x10 + 4 * i)
 			& 255) << (i * 8);
 
 	if (cid != AMBA_CID) {
-		d40_err(&pdev->dev, "Unknown hardware! No PrimeCell ID\n");
-		goto unmap_io;
+		d40_err(dev, "Unknown hardware! No PrimeCell ID\n");
+		return -EINVAL;
 	}
 	if (AMBA_MANF_BITS(pid) != AMBA_VENDOR_ST) {
-		d40_err(&pdev->dev, "Unknown designer! Got %x wanted %x\n",
+		d40_err(dev, "Unknown designer! Got %x wanted %x\n",
 			AMBA_MANF_BITS(pid),
 			AMBA_VENDOR_ST);
-		goto unmap_io;
+		return -EINVAL;
 	}
 	/*
 	 * HW revision:
@@ -3170,8 +3187,8 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 	 */
 	rev = AMBA_REV_BITS(pid);
 	if (rev < 2) {
-		d40_err(&pdev->dev, "hardware revision: %d is not supported", rev);
-		goto unmap_io;
+		d40_err(dev, "hardware revision: %d is not supported", rev);
+		return -EINVAL;
 	}
 
 	/* The number of physical channels on this HW */
@@ -3188,27 +3205,26 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 
 	num_log_chans = num_phy_chans * D40_MAX_LOG_CHAN_PER_PHY;
 
-	dev_info(&pdev->dev,
-		 "hardware rev: %d @ %pa with %d physical and %d logical channels\n",
-		 rev, &res->start, num_phy_chans, num_log_chans);
+	dev_info(dev,
+		 "hardware rev: %d with %d physical and %d logical channels\n",
+		 rev, num_phy_chans, num_log_chans);
 
-	base = kzalloc(ALIGN(sizeof(struct d40_base), 4) +
-		       (num_phy_chans + num_log_chans + num_memcpy_chans) *
-		       sizeof(struct d40_chan), GFP_KERNEL);
+	base = devm_kzalloc(dev,
+		ALIGN(sizeof(struct d40_base), 4) +
+		(num_phy_chans + num_log_chans + num_memcpy_chans) *
+		sizeof(struct d40_chan), GFP_KERNEL);
 
-	if (base == NULL)
-		goto unmap_io;
+	if (!base)
+		return -ENOMEM;
 
 	base->rev = rev;
 	base->clk = clk;
 	base->num_memcpy_chans = num_memcpy_chans;
 	base->num_phy_chans = num_phy_chans;
 	base->num_log_chans = num_log_chans;
-	base->phy_start = res->start;
-	base->phy_size = resource_size(res);
 	base->virtbase = virtbase;
 	base->plat_data = plat_data;
-	base->dev = &pdev->dev;
+	base->dev = dev;
 	base->phy_chans = ((void *)base) + ALIGN(sizeof(struct d40_base), 4);
 	base->log_chans = &base->phy_chans[num_phy_chans];
 
@@ -3242,76 +3258,57 @@ static struct d40_base * __init d40_hw_detect_init(struct platform_device *pdev)
 		base->gen_dmac.init_reg_size = ARRAY_SIZE(dma_init_reg_v4a);
 	}
 
-	base->phy_res = kcalloc(num_phy_chans,
-				sizeof(*base->phy_res),
-				GFP_KERNEL);
+	base->phy_res = devm_kcalloc(dev, num_phy_chans,
+				     sizeof(*base->phy_res),
+				     GFP_KERNEL);
 	if (!base->phy_res)
-		goto free_base;
+		return -ENOMEM;
 
-	base->lookup_phy_chans = kcalloc(num_phy_chans,
-					 sizeof(*base->lookup_phy_chans),
-					 GFP_KERNEL);
+	base->lookup_phy_chans = devm_kcalloc(dev, num_phy_chans,
+					      sizeof(*base->lookup_phy_chans),
+					      GFP_KERNEL);
 	if (!base->lookup_phy_chans)
-		goto free_phy_res;
+		return -ENOMEM;
 
