Merge tag 'dmaengine-6.8-rc1' into fixes

dmaengine updates for v6.8

 New support:
  - Loongson LS2X APB DMA controller
  - sf-pdma: mpfs-pdma support
  - Qualcomm X1E80100 GPI dma controller support

 Updates:
  - Xilinx XDMA updates to support interleaved DMA transfers
  - TI PSIL threads for AM62P and J722S and cfg register regions description
  - axi-dmac Improving the cyclic DMA transfers
  - Tegra Support dma-channel-mask property
  - Remaining platform remove callback returning void conversions

Documentation/devicetree/bindings/dma/dma-controller.yaml

@@ -19,19 +19,4 @@ properties:
 
 additionalProperties: true
 
-examples:
-  - |
-    dma: dma-controller@48000000 {
-        compatible = "ti,omap-sdma";
-        reg = <0x48000000 0x1000>;
-        interrupts = <0 12 0x4>,
-                     <0 13 0x4>,
-                     <0 14 0x4>,
-                     <0 15 0x4>;
-        #dma-cells = <1>;
-        dma-channels = <32>;
-        dma-requests = <127>;
-        dma-channel-mask = <0xfffe>;
-    };
-
 ...

Documentation/devicetree/bindings/dma/dma-router.yaml

@@ -40,15 +40,4 @@ required:
 
 additionalProperties: true
 
-examples:
-  - |
-    sdma_xbar: dma-router@4a002b78 {
-        compatible = "ti,dra7-dma-crossbar";
-        reg = <0x4a002b78 0xfc>;
-        #dma-cells = <1>;
-        dma-requests = <205>;
-        ti,dma-safe-map = <0>;
-        dma-masters = <&sdma>;
-    };
-
 ...

Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/loongson,ls2x-apbdma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Loongson LS2X APB DMA controller
+
+description:
+  The Loongson LS2X APB DMA controller is used for transferring data
+  between system memory and the peripherals on the APB bus.
+
+maintainers:
+  - Binbin Zhou <zhoubinbin@loongson.cn>
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    oneOf:
+      - const: loongson,ls2k1000-apbdma
+      - items:
+          - const: loongson,ls2k0500-apbdma
+          - const: loongson,ls2k1000-apbdma
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  '#dma-cells':
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - '#dma-cells'
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/clock/loongson,ls2k-clk.h>
+
+    dma-controller@1fe00c00 {
+        compatible = "loongson,ls2k1000-apbdma";
+        reg = <0x1fe00c00 0x8>;
+        interrupt-parent = <&liointc1>;
+        interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&clk LOONGSON2_APB_CLK>;
+        #dma-cells = <1>;
+    };
+
+...

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

@@ -53,6 +53,9 @@ properties:
       ADMA_CHn_CTRL register.
     const: 1
 
+  dma-channel-mask:
+    maxItems: 1
+
 required:
   - compatible
   - reg

Documentation/devicetree/bindings/dma/qcom,gpi.yaml

@@ -32,6 +32,8 @@ properties:
               - qcom,sm8350-gpi-dma
               - qcom,sm8450-gpi-dma
               - qcom,sm8550-gpi-dma
+              - qcom,sm8650-gpi-dma
+              - qcom,x1e80100-gpi-dma
           - const: qcom,sm6350-gpi-dma
       - items:
           - enum:

Documentation/devicetree/bindings/dma/renesas,rz-dmac.yaml

@@ -16,7 +16,7 @@ properties:
   compatible:
     items:
       - enum:
-          - renesas,r9a07g043-dmac # RZ/G2UL
+          - renesas,r9a07g043-dmac # RZ/G2UL and RZ/Five
           - renesas,r9a07g044-dmac # RZ/G2{L,LC}
           - renesas,r9a07g054-dmac # RZ/V2L
       - const: renesas,rz-dmac

Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml

@@ -29,6 +29,7 @@ properties:
   compatible:
     items:
       - enum:
+          - microchip,mpfs-pdma
           - sifive,fu540-c000-pdma
       - const: sifive,pdma0
     description:

Documentation/devicetree/bindings/dma/ti/k3-bcdma.yaml

@@ -37,11 +37,11 @@ properties:
 
   reg:
     minItems: 3
-    maxItems: 5
+    maxItems: 9
 
   reg-names:
     minItems: 3
-    maxItems: 5
+    maxItems: 9
 
   "#dma-cells":
     const: 3
@@ -141,7 +141,10 @@ allOf:
         ti,sci-rm-range-tchan: false
 
         reg:
-          maxItems: 3
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: RX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
 
         reg-names:
           items:
@@ -161,14 +164,29 @@ allOf:
       properties:
         reg:
           minItems: 5
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: Block Copy Channel Realtime Registers region
+            - description: RX Channel Realtime Registers region
+            - description: TX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
+            - description: Ring Configuration Registers region
+            - description: TX Channel Configuration Registers region
+            - description: RX Channel Configuration Registers region
+            - description: Block Copy Channel Configuration Registers region
 
         reg-names:
+          minItems: 5
           items:
             - const: gcfg
             - const: bchanrt
             - const: rchanrt
             - const: tchanrt
             - const: ringrt
+            - const: ring
+            - const: tchan
+            - const: rchan
+            - const: bchan
 
       required:
         - ti,sci-rm-range-bchan
@@ -184,7 +202,11 @@ allOf:
         ti,sci-rm-range-bchan: false
 
         reg:
-          maxItems: 4
+          items:
+            - description: BCDMA Control /Status Registers region
+            - description: RX Channel Realtime Registers region
+            - description: TX Channel Realtime Registers region
+            - description: Ring Realtime Registers region
 
         reg-names:
           items:
@@ -220,8 +242,13 @@ examples:
                       <0x0 0x4c000000 0x0 0x20000>,
                       <0x0 0x4a820000 0x0 0x20000>,
                       <0x0 0x4aa40000 0x0 0x20000>,
-                      <0x0 0x4bc00000 0x0 0x100000>;
-                reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt";
+                      <0x0 0x4bc00000 0x0 0x100000>,
+                      <0x0 0x48600000 0x0 0x8000>,
+                      <0x0 0x484a4000 0x0 0x2000>,
+                      <0x0 0x484c2000 0x0 0x2000>,
+                      <0x0 0x48420000 0x0 0x2000>;
+                reg-names = "gcfg", "bchanrt", "rchanrt", "tchanrt", "ringrt",
+                            "ring", "tchan", "rchan", "bchan";
                 msi-parent = <&inta_main_dmss>;
                 #dma-cells = <3>;
 

