Merge tag 'dmaengine-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine

Pull dmaengine updates from Vinod Koul:
 "New hardware support:
   - Allwinner H616 dma support
   - Renesas r8a779h0 dma controller support
   - TI CSI2RX dma support

  Updates:
   - Freescale edma driver updates for TCD64csupport for i.MX95
   - constify of pointers and args
   - Yaml conversion for MediaTek High-Speed controller binding
   - TI k3 udma support for TX/RX DMA channels for thread IDs:

* tag 'dmaengine-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vkoul/dmaengine: (25 commits)
  dmaengine: of: constify of_phandle_args in of_dma_find_controller()
  dmaengine: pl08x: constify pointer to char in filter function
  MAINTAINERS: change in AMD ptdma maintainer
  MAINTAINERS: adjust file entry in MEDIATEK DMA DRIVER
  dmaengine: idxd: constify the struct device_type usage
  dt-bindings: renesas,rcar-dmac: Add r8a779h0 support
  dt-bindings: dma: convert MediaTek High-Speed controller to the json-schema
  dmaengine: idxd: make dsa_bus_type const
  dmaengine: fsl-edma: integrate TCD64 support for i.MX95
  dt-bindings: fsl-dma: fsl-edma: add fsl,imx95-edma5 compatible string
  dmaengine: mcf-edma: utilize edma_write_tcdreg() macro for TCD Access
  dmaengine: fsl-edma: add address for channel mux register in fsl_edma_chan
  dmaengine: fsl-edma: fix spare build warning
  dmaengine: fsl-edma: involve help macro fsl_edma_set(get)_tcd()
  dt-bindings: mmp-dma: convert to YAML
  dmaengine: ti: k3-psil-j721s2: Add entry for CSI2RX
  dmaengine: ti: k3-udma-glue: Add function to request RX chan for thread ID
  dmaengine: ti: k3-udma-glue: Add function to request TX chan for thread ID
  dmaengine: ti: k3-udma-glue: Update name for remote RX channel device
  dmaengine: ti: k3-udma-glue: Add function to parse channel by ID
  ...

Documentation/devicetree/bindings/dma/allwinner,sun50i-a64-dma.yaml

@@ -28,6 +28,9 @@ properties:
       - items:
           - const: allwinner,sun8i-r40-dma
           - const: allwinner,sun50i-a64-dma
+      - items:
+          - const: allwinner,sun50i-h616-dma
+          - const: allwinner,sun50i-a100-dma
 
   reg:
     maxItems: 1
@@ -59,10 +62,11 @@ required:
 if:
   properties:
     compatible:
-      enum:
-        - allwinner,sun20i-d1-dma
-        - allwinner,sun50i-a100-dma
-        - allwinner,sun50i-h6-dma
+      contains:
+        enum:
+          - allwinner,sun20i-d1-dma
+          - allwinner,sun50i-a100-dma
+          - allwinner,sun50i-h6-dma
 
 then:
   properties:

Documentation/devicetree/bindings/dma/fsl,edma.yaml

@@ -25,6 +25,7 @@ properties:
           - fsl,imx8qm-edma
           - fsl,imx93-edma3
           - fsl,imx93-edma4
+          - fsl,imx95-edma5
       - items:
           - const: fsl,ls1028a-edma
           - const: fsl,vf610-edma
@@ -83,6 +84,7 @@ allOf:
               - fsl,imx8qm-edma
               - fsl,imx93-edma3
               - fsl,imx93-edma4
+              - fsl,imx95-edma5
     then:
       properties:
         "#dma-cells":

Documentation/devicetree/bindings/dma/marvell,mmp-dma.yaml

+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/marvell,mmp-dma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell MMP DMA controller
+
+maintainers:
+  - Duje Mihanović <duje.mihanovic@skole.hr>
+
+description:
+  Marvell MMP SoCs may have two types of DMA controllers, peripheral and audio.
+
+properties:
+  compatible:
+    enum:
+      - marvell,pdma-1.0
+      - marvell,adma-1.0
+      - marvell,pxa910-squ
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    description:
+      Interrupt lines for the controller, may be shared or one per DMA channel
+    minItems: 1
+
+  asram:
+    description:
+      A phandle to the SRAM pool
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+  '#dma-channels':
+    deprecated: true
+
+  '#dma-requests':
+    deprecated: true
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - '#dma-cells'
+
+allOf:
+  - $ref: dma-controller.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - marvell,pdma-1.0
+    then:
+      properties:
+        asram: false
+    else:
+      required:
+        - asram
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    dma-controller@d4000000 {
+        compatible = "marvell,pdma-1.0";
+        reg = <0xd4000000 0x10000>;
+        interrupts = <47>;
+        #dma-cells = <2>;
+        dma-channels = <16>;
+    };

Documentation/devicetree/bindings/dma/mediatek,mt7622-hsdma.yaml

+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/dma/mediatek,mt7622-hsdma.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: MediaTek High-Speed DMA Controller
+
+maintainers:
+  - Sean Wang <sean.wang@mediatek.com>
+
+allOf:
+  - $ref: dma-controller.yaml#
+
+properties:
+  compatible:
+    enum:
+      - mediatek,mt7622-hsdma
+      - mediatek,mt7623-hsdma
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    const: hsdma
+
+  power-domains:
+    maxItems: 1
+
+  "#dma-cells":
+    description: Channel number
+    const: 1
+
+required:
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - power-domains
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/mt2701-clk.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/mt2701-power.h>
+
+    dma-controller@1b007000 {
+        compatible = "mediatek,mt7623-hsdma";
+        reg = <0x1b007000 0x1000>;
+        interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_LOW>;
+        clocks = <&ethsys CLK_ETHSYS_HSDMA>;
+        clock-names = "hsdma";
+        power-domains = <&scpsys MT2701_POWER_DOMAIN_ETH>;
+        #dma-cells = <1>;
+    };

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

-* MARVELL MMP DMA controller
-
-Marvell Peripheral DMA Controller
-Used platforms: pxa688, pxa910, pxa3xx, etc
-
-Required properties:
-- compatible: Should be "marvell,pdma-1.0"
-- reg: Should contain DMA registers location and length.
-- interrupts: Either contain all of the per-channel DMA interrupts
-		or one irq for pdma device
-
-Optional properties:
-- dma-channels: Number of DMA channels supported by the controller (defaults
-  to 32 when not specified)
-- #dma-channels: deprecated
-- dma-requests: Number of DMA requestor lines supported by the controller
-  (defaults to 32 when not specified)
-- #dma-requests: deprecated
-
-"marvell,pdma-1.0"
-Used platforms: pxa25x, pxa27x, pxa3xx, pxa93x, pxa168, pxa910, pxa688.
-
-Examples:
-
-/*
- * Each channel has specific irq
- * ICU parse out irq channel from ICU register,
- * while DMA controller may not able to distinguish the irq channel
- * Using this method, interrupt-parent is required as demuxer
- * For example, pxa688 icu register 0x128, bit 0~15 is PDMA channel irq,
- * 18~21 is ADMA irq
- */
-pdma: dma-controller@d4000000 {
-	      compatible = "marvell,pdma-1.0";
-	      reg = <0xd4000000 0x10000>;
-	      interrupts = <0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15>;
-	      interrupt-parent = <&intcmux32>;
-	      dma-channels = <16>;
-      };
-
-/*
- * One irq for all channels
- * Dmaengine driver (DMA controller) distinguish irq channel via
- * parsing internal register
- */
-pdma: dma-controller@d4000000 {
-	      compatible = "marvell,pdma-1.0";
-	      reg = <0xd4000000 0x10000>;
-	      interrupts = <47>;
-	      dma-channels = <16>;
-      };
-
-
-Marvell Two Channel DMA Controller used specifically for audio
-Used platforms: pxa688, pxa910
-
-Required properties:
-- compatible: Should be "marvell,adma-1.0" or "marvell,pxa910-squ"
-- reg: Should contain DMA registers location and length.
-- interrupts: Either contain all of the per-channel DMA interrupts
-		or one irq for dma device
-
-"marvell,adma-1.0" used on pxa688
-"marvell,pxa910-squ" used on pxa910
-
-Examples:
-
-/* each channel has specific irq */
-adma0: dma-controller@d42a0800 {
-	      compatible = "marvell,adma-1.0";
-	      reg = <0xd42a0800 0x100>;
-	      interrupts = <18 19>;
-	      interrupt-parent = <&intcmux32>;
-      };
-
-/* One irq for all channels */
-squ: dma-controller@d42a0800 {
-	      compatible = "marvell,pxa910-squ";
-	      reg = <0xd42a0800 0x100>;
-	      interrupts = <46>;
-      };