-	base->lookup_log_chans = kcalloc(num_log_chans,
-					 sizeof(*base->lookup_log_chans),
-					 GFP_KERNEL);
+	base->lookup_log_chans = devm_kcalloc(dev, num_log_chans,
+					      sizeof(*base->lookup_log_chans),
+					      GFP_KERNEL);
 	if (!base->lookup_log_chans)
-		goto free_phy_chans;
+		return -ENOMEM;
 
-	base->reg_val_backup_chan = kmalloc_array(base->num_phy_chans,
+	base->reg_val_backup_chan = devm_kmalloc_array(dev, base->num_phy_chans,
 						  sizeof(d40_backup_regs_chan),
 						  GFP_KERNEL);
 	if (!base->reg_val_backup_chan)
-		goto free_log_chans;
+		return -ENOMEM;
 
-	base->lcla_pool.alloc_map = kcalloc(num_phy_chans
+	base->lcla_pool.alloc_map = devm_kcalloc(dev, num_phy_chans
 					    * D40_LCLA_LINK_PER_EVENT_GRP,
 					    sizeof(*base->lcla_pool.alloc_map),
 					    GFP_KERNEL);
 	if (!base->lcla_pool.alloc_map)
-		goto free_backup_chan;
+		return -ENOMEM;
 
-	base->regs_interrupt = kmalloc_array(base->gen_dmac.il_size,
+	base->regs_interrupt = devm_kmalloc_array(dev, base->gen_dmac.il_size,
 					     sizeof(*base->regs_interrupt),
 					     GFP_KERNEL);
 	if (!base->regs_interrupt)
-		goto free_map;
+		return -ENOMEM;
 
 	base->desc_slab = kmem_cache_create(D40_NAME, sizeof(struct d40_desc),
 					    0, SLAB_HWCACHE_ALIGN,
 					    NULL);
-	if (base->desc_slab == NULL)
-		goto free_regs;
+	if (!base->desc_slab)
+		return -ENOMEM;
 
+	ret = devm_add_action_or_reset(dev, d40_drop_kmem_cache_action,
+				       base->desc_slab);
+	if (ret)
+		return ret;
 
-	return base;
- free_regs:
-	kfree(base->regs_interrupt);
- free_map:
-	kfree(base->lcla_pool.alloc_map);
- free_backup_chan:
-	kfree(base->reg_val_backup_chan);
- free_log_chans:
-	kfree(base->lookup_log_chans);
- free_phy_chans:
-	kfree(base->lookup_phy_chans);
- free_phy_res:
-	kfree(base->phy_res);
- free_base:
-	kfree(base);
- unmap_io:
-	iounmap(virtbase);
- release_region:
-	release_mem_region(res->start, resource_size(res));
- check_prepare_enabled:
-	if (!clk_ret)
- disable_unprepare:
-		clk_disable_unprepare(clk);
-	if (!IS_ERR(clk))
-		clk_put(clk);
-	return NULL;
+	*retbase = base;
+
+	return 0;
 }
 
 static void __init d40_hw_init(struct d40_base *base)
@@ -3451,14 +3448,14 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 	return ret;
 }
 
-static int __init d40_of_probe(struct platform_device *pdev,
+static int __init d40_of_probe(struct device *dev,
 			       struct device_node *np)
 {
 	struct stedma40_platform_data *pdata;
 	int num_phy = 0, num_memcpy = 0, num_disabled = 0;
 	const __be32 *list;
 
-	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
 
@@ -3471,7 +3468,7 @@ static int __init d40_of_probe(struct platform_device *pdev,
 	num_memcpy /= sizeof(*list);
 
 	if (num_memcpy > D40_MEMCPY_MAX_CHANS || num_memcpy <= 0) {
-		d40_err(&pdev->dev,
+		d40_err(dev,
 			"Invalid number of memcpy channels specified (%d)\n",
 			num_memcpy);
 		return -EINVAL;
@@ -3486,7 +3483,7 @@ static int __init d40_of_probe(struct platform_device *pdev,
 	num_disabled /= sizeof(*list);
 
 	if (num_disabled >= STEDMA40_MAX_PHYS || num_disabled < 0) {
-		d40_err(&pdev->dev,
+		d40_err(dev,
 			"Invalid number of disabled channels specified (%d)\n",
 			num_disabled);
 		return -EINVAL;
@@ -3497,35 +3494,30 @@ static int __init d40_of_probe(struct platform_device *pdev,
 				   num_disabled);
 	pdata->disabled_channels[num_disabled] = -1;
 