Documentation/devicetree/bindings/dma/ti/k3-pktdma.yaml

@@ -45,14 +45,28 @@ properties:
       The second cell is the ASEL value for the channel
 
   reg:
-    maxItems: 4
+    minItems: 4
+    items:
+      - description: Packet DMA Control /Status Registers region
+      - description: RX Channel Realtime Registers region
+      - description: TX Channel Realtime Registers region
+      - description: Ring Realtime Registers region
+      - description: Ring Configuration Registers region
+      - description: TX Configuration Registers region
+      - description: RX Configuration Registers region
+      - description: RX Flow Configuration Registers region
 
   reg-names:
+    minItems: 4
     items:
       - const: gcfg
       - const: rchanrt
       - const: tchanrt
       - const: ringrt
+      - const: ring
+      - const: tchan
+      - const: rchan
+      - const: rflow
 
   msi-parent: true
 
@@ -136,8 +150,14 @@ examples:
                 reg = <0x0 0x485c0000 0x0 0x100>,
                       <0x0 0x4a800000 0x0 0x20000>,
                       <0x0 0x4aa00000 0x0 0x40000>,
-                      <0x0 0x4b800000 0x0 0x400000>;
-                reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt";
+                      <0x0 0x4b800000 0x0 0x400000>,
+                      <0x0 0x485e0000 0x0 0x20000>,
+                      <0x0 0x484a0000 0x0 0x4000>,
+                      <0x0 0x484c0000 0x0 0x2000>,
+                      <0x0 0x48430000 0x0 0x4000>;
+                reg-names = "gcfg", "rchanrt", "tchanrt", "ringrt",
+                            "ring", "tchan", "rchan", "rflow";
+
                 msi-parent = <&inta_main_dmss>;
                 #dma-cells = <2>;
 

Documentation/devicetree/bindings/dma/ti/k3-udma.yaml

@@ -69,13 +69,24 @@ properties:
       - ti,j721e-navss-mcu-udmap
 
   reg:
-    maxItems: 3
+    minItems: 3
+    items:
+      - description: UDMA-P Control /Status Registers region
+      - description: RX Channel Realtime Registers region
+      - description: TX Channel Realtime Registers region
+      - description: TX Configuration Registers region
+      - description: RX Configuration Registers region
+      - description: RX Flow Configuration Registers region
 
   reg-names:
+    minItems: 3
     items:
       - const: gcfg
       - const: rchanrt
       - const: tchanrt
+      - const: tchan
+      - const: rchan
+      - const: rflow
 
   msi-parent: true
 
@@ -158,8 +169,11 @@ examples:
                 compatible = "ti,am654-navss-main-udmap";
                 reg = <0x0 0x31150000 0x0 0x100>,
                       <0x0 0x34000000 0x0 0x100000>,
-                      <0x0 0x35000000 0x0 0x100000>;
-                reg-names = "gcfg", "rchanrt", "tchanrt";
+                      <0x0 0x35000000 0x0 0x100000>,
+                      <0x0 0x30b00000 0x0 0x20000>,
+                      <0x0 0x30c00000 0x0 0x8000>,
+                      <0x0 0x30d00000 0x0 0x4000>;
+                reg-names = "gcfg", "rchanrt", "tchanrt", "tchan", "rchan", "rflow";
                 #dma-cells = <1>;
 
                 ti,ringacc = <&ringacc>;

MAINTAINERS

@@ -12507,6 +12507,13 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/gpio/loongson,ls-gpio.yaml
 F:	drivers/gpio/gpio-loongson-64bit.c
 
+LOONGSON LS2X APB DMA DRIVER
+M:	Binbin Zhou <zhoubinbin@loongson.cn>
+L:	dmaengine@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/dma/loongson,ls2x-apbdma.yaml
+F:	drivers/dma/ls2x-apb-dma.c
+
 LOONGSON LS2X I2C DRIVER
 M:	Binbin Zhou <zhoubinbin@loongson.cn>
 L:	linux-i2c@vger.kernel.org

drivers/dma/Kconfig

@@ -378,6 +378,20 @@ config LPC18XX_DMAMUX
 	  Enable support for DMA on NXP LPC18xx/43xx platforms
 	  with PL080 and multiplexed DMA request lines.
 
+config LS2X_APB_DMA
+	tristate "Loongson LS2X APB DMA support"
+	depends on LOONGARCH || COMPILE_TEST
+	select DMA_ENGINE
+	select DMA_VIRTUAL_CHANNELS
+	help
+	  Support for the Loongson LS2X APB DMA controller driver. The
+	  DMA controller is having single DMA channel which can be
+	  configured for different peripherals like audio, nand, sdio
+	  etc which is in APB bus.
+
+	  This DMA controller transfers data from memory to peripheral fifo.
+	  It does not support memory to memory data transfer.
+
 config MCF_EDMA
 	tristate "Freescale eDMA engine support, ColdFire mcf5441x SoCs"
 	depends on M5441x || COMPILE_TEST

drivers/dma/Makefile

@@ -48,6 +48,7 @@ obj-$(CONFIG_INTEL_IOATDMA) += ioat/
 obj-y += idxd/
 obj-$(CONFIG_K3_DMA) += k3dma.o
 obj-$(CONFIG_LPC18XX_DMAMUX) += lpc18xx-dmamux.o
+obj-$(CONFIG_LS2X_APB_DMA) += ls2x-apb-dma.o
 obj-$(CONFIG_MILBEAUT_HDMAC) += milbeaut-hdmac.o
 obj-$(CONFIG_MILBEAUT_XDMAC) += milbeaut-xdmac.o
 obj-$(CONFIG_MMP_PDMA) += mmp_pdma.o

drivers/dma/apple-admac.c

@@ -57,6 +57,8 @@
 
 #define REG_BUS_WIDTH(ch)	(0x8040 + (ch) * 0x200)
 
+#define BUS_WIDTH_WORD_SIZE	GENMASK(3, 0)
+#define BUS_WIDTH_FRAME_SIZE	GENMASK(7, 4)
 #define BUS_WIDTH_8BIT		0x00
 #define BUS_WIDTH_16BIT		0x01
 #define BUS_WIDTH_32BIT		0x02
@@ -740,7 +742,8 @@ static int admac_device_config(struct dma_chan *chan,
 	struct admac_data *ad = adchan->host;
 	bool is_tx = admac_chan_direction(adchan->no) == DMA_MEM_TO_DEV;
 	int wordsize = 0;
-	u32 bus_width = 0;
+	u32 bus_width = readl_relaxed(ad->base + REG_BUS_WIDTH(adchan->no)) &
+		~(BUS_WIDTH_WORD_SIZE | BUS_WIDTH_FRAME_SIZE);
 
 	switch (is_tx ? config->dst_addr_width : config->src_addr_width) {
 	case DMA_SLAVE_BUSWIDTH_1_BYTE:

drivers/dma/dmaengine.c

@@ -1103,6 +1103,9 @@ EXPORT_SYMBOL_GPL(dma_async_device_channel_register);
 static void __dma_async_device_channel_unregister(struct dma_device *device,
 						  struct dma_chan *chan)
 {
+	if (chan->local == NULL)
+		return;
+
 	WARN_ONCE(!device->device_release && chan->client_count,
 		  "%s called while %d clients hold a reference\n",
 		  __func__, chan->client_count);

drivers/dma/dmatest.c

@@ -21,6 +21,10 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 
+static bool nobounce;
+module_param(nobounce, bool, 0644);
+MODULE_PARM_DESC(nobounce, "Prevent using swiotlb buffer (default: use swiotlb buffer)");
+
 static unsigned int test_buf_size = 16384;
 module_param(test_buf_size, uint, 0644);
 MODULE_PARM_DESC(test_buf_size, "Size of the memcpy test buffer");
@@ -90,6 +94,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
 