Documentation/devicetree/bindings/dma/mtk-hsdma.txt

-MediaTek High-Speed DMA Controller
-==================================
-
-This device follows the generic DMA bindings defined in dma/dma.txt.
-
-Required properties:
-
-- compatible:	Must be one of
-		  "mediatek,mt7622-hsdma": for MT7622 SoC
-		  "mediatek,mt7623-hsdma": for MT7623 SoC
-- reg:		Should contain the register's base address and length.
-- interrupts:	Should contain a reference to the interrupt used by this
-		device.
-- clocks:	Should be the clock specifiers corresponding to the entry in
-		clock-names property.
-- clock-names:	Should contain "hsdma" entries.
-- power-domains: Phandle to the power domain that the device is part of
-- #dma-cells: 	The length of the DMA specifier, must be <1>. This one cell
-		in dmas property of a client device represents the channel
-		number.
-Example:
-
-        hsdma: dma-controller@1b007000 {
-		compatible = "mediatek,mt7623-hsdma";
-		reg = <0 0x1b007000 0 0x1000>;
-		interrupts = <GIC_SPI 98 IRQ_TYPE_LEVEL_LOW>;
-		clocks = <&ethsys CLK_ETHSYS_HSDMA>;
-		clock-names = "hsdma";
-		power-domains = <&scpsys MT2701_POWER_DOMAIN_ETH>;
-		#dma-cells = <1>;
-	};
-
-DMA clients must use the format described in dma/dma.txt file.

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

@@ -46,6 +46,7 @@ properties:
               - renesas,dmac-r8a779a0     # R-Car V3U
               - renesas,dmac-r8a779f0     # R-Car S4-8
               - renesas,dmac-r8a779g0     # R-Car V4H
+              - renesas,dmac-r8a779h0     # R-Car V4M
           - const: renesas,rcar-gen4-dmac # R-Car Gen4
 
   reg: true

MAINTAINERS

@@ -1064,7 +1064,7 @@ F:	include/linux/amd-pstate.h
 F:	tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py
 
 AMD PTDMA DRIVER
-M:	Sanjay R Mehta <sanju.mehta@amd.com>
+M:	Basavaraj Natikar <Basavaraj.Natikar@amd.com>
 L:	dmaengine@vger.kernel.org
 S:	Maintained
 F:	drivers/dma/ptdma/
@@ -13719,7 +13719,7 @@ L:	dmaengine@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-mediatek@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-F:	Documentation/devicetree/bindings/dma/mtk-*
+F:	Documentation/devicetree/bindings/dma/mediatek,*
 F:	drivers/dma/mediatek/
 
 MEDIATEK ETHERNET DRIVER

drivers/dma/Kconfig

@@ -643,16 +643,16 @@ config TEGRA20_APB_DMA
 
 config TEGRA210_ADMA
 	tristate "NVIDIA Tegra210 ADMA support"
-	depends on (ARCH_TEGRA_210_SOC || COMPILE_TEST)
+	depends on (ARCH_TEGRA || COMPILE_TEST)
 	select DMA_ENGINE
 	select DMA_VIRTUAL_CHANNELS
 	help
-	  Support for the NVIDIA Tegra210 ADMA controller driver. The
-	  DMA controller has multiple DMA channels and is used to service
-	  various audio clients in the Tegra210 audio processing engine
-	  (APE). This DMA controller transfers data from memory to
-	  peripheral and vice versa. It does not support memory to
-	  memory data transfer.
+	  Support for the NVIDIA Tegra210/Tegra186/Tegra194/Tegra234 ADMA
+	  controller driver. The DMA controller has multiple DMA channels
+	  and is used to service various audio clients in the Tegra210
+	  audio processing engine (APE). This DMA controller transfers
+	  data from memory to peripheral and vice versa. It does not
+	  support memory to memory data transfer.
 
 config TIMB_DMA
 	tristate "Timberdale FPGA DMA support"

drivers/dma/amba-pl08x.c

@@ -2239,7 +2239,7 @@ static int pl08x_resume(struct dma_chan *chan)
 bool pl08x_filter_id(struct dma_chan *chan, void *chan_id)
 {
 	struct pl08x_dma_chan *plchan;
-	char *name = chan_id;
+	const char *name = chan_id;
 
 	/* Reject channels for devices not bound to this driver */
 	if (chan->device->dev->driver != &pl08x_amba_driver.drv)

drivers/dma/bestcomm/sram.c

@@ -90,13 +90,8 @@ int bcom_sram_init(struct device_node *sram_node, char *owner)
 	bcom_sram->rh = rh_create(4);
 
 	/* Attach the free zones */
-#if 0
-	/* Currently disabled ... for future use only */
-	reg_addr_p = of_get_property(sram_node, "available", &psize);
-#else
 	regaddr_p = NULL;
 	psize = 0;
-#endif
 
 	if (!regaddr_p || !psize) {
 		/* Attach the whole zone */

drivers/dma/fsl-edma-common.c

@@ -97,8 +97,8 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan)
 		 * ch_mux: With the exception of 0, attempts to write a value
 		 * already in use will be forced to 0.
 		 */
-		if (!edma_readl_chreg(fsl_chan, ch_mux))
-			edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux);
+		if (!edma_readl(fsl_chan->edma, fsl_chan->mux_addr))
+			edma_writel(fsl_chan->edma, fsl_chan->srcid, fsl_chan->mux_addr);
 	}
 
 	val = edma_readl_chreg(fsl_chan, ch_csr);
@@ -134,7 +134,7 @@ static void fsl_edma3_disable_request(struct fsl_edma_chan *fsl_chan)
 	flags = fsl_edma_drvflags(fsl_chan);
 
 	if (flags & FSL_EDMA_DRV_HAS_CHMUX)
-		edma_writel_chreg(fsl_chan, 0, ch_mux);
+		edma_writel(fsl_chan->edma, 0, fsl_chan->mux_addr);
 
 	val &= ~EDMA_V3_CH_CSR_ERQ;
 	edma_writel_chreg(fsl_chan, val, ch_csr);
@@ -351,39 +351,45 @@ static size_t fsl_edma_desc_residue(struct fsl_edma_chan *fsl_chan,
 {
 	struct fsl_edma_desc *edesc = fsl_chan->edesc;
 	enum dma_transfer_direction dir = edesc->dirn;
-	dma_addr_t cur_addr, dma_addr;
+	dma_addr_t cur_addr, dma_addr, old_addr;
 	size_t len, size;
 	u32 nbytes = 0;
 	int i;
 
 	/* calculate the total size in this desc */
 	for (len = i = 0; i < fsl_chan->edesc->n_tcds; i++) {
-		nbytes = le32_to_cpu(edesc->tcd[i].vtcd->nbytes);
+		nbytes = fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, nbytes);
 		if (nbytes & (EDMA_V3_TCD_NBYTES_DMLOE | EDMA_V3_TCD_NBYTES_SMLOE))
 			nbytes = EDMA_V3_TCD_NBYTES_MLOFF_NBYTES(nbytes);
-		len += nbytes * le16_to_cpu(edesc->tcd[i].vtcd->biter);
+		len += nbytes * fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, biter);
 	}
 
 	if (!in_progress)
 		return len;
 