-	pdev->dev.platform_data = pdata;
+	dev->platform_data = pdata;
 
 	return 0;
 }
 
 static int __init d40_probe(struct platform_device *pdev)
 {
-	struct stedma40_platform_data *plat_data = dev_get_platdata(&pdev->dev);
+	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
-	int ret = -ENOENT;
+	struct device_node *np_lcpa;
 	struct d40_base *base;
 	struct resource *res;
+	struct resource res_lcpa;
 	int num_reserved_chans;
 	u32 val;
+	int ret;
 
-	if (!plat_data) {
-		if (np) {
-			if (d40_of_probe(pdev, np)) {
-				ret = -ENOMEM;
-				goto report_failure;
-			}
-		} else {
-			d40_err(&pdev->dev, "No pdata or Device Tree provided\n");
-			goto report_failure;
-		}
+	if (d40_of_probe(dev, np)) {
+		ret = -ENOMEM;
+		goto report_failure;
 	}
 
-	base = d40_hw_detect_init(pdev);
-	if (!base)
+	ret = d40_hw_detect_init(pdev, &base);
+	if (ret)
 		goto report_failure;
 
 	num_reserved_chans = d40_phy_res_init(base);
@@ -3535,37 +3527,38 @@ static int __init d40_probe(struct platform_device *pdev)
 	spin_lock_init(&base->interrupt_lock);
 	spin_lock_init(&base->execmd_lock);
 
-	/* Get IO for logical channel parameter address */
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "lcpa");
-	if (!res) {
-		ret = -ENOENT;
-		d40_err(&pdev->dev, "No \"lcpa\" memory resource\n");
-		goto destroy_cache;
+	/* Get IO for logical channel parameter address (LCPA) */
+	np_lcpa = of_parse_phandle(np, "sram", 0);
+	if (!np_lcpa) {
+		dev_err(dev, "no LCPA SRAM node\n");
+		ret = -EINVAL;
+		goto report_failure;
 	}
-	base->lcpa_size = resource_size(res);
-	base->phy_lcpa = res->start;
-
-	if (request_mem_region(res->start, resource_size(res),
-			       D40_NAME " I/O lcpa") == NULL) {
-		ret = -EBUSY;
-		d40_err(&pdev->dev, "Failed to request LCPA region %pR\n", res);
-		goto destroy_cache;
+	/* This is no device so read the address directly from the node */
+	ret = of_address_to_resource(np_lcpa, 0, &res_lcpa);
+	if (ret) {
+		dev_err(dev, "no LCPA SRAM resource\n");
+		goto report_failure;
 	}
+	base->lcpa_size = resource_size(&res_lcpa);
+	base->phy_lcpa = res_lcpa.start;
+	dev_info(dev, "found LCPA SRAM at %pad, size %pa\n",
+		 &base->phy_lcpa, &base->lcpa_size);
 
 	/* We make use of ESRAM memory for this. */
 	val = readl(base->virtbase + D40_DREG_LCPA);
-	if (res->start != val && val != 0) {
-		dev_warn(&pdev->dev,
-			 "[%s] Mismatch LCPA dma 0x%x, def %pa\n",
-			 __func__, val, &res->start);
+	if (base->phy_lcpa != val && val != 0) {
+		dev_warn(dev,
+			 "[%s] Mismatch LCPA dma 0x%x, def %08x\n",
+			 __func__, val, (u32)base->phy_lcpa);
 	} else
-		writel(res->start, base->virtbase + D40_DREG_LCPA);
+		writel(base->phy_lcpa, base->virtbase + D40_DREG_LCPA);
 