 /**
  * struct dmatest_params - test parameters.
+ * @nobounce:		prevent using swiotlb buffer
  * @buf_size:		size of the memcpy test buffer
  * @channel:		bus ID of the channel to test
  * @device:		bus ID of the DMA Engine to test
@@ -106,6 +111,7 @@ MODULE_PARM_DESC(polled, "Use polling for completion instead of interrupts");
  * @polled:		use polling for completion instead of interrupts
  */
 struct dmatest_params {
+	bool		nobounce;
 	unsigned int	buf_size;
 	char		channel[20];
 	char		device[32];
@@ -215,6 +221,7 @@ struct dmatest_done {
 struct dmatest_data {
 	u8		**raw;
 	u8		**aligned;
+	gfp_t		gfp_flags;
 	unsigned int	cnt;
 	unsigned int	off;
 };
@@ -533,7 +540,7 @@ static int dmatest_alloc_test_data(struct dmatest_data *d,
 		goto err;
 
 	for (i = 0; i < d->cnt; i++) {
-		d->raw[i] = kmalloc(buf_size + align, GFP_KERNEL);
+		d->raw[i] = kmalloc(buf_size + align, d->gfp_flags);
 		if (!d->raw[i])
 			goto err;
 
@@ -655,6 +662,13 @@ static int dmatest_func(void *data)
 		goto err_free_coefs;
 	}
 
+	src->gfp_flags = GFP_KERNEL;
+	dst->gfp_flags = GFP_KERNEL;
+	if (params->nobounce) {
+		src->gfp_flags = GFP_DMA;
+		dst->gfp_flags = GFP_DMA;
+	}
+
 	if (dmatest_alloc_test_data(src, buf_size, align) < 0)
 		goto err_free_coefs;
 
@@ -1093,6 +1107,7 @@ static void add_threaded_test(struct dmatest_info *info)
 	struct dmatest_params *params = &info->params;
 
 	/* Copy test parameters */
+	params->nobounce = nobounce;
 	params->buf_size = test_buf_size;
 	strscpy(params->channel, strim(test_channel), sizeof(params->channel));
 	strscpy(params->device, strim(test_device), sizeof(params->device));

drivers/dma/fsl-edma-main.c

@@ -9,6 +9,7 @@
  * Vybrid and Layerscape SoCs.
  */
 
+#include <dt-bindings/dma/fsl-edma.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/clk.h>
@@ -21,10 +22,6 @@
 
 #include "fsl-edma-common.h"
 
-#define ARGS_RX                         BIT(0)
-#define ARGS_REMOTE                     BIT(1)
-#define ARGS_MULTI_FIFO                 BIT(2)
-
 static void fsl_edma_synchronize(struct dma_chan *chan)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
@@ -153,9 +150,15 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec,
 		i = fsl_chan - fsl_edma->chans;
 
 		fsl_chan->priority = dma_spec->args[1];
-		fsl_chan->is_rxchan = dma_spec->args[2] & ARGS_RX;
-		fsl_chan->is_remote = dma_spec->args[2] & ARGS_REMOTE;
-		fsl_chan->is_multi_fifo = dma_spec->args[2] & ARGS_MULTI_FIFO;
+		fsl_chan->is_rxchan = dma_spec->args[2] & FSL_EDMA_RX;
+		fsl_chan->is_remote = dma_spec->args[2] & FSL_EDMA_REMOTE;
+		fsl_chan->is_multi_fifo = dma_spec->args[2] & FSL_EDMA_MULTI_FIFO;
+
+		if ((dma_spec->args[2] & FSL_EDMA_EVEN_CH) && (i & 0x1))
+			continue;
+
+		if ((dma_spec->args[2] & FSL_EDMA_ODD_CH) && !(i & 0x1))
+			continue;
 
 		if (!b_chmux && i == dma_spec->args[0]) {
 			chan = dma_get_slave_channel(chan);

drivers/dma/idxd/cdev.c

@@ -165,7 +165,7 @@ static void idxd_cdev_dev_release(struct device *dev)
 	struct idxd_wq *wq = idxd_cdev->wq;
 
 	cdev_ctx = &ictx[wq->idxd->data->type];
-	ida_simple_remove(&cdev_ctx->minor_ida, idxd_cdev->minor);
+	ida_free(&cdev_ctx->minor_ida, idxd_cdev->minor);
 	kfree(idxd_cdev);
 }
 
@@ -463,7 +463,7 @@ int idxd_wq_add_cdev(struct idxd_wq *wq)
 	cdev = &idxd_cdev->cdev;
 	dev = cdev_dev(idxd_cdev);
 	cdev_ctx = &ictx[wq->idxd->data->type];
-	minor = ida_simple_get(&cdev_ctx->minor_ida, 0, MINORMASK, GFP_KERNEL);
+	minor = ida_alloc_max(&cdev_ctx->minor_ida, MINORMASK, GFP_KERNEL);
 	if (minor < 0) {
 		kfree(idxd_cdev);
 		return minor;

drivers/dma/idxd/device.c

@@ -802,6 +802,9 @@ static int idxd_device_evl_setup(struct idxd_device *idxd)
 
 static void idxd_device_evl_free(struct idxd_device *idxd)
 {
+	void *evl_log;
+	unsigned int evl_log_size;
+	dma_addr_t evl_dma;
 	union gencfg_reg gencfg;
 	union genctrl_reg genctrl;
 	struct device *dev = &idxd->pdev->dev;
@@ -822,11 +825,15 @@ static void idxd_device_evl_free(struct idxd_device *idxd)
 	iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET);
 	iowrite64(0, idxd->reg_base + IDXD_EVLCFG_OFFSET + 8);
 
-	dma_free_coherent(dev, evl->log_size, evl->log, evl->dma);
 	bitmap_free(evl->bmap);
+	evl_log = evl->log;
+	evl_log_size = evl->log_size;
+	evl_dma = evl->dma;
 	evl->log = NULL;
 	evl->size = IDXD_EVL_SIZE_MIN;
 	spin_unlock(&evl->lock);
+
+	dma_free_coherent(dev, evl_log_size, evl_log, evl_dma);
 }
 
 static void idxd_group_config_write(struct idxd_group *group)

drivers/dma/milbeaut-hdmac.c

@@ -531,7 +531,7 @@ static int milbeaut_hdmac_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int milbeaut_hdmac_remove(struct platform_device *pdev)
+static void milbeaut_hdmac_remove(struct platform_device *pdev)
 {
 	struct milbeaut_hdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -546,16 +546,21 @@ static int milbeaut_hdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		milbeaut_hdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&mdev->ddev);
 	clk_disable_unprepare(mdev->clk);
-
-	return 0;
 }
 
 static const struct of_device_id milbeaut_hdmac_match[] = {
@@ -566,7 +571,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_hdmac_match);
 
 static struct platform_driver milbeaut_hdmac_driver = {
 	.probe = milbeaut_hdmac_probe,
-	.remove = milbeaut_hdmac_remove,
+	.remove_new = milbeaut_hdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-hdmac",
 		.of_match_table = milbeaut_hdmac_match,

drivers/dma/milbeaut-xdmac.c

@@ -368,7 +368,7 @@ static int milbeaut_xdmac_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int milbeaut_xdmac_remove(struct platform_device *pdev)
+static void milbeaut_xdmac_remove(struct platform_device *pdev)
 {
 	struct milbeaut_xdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -383,8 +383,15 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		milbeaut_xdmac_free_chan_resources(chan);
 	}
 