-	if (dir == DMA_MEM_TO_DEV)
-		cur_addr = edma_read_tcdreg(fsl_chan, saddr);
-	else
-		cur_addr = edma_read_tcdreg(fsl_chan, daddr);
+	/* 64bit read is not atomic, need read retry when high 32bit changed */
+	do {
+		if (dir == DMA_MEM_TO_DEV) {
+			old_addr = edma_read_tcdreg(fsl_chan, saddr);
+			cur_addr = edma_read_tcdreg(fsl_chan, saddr);
+		} else {
+			old_addr = edma_read_tcdreg(fsl_chan, daddr);
+			cur_addr = edma_read_tcdreg(fsl_chan, daddr);
+		}
+	} while (upper_32_bits(cur_addr) != upper_32_bits(old_addr));
 
 	/* figure out the finished and calculate the residue */
 	for (i = 0; i < fsl_chan->edesc->n_tcds; i++) {
-		nbytes = le32_to_cpu(edesc->tcd[i].vtcd->nbytes);
+		nbytes = fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, nbytes);
 		if (nbytes & (EDMA_V3_TCD_NBYTES_DMLOE | EDMA_V3_TCD_NBYTES_SMLOE))
 			nbytes = EDMA_V3_TCD_NBYTES_MLOFF_NBYTES(nbytes);
 
-		size = nbytes * le16_to_cpu(edesc->tcd[i].vtcd->biter);
+		size = nbytes * fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, biter);
 
 		if (dir == DMA_MEM_TO_DEV)
-			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->saddr);
+			dma_addr = fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, saddr);
 		else
-			dma_addr = le32_to_cpu(edesc->tcd[i].vtcd->daddr);
+			dma_addr = fsl_edma_get_tcd_to_cpu(fsl_chan, edesc->tcd[i].vtcd, daddr);
 
 		len -= size;
 		if (cur_addr >= dma_addr && cur_addr < dma_addr + size) {
@@ -426,8 +432,7 @@ enum dma_status fsl_edma_tx_status(struct dma_chan *chan,
 	return fsl_chan->status;
 }
 
-static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
-				  struct fsl_edma_hw_tcd *tcd)
+static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan, void *tcd)
 {
 	u16 csr = 0;
 
@@ -439,26 +444,26 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 	 */
 	edma_write_tcdreg(fsl_chan, 0, csr);
 
-	edma_write_tcdreg(fsl_chan, tcd->saddr, saddr);
-	edma_write_tcdreg(fsl_chan, tcd->daddr, daddr);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, saddr);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, daddr);
 
-	edma_write_tcdreg(fsl_chan, tcd->attr, attr);
-	edma_write_tcdreg(fsl_chan, tcd->soff, soff);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, attr);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, soff);
 
-	edma_write_tcdreg(fsl_chan, tcd->nbytes, nbytes);
-	edma_write_tcdreg(fsl_chan, tcd->slast, slast);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, nbytes);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, slast);
 
-	edma_write_tcdreg(fsl_chan, tcd->citer, citer);
-	edma_write_tcdreg(fsl_chan, tcd->biter, biter);
-	edma_write_tcdreg(fsl_chan, tcd->doff, doff);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, citer);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, biter);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, doff);
 
-	edma_write_tcdreg(fsl_chan, tcd->dlast_sga, dlast_sga);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, dlast_sga);
 
-	csr = le16_to_cpu(tcd->csr);
+	csr = fsl_edma_get_tcd_to_cpu(fsl_chan, tcd, csr);
 
 	if (fsl_chan->is_sw) {
 		csr |= EDMA_TCD_CSR_START;
-		tcd->csr = cpu_to_le16(csr);
+		fsl_edma_set_tcd_to_le(fsl_chan, tcd, csr, csr);
 	}
 
 	/*
@@ -473,14 +478,14 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 		edma_writel_chreg(fsl_chan, edma_readl_chreg(fsl_chan, ch_csr), ch_csr);
 
 
-	edma_write_tcdreg(fsl_chan, tcd->csr, csr);
+	edma_cp_tcd_to_reg(fsl_chan, tcd, csr);
 }
 
 static inline
 void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
-		       struct fsl_edma_hw_tcd *tcd, u32 src, u32 dst,
-		       u16 attr, u16 soff, u32 nbytes, u32 slast, u16 citer,
-		       u16 biter, u16 doff, u32 dlast_sga, bool major_int,
+		       struct fsl_edma_hw_tcd *tcd, dma_addr_t src, dma_addr_t dst,
+		       u16 attr, u16 soff, u32 nbytes, dma_addr_t slast, u16 citer,
+		       u16 biter, u16 doff, dma_addr_t dlast_sga, bool major_int,
 		       bool disable_req, bool enable_sg)
 {
 	struct dma_slave_config *cfg = &fsl_chan->cfg;
@@ -493,12 +498,12 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 	 * So we put the value in little endian in memory, waiting
 	 * for fsl_edma_set_tcd_regs doing the swap.
 	 */
-	tcd->saddr = cpu_to_le32(src);
-	tcd->daddr = cpu_to_le32(dst);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, src, saddr);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, dst, daddr);
 
-	tcd->attr = cpu_to_le16(attr);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, attr, attr);
 
-	tcd->soff = cpu_to_le16(soff);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, soff, soff);
 
 	if (fsl_chan->is_multi_fifo) {
 		/* set mloff to support multiple fifo */
@@ -515,15 +520,16 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 		}
 	}
 
-	tcd->nbytes = cpu_to_le32(nbytes);
-	tcd->slast = cpu_to_le32(slast);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, nbytes, nbytes);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, slast, slast);
+
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, EDMA_TCD_CITER_CITER(citer), citer);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, doff, doff);
 
-	tcd->citer = cpu_to_le16(EDMA_TCD_CITER_CITER(citer));
-	tcd->doff = cpu_to_le16(doff);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, dlast_sga, dlast_sga);
 
-	tcd->dlast_sga = cpu_to_le32(dlast_sga);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, EDMA_TCD_BITER_BITER(biter), biter);
 
-	tcd->biter = cpu_to_le16(EDMA_TCD_BITER_BITER(biter));
 	if (major_int)
 		csr |= EDMA_TCD_CSR_INT_MAJOR;
 
@@ -539,7 +545,7 @@ void fsl_edma_fill_tcd(struct fsl_edma_chan *fsl_chan,
 	if (fsl_chan->is_sw)
 		csr |= EDMA_TCD_CSR_START;
 
-	tcd->csr = cpu_to_le16(csr);
+	fsl_edma_set_tcd_to_le(fsl_chan, tcd, csr, csr);
 }
 
 static struct fsl_edma_desc *fsl_edma_alloc_desc(struct fsl_edma_chan *fsl_chan,
@@ -580,8 +586,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 	dma_addr_t dma_buf_next;
 	bool major_int = true;
 	int sg_len, i;
-	u32 src_addr, dst_addr, last_sg, nbytes;
+	dma_addr_t src_addr, dst_addr, last_sg;
 	u16 soff, doff, iter;
+	u32 nbytes;
 
 	if (!is_slave_direction(direction))
 		return NULL;
@@ -653,8 +660,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
 	struct fsl_edma_desc *fsl_desc;
 	struct scatterlist *sg;
-	u32 src_addr, dst_addr, last_sg, nbytes;
+	dma_addr_t src_addr, dst_addr, last_sg;
 	u16 soff, doff, iter;
+	u32 nbytes;
 	int i;
 
 	if (!is_slave_direction(direction))
@@ -803,7 +811,8 @@ int fsl_edma_alloc_chan_resources(struct dma_chan *chan)
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
 
 	fsl_chan->tcd_pool = dma_pool_create("tcd_pool", chan->device->dev,
-				sizeof(struct fsl_edma_hw_tcd),
+				fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_TCD64 ?
+				sizeof(struct fsl_edma_hw_tcd64) : sizeof(struct fsl_edma_hw_tcd),
 				32, 0);
 	return 0;
 }

drivers/dma/fsl-edma-common.h

@@ -88,6 +88,20 @@ struct fsl_edma_hw_tcd {
 	__le16	biter;
 };
 