-	base->lcpa_base = ioremap(res->start, resource_size(res));
+	base->lcpa_base = devm_ioremap(dev, base->phy_lcpa, base->lcpa_size);
 	if (!base->lcpa_base) {
 		ret = -ENOMEM;
-		d40_err(&pdev->dev, "Failed to ioremap LCPA region\n");
-		goto destroy_cache;
+		d40_err(dev, "Failed to ioremap LCPA region\n");
+		goto report_failure;
 	}
 	/* If lcla has to be located in ESRAM we don't need to allocate */
 	if (base->plat_data->use_esram_lcla) {
@@ -3573,23 +3566,23 @@ static int __init d40_probe(struct platform_device *pdev)
 							"lcla_esram");
 		if (!res) {
 			ret = -ENOENT;
-			d40_err(&pdev->dev,
+			d40_err(dev,
 				"No \"lcla_esram\" memory resource\n");
-			goto destroy_cache;
+			goto report_failure;
 		}
-		base->lcla_pool.base = ioremap(res->start,
-						resource_size(res));
+		base->lcla_pool.base = devm_ioremap(dev, res->start,
+						    resource_size(res));
 		if (!base->lcla_pool.base) {
 			ret = -ENOMEM;
-			d40_err(&pdev->dev, "Failed to ioremap LCLA region\n");
-			goto destroy_cache;
+			d40_err(dev, "Failed to ioremap LCLA region\n");
+			goto report_failure;
 		}
 		writel(res->start, base->virtbase + D40_DREG_LCLA);
 
 	} else {
 		ret = d40_lcla_allocate(base);
 		if (ret) {
-			d40_err(&pdev->dev, "Failed to allocate LCLA area\n");
+			d40_err(dev, "Failed to allocate LCLA area\n");
 			goto destroy_cache;
 		}
 	}
@@ -3600,7 +3593,7 @@ static int __init d40_probe(struct platform_device *pdev)
 
 	ret = request_irq(base->irq, d40_handle_interrupt, 0, D40_NAME, base);
 	if (ret) {
-		d40_err(&pdev->dev, "No IRQ defined\n");
+		d40_err(dev, "No IRQ defined\n");
 		goto destroy_cache;
 	}
 
@@ -3608,7 +3601,7 @@ static int __init d40_probe(struct platform_device *pdev)
 
 		base->lcpa_regulator = regulator_get(base->dev, "lcla_esram");
 		if (IS_ERR(base->lcpa_regulator)) {
-			d40_err(&pdev->dev, "Failed to get lcpa_regulator\n");
+			d40_err(dev, "Failed to get lcpa_regulator\n");
 			ret = PTR_ERR(base->lcpa_regulator);
 			base->lcpa_regulator = NULL;
 			goto destroy_cache;
@@ -3616,7 +3609,7 @@ static int __init d40_probe(struct platform_device *pdev)
 
 		ret = regulator_enable(base->lcpa_regulator);
 		if (ret) {
-			d40_err(&pdev->dev,
+			d40_err(dev,
 				"Failed to enable lcpa_regulator\n");
 			regulator_put(base->lcpa_regulator);
 			base->lcpa_regulator = NULL;
@@ -3639,31 +3632,23 @@ static int __init d40_probe(struct platform_device *pdev)
 
 	ret = dma_set_max_seg_size(base->dev, STEDMA40_MAX_SEG_SIZE);
 	if (ret) {
-		d40_err(&pdev->dev, "Failed to set dma max seg size\n");
+		d40_err(dev, "Failed to set dma max seg size\n");
 		goto destroy_cache;
 	}
 
 	d40_hw_init(base);
 