@@ -392,8 +399,6 @@ static int milbeaut_xdmac_remove(struct platform_device *pdev)
 	dma_async_device_unregister(&mdev->ddev);
 
 	disable_xdmac(mdev);
-
-	return 0;
 }
 
 static const struct of_device_id milbeaut_xdmac_match[] = {
@@ -404,7 +409,7 @@ MODULE_DEVICE_TABLE(of, milbeaut_xdmac_match);
 
 static struct platform_driver milbeaut_xdmac_driver = {
 	.probe = milbeaut_xdmac_probe,
-	.remove = milbeaut_xdmac_remove,
+	.remove_new = milbeaut_xdmac_remove,
 	.driver = {
 		.name = "milbeaut-m10v-xdmac",
 		.of_match_table = milbeaut_xdmac_match,

drivers/dma/pl330.c

@@ -1053,6 +1053,9 @@ static bool _trigger(struct pl330_thread *thrd)
 
 	thrd->req_running = idx;
 
+	if (desc->rqtype == DMA_MEM_TO_DEV || desc->rqtype == DMA_DEV_TO_MEM)
+		UNTIL(thrd, PL330_STATE_WFP);
+
 	return true;
 }
 

drivers/dma/sf-pdma/sf-pdma.c

@@ -20,10 +20,13 @@
 #include <linux/mod_devicetable.h>
 #include <linux/dma-mapping.h>
 #include <linux/of.h>
+#include <linux/of_dma.h>
 #include <linux/slab.h>
 
 #include "sf-pdma.h"
 
+#define PDMA_QUIRK_NO_STRICT_ORDERING   BIT(0)
+
 #ifndef readq
 static inline unsigned long long readq(void __iomem *addr)
 {
@@ -65,7 +68,7 @@ static struct sf_pdma_desc *sf_pdma_alloc_desc(struct sf_pdma_chan *chan)
 static void sf_pdma_fill_desc(struct sf_pdma_desc *desc,
 			      u64 dst, u64 src, u64 size)
 {
-	desc->xfer_type = PDMA_FULL_SPEED;
+	desc->xfer_type =  desc->chan->pdma->transfer_type;
 	desc->xfer_size = size;
 	desc->dst_addr = dst;
 	desc->src_addr = src;
@@ -492,6 +495,7 @@ static void sf_pdma_setup_chans(struct sf_pdma *pdma)
 
 static int sf_pdma_probe(struct platform_device *pdev)
 {
+	const struct sf_pdma_driver_platdata *ddata;
 	struct sf_pdma *pdma;
 	int ret, n_chans;
 	const enum dma_slave_buswidth widths =
@@ -517,6 +521,14 @@ static int sf_pdma_probe(struct platform_device *pdev)
 
 	pdma->n_chans = n_chans;
 
+	pdma->transfer_type = PDMA_FULL_SPEED | PDMA_STRICT_ORDERING;
+
+	ddata  = device_get_match_data(&pdev->dev);
+	if (ddata) {
+		if (ddata->quirks & PDMA_QUIRK_NO_STRICT_ORDERING)
+			pdma->transfer_type &= ~PDMA_STRICT_ORDERING;
+	}
+
 	pdma->membase = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(pdma->membase))
 		return PTR_ERR(pdma->membase);
@@ -563,7 +575,20 @@ static int sf_pdma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = of_dma_controller_register(pdev->dev.of_node,
+					 of_dma_xlate_by_chan_id, pdma);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"Can't register SiFive Platform OF_DMA. (%d)\n", ret);
+		goto err_unregister;
+	}
+
 	return 0;
+
+err_unregister:
+	dma_async_device_unregister(&pdma->dma_dev);
+
+	return ret;
 }
 
 static void sf_pdma_remove(struct platform_device *pdev)
@@ -583,12 +608,25 @@ static void sf_pdma_remove(struct platform_device *pdev)
 		tasklet_kill(&ch->err_tasklet);
 	}
 
+	if (pdev->dev.of_node)
+		of_dma_controller_free(pdev->dev.of_node);
+
 	dma_async_device_unregister(&pdma->dma_dev);
 }
 
+static const struct sf_pdma_driver_platdata mpfs_pdma = {
+	.quirks = PDMA_QUIRK_NO_STRICT_ORDERING,
+};
+
 static const struct of_device_id sf_pdma_dt_ids[] = {
-	{ .compatible = "sifive,fu540-c000-pdma" },
-	{ .compatible = "sifive,pdma0" },
+	{
+		.compatible = "sifive,fu540-c000-pdma",
+	}, {
+		.compatible = "sifive,pdma0",
+	}, {
+		.compatible = "microchip,mpfs-pdma",
+		.data	    = &mpfs_pdma,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, sf_pdma_dt_ids);

drivers/dma/sf-pdma/sf-pdma.h

@@ -48,7 +48,8 @@
 #define PDMA_ERR_STATUS_MASK				GENMASK(31, 31)
 
 /* Transfer Type */
-#define PDMA_FULL_SPEED					0xFF000008
+#define PDMA_FULL_SPEED					0xFF000000
+#define PDMA_STRICT_ORDERING				BIT(3)
 
 /* Error Recovery */
 #define MAX_RETRY					1
@@ -112,8 +113,13 @@ struct sf_pdma {
 	struct dma_device       dma_dev;
 	void __iomem            *membase;
 	void __iomem            *mappedbase;
+	u32			transfer_type;
 	u32			n_chans;
 	struct sf_pdma_chan	chans[] __counted_by(n_chans);
 };
 
+struct sf_pdma_driver_platdata {
+	u32 quirks;
+};
+
 #endif /* _SF_PDMA_H */

drivers/dma/ste_dma40.c

@@ -31,13 +31,11 @@
 /**
  * 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
+ * SoftLLI introduces relink overhead that could impact performance for
  * certain use cases.
  * @num_of_soft_lli_chans: The number of channels that needs to be configured
  * to use SoftLLI.
@@ -184,7 +182,7 @@ static __maybe_unused u32 d40_backup_regs[] = {
 
 /*
  * since 9540 and 8540 has the same HW revision
- * use v4a for 9540 or ealier
+ * use v4a for 9540 or earlier
  * use v4b for 8540 or later
  * HW revision:
  * DB8500ed has revision 0
@@ -411,7 +409,7 @@ struct d40_desc {
  *
  * @base: The virtual address of LCLA. 18 bit aligned.
  * @dma_addr: DMA address, if mapped
- * @base_unaligned: The orignal kmalloc pointer, if kmalloc is used.
+ * @base_unaligned: The original kmalloc pointer, if kmalloc is used.
  * This pointer is only there for clean-up on error.
  * @pages: The number of pages needed for all physical channels.
  * Only used later for clean-up on error
@@ -1655,7 +1653,7 @@ static void dma_tasklet(struct tasklet_struct *t)
 
 	return;
  check_pending_tx:
-	/* Rescue manouver if receiving double interrupts */
+	/* Rescue maneuver if receiving double interrupts */
 	if (d40c->pending_tx > 0)
 		d40c->pending_tx--;
 	spin_unlock_irqrestore(&d40c->lock, flags);
@@ -3412,7 +3410,7 @@ static int __init d40_lcla_allocate(struct d40_base *base)
 		base->lcla_pool.base = (void *)page_list[i];
 	} else {
 		/*
-		 * After many attempts and no succees with finding the correct
+		 * After many attempts and no success with finding the correct
 		 * alignment, try with allocating a big buffer.
 		 */
 		dev_warn(base->dev,

drivers/dma/tegra210-adma.c

@@ -153,6 +153,7 @@ struct tegra_adma {
 	void __iomem			*base_addr;
 	struct clk			*ahub_clk;
 	unsigned int			nr_channels;
+	unsigned long			*dma_chan_mask;
 	unsigned long			rx_requests_reserved;
 	unsigned long			tx_requests_reserved;
 