+struct fsl_edma_hw_tcd64 {
+	__le64  saddr;
+	__le16  soff;
+	__le16  attr;
+	__le32  nbytes;
+	__le64  slast;
+	__le64  daddr;
+	__le64  dlast_sga;
+	__le16  doff;
+	__le16  citer;
+	__le16  csr;
+	__le16  biter;
+} __packed;
+
 struct fsl_edma3_ch_reg {
 	__le32	ch_csr;
 	__le32	ch_es;
@@ -97,7 +111,10 @@ struct fsl_edma3_ch_reg {
 	__le32	ch_mux;
 	__le32  ch_mattr; /* edma4, reserved for edma3 */
 	__le32  ch_reserved;
-	struct fsl_edma_hw_tcd tcd;
+	union {
+		struct fsl_edma_hw_tcd tcd;
+		struct fsl_edma_hw_tcd64 tcd64;
+	};
 } __packed;
 
 /*
@@ -126,7 +143,7 @@ struct edma_regs {
 
 struct fsl_edma_sw_tcd {
 	dma_addr_t			ptcd;
-	struct fsl_edma_hw_tcd		*vtcd;
+	void				*vtcd;
 };
 
 struct fsl_edma_chan {
@@ -145,7 +162,8 @@ struct fsl_edma_chan {
 	u32				dma_dev_size;
 	enum dma_data_direction		dma_dir;
 	char				chan_name[32];
-	struct fsl_edma_hw_tcd __iomem *tcd;
+	void __iomem			*tcd;
+	void __iomem			*mux_addr;
 	u32				real_count;
 	struct work_struct		issue_worker;
 	struct platform_device		*pdev;
@@ -188,6 +206,7 @@ struct fsl_edma_desc {
 #define FSL_EDMA_DRV_CLEAR_DONE_E_SG	BIT(13)
 /* Need clean CHn_CSR DONE before enable TCD's MAJORELINK */
 #define FSL_EDMA_DRV_CLEAR_DONE_E_LINK	BIT(14)
+#define FSL_EDMA_DRV_TCD64		BIT(15)
 
 #define FSL_EDMA_DRV_EDMA3	(FSL_EDMA_DRV_SPLIT_REG |	\
 				 FSL_EDMA_DRV_BUS_8BYTE |	\
@@ -207,6 +226,8 @@ struct fsl_edma_drvdata {
 	u32			chreg_off;
 	u32			chreg_space_sz;
 	u32			flags;
+	u32			mux_off;	/* channel mux register offset */
+	u32			mux_skip;	/* how much skip for each channel */
 	int			(*setup_irq)(struct platform_device *pdev,
 					     struct fsl_edma_engine *fsl_edma);
 };
@@ -229,23 +250,108 @@ struct fsl_edma_engine {
 	struct fsl_edma_chan	chans[] __counted_by(n_chans);
 };
 
-#define edma_read_tcdreg(chan, __name)				\
-(sizeof(chan->tcd->__name) == sizeof(u32) ?			\
-	edma_readl(chan->edma, &chan->tcd->__name) :		\
-	edma_readw(chan->edma, &chan->tcd->__name))
-
-#define edma_write_tcdreg(chan, val, __name)			\
-(sizeof(chan->tcd->__name) == sizeof(u32) ?			\
-	edma_writel(chan->edma, (u32 __force)val, &chan->tcd->__name) :	\
-	edma_writew(chan->edma, (u16 __force)val, &chan->tcd->__name))
+#define edma_read_tcdreg_c(chan, _tcd,  __name)				\
+(sizeof((_tcd)->__name) == sizeof(u64) ?				\
+	edma_readq(chan->edma, &(_tcd)->__name) :			\
+		((sizeof((_tcd)->__name) == sizeof(u32)) ?		\
+			edma_readl(chan->edma, &(_tcd)->__name) :	\
+			edma_readw(chan->edma, &(_tcd)->__name)		\
+		))
+
+#define edma_read_tcdreg(chan, __name)								\
+((fsl_edma_drvflags(chan) & FSL_EDMA_DRV_TCD64) ?						\
+	edma_read_tcdreg_c(chan, ((struct fsl_edma_hw_tcd64 __iomem *)chan->tcd), __name) :	\
+	edma_read_tcdreg_c(chan, ((struct fsl_edma_hw_tcd __iomem *)chan->tcd), __name)		\
+)
+
+#define edma_write_tcdreg_c(chan, _tcd, _val, __name)				\
+do {										\
+	switch (sizeof(_tcd->__name)) {						\
+	case sizeof(u64):							\
+		edma_writeq(chan->edma, (u64 __force)_val, &_tcd->__name);	\
+		break;								\
+	case sizeof(u32):							\
+		edma_writel(chan->edma, (u32 __force)_val, &_tcd->__name);	\
+		break;								\
+	case sizeof(u16):							\
+		edma_writew(chan->edma, (u16 __force)_val, &_tcd->__name);	\
+		break;								\
+	case sizeof(u8):							\
+		edma_writeb(chan->edma, (u8 __force)_val, &_tcd->__name);	\
+		break;								\
+	}									\
+} while (0)
+
+#define edma_write_tcdreg(chan, val, __name)							   \
+do {												   \
+	struct fsl_edma_hw_tcd64 __iomem *tcd64_r = (struct fsl_edma_hw_tcd64 __iomem *)chan->tcd; \
+	struct fsl_edma_hw_tcd __iomem *tcd_r = (struct fsl_edma_hw_tcd __iomem *)chan->tcd;	   \
+												   \
+	if (fsl_edma_drvflags(chan) & FSL_EDMA_DRV_TCD64)					   \
+		edma_write_tcdreg_c(chan, tcd64_r, val, __name);				   \
+	else											   \
+		edma_write_tcdreg_c(chan, tcd_r, val, __name);					   \
+} while (0)
+
+#define edma_cp_tcd_to_reg(chan, __tcd, __name)							   \
+do {	\
+	struct fsl_edma_hw_tcd64 __iomem *tcd64_r = (struct fsl_edma_hw_tcd64 __iomem *)chan->tcd; \
+	struct fsl_edma_hw_tcd __iomem *tcd_r = (struct fsl_edma_hw_tcd __iomem *)chan->tcd;	   \
+	struct fsl_edma_hw_tcd64 *tcd64_m = (struct fsl_edma_hw_tcd64 *)__tcd;			   \
+	struct fsl_edma_hw_tcd *tcd_m = (struct fsl_edma_hw_tcd *)__tcd;			   \
+												   \
+	if (fsl_edma_drvflags(chan) & FSL_EDMA_DRV_TCD64)					   \
+		edma_write_tcdreg_c(chan, tcd64_r,  tcd64_m->__name, __name);			   \
+	else											   \
+		edma_write_tcdreg_c(chan, tcd_r, tcd_m->__name, __name);			   \
+} while (0)
 
 #define edma_readl_chreg(chan, __name)				\
 	edma_readl(chan->edma,					\
-		   (void __iomem *)&(container_of(chan->tcd, struct fsl_edma3_ch_reg, tcd)->__name))
+		   (void __iomem *)&(container_of(((__force void *)chan->tcd),\
+						  struct fsl_edma3_ch_reg, tcd)->__name))
 