-	if (np) {
-		ret = of_dma_controller_register(np, d40_xlate, NULL);
-		if (ret)
-			dev_err(&pdev->dev,
-				"could not register of_dma_controller\n");
+	ret = of_dma_controller_register(np, d40_xlate, NULL);
+	if (ret) {
+		dev_err(dev,
+			"could not register of_dma_controller\n");
+		goto destroy_cache;
 	}
 
 	dev_info(base->dev, "initialized\n");
 	return 0;
+
  destroy_cache:
-	kmem_cache_destroy(base->desc_slab);
-	if (base->virtbase)
-		iounmap(base->virtbase);
-
-	if (base->lcla_pool.base && base->plat_data->use_esram_lcla) {
-		iounmap(base->lcla_pool.base);
-		base->lcla_pool.base = NULL;
-	}
-
 	if (base->lcla_pool.dma_addr)
 		dma_unmap_single(base->dev, base->lcla_pool.dma_addr,
 				 SZ_1K * base->num_phy_chans,
@@ -3675,32 +3660,13 @@ static int __init d40_probe(struct platform_device *pdev)
 
 	kfree(base->lcla_pool.base_unaligned);
 
-	if (base->lcpa_base)
-		iounmap(base->lcpa_base);
-
-	if (base->phy_lcpa)
-		release_mem_region(base->phy_lcpa,
-				   base->lcpa_size);
-	if (base->phy_start)
-		release_mem_region(base->phy_start,
-				   base->phy_size);
-	if (base->clk) {
-		clk_disable_unprepare(base->clk);
-		clk_put(base->clk);
-	}
-
 	if (base->lcpa_regulator) {
 		regulator_disable(base->lcpa_regulator);
 		regulator_put(base->lcpa_regulator);
 	}
 
-	kfree(base->lcla_pool.alloc_map);
-	kfree(base->lookup_log_chans);
-	kfree(base->lookup_phy_chans);
-	kfree(base->phy_res);
-	kfree(base);
  report_failure:
-	d40_err(&pdev->dev, "probe failed\n");
+	d40_err(dev, "probe failed\n");
 	return ret;
 }
 
diff --git a/include/linux/platform_data/dma-ste-dma40.h b/drivers/dma/ste_dma40.h
similarity index 51%
rename from include/linux/platform_data/dma-ste-dma40.h
rename to drivers/dma/ste_dma40.h
index 10641633facc..c697bfe16a01 100644
--- a/include/linux/platform_data/dma-ste-dma40.h
+++ b/drivers/dma/ste_dma40.h
@@ -1,19 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) ST-Ericsson SA 2007-2010
- * Author: Per Forlin <per.forlin@stericsson.com> for ST-Ericsson
- * Author: Jonas Aaberg <jonas.aberg@stericsson.com> for ST-Ericsson
- */
-
 
 #ifndef STE_DMA40_H
 #define STE_DMA40_H
 
-#include <linux/dmaengine.h>
-#include <linux/scatterlist.h>
-#include <linux/workqueue.h>
-#include <linux/interrupt.h>
-
 /*
  * Maxium size for a single dma descriptor
  * Size is limited to 16 bits.
@@ -118,92 +107,4 @@ struct stedma40_chan_cfg {
 	int					 phy_channel;
 };
 