@@ -741,6 +742,10 @@ static int __maybe_unused tegra_adma_runtime_suspend(struct device *dev)
 
 	for (i = 0; i < tdma->nr_channels; i++) {
 		tdc = &tdma->channels[i];
+		/* skip for reserved channels */
+		if (!tdc->tdma)
+			continue;
+
 		ch_reg = &tdc->ch_regs;
 		ch_reg->cmd = tdma_ch_read(tdc, ADMA_CH_CMD);
 		/* skip if channel is not active */
@@ -779,6 +784,9 @@ static int __maybe_unused tegra_adma_runtime_resume(struct device *dev)
 
 	for (i = 0; i < tdma->nr_channels; i++) {
 		tdc = &tdma->channels[i];
+		/* skip for reserved channels */
+		if (!tdc->tdma)
+			continue;
 		ch_reg = &tdc->ch_regs;
 		/* skip if channel was not active earlier */
 		if (!ch_reg->cmd)
@@ -867,10 +875,31 @@ static int tegra_adma_probe(struct platform_device *pdev)
 		return PTR_ERR(tdma->ahub_clk);
 	}
 
+	tdma->dma_chan_mask = devm_kzalloc(&pdev->dev,
+					   BITS_TO_LONGS(tdma->nr_channels) * sizeof(unsigned long),
+					   GFP_KERNEL);
+	if (!tdma->dma_chan_mask)
+		return -ENOMEM;
+
+	/* Enable all channels by default */
+	bitmap_fill(tdma->dma_chan_mask, tdma->nr_channels);
+
+	ret = of_property_read_u32_array(pdev->dev.of_node, "dma-channel-mask",
+					 (u32 *)tdma->dma_chan_mask,
+					 BITS_TO_U32(tdma->nr_channels));
+	if (ret < 0 && (ret != -EINVAL)) {
+		dev_err(&pdev->dev, "dma-channel-mask is not complete.\n");
+		return ret;
+	}
+
 	INIT_LIST_HEAD(&tdma->dma_dev.channels);
 	for (i = 0; i < tdma->nr_channels; i++) {
 		struct tegra_adma_chan *tdc = &tdma->channels[i];
 
+		/* skip for reserved channels */
+		if (!test_bit(i, tdma->dma_chan_mask))
+			continue;
+
 		tdc->chan_addr = tdma->base_addr + cdata->ch_base_offset
 				 + (cdata->ch_reg_size * i);
 
@@ -957,8 +986,10 @@ static void tegra_adma_remove(struct platform_device *pdev)
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&tdma->dma_dev);
 
-	for (i = 0; i < tdma->nr_channels; ++i)
-		irq_dispose_mapping(tdma->channels[i].irq);
+	for (i = 0; i < tdma->nr_channels; ++i) {
+		if (tdma->channels[i].irq)
+			irq_dispose_mapping(tdma->channels[i].irq);
+	}
 
 	pm_runtime_disable(&pdev->dev);
 }

drivers/dma/ti/Makefile

@@ -12,6 +12,7 @@ k3-psil-lib-objs := k3-psil.o \
 		    k3-psil-j721s2.o \
 		    k3-psil-am62.o \
 		    k3-psil-am62a.o \
-		    k3-psil-j784s4.o
+		    k3-psil-j784s4.o \
+		    k3-psil-am62p.o
 obj-$(CONFIG_TI_K3_PSIL) += k3-psil-lib.o
 obj-$(CONFIG_TI_DMA_CROSSBAR) += dma-crossbar.o