 #define edma_writel_chreg(chan, val,  __name)			\
 	edma_writel(chan->edma, val,				\
-		   (void __iomem *)&(container_of(chan->tcd, struct fsl_edma3_ch_reg, tcd)->__name))
+		   (void __iomem *)&(container_of(((__force void *)chan->tcd),\
+						  struct fsl_edma3_ch_reg, tcd)->__name))
+
+#define fsl_edma_get_tcd(_chan, _tcd, _field)			\
+(fsl_edma_drvflags(_chan) & FSL_EDMA_DRV_TCD64 ? (((struct fsl_edma_hw_tcd64 *)_tcd)->_field) : \
+						 (((struct fsl_edma_hw_tcd *)_tcd)->_field))
+
+#define fsl_edma_le_to_cpu(x)						\
+(sizeof(x) == sizeof(u64) ? le64_to_cpu((__force __le64)(x)) :		\
+	(sizeof(x) == sizeof(u32) ? le32_to_cpu((__force __le32)(x)) :	\
+				    le16_to_cpu((__force __le16)(x))))
+
+#define fsl_edma_get_tcd_to_cpu(_chan, _tcd, _field)				\
+(fsl_edma_drvflags(_chan) & FSL_EDMA_DRV_TCD64 ?				\
+	fsl_edma_le_to_cpu(((struct fsl_edma_hw_tcd64 *)_tcd)->_field) :	\
+	fsl_edma_le_to_cpu(((struct fsl_edma_hw_tcd *)_tcd)->_field))
+
+#define fsl_edma_set_tcd_to_le_c(_tcd, _val, _field)					\
+do {											\
+	switch (sizeof((_tcd)->_field)) {						\
+	case sizeof(u64):								\
+		*(__force __le64 *)(&((_tcd)->_field)) = cpu_to_le64(_val);		\
+		break;									\
+	case sizeof(u32):								\
+		*(__force __le32 *)(&((_tcd)->_field)) = cpu_to_le32(_val);		\
+		break;									\
+	case sizeof(u16):								\
+		*(__force __le16 *)(&((_tcd)->_field)) = cpu_to_le16(_val);		\
+		break;									\
+	}										\
+} while (0)
+
+#define fsl_edma_set_tcd_to_le(_chan, _tcd, _val, _field)	\
+do {								\
+	if (fsl_edma_drvflags(_chan) & FSL_EDMA_DRV_TCD64)	\
+		fsl_edma_set_tcd_to_le_c((struct fsl_edma_hw_tcd64 *)_tcd, _val, _field);	\
+	else											\
+		fsl_edma_set_tcd_to_le_c((struct fsl_edma_hw_tcd *)_tcd, _val, _field);		\
+} while (0)
 
 /*
  * R/W functions for big- or little-endian registers:
@@ -253,6 +359,21 @@ struct fsl_edma_engine {
  * For the big-endian IP module, the offset for 8-bit or 16-bit registers
  * should also be swapped opposite to that in little-endian IP.
  */
+static inline u64 edma_readq(struct fsl_edma_engine *edma, void __iomem *addr)
+{
+	u64 l, h;
+
+	if (edma->big_endian) {
+		l = ioread32be(addr);
+		h = ioread32be(addr + 4);
+	} else {
+		l = ioread32(addr);
+		h = ioread32(addr + 4);
+	}
+
+	return (h << 32) | l;
+}
+
 static inline u32 edma_readl(struct fsl_edma_engine *edma, void __iomem *addr)
 {
 	if (edma->big_endian)
@@ -298,6 +419,18 @@ static inline void edma_writel(struct fsl_edma_engine *edma,
 		iowrite32(val, addr);
 }
 
+static inline void edma_writeq(struct fsl_edma_engine *edma,
+			       u64 val, void __iomem *addr)
+{
+	if (edma->big_endian) {
+		iowrite32be(val & 0xFFFFFFFF, addr);
+		iowrite32be(val >> 32, addr + 4);
+	} else {
+		iowrite32(val & 0xFFFFFFFF, addr);
+		iowrite32(val >> 32, addr + 4);
+	}
+}
+
 static inline struct fsl_edma_chan *to_fsl_edma_chan(struct dma_chan *chan)
 {
 	return container_of(chan, struct fsl_edma_chan, vchan.chan);

drivers/dma/fsl-edma-main.c

@@ -360,6 +360,18 @@ static struct fsl_edma_drvdata imx93_data4 = {
 	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4,
 	.chreg_space_sz = 0x8000,
 	.chreg_off = 0x10000,
+	.mux_off = 0x10000 + offsetof(struct fsl_edma3_ch_reg, ch_mux),
+	.mux_skip = 0x8000,
+	.setup_irq = fsl_edma3_irq_init,
+};
+
+static struct fsl_edma_drvdata imx95_data5 = {
+	.flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4 |
+		 FSL_EDMA_DRV_TCD64,
+	.chreg_space_sz = 0x8000,
+	.chreg_off = 0x10000,
+	.mux_off = 0x200,
+	.mux_skip = sizeof(u32),
 	.setup_irq = fsl_edma3_irq_init,
 };
 
@@ -371,6 +383,7 @@ static const struct of_device_id fsl_edma_dt_ids[] = {
 	{ .compatible = "fsl,imx8qm-adma", .data = &imx8qm_audio_data},
 	{ .compatible = "fsl,imx93-edma3", .data = &imx93_data3},
 	{ .compatible = "fsl,imx93-edma4", .data = &imx93_data4},
+	{ .compatible = "fsl,imx95-edma5", .data = &imx95_data5},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_edma_dt_ids);
@@ -511,6 +524,9 @@ static int fsl_edma_probe(struct platform_device *pdev)
 			return ret;
 	}
 
+	if (drvdata->flags & FSL_EDMA_DRV_TCD64)
+		dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+
 	INIT_LIST_HEAD(&fsl_edma->dma_dev.channels);
 	for (i = 0; i < fsl_edma->n_chans; i++) {
 		struct fsl_edma_chan *fsl_chan = &fsl_edma->chans[i];
@@ -533,11 +549,12 @@ static int fsl_edma_probe(struct platform_device *pdev)
 				offsetof(struct fsl_edma3_ch_reg, tcd) : 0;
 		fsl_chan->tcd = fsl_edma->membase
 				+ i * drvdata->chreg_space_sz + drvdata->chreg_off + len;
+		fsl_chan->mux_addr = fsl_edma->membase + drvdata->mux_off + i * drvdata->mux_skip;
 
 		fsl_chan->pdev = pdev;
 		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
 
-		edma_write_tcdreg(fsl_chan, 0, csr);
+		edma_write_tcdreg(fsl_chan, cpu_to_le32(0), csr);
 		fsl_edma_chan_mux(fsl_chan, 0, false);
 	}
 

drivers/dma/idxd/bus.c

@@ -72,7 +72,7 @@ static int idxd_bus_uevent(const struct device *dev, struct kobj_uevent_env *env
 	return add_uevent_var(env, "MODALIAS=" IDXD_DEVICES_MODALIAS_FMT, 0);
 }
 
-struct bus_type dsa_bus_type = {
+const struct bus_type dsa_bus_type = {
 	.name = "dsa",
 	.match = idxd_config_bus_match,
 	.probe = idxd_config_bus_probe,

drivers/dma/idxd/cdev.c

@@ -152,7 +152,7 @@ static void idxd_file_dev_release(struct device *dev)
 	mutex_unlock(&wq->wq_lock);
 }
 
-static struct device_type idxd_cdev_file_type = {
+static const struct device_type idxd_cdev_file_type = {
 	.name = "idxd_file",
 	.release = idxd_file_dev_release,
 	.groups = cdev_file_attribute_groups,
@@ -169,7 +169,7 @@ static void idxd_cdev_dev_release(struct device *dev)
 	kfree(idxd_cdev);
 }
 
-static struct device_type idxd_cdev_device_type = {
+static const struct device_type idxd_cdev_device_type = {
 	.name = "idxd_cdev",
 	.release = idxd_cdev_dev_release,
 };

drivers/dma/idxd/idxd.h

@@ -282,7 +282,7 @@ typedef int (*load_device_defaults_fn_t) (struct idxd_device *idxd);
 struct idxd_driver_data {
 	const char *name_prefix;
 	enum idxd_type type;
-	struct device_type *dev_type;
+	const struct device_type *dev_type;
 	int compl_size;
 	int align;
 	int evl_cr_off;
@@ -515,15 +515,15 @@ static inline void idxd_set_user_intr(struct idxd_device *idxd, bool enable)
 	iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
 }
 
-extern struct bus_type dsa_bus_type;
+extern const struct bus_type dsa_bus_type;
 
 extern bool support_enqcmd;
 extern struct ida idxd_ida;
-extern struct device_type dsa_device_type;
-extern struct device_type iax_device_type;
-extern struct device_type idxd_wq_device_type;
-extern struct device_type idxd_engine_device_type;
-extern struct device_type idxd_group_device_type;
+extern const struct device_type dsa_device_type;
+extern const struct device_type iax_device_type;
+extern const struct device_type idxd_wq_device_type;
+extern const struct device_type idxd_engine_device_type;
+extern const struct device_type idxd_group_device_type;
 
 static inline bool is_dsa_dev(struct idxd_dev *idxd_dev)
 {

drivers/dma/idxd/sysfs.c

@@ -91,7 +91,7 @@ static void idxd_conf_engine_release(struct device *dev)
 	kfree(engine);
 }
 