-/**
- * struct stedma40_platform_data - Configuration struct for the dma device.
- *
- * @dev_tx: mapping between destination event line and io address
- * @dev_rx: mapping between source event line and io address
- * @disabled_channels: A vector, ending with -1, that marks physical channels
- * that are for different reasons not available for the driver.
- * @soft_lli_chans: A vector, that marks physical channels will use LLI by SW
- * which avoids HW bug that exists in some versions of the controller.
- * SoftLLI introduces relink overhead that could impact performace for
- * certain use cases.
- * @num_of_soft_lli_chans: The number of channels that needs to be configured
- * to use SoftLLI.
- * @use_esram_lcla: flag for mapping the lcla into esram region
- * @num_of_memcpy_chans: The number of channels reserved for memcpy.
- * @num_of_phy_chans: The number of physical channels implemented in HW.
- * 0 means reading the number of channels from DMA HW but this is only valid
- * for 'multiple of 4' channels, like 8.
- */
-struct stedma40_platform_data {
-	int				 disabled_channels[STEDMA40_MAX_PHYS];
-	int				*soft_lli_chans;
-	int				 num_of_soft_lli_chans;
-	bool				 use_esram_lcla;
-	int				 num_of_memcpy_chans;
-	int				 num_of_phy_chans;
-};
-
-#ifdef CONFIG_STE_DMA40
-
-/**
- * stedma40_filter() - Provides stedma40_chan_cfg to the
- * ste_dma40 dma driver via the dmaengine framework.
- * does some checking of what's provided.
- *
- * Never directly called by client. It used by dmaengine.
- * @chan: dmaengine handle.
- * @data: Must be of type: struct stedma40_chan_cfg and is
- * the configuration of the framework.
- *
- *
- */
-
-bool stedma40_filter(struct dma_chan *chan, void *data);
-
-/**
- * stedma40_slave_mem() - Transfers a raw data buffer to or from a slave
- * (=device)
- *
- * @chan: dmaengine handle
- * @addr: source or destination physicall address.
- * @size: bytes to transfer
- * @direction: direction of transfer
- * @flags: is actually enum dma_ctrl_flags. See dmaengine.h
- */
-
-static inline struct
-dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan,
-					    dma_addr_t addr,
-					    unsigned int size,
-					    enum dma_transfer_direction direction,
-					    unsigned long flags)
-{
-	struct scatterlist sg;
-	sg_init_table(&sg, 1);
-	sg.dma_address = addr;
-	sg.length = size;
-
-	return dmaengine_prep_slave_sg(chan, &sg, 1, direction, flags);
-}
-
-#else
-static inline bool stedma40_filter(struct dma_chan *chan, void *data)
-{
-	return false;
-}
-
-static inline struct
-dma_async_tx_descriptor *stedma40_slave_mem(struct dma_chan *chan,
-					    dma_addr_t addr,
-					    unsigned int size,
-					    enum dma_transfer_direction direction,
-					    unsigned long flags)
-{
-	return NULL;
-}
-#endif
-
-#endif
+#endif /* STE_DMA40_H */
diff --git a/drivers/dma/ste_dma40_ll.c b/drivers/dma/ste_dma40_ll.c
index b5287c661eb7..4c489b126cb2 100644
--- a/drivers/dma/ste_dma40_ll.c
+++ b/drivers/dma/ste_dma40_ll.c
@@ -6,8 +6,9 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/platform_data/dma-ste-dma40.h>
+#include <linux/dmaengine.h>
 
+#include "ste_dma40.h"
 #include "ste_dma40_ll.h"
 
 static u8 d40_width_to_bits(enum dma_slave_buswidth width)
diff --git a/drivers/dma/ti/k3-psil-j721s2.c b/drivers/dma/ti/k3-psil-j721s2.c
index a488c2250623..1d5430fc5724 100644
--- a/drivers/dma/ti/k3-psil-j721s2.c
+++ b/drivers/dma/ti/k3-psil-j721s2.c
@@ -99,6 +99,8 @@ static struct psil_ep j721s2_src_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0x461d),
 	PSIL_PDMA_XY_PKT(0x461e),
 	PSIL_PDMA_XY_PKT(0x461f),
+	/* MAIN_CPSW2G */
+	PSIL_ETHERNET(0x4640),
 	/* PDMA_USART_G0 - UART0-1 */
 	PSIL_PDMA_XY_PKT(0x4700),
 	PSIL_PDMA_XY_PKT(0x4701),
@@ -161,6 +163,15 @@ static struct psil_ep j721s2_dst_ep_map[] = {
 	PSIL_ETHERNET(0xf005),
 	PSIL_ETHERNET(0xf006),
 	PSIL_ETHERNET(0xf007),
+	/* MAIN_CPSW2G */
+	PSIL_ETHERNET(0xc640),
+	PSIL_ETHERNET(0xc641),
+	PSIL_ETHERNET(0xc642),
+	PSIL_ETHERNET(0xc643),
+	PSIL_ETHERNET(0xc644),
+	PSIL_ETHERNET(0xc645),
+	PSIL_ETHERNET(0xc646),
+	PSIL_ETHERNET(0xc647),
 	/* SA2UL */
 	PSIL_SA2UL(0xf500, 1),
 	PSIL_SA2UL(0xf501, 1),
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index b8329a23728d..eb4dc5fffe64 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -4308,6 +4308,15 @@ static struct udma_soc_data am62a_dmss_csi_soc_data = {
 	},
 };
 
+static struct udma_soc_data j721s2_bcdma_csi_soc_data = {
+	.oes = {
+		.bcdma_tchan_data = 0x800,
+		.bcdma_tchan_ring = 0xa00,
+		.bcdma_rchan_data = 0xe00,
+		.bcdma_rchan_ring = 0x1000,
+	},
+};
+
 static struct udma_match_data am62a_bcdma_csirx_data = {
 	.type = DMA_TYPE_BCDMA,
 	.psil_base = 0x3100,
@@ -4346,6 +4355,18 @@ static struct udma_match_data am64_pktdma_data = {
 	},
 };
 
+static struct udma_match_data j721s2_bcdma_csi_data = {
+	.type = DMA_TYPE_BCDMA,
+	.psil_base = 0x2000,
+	.enable_memcpy_support = false,
+	.burst_size = {
+		TI_SCI_RM_UDMAP_CHAN_BURST_SIZE_64_BYTES, /* Normal Channels */
+		0, /* No H Channels */
+		0, /* No UH Channels */
+	},
+	.soc_data = &j721s2_bcdma_csi_soc_data,
+};
+
 static const struct of_device_id udma_of_match[] = {
 	{
 		.compatible = "ti,am654-navss-main-udmap",
@@ -4373,6 +4394,10 @@ static const struct of_device_id udma_of_match[] = {
 		.compatible = "ti,am62a-dmss-bcdma-csirx",
 		.data = &am62a_bcdma_csirx_data,
 	},
+	{
+		.compatible = "ti,j721s2-dmss-bcdma-csi",
+		.data = &j721s2_bcdma_csi_data,
+	},
 	{ /* Sentinel */ },
 };
 
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index df092229e97d..c87848cd8686 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -834,7 +834,7 @@ static int dw_pcie_edma_irq_vector(struct device *dev, unsigned int nr)
 	return platform_get_irq_byname_optional(pdev, name);
 }
 
-static struct dw_edma_core_ops dw_pcie_edma_ops = {
+static struct dw_edma_plat_ops dw_pcie_edma_ops = {
 	.irq_vector = dw_pcie_edma_irq_vector,
 };
 
diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h
index d2638d9259dc..3080747689f6 100644
--- a/include/linux/dma/edma.h
+++ b/include/linux/dma/edma.h
@@ -40,7 +40,7 @@ struct dw_edma_region {
  *			iATU windows. That will be done by the controller
  *			automatically.
  */
-struct dw_edma_core_ops {
+struct dw_edma_plat_ops {
 	int (*irq_vector)(struct device *dev, unsigned int nr);
 	u64 (*pci_address)(struct device *dev, phys_addr_t cpu_addr);
 };
@@ -48,7 +48,8 @@ struct dw_edma_core_ops {
 enum dw_edma_map_format {
 	EDMA_MF_EDMA_LEGACY = 0x0,
 	EDMA_MF_EDMA_UNROLL = 0x1,
-	EDMA_MF_HDMA_COMPAT = 0x5
+	EDMA_MF_HDMA_COMPAT = 0x5,
+	EDMA_MF_HDMA_NATIVE = 0x7,
 };
 
 /**
@@ -80,7 +81,7 @@ enum dw_edma_chip_flags {
 struct dw_edma_chip {
 	struct device		*dev;
 	int			nr_irqs;
-	const struct dw_edma_core_ops   *ops;
+	const struct dw_edma_plat_ops	*ops;
 	u32			flags;
 
 	void __iomem		*reg_base;