drivers/dma/ti/k3-psil-am62p.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com
+ */
+
+#include <linux/kernel.h>
+
+#include "k3-psil-priv.h"
+
+#define PSIL_PDMA_XY_TR(x)					\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_PDMA_XY,		\
+			.mapped_channel_id = -1,		\
+			.default_flow_id = -1,			\
+		},						\
+	}
+
+#define PSIL_PDMA_XY_PKT(x)					\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_PDMA_XY,		\
+			.mapped_channel_id = -1,		\
+			.default_flow_id = -1,			\
+			.pkt_mode = 1,				\
+		},						\
+	}
+
+#define PSIL_ETHERNET(x, ch, flow_base, flow_cnt)		\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_NATIVE,		\
+			.pkt_mode = 1,				\
+			.needs_epib = 1,			\
+			.psd_size = 16,				\
+			.mapped_channel_id = ch,		\
+			.flow_start = flow_base,		\
+			.flow_num = flow_cnt,			\
+			.default_flow_id = flow_base,		\
+		},						\
+	}
+
+#define PSIL_SAUL(x, ch, flow_base, flow_cnt, default_flow, tx)	\
+	{							\
+		.thread_id = x,					\
+		.ep_config = {					\
+			.ep_type = PSIL_EP_NATIVE,		\
+			.pkt_mode = 1,				\
+			.needs_epib = 1,			\
+			.psd_size = 64,				\
+			.mapped_channel_id = ch,		\
+			.flow_start = flow_base,		\
+			.flow_num = flow_cnt,			\
+			.default_flow_id = default_flow,	\
+			.notdpkt = tx,				\
+		},						\
+	}
+
+#define PSIL_PDMA_MCASP(x)				\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_PDMA_XY,	\
+			.pdma_acc32 = 1,		\
+			.pdma_burst = 1,		\
+		},					\
+	}
+
+#define PSIL_CSI2RX(x)					\
+	{						\
+		.thread_id = x,				\
+		.ep_config = {				\
+			.ep_type = PSIL_EP_NATIVE,	\
+		},					\
+	}
+
+/* PSI-L source thread IDs, used for RX (DMA_DEV_TO_MEM) */
+static struct psil_ep am62p_src_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0x7504, 20, 35, 8, 35, 0),
+	PSIL_SAUL(0x7505, 21, 35, 8, 36, 0),
+	PSIL_SAUL(0x7506, 22, 43, 8, 43, 0),
+	PSIL_SAUL(0x7507, 23, 43, 8, 44, 0),
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0x4300),
+	PSIL_PDMA_XY_PKT(0x4301),
+	PSIL_PDMA_XY_PKT(0x4302),
+	PSIL_PDMA_XY_PKT(0x4303),
+	PSIL_PDMA_XY_PKT(0x4304),
+	PSIL_PDMA_XY_PKT(0x4305),
+	PSIL_PDMA_XY_PKT(0x4306),
+	PSIL_PDMA_XY_PKT(0x4307),
+	PSIL_PDMA_XY_PKT(0x4308),
+	PSIL_PDMA_XY_PKT(0x4309),
+	PSIL_PDMA_XY_PKT(0x430a),
+	PSIL_PDMA_XY_PKT(0x430b),
+	/* PDMA_MAIN1 - UART0-6 */
+	PSIL_PDMA_XY_PKT(0x4400),
+	PSIL_PDMA_XY_PKT(0x4401),
+	PSIL_PDMA_XY_PKT(0x4402),
+	PSIL_PDMA_XY_PKT(0x4403),
+	PSIL_PDMA_XY_PKT(0x4404),
+	PSIL_PDMA_XY_PKT(0x4405),
+	PSIL_PDMA_XY_PKT(0x4406),
+	/* PDMA_MAIN2 - MCASP0-2 */
+	PSIL_PDMA_MCASP(0x4500),
+	PSIL_PDMA_MCASP(0x4501),
+	PSIL_PDMA_MCASP(0x4502),
+	/* CPSW3G */
+	PSIL_ETHERNET(0x4600, 19, 19, 16),
+	/* CSI2RX */
+	PSIL_CSI2RX(0x5000),
+	PSIL_CSI2RX(0x5001),
+	PSIL_CSI2RX(0x5002),
+	PSIL_CSI2RX(0x5003),
+	PSIL_CSI2RX(0x5004),
+	PSIL_CSI2RX(0x5005),
+	PSIL_CSI2RX(0x5006),
+	PSIL_CSI2RX(0x5007),
+	PSIL_CSI2RX(0x5008),
+	PSIL_CSI2RX(0x5009),
+	PSIL_CSI2RX(0x500a),
+	PSIL_CSI2RX(0x500b),
+	PSIL_CSI2RX(0x500c),
+	PSIL_CSI2RX(0x500d),
+	PSIL_CSI2RX(0x500e),
+	PSIL_CSI2RX(0x500f),
+	PSIL_CSI2RX(0x5010),
+	PSIL_CSI2RX(0x5011),
+	PSIL_CSI2RX(0x5012),
+	PSIL_CSI2RX(0x5013),
+	PSIL_CSI2RX(0x5014),
+	PSIL_CSI2RX(0x5015),
+	PSIL_CSI2RX(0x5016),
+	PSIL_CSI2RX(0x5017),
+	PSIL_CSI2RX(0x5018),
+	PSIL_CSI2RX(0x5019),
+	PSIL_CSI2RX(0x501a),
+	PSIL_CSI2RX(0x501b),
+	PSIL_CSI2RX(0x501c),
+	PSIL_CSI2RX(0x501d),
+	PSIL_CSI2RX(0x501e),
+	PSIL_CSI2RX(0x501f),
+	PSIL_CSI2RX(0x5000),
+	PSIL_CSI2RX(0x5001),
+	PSIL_CSI2RX(0x5002),
+	PSIL_CSI2RX(0x5003),
+	PSIL_CSI2RX(0x5004),
+	PSIL_CSI2RX(0x5005),
+	PSIL_CSI2RX(0x5006),
+	PSIL_CSI2RX(0x5007),
+	PSIL_CSI2RX(0x5008),
+	PSIL_CSI2RX(0x5009),
+	PSIL_CSI2RX(0x500a),
+	PSIL_CSI2RX(0x500b),
+	PSIL_CSI2RX(0x500c),
+	PSIL_CSI2RX(0x500d),
+	PSIL_CSI2RX(0x500e),
+	PSIL_CSI2RX(0x500f),
+	PSIL_CSI2RX(0x5010),
+	PSIL_CSI2RX(0x5011),
+	PSIL_CSI2RX(0x5012),
+	PSIL_CSI2RX(0x5013),
+	PSIL_CSI2RX(0x5014),
+	PSIL_CSI2RX(0x5015),
+	PSIL_CSI2RX(0x5016),
+	PSIL_CSI2RX(0x5017),
+	PSIL_CSI2RX(0x5018),
+	PSIL_CSI2RX(0x5019),
+	PSIL_CSI2RX(0x501a),
+	PSIL_CSI2RX(0x501b),
+	PSIL_CSI2RX(0x501c),
+	PSIL_CSI2RX(0x501d),
+	PSIL_CSI2RX(0x501e),
+	PSIL_CSI2RX(0x501f),
+	/* CSIRX 1-3 (only for J722S) */
+	PSIL_CSI2RX(0x5100),
+	PSIL_CSI2RX(0x5101),
+	PSIL_CSI2RX(0x5102),
+	PSIL_CSI2RX(0x5103),
+	PSIL_CSI2RX(0x5104),
+	PSIL_CSI2RX(0x5105),
+	PSIL_CSI2RX(0x5106),
+	PSIL_CSI2RX(0x5107),
+	PSIL_CSI2RX(0x5108),
+	PSIL_CSI2RX(0x5109),
+	PSIL_CSI2RX(0x510a),
+	PSIL_CSI2RX(0x510b),
+	PSIL_CSI2RX(0x510c),
+	PSIL_CSI2RX(0x510d),
+	PSIL_CSI2RX(0x510e),
+	PSIL_CSI2RX(0x510f),
+	PSIL_CSI2RX(0x5110),
+	PSIL_CSI2RX(0x5111),
+	PSIL_CSI2RX(0x5112),
+	PSIL_CSI2RX(0x5113),
+	PSIL_CSI2RX(0x5114),
+	PSIL_CSI2RX(0x5115),
+	PSIL_CSI2RX(0x5116),
+	PSIL_CSI2RX(0x5117),
+	PSIL_CSI2RX(0x5118),
+	PSIL_CSI2RX(0x5119),
+	PSIL_CSI2RX(0x511a),
+	PSIL_CSI2RX(0x511b),
+	PSIL_CSI2RX(0x511c),
+	PSIL_CSI2RX(0x511d),
+	PSIL_CSI2RX(0x511e),
+	PSIL_CSI2RX(0x511f),
+	PSIL_CSI2RX(0x5200),
+	PSIL_CSI2RX(0x5201),
+	PSIL_CSI2RX(0x5202),
+	PSIL_CSI2RX(0x5203),
+	PSIL_CSI2RX(0x5204),
+	PSIL_CSI2RX(0x5205),
+	PSIL_CSI2RX(0x5206),
+	PSIL_CSI2RX(0x5207),
+	PSIL_CSI2RX(0x5208),
+	PSIL_CSI2RX(0x5209),
+	PSIL_CSI2RX(0x520a),
+	PSIL_CSI2RX(0x520b),
+	PSIL_CSI2RX(0x520c),
+	PSIL_CSI2RX(0x520d),
+	PSIL_CSI2RX(0x520e),
+	PSIL_CSI2RX(0x520f),
+	PSIL_CSI2RX(0x5210),
+	PSIL_CSI2RX(0x5211),
+	PSIL_CSI2RX(0x5212),
+	PSIL_CSI2RX(0x5213),
+	PSIL_CSI2RX(0x5214),
+	PSIL_CSI2RX(0x5215),
+	PSIL_CSI2RX(0x5216),
+	PSIL_CSI2RX(0x5217),
+	PSIL_CSI2RX(0x5218),
+	PSIL_CSI2RX(0x5219),
+	PSIL_CSI2RX(0x521a),
+	PSIL_CSI2RX(0x521b),
+	PSIL_CSI2RX(0x521c),
+	PSIL_CSI2RX(0x521d),
+	PSIL_CSI2RX(0x521e),
+	PSIL_CSI2RX(0x521f),
+	PSIL_CSI2RX(0x5300),
+	PSIL_CSI2RX(0x5301),
+	PSIL_CSI2RX(0x5302),
+	PSIL_CSI2RX(0x5303),
+	PSIL_CSI2RX(0x5304),
+	PSIL_CSI2RX(0x5305),
+	PSIL_CSI2RX(0x5306),
+	PSIL_CSI2RX(0x5307),
+	PSIL_CSI2RX(0x5308),
+	PSIL_CSI2RX(0x5309),
+	PSIL_CSI2RX(0x530a),
+	PSIL_CSI2RX(0x530b),
+	PSIL_CSI2RX(0x530c),
+	PSIL_CSI2RX(0x530d),
+	PSIL_CSI2RX(0x530e),
+	PSIL_CSI2RX(0x530f),
+	PSIL_CSI2RX(0x5310),
+	PSIL_CSI2RX(0x5311),
+	PSIL_CSI2RX(0x5312),
+	PSIL_CSI2RX(0x5313),
+	PSIL_CSI2RX(0x5314),
+	PSIL_CSI2RX(0x5315),
+	PSIL_CSI2RX(0x5316),
+	PSIL_CSI2RX(0x5317),
+	PSIL_CSI2RX(0x5318),
+	PSIL_CSI2RX(0x5319),
+	PSIL_CSI2RX(0x531a),
+	PSIL_CSI2RX(0x531b),
+	PSIL_CSI2RX(0x531c),
+	PSIL_CSI2RX(0x531d),
+	PSIL_CSI2RX(0x531e),
+	PSIL_CSI2RX(0x531f),
+};
+
+/* PSI-L destination thread IDs, used for TX (DMA_MEM_TO_DEV) */
+static struct psil_ep am62p_dst_ep_map[] = {
+	/* SAUL */
+	PSIL_SAUL(0xf500, 27, 83, 8, 83, 1),
+	PSIL_SAUL(0xf501, 28, 91, 8, 91, 1),
+	/* PDMA_MAIN0 - SPI0-2 */
+	PSIL_PDMA_XY_PKT(0xc300),
+	PSIL_PDMA_XY_PKT(0xc301),
+	PSIL_PDMA_XY_PKT(0xc302),
+	PSIL_PDMA_XY_PKT(0xc303),
+	PSIL_PDMA_XY_PKT(0xc304),
+	PSIL_PDMA_XY_PKT(0xc305),
+	PSIL_PDMA_XY_PKT(0xc306),
+	PSIL_PDMA_XY_PKT(0xc307),
+	PSIL_PDMA_XY_PKT(0xc308),
+	PSIL_PDMA_XY_PKT(0xc309),
+	PSIL_PDMA_XY_PKT(0xc30a),
+	PSIL_PDMA_XY_PKT(0xc30b),
+	/* PDMA_MAIN1 - UART0-6 */
+	PSIL_PDMA_XY_PKT(0xc400),
+	PSIL_PDMA_XY_PKT(0xc401),
+	PSIL_PDMA_XY_PKT(0xc402),
+	PSIL_PDMA_XY_PKT(0xc403),
+	PSIL_PDMA_XY_PKT(0xc404),
+	PSIL_PDMA_XY_PKT(0xc405),
+	PSIL_PDMA_XY_PKT(0xc406),
+	/* PDMA_MAIN2 - MCASP0-2 */
+	PSIL_PDMA_MCASP(0xc500),
+	PSIL_PDMA_MCASP(0xc501),
+	PSIL_PDMA_MCASP(0xc502),
+	/* CPSW3G */
+	PSIL_ETHERNET(0xc600, 19, 19, 8),
+	PSIL_ETHERNET(0xc601, 20, 27, 8),
+	PSIL_ETHERNET(0xc602, 21, 35, 8),
+	PSIL_ETHERNET(0xc603, 22, 43, 8),
+	PSIL_ETHERNET(0xc604, 23, 51, 8),
+	PSIL_ETHERNET(0xc605, 24, 59, 8),
+	PSIL_ETHERNET(0xc606, 25, 67, 8),
+	PSIL_ETHERNET(0xc607, 26, 75, 8),
+};
+
+struct psil_ep_map am62p_ep_map = {
+	.name = "am62p",
+	.src = am62p_src_ep_map,
+	.src_count = ARRAY_SIZE(am62p_src_ep_map),
+	.dst = am62p_dst_ep_map,
+	.dst_count = ARRAY_SIZE(am62p_dst_ep_map),
+};