-struct device_type idxd_engine_device_type = {
+const struct device_type idxd_engine_device_type = {
 	.name = "engine",
 	.release = idxd_conf_engine_release,
 	.groups = idxd_engine_attribute_groups,
@@ -577,7 +577,7 @@ static void idxd_conf_group_release(struct device *dev)
 	kfree(group);
 }
 
-struct device_type idxd_group_device_type = {
+const struct device_type idxd_group_device_type = {
 	.name = "group",
 	.release = idxd_conf_group_release,
 	.groups = idxd_group_attribute_groups,
@@ -1369,7 +1369,7 @@ static void idxd_conf_wq_release(struct device *dev)
 	kfree(wq);
 }
 
-struct device_type idxd_wq_device_type = {
+const struct device_type idxd_wq_device_type = {
 	.name = "wq",
 	.release = idxd_conf_wq_release,
 	.groups = idxd_wq_attribute_groups,
@@ -1798,13 +1798,13 @@ static void idxd_conf_device_release(struct device *dev)
 	kfree(idxd);
 }
 
-struct device_type dsa_device_type = {
+const struct device_type dsa_device_type = {
 	.name = "dsa",
 	.release = idxd_conf_device_release,
 	.groups = idxd_attribute_groups,
 };
 
-struct device_type iax_device_type = {
+const struct device_type iax_device_type = {
 	.name = "iax",
 	.release = idxd_conf_device_release,
 	.groups = idxd_attribute_groups,

drivers/dma/mcf-edma-main.c

@@ -202,7 +202,7 @@ static int mcf_edma_probe(struct platform_device *pdev)
 		vchan_init(&mcf_chan->vchan, &mcf_edma->dma_dev);
 		mcf_chan->tcd = mcf_edma->membase + EDMA_TCD
 				+ i * sizeof(struct fsl_edma_hw_tcd);
-		iowrite32(0x0, &mcf_chan->tcd->csr);
+		edma_write_tcdreg(mcf_chan, cpu_to_le32(0), csr);
 	}
 
 	iowrite32(~0, regs->inth);

drivers/dma/of-dma.c

@@ -29,7 +29,7 @@ static DEFINE_MUTEX(of_dma_lock);
  * to the DMA data stored is retuned. A NULL pointer is returned if no match is
  * found.
  */
-static struct of_dma *of_dma_find_controller(struct of_phandle_args *dma_spec)
+static struct of_dma *of_dma_find_controller(const struct of_phandle_args *dma_spec)
 {
 	struct of_dma *ofdma;
 

drivers/dma/pl330.c

@@ -2588,6 +2588,7 @@ static struct dma_pl330_desc *pluck_desc(struct list_head *pool,
 
 		desc->status = PREP;
 		desc->txd.callback = NULL;
+		desc->txd.callback_result = NULL;
 	}
 
 	spin_unlock_irqrestore(lock, flags);

drivers/dma/ti/k3-psil-j721s2.c

@@ -57,6 +57,14 @@
 		},					\
 	}
 
+#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 j721s2_src_ep_map[] = {
 	/* PDMA_MCASP - McASP0-4 */
@@ -114,6 +122,71 @@ static struct psil_ep j721s2_src_ep_map[] = {
 	PSIL_PDMA_XY_PKT(0x4707),
 	PSIL_PDMA_XY_PKT(0x4708),
 	PSIL_PDMA_XY_PKT(0x4709),
+	/* CSI2RX */
+	PSIL_CSI2RX(0x4940),
+	PSIL_CSI2RX(0x4941),
+	PSIL_CSI2RX(0x4942),
+	PSIL_CSI2RX(0x4943),
+	PSIL_CSI2RX(0x4944),
+	PSIL_CSI2RX(0x4945),
+	PSIL_CSI2RX(0x4946),
+	PSIL_CSI2RX(0x4947),
+	PSIL_CSI2RX(0x4948),
+	PSIL_CSI2RX(0x4949),
+	PSIL_CSI2RX(0x494a),
+	PSIL_CSI2RX(0x494b),
+	PSIL_CSI2RX(0x494c),
+	PSIL_CSI2RX(0x494d),
+	PSIL_CSI2RX(0x494e),
+	PSIL_CSI2RX(0x494f),
+	PSIL_CSI2RX(0x4950),
+	PSIL_CSI2RX(0x4951),
+	PSIL_CSI2RX(0x4952),
+	PSIL_CSI2RX(0x4953),
+	PSIL_CSI2RX(0x4954),
+	PSIL_CSI2RX(0x4955),
+	PSIL_CSI2RX(0x4956),
+	PSIL_CSI2RX(0x4957),
+	PSIL_CSI2RX(0x4958),
+	PSIL_CSI2RX(0x4959),
+	PSIL_CSI2RX(0x495a),
+	PSIL_CSI2RX(0x495b),
+	PSIL_CSI2RX(0x495c),
+	PSIL_CSI2RX(0x495d),
+	PSIL_CSI2RX(0x495e),
+	PSIL_CSI2RX(0x495f),
+	PSIL_CSI2RX(0x4960),
+	PSIL_CSI2RX(0x4961),
+	PSIL_CSI2RX(0x4962),
+	PSIL_CSI2RX(0x4963),
+	PSIL_CSI2RX(0x4964),
+	PSIL_CSI2RX(0x4965),
+	PSIL_CSI2RX(0x4966),
+	PSIL_CSI2RX(0x4967),
+	PSIL_CSI2RX(0x4968),
+	PSIL_CSI2RX(0x4969),
+	PSIL_CSI2RX(0x496a),
+	PSIL_CSI2RX(0x496b),
+	PSIL_CSI2RX(0x496c),
+	PSIL_CSI2RX(0x496d),
+	PSIL_CSI2RX(0x496e),
+	PSIL_CSI2RX(0x496f),
+	PSIL_CSI2RX(0x4970),
+	PSIL_CSI2RX(0x4971),
+	PSIL_CSI2RX(0x4972),
+	PSIL_CSI2RX(0x4973),
+	PSIL_CSI2RX(0x4974),
+	PSIL_CSI2RX(0x4975),
+	PSIL_CSI2RX(0x4976),
+	PSIL_CSI2RX(0x4977),
+	PSIL_CSI2RX(0x4978),
+	PSIL_CSI2RX(0x4979),
+	PSIL_CSI2RX(0x497a),
+	PSIL_CSI2RX(0x497b),
+	PSIL_CSI2RX(0x497c),
+	PSIL_CSI2RX(0x497d),
+	PSIL_CSI2RX(0x497e),
+	PSIL_CSI2RX(0x497f),
 	/* MAIN SA2UL */
 	PSIL_SA2UL(0x4a40, 0),
 	PSIL_SA2UL(0x4a41, 0),

drivers/dma/ti/k3-udma-glue.c

@@ -111,6 +111,35 @@ static int of_k3_udma_glue_parse(struct device_node *udmax_np,
 	return 0;
 }
 
+static int of_k3_udma_glue_parse_chn_common(struct k3_udma_glue_common *common, u32 thread_id,
+					    bool tx_chn)
+{
+	if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET))
+		return -EINVAL;
+
+	if (!tx_chn && (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET))
+		return -EINVAL;
+
+	/* get psil endpoint config */
+	common->ep_config = psil_get_ep_config(thread_id);
+	if (IS_ERR(common->ep_config)) {
+		dev_err(common->dev,
+			"No configuration for psi-l thread 0x%04x\n",
+			thread_id);
+		return PTR_ERR(common->ep_config);
+	}
+
+	common->epib = common->ep_config->needs_epib;
+	common->psdata_size = common->ep_config->psd_size;
+
+	if (tx_chn)
+		common->dst_thread = thread_id;
+	else
+		common->src_thread = thread_id;
+
+	return 0;
+}
+
 static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 		const char *name, struct k3_udma_glue_common *common,
 		bool tx_chn)
@@ -153,38 +182,32 @@ static int of_k3_udma_glue_parse_chn(struct device_node *chn_np,
 		common->atype_asel = dma_spec.args[1];
 	}
 