drivers/dma/ti/k3-psil-priv.h

@@ -45,5 +45,6 @@ extern struct psil_ep_map j721s2_ep_map;
 extern struct psil_ep_map am62_ep_map;
 extern struct psil_ep_map am62a_ep_map;
 extern struct psil_ep_map j784s4_ep_map;
+extern struct psil_ep_map am62p_ep_map;
 
 #endif /* K3_PSIL_PRIV_H_ */

drivers/dma/ti/k3-psil.c

@@ -26,6 +26,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "AM62X", .data = &am62_ep_map },
 	{ .family = "AM62AX", .data = &am62a_ep_map },
 	{ .family = "J784S4", .data = &j784s4_ep_map },
+	{ .family = "AM62PX", .data = &am62p_ep_map },
+	{ .family = "J722S", .data = &am62p_ep_map },
 	{ /* sentinel */ }
 };
 

drivers/dma/ti/k3-udma.c

@@ -4441,6 +4441,8 @@ static const struct soc_device_attribute k3_soc_devices[] = {
 	{ .family = "AM62X", .data = &am64_soc_data },
 	{ .family = "AM62AX", .data = &am64_soc_data },
 	{ .family = "J784S4", .data = &j721e_soc_data },
+	{ .family = "AM62PX", .data = &am64_soc_data },
+	{ .family = "J722S", .data = &am64_soc_data },
 	{ /* sentinel */ }
 };
 

drivers/dma/uniphier-mdmac.c

@@ -453,7 +453,7 @@ static int uniphier_mdmac_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int uniphier_mdmac_remove(struct platform_device *pdev)
+static void uniphier_mdmac_remove(struct platform_device *pdev)
 {
 	struct uniphier_mdmac_device *mdev = platform_get_drvdata(pdev);
 	struct dma_chan *chan;
@@ -468,16 +468,21 @@ static int uniphier_mdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &mdev->ddev.channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *mdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		uniphier_mdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&mdev->ddev);
 	clk_disable_unprepare(mdev->clk);
-
-	return 0;
 }
 
 static const struct of_device_id uniphier_mdmac_match[] = {
@@ -488,7 +493,7 @@ MODULE_DEVICE_TABLE(of, uniphier_mdmac_match);
 
 static struct platform_driver uniphier_mdmac_driver = {
 	.probe = uniphier_mdmac_probe,
-	.remove = uniphier_mdmac_remove,
+	.remove_new = uniphier_mdmac_remove,
 	.driver = {
 		.name = "uniphier-mio-dmac",
 		.of_match_table = uniphier_mdmac_match,

drivers/dma/uniphier-xdmac.c

@@ -563,7 +563,7 @@ static int uniphier_xdmac_probe(struct platform_device *pdev)
 	return ret;
 }
 
-static int uniphier_xdmac_remove(struct platform_device *pdev)
+static void uniphier_xdmac_remove(struct platform_device *pdev)
 {
 	struct uniphier_xdmac_device *xdev = platform_get_drvdata(pdev);
 	struct dma_device *ddev = &xdev->ddev;
@@ -579,15 +579,20 @@ static int uniphier_xdmac_remove(struct platform_device *pdev)
 	 */
 	list_for_each_entry(chan, &ddev->channels, device_node) {
 		ret = dmaengine_terminate_sync(chan);
-		if (ret)
-			return ret;
+		if (ret) {
+			/*
+			 * This results in resource leakage and maybe also
+			 * use-after-free errors as e.g. *xdev is kfreed.
+			 */
+			dev_alert(&pdev->dev, "Failed to terminate channel %d (%pe)\n",
+				  chan->chan_id, ERR_PTR(ret));
+			return;
+		}
 		uniphier_xdmac_free_chan_resources(chan);
 	}
 
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(ddev);
-
-	return 0;
 }
 
 static const struct of_device_id uniphier_xdmac_match[] = {
@@ -598,7 +603,7 @@ MODULE_DEVICE_TABLE(of, uniphier_xdmac_match);
 
 static struct platform_driver uniphier_xdmac_driver = {
 	.probe = uniphier_xdmac_probe,
-	.remove = uniphier_xdmac_remove,
+	.remove_new = uniphier_xdmac_remove,
 	.driver = {
 		.name = "uniphier-xdmac",
 		.of_match_table = uniphier_xdmac_match,

drivers/dma/xilinx/xdma-regs.h

@@ -64,9 +64,10 @@ struct xdma_hw_desc {
 	__le64		next_desc;
 };
 
-#define XDMA_DESC_SIZE		sizeof(struct xdma_hw_desc)
-#define XDMA_DESC_BLOCK_SIZE	(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
-#define XDMA_DESC_BLOCK_ALIGN	4096
+#define XDMA_DESC_SIZE			sizeof(struct xdma_hw_desc)
+#define XDMA_DESC_BLOCK_SIZE		(XDMA_DESC_SIZE * XDMA_DESC_ADJACENT)
+#define XDMA_DESC_BLOCK_ALIGN		32
+#define XDMA_DESC_BLOCK_BOUNDARY	4096
 
 /*
  * Channel registers
@@ -76,6 +77,7 @@ struct xdma_hw_desc {
 #define XDMA_CHAN_CONTROL_W1S		0x8
 #define XDMA_CHAN_CONTROL_W1C		0xc
 #define XDMA_CHAN_STATUS		0x40
+#define XDMA_CHAN_STATUS_RC		0x44
 #define XDMA_CHAN_COMPLETED_DESC	0x48
 #define XDMA_CHAN_ALIGNMENTS		0x4c
 #define XDMA_CHAN_INTR_ENABLE		0x90
@@ -101,6 +103,7 @@ struct xdma_hw_desc {
 #define CHAN_CTRL_IE_MAGIC_STOPPED		BIT(4)
 #define CHAN_CTRL_IE_IDLE_STOPPED		BIT(6)
 #define CHAN_CTRL_IE_READ_ERROR			GENMASK(13, 9)
+#define CHAN_CTRL_IE_WRITE_ERROR		GENMASK(18, 14)
 #define CHAN_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
 #define CHAN_CTRL_NON_INCR_ADDR			BIT(25)
 #define CHAN_CTRL_POLL_MODE_WB			BIT(26)
@@ -111,8 +114,17 @@ struct xdma_hw_desc {
 			 CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |		\
 			 CHAN_CTRL_IE_MAGIC_STOPPED |			\
 			 CHAN_CTRL_IE_READ_ERROR |			\
+			 CHAN_CTRL_IE_WRITE_ERROR |			\
 			 CHAN_CTRL_IE_DESC_ERROR)
 
+#define XDMA_CHAN_STATUS_MASK CHAN_CTRL_START
+
+#define XDMA_CHAN_ERROR_MASK (CHAN_CTRL_IE_DESC_ALIGN_MISMATCH |	\
+			      CHAN_CTRL_IE_MAGIC_STOPPED |		\
+			      CHAN_CTRL_IE_READ_ERROR |			\
+			      CHAN_CTRL_IE_WRITE_ERROR |		\
+			      CHAN_CTRL_IE_DESC_ERROR)
+
 /* bits of the channel interrupt enable mask */
 #define CHAN_IM_DESC_ERROR			BIT(19)
 #define CHAN_IM_READ_ERROR			BIT(9)
@@ -134,18 +146,6 @@ struct xdma_hw_desc {
 #define XDMA_SGDMA_DESC_ADJ	0x4088
 #define XDMA_SGDMA_DESC_CREDIT	0x408c
 
-/* bits of the SG DMA control register */
-#define XDMA_CTRL_RUN_STOP			BIT(0)
-#define XDMA_CTRL_IE_DESC_STOPPED		BIT(1)
-#define XDMA_CTRL_IE_DESC_COMPLETED		BIT(2)
-#define XDMA_CTRL_IE_DESC_ALIGN_MISMATCH	BIT(3)
-#define XDMA_CTRL_IE_MAGIC_STOPPED		BIT(4)
-#define XDMA_CTRL_IE_IDLE_STOPPED		BIT(6)
-#define XDMA_CTRL_IE_READ_ERROR			GENMASK(13, 9)
-#define XDMA_CTRL_IE_DESC_ERROR			GENMASK(23, 19)
-#define XDMA_CTRL_NON_INCR_ADDR			BIT(25)
-#define XDMA_CTRL_POLL_MODE_WB			BIT(26)
-
 /*
  * interrupt registers
  */

drivers/dma/xilinx/xilinx_dpdma.c

@@ -309,7 +309,7 @@ static ssize_t xilinx_dpdma_debugfs_desc_done_irq_read(char *buf)
 
 	out_str_len = strlen(XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR);
 	out_str_len = min_t(size_t, XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE,
-			    out_str_len);
+			    out_str_len + 1);
 	snprintf(buf, out_str_len, "%d",
 		 dpdma_debugfs.xilinx_dpdma_irq_done_count);
 

include/dt-bindings/dma/fsl-edma.h

+/* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
+
+#ifndef _FSL_EDMA_DT_BINDING_H_
+#define _FSL_EDMA_DT_BINDING_H_
+
+/* Receive Channel */
+#define FSL_EDMA_RX		0x1
+
+/* iMX8 audio remote DMA */
+#define FSL_EDMA_REMOTE		0x2
+
+/* FIFO is continue memory region */
+#define FSL_EDMA_MULTI_FIFO	0x4
+
+/* Channel need stick to even channel */
+#define FSL_EDMA_EVEN_CH	0x8
+
+/* Channel need stick to odd channel */
+#define FSL_EDMA_ODD_CH		0x10
+
+#endif