-	if (tx_chn && !(thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
-		ret = -EINVAL;
-		goto out_put_spec;
-	}
+	ret = of_k3_udma_glue_parse_chn_common(common, thread_id, tx_chn);
 
-	if (!tx_chn && (thread_id & K3_PSIL_DST_THREAD_ID_OFFSET)) {
-		ret = -EINVAL;
-		goto out_put_spec;
-	}
+out_put_spec:
+	of_node_put(dma_spec.np);
+	return ret;
+}
 
-	/* get psil endpoint config */
-	common->ep_config = psil_get_ep_config(thread_id);
-	if (IS_ERR(common->ep_config)) {
-		dev_err(common->dev,
-			"No configuration for psi-l thread 0x%04x\n",
-			thread_id);
-		ret = PTR_ERR(common->ep_config);
-		goto out_put_spec;
-	}
+static int
+of_k3_udma_glue_parse_chn_by_id(struct device_node *udmax_np, struct k3_udma_glue_common *common,
+				bool tx_chn, u32 thread_id)
+{
+	int ret = 0;
 
-	common->epib = common->ep_config->needs_epib;
-	common->psdata_size = common->ep_config->psd_size;
+	if (unlikely(!udmax_np))
+		return -EINVAL;
 
-	if (tx_chn)
-		common->dst_thread = thread_id;
-	else
-		common->src_thread = thread_id;
+	ret = of_k3_udma_glue_parse(udmax_np, common);
+	if (ret)
+		goto out_put_spec;
+
+	ret = of_k3_udma_glue_parse_chn_common(common, thread_id, tx_chn);
 
 out_put_spec:
-	of_node_put(dma_spec.np);
+	of_node_put(udmax_np);
 	return ret;
-};
+}
 
 static void k3_udma_glue_dump_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 {
@@ -251,29 +274,13 @@ static int k3_udma_glue_cfg_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 	return tisci_rm->tisci_udmap_ops->tx_ch_cfg(tisci_rm->tisci, &req);
 }
 
-struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
-		const char *name, struct k3_udma_glue_tx_channel_cfg *cfg)
+static int
+k3_udma_glue_request_tx_chn_common(struct device *dev,
+				   struct k3_udma_glue_tx_channel *tx_chn,
+				   struct k3_udma_glue_tx_channel_cfg *cfg)
 {
-	struct k3_udma_glue_tx_channel *tx_chn;
 	int ret;
 
-	tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL);
-	if (!tx_chn)
-		return ERR_PTR(-ENOMEM);
-
-	tx_chn->common.dev = dev;
-	tx_chn->common.swdata_size = cfg->swdata_size;
-	tx_chn->tx_pause_on_err = cfg->tx_pause_on_err;
-	tx_chn->tx_filt_einfo = cfg->tx_filt_einfo;
-	tx_chn->tx_filt_pswords = cfg->tx_filt_pswords;
-	tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt;
-
-	/* parse of udmap channel */
-	ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
-					&tx_chn->common, true);
-	if (ret)
-		goto err;
-
 	tx_chn->common.hdesc_size = cppi5_hdesc_calc_size(tx_chn->common.epib,
 						tx_chn->common.psdata_size,
 						tx_chn->common.swdata_size);
@@ -289,7 +296,7 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	if (IS_ERR(tx_chn->udma_tchanx)) {
 		ret = PTR_ERR(tx_chn->udma_tchanx);
 		dev_err(dev, "UDMAX tchanx get err %d\n", ret);
-		goto err;
+		return ret;
 	}
 	tx_chn->udma_tchan_id = xudma_tchan_get_id(tx_chn->udma_tchanx);
 
@@ -302,7 +309,7 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 		dev_err(dev, "Channel Device registration failed %d\n", ret);
 		put_device(&tx_chn->common.chan_dev);
 		tx_chn->common.chan_dev.parent = NULL;
-		goto err;
+		return ret;
 	}
 
 	if (xudma_is_pktdma(tx_chn->common.udmax)) {
@@ -326,7 +333,7 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 					     &tx_chn->ringtxcq);
 	if (ret) {
 		dev_err(dev, "Failed to get TX/TXCQ rings %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	/* Set the dma_dev for the rings to be configured */
@@ -342,13 +349,13 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	ret = k3_ringacc_ring_cfg(tx_chn->ringtx, &cfg->tx_cfg);
 	if (ret) {
 		dev_err(dev, "Failed to cfg ringtx %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	ret = k3_ringacc_ring_cfg(tx_chn->ringtxcq, &cfg->txcq_cfg);
 	if (ret) {
 		dev_err(dev, "Failed to cfg ringtx %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	/* request and cfg psi-l */
@@ -359,11 +366,42 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 	ret = k3_udma_glue_cfg_tx_chn(tx_chn);
 	if (ret) {
 		dev_err(dev, "Failed to cfg tchan %d\n", ret);
-		goto err;
+		return ret;
 	}
 
 	k3_udma_glue_dump_tx_chn(tx_chn);
 
+	return 0;
+}
+
+struct k3_udma_glue_tx_channel *
+k3_udma_glue_request_tx_chn(struct device *dev, const char *name,
+			    struct k3_udma_glue_tx_channel_cfg *cfg)
+{
+	struct k3_udma_glue_tx_channel *tx_chn;
+	int ret;
+
+	tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL);
+	if (!tx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	tx_chn->common.dev = dev;
+	tx_chn->common.swdata_size = cfg->swdata_size;
+	tx_chn->tx_pause_on_err = cfg->tx_pause_on_err;
+	tx_chn->tx_filt_einfo = cfg->tx_filt_einfo;
+	tx_chn->tx_filt_pswords = cfg->tx_filt_pswords;
+	tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt;
+
+	/* parse of udmap channel */
+	ret = of_k3_udma_glue_parse_chn(dev->of_node, name,
+					&tx_chn->common, true);
+	if (ret)
+		goto err;
+
+	ret = k3_udma_glue_request_tx_chn_common(dev, tx_chn, cfg);
+	if (ret)
+		goto err;
+
 	return tx_chn;
 
 err:
@@ -372,6 +410,41 @@ struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(k3_udma_glue_request_tx_chn);
 
+struct k3_udma_glue_tx_channel *
+k3_udma_glue_request_tx_chn_for_thread_id(struct device *dev,
+					  struct k3_udma_glue_tx_channel_cfg *cfg,
+					  struct device_node *udmax_np, u32 thread_id)
+{
+	struct k3_udma_glue_tx_channel *tx_chn;
+	int ret;
+
+	tx_chn = devm_kzalloc(dev, sizeof(*tx_chn), GFP_KERNEL);
+	if (!tx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	tx_chn->common.dev = dev;
+	tx_chn->common.swdata_size = cfg->swdata_size;
+	tx_chn->tx_pause_on_err = cfg->tx_pause_on_err;
+	tx_chn->tx_filt_einfo = cfg->tx_filt_einfo;
+	tx_chn->tx_filt_pswords = cfg->tx_filt_pswords;
+	tx_chn->tx_supr_tdpkt = cfg->tx_supr_tdpkt;
+
+	ret = of_k3_udma_glue_parse_chn_by_id(udmax_np, &tx_chn->common, true, thread_id);
+	if (ret)
+		goto err;
+
+	ret = k3_udma_glue_request_tx_chn_common(dev, tx_chn, cfg);
+	if (ret)
+		goto err;
+
+	return tx_chn;
+
+err:
+	k3_udma_glue_release_tx_chn(tx_chn);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(k3_udma_glue_request_tx_chn_for_thread_id);
+
 void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn)
 {
 	if (tx_chn->psil_paired) {
@@ -1000,12 +1073,59 @@ k3_udma_glue_request_rx_chn_priv(struct device *dev, const char *name,
 	return ERR_PTR(ret);
 }
 
+static int
+k3_udma_glue_request_remote_rx_chn_common(struct k3_udma_glue_rx_channel *rx_chn,
+					  struct k3_udma_glue_rx_channel_cfg *cfg,
+					  struct device *dev)
+{
+	int ret, i;
+
+	rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib,
+						rx_chn->common.psdata_size,
+						rx_chn->common.swdata_size);
+
+	rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
+				     sizeof(*rx_chn->flows), GFP_KERNEL);
+	if (!rx_chn->flows)
+		return -ENOMEM;
+
+	rx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
+	rx_chn->common.chan_dev.parent = xudma_get_device(rx_chn->common.udmax);
+	dev_set_name(&rx_chn->common.chan_dev, "rchan_remote-0x%04x-0x%02x",
+		     rx_chn->common.src_thread, rx_chn->flow_id_base);
+	ret = device_register(&rx_chn->common.chan_dev);
+	if (ret) {
+		dev_err(dev, "Channel Device registration failed %d\n", ret);
+		put_device(&rx_chn->common.chan_dev);
+		rx_chn->common.chan_dev.parent = NULL;
+		return ret;
+	}
+
+	if (xudma_is_pktdma(rx_chn->common.udmax)) {
+		/* prepare the channel device as coherent */
+		rx_chn->common.chan_dev.dma_coherent = true;
+		dma_coerce_mask_and_coherent(&rx_chn->common.chan_dev,
+					     DMA_BIT_MASK(48));
+	}
+
+	ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < rx_chn->flow_num; i++)
+		rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i;
+
+	k3_udma_glue_dump_rx_chn(rx_chn);
+
+	return 0;
+}
+
 static struct k3_udma_glue_rx_channel *
 k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
 				   struct k3_udma_glue_rx_channel_cfg *cfg)
 {
 	struct k3_udma_glue_rx_channel *rx_chn;
-	int ret, i;
+	int ret;
 
 	if (cfg->flow_id_num <= 0 ||
 	    cfg->flow_id_use_rxchan_id ||
@@ -1036,44 +1156,55 @@ k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
 	if (ret)
 		goto err;
 
-	rx_chn->common.hdesc_size = cppi5_hdesc_calc_size(rx_chn->common.epib,
-						rx_chn->common.psdata_size,
-						rx_chn->common.swdata_size);
-
-	rx_chn->flows = devm_kcalloc(dev, rx_chn->flow_num,
-				     sizeof(*rx_chn->flows), GFP_KERNEL);
-	if (!rx_chn->flows) {
-		ret = -ENOMEM;
+	ret = k3_udma_glue_request_remote_rx_chn_common(rx_chn, cfg, dev);
+	if (ret)
 		goto err;
-	}
 
-	rx_chn->common.chan_dev.class = &k3_udma_glue_devclass;
-	rx_chn->common.chan_dev.parent = xudma_get_device(rx_chn->common.udmax);
-	dev_set_name(&rx_chn->common.chan_dev, "rchan_remote-0x%04x",
-		     rx_chn->common.src_thread);
-	ret = device_register(&rx_chn->common.chan_dev);
-	if (ret) {
-		dev_err(dev, "Channel Device registration failed %d\n", ret);
-		put_device(&rx_chn->common.chan_dev);
-		rx_chn->common.chan_dev.parent = NULL;
-		goto err;
-	}
+	return rx_chn;
 
-	if (xudma_is_pktdma(rx_chn->common.udmax)) {
-		/* prepare the channel device as coherent */
-		rx_chn->common.chan_dev.dma_coherent = true;
-		dma_coerce_mask_and_coherent(&rx_chn->common.chan_dev,
-					     DMA_BIT_MASK(48));
-	}
+err:
+	k3_udma_glue_release_rx_chn(rx_chn);
+	return ERR_PTR(ret);
+}
 
-	ret = k3_udma_glue_allocate_rx_flows(rx_chn, cfg);
+struct k3_udma_glue_rx_channel *
+k3_udma_glue_request_remote_rx_chn_for_thread_id(struct device *dev,
+						 struct k3_udma_glue_rx_channel_cfg *cfg,
+						 struct device_node *udmax_np, u32 thread_id)
+{
+	struct k3_udma_glue_rx_channel *rx_chn;
+	int ret;
+
+	if (cfg->flow_id_num <= 0 ||
+	    cfg->flow_id_use_rxchan_id ||
+	    cfg->def_flow_cfg ||
+	    cfg->flow_id_base < 0)
+		return ERR_PTR(-EINVAL);
+
+	/*
+	 * Remote RX channel is under control of Remote CPU core, so
+	 * Linux can only request and manipulate by dedicated RX flows
+	 */
+
+	rx_chn = devm_kzalloc(dev, sizeof(*rx_chn), GFP_KERNEL);
+	if (!rx_chn)
+		return ERR_PTR(-ENOMEM);
+
+	rx_chn->common.dev = dev;
+	rx_chn->common.swdata_size = cfg->swdata_size;
+	rx_chn->remote = true;
+	rx_chn->udma_rchan_id = -1;
+	rx_chn->flow_num = cfg->flow_id_num;
+	rx_chn->flow_id_base = cfg->flow_id_base;
+	rx_chn->psil_paired = false;
+
+	ret = of_k3_udma_glue_parse_chn_by_id(udmax_np, &rx_chn->common, false, thread_id);
 	if (ret)
 		goto err;
 
-	for (i = 0; i < rx_chn->flow_num; i++)
-		rx_chn->flows[i].udma_rflow_id = rx_chn->flow_id_base + i;
-
-	k3_udma_glue_dump_rx_chn(rx_chn);
+	ret = k3_udma_glue_request_remote_rx_chn_common(rx_chn, cfg, dev);
+	if (ret)
+		goto err;
 
 	return rx_chn;
 
@@ -1081,6 +1212,7 @@ k3_udma_glue_request_remote_rx_chn(struct device *dev, const char *name,
 	k3_udma_glue_release_rx_chn(rx_chn);
 	return ERR_PTR(ret);
 }
+EXPORT_SYMBOL_GPL(k3_udma_glue_request_remote_rx_chn_for_thread_id);
 
 struct k3_udma_glue_rx_channel *
 k3_udma_glue_request_rx_chn(struct device *dev, const char *name,

drivers/dma/xilinx/xilinx_dma.c

@@ -112,7 +112,9 @@
 
 /* Register Direct Mode Registers */
 #define XILINX_DMA_REG_VSIZE			0x0000
+#define XILINX_DMA_VSIZE_MASK			GENMASK(12, 0)
 #define XILINX_DMA_REG_HSIZE			0x0004
+#define XILINX_DMA_HSIZE_MASK			GENMASK(15, 0)
 
 #define XILINX_DMA_REG_FRMDLY_STRIDE		0x0008
 #define XILINX_DMA_FRMDLY_STRIDE_FRMDLY_SHIFT	24
@@ -2050,6 +2052,10 @@ xilinx_vdma_dma_prep_interleaved(struct dma_chan *dchan,
 	if (!xt->numf || !xt->sgl[0].size)
 		return NULL;
 
+	if (xt->numf & ~XILINX_DMA_VSIZE_MASK ||
+	    xt->sgl[0].size & ~XILINX_DMA_HSIZE_MASK)
+		return NULL;
+
 	if (xt->frame_size != 1)
 		return NULL;
 

include/linux/dma/k3-udma-glue.h

@@ -26,6 +26,11 @@ struct k3_udma_glue_tx_channel;
 struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 		const char *name, struct k3_udma_glue_tx_channel_cfg *cfg);
 
+struct k3_udma_glue_tx_channel *
+k3_udma_glue_request_tx_chn_for_thread_id(struct device *dev,
+					  struct k3_udma_glue_tx_channel_cfg *cfg,
+					  struct device_node *udmax_np, u32 thread_id);
+
 void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn);
 int k3_udma_glue_push_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
 			     struct cppi5_host_desc_t *desc_tx,
@@ -109,6 +114,11 @@ struct k3_udma_glue_rx_channel *k3_udma_glue_request_rx_chn(
 		const char *name,
 		struct k3_udma_glue_rx_channel_cfg *cfg);
 
+struct k3_udma_glue_rx_channel *
+k3_udma_glue_request_remote_rx_chn_for_thread_id(struct device *dev,
+						 struct k3_udma_glue_rx_channel_cfg *cfg,
+						 struct device_node *udmax_np, u32 thread_id);
+
 void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn);
 int k3_udma_glue_enable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn);
 void k3_udma_glue_disable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn);