Merge tag 'dmaengine-5.1-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:

 - dmatest updates for modularizing common struct and code

 - remove SG support for VDMA xilinx IP and updates to driver

 - Update to dw driver to support Intel iDMA controllers multi-block
   support

 - tegra updates for proper reporting of residue

 - Add Snow Ridge ioatdma device id and support for IOATDMA v3.4

 - struct_size() usage and useless LIST_HEAD cleanups in subsystem.

 - qDMA controller driver for Layerscape SoCs

 - stm32-dma PM Runtime support

 - And usual updates to imx-sdma, sprd, Documentation, fsl-edma,
   bcm2835, qcom_hidma etc

* tag 'dmaengine-5.1-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (81 commits)
  dmaengine: imx-sdma: fix consistent dma test failures
  dmaengine: imx-sdma: add a test for imx8mq multi sdma devices
  dmaengine: imx-sdma: add clock ratio 1:1 check
  dmaengine: dmatest: move test data alloc & free into functions
  dmaengine: dmatest: add short-hand `buf_size` var in dmatest_func()
  dmaengine: dmatest: wrap src & dst data into a struct
  dmaengine: ioatdma: support latency tolerance report (LTR) for v3.4
  dmaengine: ioatdma: add descriptor pre-fetch support for v3.4
  dmaengine: ioatdma: disable DCA enabling on IOATDMA v3.4
  dmaengine: ioatdma: Add Snow Ridge ioatdma device id
  dmaengine: sprd: Change channel id to slave id for DMA cell specifier
  dt-bindings: dmaengine: sprd: Change channel id to slave id for DMA cell specifier
  dmaengine: mv_xor: Use correct device for DMA API
  Documentation :dmaengine: clarify DMA desc. pointer after submission
  Documentation: dmaengine: fix dmatest.rst warning
  dmaengine: k3dma: Add support for dma-channel-mask
  dmaengine: k3dma: Delete axi_config
  dmaengine: k3dma: Upgrade k3dma driver to support hisi_asp_dma hardware
  Documentation: bindings: dma: Add binding for dma-channel-mask
  Documentation: bindings: k3dma: Extend the k3dma driver binding to support hisi-asp
  ...

Documentation/devicetree/bindings/dma/dma.txt

@@ -16,6 +16,9 @@ Optional properties:
 - dma-channels: 	Number of DMA channels supported by the controller.
 - dma-requests: 	Number of DMA request signals supported by the
 			controller.
+- dma-channel-mask:	Bitmask of available DMA channels in ascending order
+			that are not reserved by firmware and are available to
+			the kernel. i.e. first channel corresponds to LSB.
 
 Example:
 
@@ -29,6 +32,7 @@ Example:
 		#dma-cells = <1>;
 		dma-channels = <32>;
 		dma-requests = <127>;
+		dma-channel-mask = <0xfffe>
 	};
 
 * DMA router

Documentation/devicetree/bindings/dma/fsl-qdma.txt

+NXP Layerscape SoC qDMA Controller
+==================================
+
+This device follows the generic DMA bindings defined in dma/dma.txt.
+
+Required properties:
+
+- compatible:		Must be one of
+			 "fsl,ls1021a-qdma": for LS1021A Board
+			 "fsl,ls1043a-qdma": for ls1043A Board
+			 "fsl,ls1046a-qdma": for ls1046A Board
+- reg:			Should contain the register's base address and length.
+- interrupts:		Should contain a reference to the interrupt used by this
+			device.
+- interrupt-names:	Should contain interrupt names:
+			 "qdma-queue0": the block0 interrupt
+			 "qdma-queue1": the block1 interrupt
+			 "qdma-queue2": the block2 interrupt
+			 "qdma-queue3": the block3 interrupt
+			 "qdma-error":  the error interrupt
+- fsl,dma-queues:	Should contain number of queues supported.
+- dma-channels:	Number of DMA channels supported
+- block-number:	the virtual block number
+- block-offset:	the offset of different virtual block
+- status-sizes:	status queue size of per virtual block
+- queue-sizes:		command queue size of per virtual block, the size number
+			based on queues
+
+Optional properties:
+
+- dma-channels:		Number of DMA channels supported by the controller.
+- big-endian:		If present registers and hardware scatter/gather descriptors
+			of the qDMA are implemented in big endian mode, otherwise in little
+			mode.
+
+Examples:
+
+	qdma: dma-controller@8390000 {
+			compatible = "fsl,ls1021a-qdma";
+			reg = <0x0 0x8388000 0x0 0x1000>, /* Controller regs */
+			      <0x0 0x8389000 0x0 0x1000>, /* Status regs */
+			      <0x0 0x838a000 0x0 0x2000>; /* Block regs */
+			interrupts = <GIC_SPI 185 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 76 IRQ_TYPE_LEVEL_HIGH>,
+				     <GIC_SPI 77 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-names = "qdma-error",
+				"qdma-queue0", "qdma-queue1";
+			dma-channels = <8>;
+			block-number = <2>;
+			block-offset = <0x1000>;
+			fsl,dma-queues = <2>;
+			status-sizes = <64>;
+			queue-sizes = <64 64>;
+			big-endian;
+		};
+
+DMA clients must use the format described in dma/dma.txt file.

Documentation/devicetree/bindings/dma/k3dma.txt

@@ -3,7 +3,9 @@
 See dma.txt first
 
 Required properties:
-- compatible: Should be "hisilicon,k3-dma-1.0"
+- compatible: Must be one of
+-              "hisilicon,k3-dma-1.0"
+-              "hisilicon,hisi-pcm-asp-dma-1.0"
 - reg: Should contain DMA registers location and length.
 - interrupts: Should contain one interrupt shared by all channel
 - #dma-cells: see dma.txt, should be 1, para number

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

@@ -23,8 +23,6 @@ Deprecated properties:
 
 
 Optional properties:
-- is_private: The device channels should be marked as private and not for by the
-  general purpose DMA channel allocator. False if not passed.
 - multi-block: Multi block transfers supported by hardware. Array property with
   one cell per channel. 0: not supported, 1 (default): supported.
 - snps,dma-protection-control: AHB HPROT[3:1] protection setting.

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

@@ -31,7 +31,7 @@ DMA clients connected to the Spreadtrum DMA controller must use the format
 described in the dma.txt file, using a two-cell specifier for each channel.
 The two cells in order are:
 1. A phandle pointing to the DMA controller.
-2. The channel id.
+2. The slave id.
 
 spi0: spi@70a00000{
 	...

Documentation/devicetree/bindings/dma/xilinx/xilinx_dma.txt

@@ -37,10 +37,11 @@ Required properties:
 Required properties for VDMA:
 - xlnx,num-fstores: Should be the number of framebuffers as configured in h/w.
 
-Optional properties:
-- xlnx,include-sg: Tells configured for Scatter-mode in
-	the hardware.
 Optional properties for AXI DMA:
+- xlnx,sg-length-width: Should be set to the width in bits of the length
+	register as configured in h/w. Takes values {8...26}. If the property
+	is missing or invalid then the default value 23 is used. This is the
+	maximum value that is supported by all IP versions.
 - xlnx,mcdma: Tells whether configured for multi-channel mode in the hardware.
 Optional properties for VDMA:
 - xlnx,flush-fsync: Tells which channel to Flush on Frame sync.

Documentation/driver-api/dmaengine/client.rst

@@ -172,7 +172,7 @@ The details of these operations are:
 
       After calling ``dmaengine_submit()`` the submitted transfer descriptor
       (``struct dma_async_tx_descriptor``) belongs to the DMA engine.
-      Consequentially, the client must consider invalid the pointer to that
+      Consequently, the client must consider invalid the pointer to that
       descriptor.
 
 5. Issue pending DMA requests and wait for callback notification

Documentation/driver-api/dmaengine/dmatest.rst

@@ -59,6 +59,7 @@ parameter, that specific channel is requested using the dmaengine and a thread
 is created with the existing parameters. This thread is set as pending
 and will be executed once run is set to 1. Any parameters set after the thread
 is created are not applied.
+
 .. hint::
   available channel list could be extracted by running the following command::
 

drivers/dma/Kconfig

@@ -218,6 +218,20 @@ config FSL_EDMA
 	  multiplexing capability for DMA request sources(slot).
 	  This module can be found on Freescale Vybrid and LS-1 SoCs.
 
+config FSL_QDMA
+       tristate "NXP Layerscape qDMA engine support"
+       depends on ARM || ARM64
+       select DMA_ENGINE
+       select DMA_VIRTUAL_CHANNELS
+       select DMA_ENGINE_RAID
+       select ASYNC_TX_ENABLE_CHANNEL_SWITCH
+       help
+         Support the NXP Layerscape qDMA engine with command queue and legacy mode.
+         Channel virtualization is supported through enqueuing of DMA jobs to,
+         or dequeuing DMA jobs from, different work queues.
+         This module can be found on NXP Layerscape SoCs.
+	  The qdma driver only work on  SoCs with a DPAA hardware block.
+
 config FSL_RAID
         tristate "Freescale RAID engine Support"
         depends on FSL_SOC && !ASYNC_TX_ENABLE_CHANNEL_SWITCH

drivers/dma/Makefile

@@ -33,6 +33,7 @@ obj-$(CONFIG_EP93XX_DMA) += ep93xx_dma.o
 obj-$(CONFIG_FSL_DMA) += fsldma.o
 obj-$(CONFIG_FSL_EDMA) += fsl-edma.o fsl-edma-common.o
 obj-$(CONFIG_MCF_EDMA) += mcf-edma.o fsl-edma-common.o
+obj-$(CONFIG_FSL_QDMA) += fsl-qdma.o
 obj-$(CONFIG_FSL_RAID) += fsl_raid.o
 obj-$(CONFIG_HSU_DMA) += hsu/
 obj-$(CONFIG_IMG_MDC_DMA) += img-mdc-dma.o

drivers/dma/at_hdmac.c

@@ -134,7 +134,6 @@ static struct at_desc *atc_desc_get(struct at_dma_chan *atchan)
 	struct at_desc *ret = NULL;
 	unsigned long flags;
 	unsigned int i = 0;
-	LIST_HEAD(tmp_list);
 
 	spin_lock_irqsave(&atchan->lock, flags);
 	list_for_each_entry_safe(desc, _desc, &atchan->free_list, desc_node) {
@@ -1387,8 +1386,6 @@ static int atc_pause(struct dma_chan *chan)
 	int			chan_id = atchan->chan_common.chan_id;
 	unsigned long		flags;
 
-	LIST_HEAD(list);
-
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
 	spin_lock_irqsave(&atchan->lock, flags);
@@ -1408,8 +1405,6 @@ static int atc_resume(struct dma_chan *chan)
 	int			chan_id = atchan->chan_common.chan_id;
 	unsigned long		flags;
 
-	LIST_HEAD(list);
-
 	dev_vdbg(chan2dev(chan), "%s\n", __func__);
 
 	if (!atc_chan_is_paused(atchan))

drivers/dma/bcm2835-dma.c

@@ -2,9 +2,6 @@
 /*
  * BCM2835 DMA engine support
  *
- * This driver only supports cyclic DMA transfers
- * as needed for the I2S module.
- *
  * Author:      Florian Meier <florian.meier@koalo.de>
  *              Copyright 2013
  *
@@ -42,7 +39,6 @@
 
 struct bcm2835_dmadev {
 	struct dma_device ddev;
-	spinlock_t lock;
 	void __iomem *base;
 	struct device_dma_parameters dma_parms;
 };
@@ -64,7 +60,6 @@ struct bcm2835_cb_entry {
 
 struct bcm2835_chan {
 	struct virt_dma_chan vc;
-	struct list_head node;
 
 	struct dma_slave_config	cfg;
 	unsigned int dreq;
@@ -312,8 +307,7 @@ static struct bcm2835_desc *bcm2835_dma_create_cb_chain(
 		return NULL;
 
 	/* allocate and setup the descriptor. */
-	d = kzalloc(sizeof(*d) + frames * sizeof(struct bcm2835_cb_entry),
-		    gfp);
+	d = kzalloc(struct_size(d, cb_list, frames), gfp);
 	if (!d)
 		return NULL;
 
@@ -406,7 +400,7 @@ static void bcm2835_dma_fill_cb_chain_with_sg(
 	}
 }
 
-static int bcm2835_dma_abort(struct bcm2835_chan *c)
+static void bcm2835_dma_abort(struct bcm2835_chan *c)
 {
 	void __iomem *chan_base = c->chan_base;
 	long int timeout = 10000;
@@ -416,7 +410,7 @@ static int bcm2835_dma_abort(struct bcm2835_chan *c)
 	 * (The ACTIVE flag in the CS register is not a reliable indicator.)
 	 */
 	if (!readl(chan_base + BCM2835_DMA_ADDR))
-		return 0;
+		return;
 
 	/* Write 0 to the active bit - Pause the DMA */
 	writel(0, chan_base + BCM2835_DMA_CS);
@@ -432,7 +426,6 @@ static int bcm2835_dma_abort(struct bcm2835_chan *c)
 			"failed to complete outstanding writes\n");
 
 	writel(BCM2835_DMA_RESET, chan_base + BCM2835_DMA_CS);
-	return 0;
 }
 
 static void bcm2835_dma_start_desc(struct bcm2835_chan *c)
@@ -504,8 +497,12 @@ static int bcm2835_dma_alloc_chan_resources(struct dma_chan *chan)
 
 	dev_dbg(dev, "Allocating DMA channel %d\n", c->ch);
 
+	/*
+	 * Control blocks are 256 bit in length and must start at a 256 bit
+	 * (32 byte) aligned address (BCM2835 ARM Peripherals, sec. 4.2.1.1).
+	 */
 	c->cb_pool = dma_pool_create(dev_name(dev), dev,
-				     sizeof(struct bcm2835_dma_cb), 0, 0);
+				     sizeof(struct bcm2835_dma_cb), 32, 0);
 	if (!c->cb_pool) {
 		dev_err(dev, "unable to allocate descriptor pool\n");
 		return -ENOMEM;
@@ -774,17 +771,11 @@ static int bcm2835_dma_slave_config(struct dma_chan *chan,
 static int bcm2835_dma_terminate_all(struct dma_chan *chan)
 {
 	struct bcm2835_chan *c = to_bcm2835_dma_chan(chan);
-	struct bcm2835_dmadev *d = to_bcm2835_dma_dev(c->vc.chan.device);
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&c->vc.lock, flags);
 
-	/* Prevent this channel being scheduled */
-	spin_lock(&d->lock);
-	list_del_init(&c->node);
-	spin_unlock(&d->lock);
-
 	/* stop DMA activity */
 	if (c->desc) {
 		vchan_terminate_vdesc(&c->desc->vd);
@@ -817,7 +808,6 @@ static int bcm2835_dma_chan_init(struct bcm2835_dmadev *d, int chan_id,
 
 	c->vc.desc_free = bcm2835_dma_desc_free;
 	vchan_init(&c->vc, &d->ddev);
-	INIT_LIST_HEAD(&c->node);
 
 	c->chan_base = BCM2835_DMA_CHANIO(d->base, chan_id);
 	c->ch = chan_id;
@@ -920,7 +910,6 @@ static int bcm2835_dma_probe(struct platform_device *pdev)
 	od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	od->ddev.dev = &pdev->dev;
 	INIT_LIST_HEAD(&od->ddev.channels);
-	spin_lock_init(&od->lock);
 
 	platform_set_drvdata(pdev, od);
 

drivers/dma/dma-axi-dmac.c

@@ -367,8 +367,7 @@ static struct axi_dmac_desc *axi_dmac_alloc_desc(unsigned int num_sgs)
 	struct axi_dmac_desc *desc;
 	unsigned int i;
 
-	desc = kzalloc(sizeof(struct axi_dmac_desc) +
-		sizeof(struct axi_dmac_sg) * num_sgs, GFP_NOWAIT);
+	desc = kzalloc(struct_size(desc, sg, num_sgs), GFP_NOWAIT);
 	if (!desc)
 		return NULL;
 

drivers/dma/dma-jz4780.c

@@ -838,9 +838,8 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	if (!soc_data)
 		return -EINVAL;
 
-	jzdma = devm_kzalloc(dev, sizeof(*jzdma)
-				+ sizeof(*jzdma->chan) * soc_data->nb_channels,
-				GFP_KERNEL);
+	jzdma = devm_kzalloc(dev, struct_size(jzdma, chan,
+			     soc_data->nb_channels), GFP_KERNEL);
 	if (!jzdma)
 		return -ENOMEM;
 

drivers/dma/dw-axi-dmac/dw-axi-dmac.h

@@ -75,7 +75,7 @@ struct __packed axi_dma_lli {
 	__le32		sstat;
 	__le32		dstat;
 	__le32		status_lo;
-	__le32		ststus_hi;
+	__le32		status_hi;
 	__le32		reserved_lo;
 	__le32		reserved_hi;
 };

drivers/dma/dw/Kconfig

+# SPDX-License-Identifier: GPL-2.0
+
 #
 # DMA engine configuration for dw
 #

drivers/dma/dw/Makefile

 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_DW_DMAC_CORE)	+= dw_dmac_core.o
-dw_dmac_core-objs	:= core.o
+dw_dmac_core-objs	:= core.o dw.o idma32.o
 
 obj-$(CONFIG_DW_DMAC)		+= dw_dmac.o
 dw_dmac-objs		:= platform.o

drivers/dma/dw/dw.c

+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2007-2008 Atmel Corporation
+// Copyright (C) 2010-2011 ST Microelectronics
+// Copyright (C) 2013,2018 Intel Corporation
+
+#include <linux/bitops.h>
+#include <linux/dmaengine.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "internal.h"
+
+static void dw_dma_initialize_chan(struct dw_dma_chan *dwc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	u32 cfghi = DWC_CFGH_FIFO_MODE;
+	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
+	bool hs_polarity = dwc->dws.hs_polarity;
+
+	cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id);
+	cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id);
+	cfghi |= DWC_CFGH_PROTCTL(dw->pdata->protctl);
+
+	/* Set polarity of handshake interface */
+	cfglo |= hs_polarity ? DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL : 0;
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void dw_dma_suspend_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+}
+
+static void dw_dma_resume_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+}
+
+static u32 dw_dma_bytes2block(struct dw_dma_chan *dwc,
+			      size_t bytes, unsigned int width, size_t *len)
+{
+	u32 block;
+
+	if ((bytes >> width) > dwc->block_size) {
+		block = dwc->block_size;
+		*len = dwc->block_size << width;
+	} else {
+		block = bytes >> width;
+		*len = bytes;
+	}
+
+	return block;
+}
+
+static size_t dw_dma_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
+{
+	return DWC_CTLH_BLOCK_TS(block) << width;
+}
+
+static u32 dw_dma_prepare_ctllo(struct dw_dma_chan *dwc)
+{
+	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
+	bool is_slave = is_slave_direction(dwc->direction);
+	u8 smsize = is_slave ? sconfig->src_maxburst : DW_DMA_MSIZE_16;
+	u8 dmsize = is_slave ? sconfig->dst_maxburst : DW_DMA_MSIZE_16;
+	u8 p_master = dwc->dws.p_master;
+	u8 m_master = dwc->dws.m_master;
+	u8 dms = (dwc->direction == DMA_MEM_TO_DEV) ? p_master : m_master;
+	u8 sms = (dwc->direction == DMA_DEV_TO_MEM) ? p_master : m_master;
+
+	return DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN |
+	       DWC_CTLL_DST_MSIZE(dmsize) | DWC_CTLL_SRC_MSIZE(smsize) |
+	       DWC_CTLL_DMS(dms) | DWC_CTLL_SMS(sms);
+}
+
+static void dw_dma_encode_maxburst(struct dw_dma_chan *dwc, u32 *maxburst)
+{
+	/*
+	 * Fix burst size according to dw_dmac. We need to convert them as:
+	 * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
+	 */
+	*maxburst = *maxburst > 1 ? fls(*maxburst) - 2 : 0;
+}
+
+static void dw_dma_set_device_name(struct dw_dma *dw, int id)
+{
+	snprintf(dw->name, sizeof(dw->name), "dw:dmac%d", id);
+}
+
+static void dw_dma_disable(struct dw_dma *dw)
+{
+	do_dw_dma_off(dw);
+}
+
+static void dw_dma_enable(struct dw_dma *dw)
+{
+	do_dw_dma_on(dw);
+}
+
+int dw_dma_probe(struct dw_dma_chip *chip)
+{
+	struct dw_dma *dw;
+
+	dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	/* Channel operations */
+	dw->initialize_chan = dw_dma_initialize_chan;
+	dw->suspend_chan = dw_dma_suspend_chan;
+	dw->resume_chan = dw_dma_resume_chan;
+	dw->prepare_ctllo = dw_dma_prepare_ctllo;
+	dw->encode_maxburst = dw_dma_encode_maxburst;
+	dw->bytes2block = dw_dma_bytes2block;
+	dw->block2bytes = dw_dma_block2bytes;
+
+	/* Device operations */
+	dw->set_device_name = dw_dma_set_device_name;
+	dw->disable = dw_dma_disable;
+	dw->enable = dw_dma_enable;
+
+	chip->dw = dw;
+	return do_dma_probe(chip);
+}
+EXPORT_SYMBOL_GPL(dw_dma_probe);
+
+int dw_dma_remove(struct dw_dma_chip *chip)
+{
+	return do_dma_remove(chip);
+}
+EXPORT_SYMBOL_GPL(dw_dma_remove);

drivers/dma/dw/idma32.c

+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2013,2018 Intel Corporation
+
+#include <linux/bitops.h>
+#include <linux/dmaengine.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "internal.h"
+
+static void idma32_initialize_chan(struct dw_dma_chan *dwc)
+{
+	u32 cfghi = 0;
+	u32 cfglo = 0;
+
+	/* Set default burst alignment */
+	cfglo |= IDMA32C_CFGL_DST_BURST_ALIGN | IDMA32C_CFGL_SRC_BURST_ALIGN;
+
+	/* Low 4 bits of the request lines */
+	cfghi |= IDMA32C_CFGH_DST_PER(dwc->dws.dst_id & 0xf);
+	cfghi |= IDMA32C_CFGH_SRC_PER(dwc->dws.src_id & 0xf);
+
+	/* Request line extension (2 bits) */
+	cfghi |= IDMA32C_CFGH_DST_PER_EXT(dwc->dws.dst_id >> 4 & 0x3);
+	cfghi |= IDMA32C_CFGH_SRC_PER_EXT(dwc->dws.src_id >> 4 & 0x3);
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void idma32_suspend_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	if (drain)
+		cfglo |= IDMA32C_CFGL_CH_DRAIN;
+
+	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+}
+
+static void idma32_resume_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	if (drain)
+		cfglo &= ~IDMA32C_CFGL_CH_DRAIN;
+
+	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+}
+
+static u32 idma32_bytes2block(struct dw_dma_chan *dwc,
+			      size_t bytes, unsigned int width, size_t *len)
+{
+	u32 block;
+
+	if (bytes > dwc->block_size) {
+		block = dwc->block_size;
+		*len = dwc->block_size;
+	} else {
+		block = bytes;
+		*len = bytes;
+	}
+
+	return block;
+}
+
+static size_t idma32_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
+{
+	return IDMA32C_CTLH_BLOCK_TS(block);
+}
+
+static u32 idma32_prepare_ctllo(struct dw_dma_chan *dwc)
+{
+	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
+	bool is_slave = is_slave_direction(dwc->direction);
+	u8 smsize = is_slave ? sconfig->src_maxburst : IDMA32_MSIZE_8;
+	u8 dmsize = is_slave ? sconfig->dst_maxburst : IDMA32_MSIZE_8;
+
+	return DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN |
+	       DWC_CTLL_DST_MSIZE(dmsize) | DWC_CTLL_SRC_MSIZE(smsize);
+}
+
+static void idma32_encode_maxburst(struct dw_dma_chan *dwc, u32 *maxburst)
+{
+	*maxburst = *maxburst > 1 ? fls(*maxburst) - 1 : 0;
+}
+
+static void idma32_set_device_name(struct dw_dma *dw, int id)
+{
+	snprintf(dw->name, sizeof(dw->name), "idma32:dmac%d", id);
+}
+
+/*
+ * Program FIFO size of channels.
+ *
+ * By default full FIFO (512 bytes) is assigned to channel 0. Here we
+ * slice FIFO on equal parts between channels.
+ */
+static void idma32_fifo_partition(struct dw_dma *dw)
+{
+	u64 value = IDMA32C_FP_PSIZE_CH0(64) | IDMA32C_FP_PSIZE_CH1(64) |
+		    IDMA32C_FP_UPDATE;
+	u64 fifo_partition = 0;
+
+	/* Fill FIFO_PARTITION low bits (Channels 0..1, 4..5) */
+	fifo_partition |= value << 0;
+
+	/* Fill FIFO_PARTITION high bits (Channels 2..3, 6..7) */
+	fifo_partition |= value << 32;
+
+	/* Program FIFO Partition registers - 64 bytes per channel */
+	idma32_writeq(dw, FIFO_PARTITION1, fifo_partition);
+	idma32_writeq(dw, FIFO_PARTITION0, fifo_partition);
+}
+
+static void idma32_disable(struct dw_dma *dw)
+{
+	do_dw_dma_off(dw);
+	idma32_fifo_partition(dw);
+}
+
+static void idma32_enable(struct dw_dma *dw)
+{
+	idma32_fifo_partition(dw);
+	do_dw_dma_on(dw);
+}
+
+int idma32_dma_probe(struct dw_dma_chip *chip)
+{
+	struct dw_dma *dw;
+
+	dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	/* Channel operations */
+	dw->initialize_chan = idma32_initialize_chan;
+	dw->suspend_chan = idma32_suspend_chan;
+	dw->resume_chan = idma32_resume_chan;
+	dw->prepare_ctllo = idma32_prepare_ctllo;
+	dw->encode_maxburst = idma32_encode_maxburst;
+	dw->bytes2block = idma32_bytes2block;
+	dw->block2bytes = idma32_block2bytes;
+
+	/* Device operations */
+	dw->set_device_name = idma32_set_device_name;
+	dw->disable = idma32_disable;
+	dw->enable = idma32_enable;
+
+	chip->dw = dw;
+	return do_dma_probe(chip);
+}
+EXPORT_SYMBOL_GPL(idma32_dma_probe);
+
+int idma32_dma_remove(struct dw_dma_chip *chip)
+{
+	return do_dma_remove(chip);
+}
+EXPORT_SYMBOL_GPL(idma32_dma_remove);

drivers/dma/dw/internal.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef _DMA_DW_INTERNAL_H
@@ -15,8 +12,14 @@
 
 #include "regs.h"
 
-int dw_dma_disable(struct dw_dma_chip *chip);
-int dw_dma_enable(struct dw_dma_chip *chip);
+int do_dma_probe(struct dw_dma_chip *chip);
+int do_dma_remove(struct dw_dma_chip *chip);
+
+void do_dw_dma_on(struct dw_dma *dw);
+void do_dw_dma_off(struct dw_dma *dw);
+
+int do_dw_dma_disable(struct dw_dma_chip *chip);
+int do_dw_dma_enable(struct dw_dma_chip *chip);
 
 extern bool dw_dma_filter(struct dma_chan *chan, void *param);
 

drivers/dma/dw/pci.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * PCI driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2013 Intel Corporation
  * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -15,21 +12,33 @@
 
 #include "internal.h"
 
-static struct dw_dma_platform_data mrfld_pdata = {
+struct dw_dma_pci_data {
+	const struct dw_dma_platform_data *pdata;
+	int (*probe)(struct dw_dma_chip *chip);
+};
+
+static const struct dw_dma_pci_data dw_pci_data = {
+	.probe = dw_dma_probe,
+};
+
+static const struct dw_dma_platform_data idma32_pdata = {
 	.nr_channels = 8,
-	.is_private = true,
-	.is_memcpy = true,
-	.is_idma32 = true,
 	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
 	.chan_priority = CHAN_PRIORITY_ASCENDING,
 	.block_size = 131071,
 	.nr_masters = 1,
 	.data_width = {4},
+	.multi_block = {1, 1, 1, 1, 1, 1, 1, 1},
+};
+
+static const struct dw_dma_pci_data idma32_pci_data = {
+	.pdata = &idma32_pdata,
+	.probe = idma32_dma_probe,
 };
 
 static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 {
-	const struct dw_dma_platform_data *pdata = (void *)pid->driver_data;
+	const struct dw_dma_pci_data *data = (void *)pid->driver_data;
 	struct dw_dma_chip *chip;
 	int ret;
 
@@ -62,9 +71,9 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 	chip->id = pdev->devfn;
 	chip->regs = pcim_iomap_table(pdev)[0];
 	chip->irq = pdev->irq;
-	chip->pdata = pdata;
+	chip->pdata = data->pdata;
 
-	ret = dw_dma_probe(chip);
+	ret = data->probe(chip);
 	if (ret)
 		return ret;
 
@@ -90,7 +99,7 @@ static int dw_pci_suspend_late(struct device *dev)
 	struct pci_dev *pci = to_pci_dev(dev);
 	struct dw_dma_chip *chip = pci_get_drvdata(pci);
 
-	return dw_dma_disable(chip);
+	return do_dw_dma_disable(chip);
 };
 
 static int dw_pci_resume_early(struct device *dev)
@@ -98,7 +107,7 @@ static int dw_pci_resume_early(struct device *dev)
 	struct pci_dev *pci = to_pci_dev(dev);
 	struct dw_dma_chip *chip = pci_get_drvdata(pci);
 
-	return dw_dma_enable(chip);
+	return do_dw_dma_enable(chip);
 };
 
 #endif /* CONFIG_PM_SLEEP */
@@ -109,24 +118,24 @@ static const struct dev_pm_ops dw_pci_dev_pm_ops = {
 
 static const struct pci_device_id dw_pci_id_table[] = {
 	/* Medfield (GPDMA) */
-	{ PCI_VDEVICE(INTEL, 0x0827) },
+	{ PCI_VDEVICE(INTEL, 0x0827), (kernel_ulong_t)&dw_pci_data },
 
 	/* BayTrail */
-	{ PCI_VDEVICE(INTEL, 0x0f06) },
-	{ PCI_VDEVICE(INTEL, 0x0f40) },
+	{ PCI_VDEVICE(INTEL, 0x0f06), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x0f40), (kernel_ulong_t)&dw_pci_data },
 
-	/* Merrifield iDMA 32-bit (GPDMA) */
-	{ PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&mrfld_pdata },
+	/* Merrifield */
+	{ PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&idma32_pci_data },
 
 	/* Braswell */
-	{ PCI_VDEVICE(INTEL, 0x2286) },
-	{ PCI_VDEVICE(INTEL, 0x22c0) },
+	{ PCI_VDEVICE(INTEL, 0x2286), (kernel_ulong_t)&dw_pci_data },
+	{ PCI_VDEVICE(INTEL, 0x22c0), (kernel_ulong_t)&dw_pci_data },
 
 	/* Haswell */
-	{ PCI_VDEVICE(INTEL, 0x9c60) },
+	{ PCI_VDEVICE(INTEL, 0x9c60), (kernel_ulong_t)&dw_pci_data },
 
 	/* Broadwell */
-	{ PCI_VDEVICE(INTEL, 0x9ce0) },
+	{ PCI_VDEVICE(INTEL, 0x9ce0), (kernel_ulong_t)&dw_pci_data },
 
 	{ }
 };

drivers/dma/dw/platform.c

+// SPDX-License-Identifier: GPL-2.0
 /*
  * Platform driver for the Synopsys DesignWare DMA Controller
  *
@@ -6,10 +7,6 @@
  * Copyright (C) 2013 Intel Corporation
  *
  * Some parts of this driver are derived from the original dw_dmac.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
@@ -128,15 +125,6 @@ dw_dma_parse_dt(struct platform_device *pdev)
 	pdata->nr_masters = nr_masters;
 	pdata->nr_channels = nr_channels;
 
-	if (of_property_read_bool(np, "is_private"))
-		pdata->is_private = true;
-
-	/*
-	 * All known devices, which use DT for configuration, support
-	 * memory-to-memory transfers. So enable it by default.
-	 */
-	pdata->is_memcpy = true;
-
 	if (!of_property_read_u32(np, "chan_allocation_order", &tmp))
 		pdata->chan_allocation_order = (unsigned char)tmp;
 
@@ -264,7 +252,7 @@ static void dw_shutdown(struct platform_device *pdev)
 	struct dw_dma_chip *chip = platform_get_drvdata(pdev);
 
 	/*
-	 * We have to call dw_dma_disable() to stop any ongoing transfer. On
+	 * We have to call do_dw_dma_disable() to stop any ongoing transfer. On
 	 * some platforms we can't do that since DMA device is powered off.
 	 * Moreover we have no possibility to check if the platform is affected
 	 * or not. That's why we call pm_runtime_get_sync() / pm_runtime_put()
@@ -273,7 +261,7 @@ static void dw_shutdown(struct platform_device *pdev)
 	 * used by the driver.
 	 */
 	pm_runtime_get_sync(chip->dev);
-	dw_dma_disable(chip);
+	do_dw_dma_disable(chip);
 	pm_runtime_put_sync_suspend(chip->dev);
 
 	clk_disable_unprepare(chip->clk);
@@ -303,7 +291,7 @@ static int dw_suspend_late(struct device *dev)
 {
 	struct dw_dma_chip *chip = dev_get_drvdata(dev);
 
-	dw_dma_disable(chip);
+	do_dw_dma_disable(chip);
 	clk_disable_unprepare(chip->clk);
 
 	return 0;
@@ -318,7 +306,7 @@ static int dw_resume_early(struct device *dev)
 	if (ret)
 		return ret;
 
-	return dw_dma_enable(chip);
+	return do_dw_dma_enable(chip);
 }
 
 #endif /* CONFIG_PM_SLEEP */

drivers/dma/dw/regs.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Driver for the Synopsys DesignWare AHB DMA Controller
  *
  * Copyright (C) 2005-2007 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
  * Copyright (C) 2016 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/bitops.h>
@@ -222,6 +219,16 @@ enum dw_dma_msize {
 
 /* iDMA 32-bit support */
 
+/* bursts size */
+enum idma32_msize {
+	IDMA32_MSIZE_1,
+	IDMA32_MSIZE_2,
+	IDMA32_MSIZE_4,
+	IDMA32_MSIZE_8,
+	IDMA32_MSIZE_16,
+	IDMA32_MSIZE_32,
+};
+
 /* Bitfields in CTL_HI */
 #define IDMA32C_CTLH_BLOCK_TS_MASK	GENMASK(16, 0)
 #define IDMA32C_CTLH_BLOCK_TS(x)	((x) & IDMA32C_CTLH_BLOCK_TS_MASK)
@@ -312,6 +319,21 @@ struct dw_dma {
 	u8			all_chan_mask;
 	u8			in_use;
 
+	/* Channel operations */
+	void	(*initialize_chan)(struct dw_dma_chan *dwc);
+	void	(*suspend_chan)(struct dw_dma_chan *dwc, bool drain);
+	void	(*resume_chan)(struct dw_dma_chan *dwc, bool drain);
+	u32	(*prepare_ctllo)(struct dw_dma_chan *dwc);
+	void	(*encode_maxburst)(struct dw_dma_chan *dwc, u32 *maxburst);
+	u32	(*bytes2block)(struct dw_dma_chan *dwc, size_t bytes,
+			       unsigned int width, size_t *len);
+	size_t	(*block2bytes)(struct dw_dma_chan *dwc, u32 block, u32 width);
+
+	/* Device operations */
+	void (*set_device_name)(struct dw_dma *dw, int id);
+	void (*disable)(struct dw_dma *dw);
+	void (*enable)(struct dw_dma *dw);
+
 	/* platform data */
 	struct dw_dma_platform_data	*pdata;
 };

drivers/dma/fsl-edma-common.c

@@ -6,6 +6,7 @@
 #include <linux/dmapool.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/dma-mapping.h>
 
 #include "fsl-edma-common.h"
 
@@ -173,12 +174,62 @@ int fsl_edma_resume(struct dma_chan *chan)
 }
 EXPORT_SYMBOL_GPL(fsl_edma_resume);
 
+static void fsl_edma_unprep_slave_dma(struct fsl_edma_chan *fsl_chan)
+{
+	if (fsl_chan->dma_dir != DMA_NONE)
+		dma_unmap_resource(fsl_chan->vchan.chan.device->dev,
+				   fsl_chan->dma_dev_addr,
+				   fsl_chan->dma_dev_size,
+				   fsl_chan->dma_dir, 0);
+	fsl_chan->dma_dir = DMA_NONE;
+}
+
+static bool fsl_edma_prep_slave_dma(struct fsl_edma_chan *fsl_chan,
+				    enum dma_transfer_direction dir)
+{
+	struct device *dev = fsl_chan->vchan.chan.device->dev;
+	enum dma_data_direction dma_dir;
+	phys_addr_t addr = 0;
+	u32 size = 0;
+
+	switch (dir) {
+	case DMA_MEM_TO_DEV:
+		dma_dir = DMA_FROM_DEVICE;
+		addr = fsl_chan->cfg.dst_addr;
+		size = fsl_chan->cfg.dst_maxburst;
+		break;
+	case DMA_DEV_TO_MEM:
+		dma_dir = DMA_TO_DEVICE;
+		addr = fsl_chan->cfg.src_addr;
+		size = fsl_chan->cfg.src_maxburst;
+		break;
+	default:
+		dma_dir = DMA_NONE;
+		break;
+	}
+
+	/* Already mapped for this config? */
+	if (fsl_chan->dma_dir == dma_dir)
+		return true;
+
+	fsl_edma_unprep_slave_dma(fsl_chan);
+
+	fsl_chan->dma_dev_addr = dma_map_resource(dev, addr, size, dma_dir, 0);
+	if (dma_mapping_error(dev, fsl_chan->dma_dev_addr))
+		return false;
+	fsl_chan->dma_dev_size = size;
+	fsl_chan->dma_dir = dma_dir;
+
+	return true;
+}
+
 int fsl_edma_slave_config(struct dma_chan *chan,
 				 struct dma_slave_config *cfg)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
 
 	memcpy(&fsl_chan->cfg, cfg, sizeof(*cfg));
+	fsl_edma_unprep_slave_dma(fsl_chan);
 
 	return 0;
 }
@@ -339,9 +390,7 @@ static struct fsl_edma_desc *fsl_edma_alloc_desc(struct fsl_edma_chan *fsl_chan,
 	struct fsl_edma_desc *fsl_desc;
 	int i;
 
-	fsl_desc = kzalloc(sizeof(*fsl_desc) +
-			   sizeof(struct fsl_edma_sw_tcd) *
-			   sg_len, GFP_NOWAIT);
+	fsl_desc = kzalloc(struct_size(fsl_desc, tcd, sg_len), GFP_NOWAIT);
 	if (!fsl_desc)
 		return NULL;
 
@@ -378,6 +427,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 	if (!is_slave_direction(direction))
 		return NULL;
 
+	if (!fsl_edma_prep_slave_dma(fsl_chan, direction))
+		return NULL;
+
 	sg_len = buf_len / period_len;
 	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
 	if (!fsl_desc)
@@ -409,11 +461,11 @@ struct dma_async_tx_descriptor *fsl_edma_prep_dma_cyclic(
 
 		if (direction == DMA_MEM_TO_DEV) {
 			src_addr = dma_buf_next;
-			dst_addr = fsl_chan->cfg.dst_addr;
+			dst_addr = fsl_chan->dma_dev_addr;
 			soff = fsl_chan->cfg.dst_addr_width;
 			doff = 0;
 		} else {
-			src_addr = fsl_chan->cfg.src_addr;
+			src_addr = fsl_chan->dma_dev_addr;
 			dst_addr = dma_buf_next;
 			soff = 0;
 			doff = fsl_chan->cfg.src_addr_width;
@@ -444,6 +496,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 	if (!is_slave_direction(direction))
 		return NULL;
 
+	if (!fsl_edma_prep_slave_dma(fsl_chan, direction))
+		return NULL;
+
 	fsl_desc = fsl_edma_alloc_desc(fsl_chan, sg_len);
 	if (!fsl_desc)
 		return NULL;
@@ -468,11 +523,11 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 
 		if (direction == DMA_MEM_TO_DEV) {
 			src_addr = sg_dma_address(sg);
-			dst_addr = fsl_chan->cfg.dst_addr;
+			dst_addr = fsl_chan->dma_dev_addr;
 			soff = fsl_chan->cfg.dst_addr_width;
 			doff = 0;
 		} else {
-			src_addr = fsl_chan->cfg.src_addr;
+			src_addr = fsl_chan->dma_dev_addr;
 			dst_addr = sg_dma_address(sg);
 			soff = 0;
 			doff = fsl_chan->cfg.src_addr_width;
@@ -555,6 +610,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
 	fsl_edma_chan_mux(fsl_chan, 0, false);
 	fsl_chan->edesc = NULL;
 	vchan_get_all_descriptors(&fsl_chan->vchan, &head);
+	fsl_edma_unprep_slave_dma(fsl_chan);
 	spin_unlock_irqrestore(&fsl_chan->vchan.lock, flags);
 
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);

drivers/dma/fsl-edma-common.h

@@ -6,6 +6,7 @@
 #ifndef _FSL_EDMA_COMMON_H_
 #define _FSL_EDMA_COMMON_H_
 
+#include <linux/dma-direction.h>
 #include "virt-dma.h"
 
 #define EDMA_CR_EDBG		BIT(1)
@@ -120,6 +121,9 @@ struct fsl_edma_chan {
 	struct dma_slave_config		cfg;
 	u32				attr;
 	struct dma_pool			*tcd_pool;
+	dma_addr_t			dma_dev_addr;
+	u32				dma_dev_size;
+	enum dma_data_direction		dma_dir;
 };
 
 struct fsl_edma_desc {

drivers/dma/fsl-edma.c

@@ -254,6 +254,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 		fsl_chan->pm_state = RUNNING;
 		fsl_chan->slave_id = 0;
 		fsl_chan->idle = true;
+		fsl_chan->dma_dir = DMA_NONE;
 		fsl_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&fsl_chan->vchan, &fsl_edma->dma_dev);
 

drivers/dma/fsldma.c

@@ -53,42 +53,42 @@ static const char msg_ld_oom[] = "No free memory for link descriptor";
 
 static void set_sr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->sr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->sr, val, 32);
 }
 
 static u32 get_sr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->sr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->sr, 32);
 }
 
 static void set_mr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->mr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->mr, val, 32);
 }
 
 static u32 get_mr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->mr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->mr, 32);
 }
 
 static void set_cdar(struct fsldma_chan *chan, dma_addr_t addr)
 {
-	DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
+	FSL_DMA_OUT(chan, &chan->regs->cdar, addr | FSL_DMA_SNEN, 64);
 }
 
 static dma_addr_t get_cdar(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
+	return FSL_DMA_IN(chan, &chan->regs->cdar, 64) & ~FSL_DMA_SNEN;
 }
 
 static void set_bcr(struct fsldma_chan *chan, u32 val)
 {
-	DMA_OUT(chan, &chan->regs->bcr, val, 32);
+	FSL_DMA_OUT(chan, &chan->regs->bcr, val, 32);
 }
 
 static u32 get_bcr(struct fsldma_chan *chan)
 {
-	return DMA_IN(chan, &chan->regs->bcr, 32);
+	return FSL_DMA_IN(chan, &chan->regs->bcr, 32);
 }
 
 /*

drivers/dma/fsldma.h

@@ -196,39 +196,67 @@ struct fsldma_chan {
 #define to_fsl_desc(lh) container_of(lh, struct fsl_desc_sw, node)
 #define tx_to_fsl_desc(tx) container_of(tx, struct fsl_desc_sw, async_tx)
 
-#ifndef __powerpc64__
-static u64 in_be64(const u64 __iomem *addr)
+#ifdef	CONFIG_PPC
+#define fsl_ioread32(p)		in_le32(p)
+#define fsl_ioread32be(p)	in_be32(p)
+#define fsl_iowrite32(v, p)	out_le32(p, v)
+#define fsl_iowrite32be(v, p)	out_be32(p, v)
+
+#ifdef __powerpc64__
+#define fsl_ioread64(p)		in_le64(p)
+#define fsl_ioread64be(p)	in_be64(p)
+#define fsl_iowrite64(v, p)	out_le64(p, v)
+#define fsl_iowrite64be(v, p)	out_be64(p, v)
+#else
+static u64 fsl_ioread64(const u64 __iomem *addr)
 {
-	return ((u64)in_be32((u32 __iomem *)addr) << 32) |
-		(in_be32((u32 __iomem *)addr + 1));
+	u32 fsl_addr = lower_32_bits(addr);
+	u64 fsl_addr_hi = (u64)in_le32((u32 *)(fsl_addr + 1)) << 32;
+
+	return fsl_addr_hi | in_le32((u32 *)fsl_addr);
 }
 
-static void out_be64(u64 __iomem *addr, u64 val)
+static void fsl_iowrite64(u64 val, u64 __iomem *addr)
 {
-	out_be32((u32 __iomem *)addr, val >> 32);
-	out_be32((u32 __iomem *)addr + 1, (u32)val);
+	out_le32((u32 __iomem *)addr + 1, val >> 32);
+	out_le32((u32 __iomem *)addr, (u32)val);
 }
 
-/* There is no asm instructions for 64 bits reverse loads and stores */
-static u64 in_le64(const u64 __iomem *addr)
+static u64 fsl_ioread64be(const u64 __iomem *addr)
 {
-	return ((u64)in_le32((u32 __iomem *)addr + 1) << 32) |
-		(in_le32((u32 __iomem *)addr));
+	u32 fsl_addr = lower_32_bits(addr);
+	u64 fsl_addr_hi = (u64)in_be32((u32 *)fsl_addr) << 32;
+
+	return fsl_addr_hi | in_be32((u32 *)(fsl_addr + 1));
 }
 
-static void out_le64(u64 __iomem *addr, u64 val)
+static void fsl_iowrite64be(u64 val, u64 __iomem *addr)
 {
-	out_le32((u32 __iomem *)addr + 1, val >> 32);
-	out_le32((u32 __iomem *)addr, (u32)val);
+	out_be32((u32 __iomem *)addr, val >> 32);
+	out_be32((u32 __iomem *)addr + 1, (u32)val);
 }
 #endif
+#endif
 
-#define DMA_IN(fsl_chan, addr, width)					\
-		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\
-			in_be##width(addr) : in_le##width(addr))
-#define DMA_OUT(fsl_chan, addr, val, width)				\
-		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\
-			out_be##width(addr, val) : out_le##width(addr, val))
+#if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
+#define fsl_ioread32(p)		ioread32(p)
+#define fsl_ioread32be(p)	ioread32be(p)
+#define fsl_iowrite32(v, p)	iowrite32(v, p)
+#define fsl_iowrite32be(v, p)	iowrite32be(v, p)
+#define fsl_ioread64(p)		ioread64(p)
+#define fsl_ioread64be(p)	ioread64be(p)
+#define fsl_iowrite64(v, p)	iowrite64(v, p)
+#define fsl_iowrite64be(v, p)	iowrite64be(v, p)
+#endif
+
+#define FSL_DMA_IN(fsl_dma, addr, width)			\
+		(((fsl_dma)->feature & FSL_DMA_BIG_ENDIAN) ?	\
+			fsl_ioread##width##be(addr) : fsl_ioread##width(addr))
+
+#define FSL_DMA_OUT(fsl_dma, addr, val, width)			\
+		(((fsl_dma)->feature & FSL_DMA_BIG_ENDIAN) ?	\
+			fsl_iowrite##width##be(val, addr) : fsl_iowrite	\
+		##width(val, addr))
 
 #define DMA_TO_CPU(fsl_chan, d, width)					\
 		(((fsl_chan)->feature & FSL_DMA_BIG_ENDIAN) ?		\

drivers/dma/imx-dma.c

@@ -278,14 +278,14 @@ static int imxdma_hw_chain(struct imxdma_channel *imxdmac)
 /*
  * imxdma_sg_next - prepare next chunk for scatter-gather DMA emulation
  */
-static inline int imxdma_sg_next(struct imxdma_desc *d)
+static inline void imxdma_sg_next(struct imxdma_desc *d)
 {
 	struct imxdma_channel *imxdmac = to_imxdma_chan(d->desc.chan);
 	struct imxdma_engine *imxdma = imxdmac->imxdma;
 	struct scatterlist *sg = d->sg;
-	unsigned long now;
+	size_t now;
 
-	now = min(d->len, sg_dma_len(sg));
+	now = min_t(size_t, d->len, sg_dma_len(sg));
 	if (d->len != IMX_DMA_LENGTH_LOOP)
 		d->len -= now;
 
@@ -303,8 +303,6 @@ static inline int imxdma_sg_next(struct imxdma_desc *d)
 		 imx_dmav1_readl(imxdma, DMA_DAR(imxdmac->channel)),
 		 imx_dmav1_readl(imxdma, DMA_SAR(imxdmac->channel)),
 		 imx_dmav1_readl(imxdma, DMA_CNTR(imxdmac->channel)));
-
-	return now;
 }
 
 static void imxdma_enable_hw(struct imxdma_desc *d)

drivers/dma/imx-sdma.c

@@ -377,6 +377,7 @@ struct sdma_channel {
 	unsigned long			watermark_level;
 	u32				shp_addr, per_addr;
 	enum dma_status			status;
+	bool				context_loaded;
 	struct imx_dma_data		data;
 	struct work_struct		terminate_worker;
 };
@@ -440,6 +441,8 @@ struct sdma_engine {
 	unsigned int			irq;
 	dma_addr_t			bd0_phys;
 	struct sdma_buffer_descriptor	*bd0;
+	/* clock ratio for AHB:SDMA core. 1:1 is 1, 2:1 is 0*/
+	bool				clk_ratio;
 };
 
 static int sdma_config_write(struct dma_chan *chan,
@@ -662,8 +665,11 @@ static int sdma_run_channel0(struct sdma_engine *sdma)
 		dev_err(sdma->dev, "Timeout waiting for CH0 ready\n");
 
 	/* Set bits of CONFIG register with dynamic context switching */
-	if (readl(sdma->regs + SDMA_H_CONFIG) == 0)
-		writel_relaxed(SDMA_H_CONFIG_CSM, sdma->regs + SDMA_H_CONFIG);
+	reg = readl(sdma->regs + SDMA_H_CONFIG);
+	if ((reg & SDMA_H_CONFIG_CSM) == 0) {
+		reg |= SDMA_H_CONFIG_CSM;
+		writel_relaxed(reg, sdma->regs + SDMA_H_CONFIG);
+	}
 
 	return ret;
 }
@@ -677,7 +683,7 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size,
 	int ret;
 	unsigned long flags;
 
-	buf_virt = dma_alloc_coherent(NULL, size, &buf_phys, GFP_KERNEL);
+	buf_virt = dma_alloc_coherent(sdma->dev, size, &buf_phys, GFP_KERNEL);
 	if (!buf_virt) {
 		return -ENOMEM;
 	}
@@ -696,7 +702,7 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size,
 
 	spin_unlock_irqrestore(&sdma->channel_0_lock, flags);
 
-	dma_free_coherent(NULL, size, buf_virt, buf_phys);
+	dma_free_coherent(sdma->dev, size, buf_virt, buf_phys);
 
 	return ret;
 }
@@ -970,6 +976,9 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 	int ret;
 	unsigned long flags;
 
+	if (sdmac->context_loaded)
+		return 0;
+
 	if (sdmac->direction == DMA_DEV_TO_MEM)
 		load_address = sdmac->pc_from_device;
 	else if (sdmac->direction == DMA_DEV_TO_DEV)
@@ -1012,6 +1021,8 @@ static int sdma_load_context(struct sdma_channel *sdmac)
 
 	spin_unlock_irqrestore(&sdma->channel_0_lock, flags);
 
+	sdmac->context_loaded = true;
+
 	return ret;
 }
 
@@ -1051,6 +1062,7 @@ static void sdma_channel_terminate_work(struct work_struct *work)
 	sdmac->desc = NULL;
 	spin_unlock_irqrestore(&sdmac->vc.lock, flags);
 	vchan_dma_desc_free_list(&sdmac->vc, &head);
+	sdmac->context_loaded = false;
 }
 
 static int sdma_disable_channel_async(struct dma_chan *chan)
@@ -1182,8 +1194,8 @@ static int sdma_request_channel0(struct sdma_engine *sdma)
 {
 	int ret = -EBUSY;
 
-	sdma->bd0 = dma_alloc_coherent(NULL, PAGE_SIZE, &sdma->bd0_phys,
-				       GFP_NOWAIT);
+	sdma->bd0 = dma_alloc_coherent(sdma->dev, PAGE_SIZE, &sdma->bd0_phys,
+					GFP_NOWAIT);
 	if (!sdma->bd0) {
 		ret = -ENOMEM;
 		goto out;
@@ -1205,8 +1217,8 @@ static int sdma_alloc_bd(struct sdma_desc *desc)
 	u32 bd_size = desc->num_bd * sizeof(struct sdma_buffer_descriptor);
 	int ret = 0;
 
-	desc->bd = dma_alloc_coherent(NULL, bd_size, &desc->bd_phys,
-				      GFP_NOWAIT);
+	desc->bd = dma_alloc_coherent(desc->sdmac->sdma->dev, bd_size,
+				       &desc->bd_phys, GFP_NOWAIT);
 	if (!desc->bd) {
 		ret = -ENOMEM;
 		goto out;
@@ -1219,7 +1231,8 @@ static void sdma_free_bd(struct sdma_desc *desc)
 {
 	u32 bd_size = desc->num_bd * sizeof(struct sdma_buffer_descriptor);
 
-	dma_free_coherent(NULL, bd_size, desc->bd, desc->bd_phys);
+	dma_free_coherent(desc->sdmac->sdma->dev, bd_size, desc->bd,
+			  desc->bd_phys);
 }
 
 static void sdma_desc_free(struct virt_dma_desc *vd)
@@ -1839,10 +1852,13 @@ static int sdma_init(struct sdma_engine *sdma)
 	if (ret)
 		goto disable_clk_ipg;
 
+	if (clk_get_rate(sdma->clk_ahb) == clk_get_rate(sdma->clk_ipg))
+		sdma->clk_ratio = 1;
+
 	/* Be sure SDMA has not started yet */
 	writel_relaxed(0, sdma->regs + SDMA_H_C0PTR);
 
-	sdma->channel_control = dma_alloc_coherent(NULL,
+	sdma->channel_control = dma_alloc_coherent(sdma->dev,
 			MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control) +
 			sizeof(struct sdma_context_data),
 			&ccb_phys, GFP_KERNEL);
@@ -1879,8 +1895,10 @@ static int sdma_init(struct sdma_engine *sdma)
 	writel_relaxed(0x4050, sdma->regs + SDMA_CHN0ADDR);
 
 	/* Set bits of CONFIG register but with static context switching */
-	/* FIXME: Check whether to set ACR bit depending on clock ratios */
-	writel_relaxed(0, sdma->regs + SDMA_H_CONFIG);
+	if (sdma->clk_ratio)
+		writel_relaxed(SDMA_H_CONFIG_ACR, sdma->regs + SDMA_H_CONFIG);
+	else
+		writel_relaxed(0, sdma->regs + SDMA_H_CONFIG);
 
 	writel_relaxed(ccb_phys, sdma->regs + SDMA_H_C0PTR);
 
@@ -1903,11 +1921,16 @@ static int sdma_init(struct sdma_engine *sdma)
 static bool sdma_filter_fn(struct dma_chan *chan, void *fn_param)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
+	struct sdma_engine *sdma = sdmac->sdma;
 	struct imx_dma_data *data = fn_param;
 
 	if (!imx_dma_is_general_purpose(chan))
 		return false;
 
+	/* return false if it's not the right device */
+	if (sdma->dev->of_node != data->of_node)
+		return false;
+
 	sdmac->data = *data;
 	chan->private = &sdmac->data;
 
@@ -1935,6 +1958,7 @@ static struct dma_chan *sdma_xlate(struct of_phandle_args *dma_spec,
 	 * be set to sdmac->event_id1.
 	 */
 	data.dma_request2 = 0;
+	data.of_node = ofdma->of_node;
 
 	return dma_request_channel(mask, sdma_filter_fn, &data);
 }
@@ -2097,6 +2121,7 @@ static int sdma_probe(struct platform_device *pdev)
 	sdma->dma_device.device_prep_dma_memcpy = sdma_prep_memcpy;
 	sdma->dma_device.device_issue_pending = sdma_issue_pending;
 	sdma->dma_device.dev->dma_parms = &sdma->dma_parms;
+	sdma->dma_device.copy_align = 2;
 	dma_set_max_seg_size(sdma->dma_device.dev, SDMA_BD_MAX_CNT);
 
 	platform_set_drvdata(pdev, sdma);

drivers/dma/ioat/dma.c

@@ -372,6 +372,7 @@ struct ioat_ring_ent **
 ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 {
 	struct ioatdma_chan *ioat_chan = to_ioat_chan(c);
+	struct ioatdma_device *ioat_dma = ioat_chan->ioat_dma;
 	struct ioat_ring_ent **ring;
 	int total_descs = 1 << order;
 	int i, chunks;
@@ -437,6 +438,17 @@ ioat_alloc_ring(struct dma_chan *c, int order, gfp_t flags)
 	}
 	ring[i]->hw->next = ring[0]->txd.phys;
 
+	/* setup descriptor pre-fetching for v3.4 */
+	if (ioat_dma->cap & IOAT_CAP_DPS) {
+		u16 drsctl = IOAT_CHAN_DRSZ_2MB | IOAT_CHAN_DRS_EN;
+
+		if (chunks == 1)
+			drsctl |= IOAT_CHAN_DRS_AUTOWRAP;
+
+		writew(drsctl, ioat_chan->reg_base + IOAT_CHAN_DRSCTL_OFFSET);
+
+	}
+
 	return ring;
 }
 

drivers/dma/ioat/dma.h

@@ -27,7 +27,7 @@
 #include "registers.h"
 #include "hw.h"
 
-#define IOAT_DMA_VERSION  "4.00"
+#define IOAT_DMA_VERSION  "5.00"
 
 #define IOAT_DMA_DCA_ANY_CPU		~0
 

drivers/dma/ioat/hw.h

@@ -66,11 +66,14 @@
 
 #define PCI_DEVICE_ID_INTEL_IOAT_SKX	0x2021
 
+#define PCI_DEVICE_ID_INTEL_IOAT_ICX	0x0b00
+
 #define IOAT_VER_1_2            0x12    /* Version 1.2 */
 #define IOAT_VER_2_0            0x20    /* Version 2.0 */
 #define IOAT_VER_3_0            0x30    /* Version 3.0 */
 #define IOAT_VER_3_2            0x32    /* Version 3.2 */
 #define IOAT_VER_3_3            0x33    /* Version 3.3 */
+#define IOAT_VER_3_4		0x34	/* Version 3.4 */
 
 
 int system_has_dca_enabled(struct pci_dev *pdev);

drivers/dma/ioat/init.c

@@ -119,6 +119,9 @@ static const struct pci_device_id ioat_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE2) },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_BDXDE3) },
 
+	/* I/OAT v3.4 platforms */
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_IOAT_ICX) },
+
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, ioat_pci_tbl);
@@ -135,10 +138,10 @@ static int ioat3_dma_self_test(struct ioatdma_device *ioat_dma);
 static int ioat_dca_enabled = 1;
 module_param(ioat_dca_enabled, int, 0644);
 MODULE_PARM_DESC(ioat_dca_enabled, "control support of dca service (default: 1)");
-int ioat_pending_level = 4;
+int ioat_pending_level = 7;
 module_param(ioat_pending_level, int, 0644);
 MODULE_PARM_DESC(ioat_pending_level,
-		 "high-water mark for pushing ioat descriptors (default: 4)");
+		 "high-water mark for pushing ioat descriptors (default: 7)");
 static char ioat_interrupt_style[32] = "msix";
 module_param_string(ioat_interrupt_style, ioat_interrupt_style,
 		    sizeof(ioat_interrupt_style), 0644);
@@ -635,6 +638,11 @@ static void ioat_free_chan_resources(struct dma_chan *c)
 	ioat_stop(ioat_chan);
 	ioat_reset_hw(ioat_chan);
 
+	/* Put LTR to idle */
+	if (ioat_dma->version >= IOAT_VER_3_4)
+		writeb(IOAT_CHAN_LTR_SWSEL_IDLE,
+			ioat_chan->reg_base + IOAT_CHAN_LTR_SWSEL_OFFSET);
+
 	spin_lock_bh(&ioat_chan->cleanup_lock);
 	spin_lock_bh(&ioat_chan->prep_lock);
 	descs = ioat_ring_space(ioat_chan);
@@ -724,6 +732,28 @@ static int ioat_alloc_chan_resources(struct dma_chan *c)
 	spin_unlock_bh(&ioat_chan->prep_lock);
 	spin_unlock_bh(&ioat_chan->cleanup_lock);
 
+	/* Setting up LTR values for 3.4 or later */
+	if (ioat_chan->ioat_dma->version >= IOAT_VER_3_4) {
+		u32 lat_val;
+
+		lat_val = IOAT_CHAN_LTR_ACTIVE_SNVAL |
+			IOAT_CHAN_LTR_ACTIVE_SNLATSCALE |
+			IOAT_CHAN_LTR_ACTIVE_SNREQMNT;
+		writel(lat_val, ioat_chan->reg_base +
+				IOAT_CHAN_LTR_ACTIVE_OFFSET);
+
+		lat_val = IOAT_CHAN_LTR_IDLE_SNVAL |
+			  IOAT_CHAN_LTR_IDLE_SNLATSCALE |
+			  IOAT_CHAN_LTR_IDLE_SNREQMNT;
+		writel(lat_val, ioat_chan->reg_base +
+				IOAT_CHAN_LTR_IDLE_OFFSET);
+
+		/* Select to active */
+		writeb(IOAT_CHAN_LTR_SWSEL_ACTIVE,
+		       ioat_chan->reg_base +
+		       IOAT_CHAN_LTR_SWSEL_OFFSET);
+	}
+
 	ioat_start_null_desc(ioat_chan);
 
 	/* check that we got off the ground */
@@ -1185,6 +1215,10 @@ static int ioat3_dma_probe(struct ioatdma_device *ioat_dma, int dca)
 	if (err)
 		return err;
 
+	if (ioat_dma->cap & IOAT_CAP_DPS)
+		writeb(ioat_pending_level + 1,
+		       ioat_dma->reg_base + IOAT_PREFETCH_LIMIT_OFFSET);
+
 	return 0;
 }
 
@@ -1350,6 +1384,8 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_set_drvdata(pdev, device);
 
 	device->version = readb(device->reg_base + IOAT_VER_OFFSET);
+	if (device->version >= IOAT_VER_3_4)
+		ioat_dca_enabled = 0;
 	if (device->version >= IOAT_VER_3_0) {
 		if (is_skx_ioat(pdev))
 			device->version = IOAT_VER_3_2;

drivers/dma/ioat/registers.h

@@ -84,6 +84,9 @@
 #define IOAT_CAP_PQ				0x00000200
 #define IOAT_CAP_DWBES				0x00002000
 #define IOAT_CAP_RAID16SS			0x00020000
+#define IOAT_CAP_DPS				0x00800000
+
+#define IOAT_PREFETCH_LIMIT_OFFSET		0x4C	/* CHWPREFLMT */
 
 #define IOAT_CHANNEL_MMIO_SIZE			0x80	/* Each Channel MMIO space is this size */
 
@@ -243,4 +246,25 @@
 
 #define IOAT_CHANERR_MASK_OFFSET		0x2C	/* 32-bit Channel Error Register */
 
+#define IOAT_CHAN_DRSCTL_OFFSET			0xB6
+#define IOAT_CHAN_DRSZ_4KB			0x0000
+#define IOAT_CHAN_DRSZ_8KB			0x0001
+#define IOAT_CHAN_DRSZ_2MB			0x0009
+#define IOAT_CHAN_DRS_EN			0x0100
+#define IOAT_CHAN_DRS_AUTOWRAP			0x0200
+
+#define IOAT_CHAN_LTR_SWSEL_OFFSET		0xBC
+#define IOAT_CHAN_LTR_SWSEL_ACTIVE		0x0
+#define IOAT_CHAN_LTR_SWSEL_IDLE		0x1
+
+#define IOAT_CHAN_LTR_ACTIVE_OFFSET		0xC0
+#define IOAT_CHAN_LTR_ACTIVE_SNVAL		0x0000	/* 0 us */
+#define IOAT_CHAN_LTR_ACTIVE_SNLATSCALE		0x0800	/* 1us scale */
+#define IOAT_CHAN_LTR_ACTIVE_SNREQMNT		0x8000	/* snoop req enable */
+
+#define IOAT_CHAN_LTR_IDLE_OFFSET		0xC4
+#define IOAT_CHAN_LTR_IDLE_SNVAL		0x0258	/* 600 us */
+#define IOAT_CHAN_LTR_IDLE_SNLATSCALE		0x0800	/* 1us scale */
+#define IOAT_CHAN_LTR_IDLE_SNREQMNT		0x8000	/* snoop req enable */
+
 #endif /* _IOAT_REGISTERS_H_ */

drivers/dma/k3dma.c

@@ -52,8 +52,6 @@
 #define CX_SRC			0x814
 #define CX_DST			0x818
 #define CX_CFG			0x81c
-#define AXI_CFG			0x820
-#define AXI_CFG_DEFAULT		0x201201
 
 #define CX_LLI_CHAIN_EN		0x2
 #define CX_CFG_EN		0x1
@@ -113,9 +111,18 @@ struct k3_dma_dev {
 	struct dma_pool		*pool;
 	u32			dma_channels;
 	u32			dma_requests;
+	u32			dma_channel_mask;
 	unsigned int		irq;
 };
 
+
+#define K3_FLAG_NOCLK	BIT(1)
+
+struct k3dma_soc_data {
+	unsigned long flags;
+};
+
+
 #define to_k3_dma(dmadev) container_of(dmadev, struct k3_dma_dev, slave)
 
 static int k3_dma_config_write(struct dma_chan *chan,
@@ -161,7 +168,6 @@ static void k3_dma_set_desc(struct k3_dma_phy *phy, struct k3_desc_hw *hw)
 	writel_relaxed(hw->count, phy->base + CX_CNT0);
 	writel_relaxed(hw->saddr, phy->base + CX_SRC);
 	writel_relaxed(hw->daddr, phy->base + CX_DST);
-	writel_relaxed(AXI_CFG_DEFAULT, phy->base + AXI_CFG);
 	writel_relaxed(hw->config, phy->base + CX_CFG);
 }
 
@@ -314,6 +320,9 @@ static void k3_dma_tasklet(unsigned long arg)
 	/* check new channel request in d->chan_pending */
 	spin_lock_irq(&d->lock);
 	for (pch = 0; pch < d->dma_channels; pch++) {
+		if (!(d->dma_channel_mask & (1 << pch)))
+			continue;
+
 		p = &d->phy[pch];
 
 		if (p->vchan == NULL && !list_empty(&d->chan_pending)) {
@@ -331,6 +340,9 @@ static void k3_dma_tasklet(unsigned long arg)
 	spin_unlock_irq(&d->lock);
 
 	for (pch = 0; pch < d->dma_channels; pch++) {
+		if (!(d->dma_channel_mask & (1 << pch)))
+			continue;
+
 		if (pch_alloc & (1 << pch)) {
 			p = &d->phy[pch];
 			c = p->vchan;
@@ -790,8 +802,21 @@ static int k3_dma_transfer_resume(struct dma_chan *chan)
 	return 0;
 }
 
+static const struct k3dma_soc_data k3_v1_dma_data = {
+	.flags = 0,
+};
+
+static const struct k3dma_soc_data asp_v1_dma_data = {
+	.flags = K3_FLAG_NOCLK,
+};
+
 static const struct of_device_id k3_pdma_dt_ids[] = {
-	{ .compatible = "hisilicon,k3-dma-1.0", },
+	{ .compatible = "hisilicon,k3-dma-1.0",
+	  .data = &k3_v1_dma_data
+	},
+	{ .compatible = "hisilicon,hisi-pcm-asp-dma-1.0",
+	  .data = &asp_v1_dma_data
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, k3_pdma_dt_ids);
@@ -810,6 +835,7 @@ static struct dma_chan *k3_of_dma_simple_xlate(struct of_phandle_args *dma_spec,
 
 static int k3_dma_probe(struct platform_device *op)
 {
+	const struct k3dma_soc_data *soc_data;
 	struct k3_dma_dev *d;
 	const struct of_device_id *of_id;
 	struct resource *iores;
@@ -823,6 +849,10 @@ static int k3_dma_probe(struct platform_device *op)
 	if (!d)
 		return -ENOMEM;
 
+	soc_data = device_get_match_data(&op->dev);
+	if (!soc_data)
+		return -EINVAL;
+
 	d->base = devm_ioremap_resource(&op->dev, iores);
 	if (IS_ERR(d->base))
 		return PTR_ERR(d->base);
@@ -833,12 +863,21 @@ static int k3_dma_probe(struct platform_device *op)
 				"dma-channels", &d->dma_channels);
 		of_property_read_u32((&op->dev)->of_node,
 				"dma-requests", &d->dma_requests);
+		ret = of_property_read_u32((&op->dev)->of_node,
+				"dma-channel-mask", &d->dma_channel_mask);
+		if (ret) {
+			dev_warn(&op->dev,
+				 "dma-channel-mask doesn't exist, considering all as available.\n");
+			d->dma_channel_mask = (u32)~0UL;
+		}
 	}
 
-	d->clk = devm_clk_get(&op->dev, NULL);
-	if (IS_ERR(d->clk)) {
-		dev_err(&op->dev, "no dma clk\n");
-		return PTR_ERR(d->clk);
+	if (!(soc_data->flags & K3_FLAG_NOCLK)) {
+		d->clk = devm_clk_get(&op->dev, NULL);
+		if (IS_ERR(d->clk)) {
+			dev_err(&op->dev, "no dma clk\n");
+			return PTR_ERR(d->clk);
+		}
 	}
 
 	irq = platform_get_irq(op, 0);
@@ -862,8 +901,12 @@ static int k3_dma_probe(struct platform_device *op)
 		return -ENOMEM;
 
 	for (i = 0; i < d->dma_channels; i++) {
-		struct k3_dma_phy *p = &d->phy[i];
+		struct k3_dma_phy *p;
+
+		if (!(d->dma_channel_mask & BIT(i)))
+			continue;
 
+		p = &d->phy[i];
 		p->idx = i;
 		p->base = d->base + i * 0x40;
 	}

drivers/dma/mcf-edma.c

@@ -214,6 +214,7 @@ static int mcf_edma_probe(struct platform_device *pdev)
 		mcf_chan->edma = mcf_edma;
 		mcf_chan->slave_id = i;
 		mcf_chan->idle = true;
+		mcf_chan->dma_dir = DMA_NONE;
 		mcf_chan->vchan.desc_free = fsl_edma_free_desc;
 		vchan_init(&mcf_chan->vchan, &mcf_edma->dma_dev);
 		iowrite32(0x0, &regs->tcd[i].csr);

drivers/dma/mv_xor.c

@@ -1059,6 +1059,7 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 		mv_chan->op_in_desc = XOR_MODE_IN_DESC;
 
 	dma_dev = &mv_chan->dmadev;
+	dma_dev->dev = &pdev->dev;
 	mv_chan->xordev = xordev;
 
 	/*
@@ -1091,7 +1092,6 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 	dma_dev->device_free_chan_resources = mv_xor_free_chan_resources;
 	dma_dev->device_tx_status = mv_xor_status;
 	dma_dev->device_issue_pending = mv_xor_issue_pending;
-	dma_dev->dev = &pdev->dev;
 
 	/* set prep routines based on capability */
 	if (dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask))
@@ -1153,7 +1153,10 @@ mv_xor_channel_add(struct mv_xor_device *xordev,
 		 dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask) ? "cpy " : "",
 		 dma_has_cap(DMA_INTERRUPT, dma_dev->cap_mask) ? "intr " : "");
 
-	dma_async_device_register(dma_dev);
+	ret = dma_async_device_register(dma_dev);
+	if (ret)
+		goto err_free_irq;
+
 	return mv_chan;
 
 err_free_irq:

drivers/dma/pl330.c

@@ -2267,7 +2267,6 @@ static int pl330_terminate_all(struct dma_chan *chan)
 	struct dma_pl330_desc *desc;
 	unsigned long flags;
 	struct pl330_dmac *pl330 = pch->dmac;
-	LIST_HEAD(list);
 	bool power_down = false;
 
 	pm_runtime_get_sync(pl330->ddma.dev);

drivers/dma/qcom/bam_dma.c

@@ -636,8 +636,8 @@ static struct dma_async_tx_descriptor *bam_prep_slave_sg(struct dma_chan *chan,
 		num_alloc += DIV_ROUND_UP(sg_dma_len(sg), BAM_FIFO_SIZE);
 
 	/* allocate enough room to accomodate the number of entries */
-	async_desc = kzalloc(sizeof(*async_desc) +
-			(num_alloc * sizeof(struct bam_desc_hw)), GFP_NOWAIT);
+	async_desc = kzalloc(struct_size(async_desc, desc, num_alloc),
+			     GFP_NOWAIT);
 
 	if (!async_desc)
 		goto err_out;

drivers/dma/qcom/hidma.c

@@ -138,24 +138,25 @@ static void hidma_process_completed(struct hidma_chan *mchan)
 		desc = &mdesc->desc;
 		last_cookie = desc->cookie;
 
+		llstat = hidma_ll_status(mdma->lldev, mdesc->tre_ch);
+
 		spin_lock_irqsave(&mchan->lock, irqflags);
+		if (llstat == DMA_COMPLETE) {
+			mchan->last_success = last_cookie;
+			result.result = DMA_TRANS_NOERROR;
+		} else {
+			result.result = DMA_TRANS_ABORTED;
+		}
+
 		dma_cookie_complete(desc);
 		spin_unlock_irqrestore(&mchan->lock, irqflags);
 
-		llstat = hidma_ll_status(mdma->lldev, mdesc->tre_ch);
 		dmaengine_desc_get_callback(desc, &cb);
 
 		dma_run_dependencies(desc);
 
 		spin_lock_irqsave(&mchan->lock, irqflags);
 		list_move(&mdesc->node, &mchan->free);
-
-		if (llstat == DMA_COMPLETE) {
-			mchan->last_success = last_cookie;
-			result.result = DMA_TRANS_NOERROR;
-		} else
-			result.result = DMA_TRANS_ABORTED;
-
 		spin_unlock_irqrestore(&mchan->lock, irqflags);
 
 		dmaengine_desc_callback_invoke(&cb, &result);
@@ -415,6 +416,7 @@ hidma_prep_dma_memcpy(struct dma_chan *dmach, dma_addr_t dest, dma_addr_t src,
 	if (!mdesc)
 		return NULL;
 
+	mdesc->desc.flags = flags;
 	hidma_ll_set_transfer_params(mdma->lldev, mdesc->tre_ch,
 				     src, dest, len, flags,
 				     HIDMA_TRE_MEMCPY);
@@ -447,6 +449,7 @@ hidma_prep_dma_memset(struct dma_chan *dmach, dma_addr_t dest, int value,
 	if (!mdesc)
 		return NULL;
 
+	mdesc->desc.flags = flags;
 	hidma_ll_set_transfer_params(mdma->lldev, mdesc->tre_ch,
 				     value, dest, len, flags,
 				     HIDMA_TRE_MEMSET);

drivers/dma/qcom/hidma_mgmt.c

@@ -423,9 +423,8 @@ static int __init hidma_mgmt_init(void)
 		hidma_mgmt_of_populate_channels(child);
 	}
 #endif
-	platform_driver_register(&hidma_mgmt_driver);
+	return platform_driver_register(&hidma_mgmt_driver);
 
-	return 0;
 }
 module_init(hidma_mgmt_init);
 MODULE_LICENSE("GPL v2");

drivers/dma/sa11x0-dma.c

@@ -705,7 +705,6 @@ static int sa11x0_dma_device_pause(struct dma_chan *chan)
 	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
 	struct sa11x0_dma_dev *d = to_sa11x0_dma(chan->device);
 	struct sa11x0_dma_phy *p;
-	LIST_HEAD(head);
 	unsigned long flags;
 
 	dev_dbg(d->slave.dev, "vchan %p: pause\n", &c->vc);
@@ -732,7 +731,6 @@ static int sa11x0_dma_device_resume(struct dma_chan *chan)
 	struct sa11x0_dma_chan *c = to_sa11x0_dma_chan(chan);
 	struct sa11x0_dma_dev *d = to_sa11x0_dma(chan->device);
 	struct sa11x0_dma_phy *p;
-	LIST_HEAD(head);
 	unsigned long flags;
 
 	dev_dbg(d->slave.dev, "vchan %p: resume\n", &c->vc);

drivers/dma/sh/usb-dmac.c

@@ -694,6 +694,8 @@ static int usb_dmac_runtime_resume(struct device *dev)
 #endif /* CONFIG_PM */
 
 static const struct dev_pm_ops usb_dmac_pm = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				      pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(usb_dmac_runtime_suspend, usb_dmac_runtime_resume,
 			   NULL)
 };

drivers/dma/sprd-dma.c

@@ -580,15 +580,7 @@ static irqreturn_t dma_irq_handle(int irq, void *dev_id)
 
 static int sprd_dma_alloc_chan_resources(struct dma_chan *chan)
 {
-	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
-	int ret;
-
-	ret = pm_runtime_get_sync(chan->device->dev);
-	if (ret < 0)
-		return ret;
-
-	schan->dev_id = SPRD_DMA_SOFTWARE_UID;
-	return 0;
+	return pm_runtime_get_sync(chan->device->dev);
 }
 
 static void sprd_dma_free_chan_resources(struct dma_chan *chan)
@@ -1021,13 +1013,10 @@ static void sprd_dma_free_desc(struct virt_dma_desc *vd)
 static bool sprd_dma_filter_fn(struct dma_chan *chan, void *param)
 {
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
-	struct sprd_dma_dev *sdev = to_sprd_dma_dev(&schan->vc.chan);
-	u32 req = *(u32 *)param;
+	u32 slave_id = *(u32 *)param;
 
-	if (req < sdev->total_chns)
-		return req == schan->chn_num + 1;
-	else
-		return false;
+	schan->dev_id = slave_id;
+	return true;
 }
 
 static int sprd_dma_probe(struct platform_device *pdev)

drivers/dma/st_fdma.c

@@ -243,8 +243,7 @@ static struct st_fdma_desc *st_fdma_alloc_desc(struct st_fdma_chan *fchan,
 	struct st_fdma_desc *fdesc;
 	int i;
 
-	fdesc = kzalloc(sizeof(*fdesc) +
-			sizeof(struct st_fdma_sw_node) * sg_len, GFP_NOWAIT);
+	fdesc = kzalloc(struct_size(fdesc, node, sg_len), GFP_NOWAIT);
 	if (!fdesc)
 		return NULL;
 
@@ -294,8 +293,6 @@ static void st_fdma_free_chan_res(struct dma_chan *chan)
 	struct rproc *rproc = fchan->fdev->slim_rproc->rproc;
 	unsigned long flags;
 
-	LIST_HEAD(head);
-
 	dev_dbg(fchan->fdev->dev, "%s: freeing chan:%d\n",
 		__func__, fchan->vchan.chan.chan_id);
 
@@ -626,7 +623,6 @@ static void st_fdma_issue_pending(struct dma_chan *chan)
 static int st_fdma_pause(struct dma_chan *chan)
 {
 	unsigned long flags;
-	LIST_HEAD(head);
 	struct st_fdma_chan *fchan = to_st_fdma_chan(chan);
 	int ch_id = fchan->vchan.chan.chan_id;
 	unsigned long cmd = FDMA_CMD_PAUSE(ch_id);

drivers/dma/stm32-dma.c

@@ -23,6 +23,7 @@
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -641,12 +642,13 @@ static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
 {
 	struct stm32_dma_chan *chan = devid;
 	struct stm32_dma_device *dmadev = stm32_dma_get_dev(chan);
-	u32 status, scr;
+	u32 status, scr, sfcr;
 
 	spin_lock(&chan->vchan.lock);
 
 	status = stm32_dma_irq_status(chan);
 	scr = stm32_dma_read(dmadev, STM32_DMA_SCR(chan->id));
+	sfcr = stm32_dma_read(dmadev, STM32_DMA_SFCR(chan->id));
 
 	if (status & STM32_DMA_TCI) {
 		stm32_dma_irq_clear(chan, STM32_DMA_TCI);
@@ -661,10 +663,12 @@ static irqreturn_t stm32_dma_chan_irq(int irq, void *devid)
 	if (status & STM32_DMA_FEI) {
 		stm32_dma_irq_clear(chan, STM32_DMA_FEI);
 		status &= ~STM32_DMA_FEI;
-		if (!(scr & STM32_DMA_SCR_EN))
-			dev_err(chan2dev(chan), "FIFO Error\n");
-		else
-			dev_dbg(chan2dev(chan), "FIFO over/underrun\n");
+		if (sfcr & STM32_DMA_SFCR_FEIE) {
+			if (!(scr & STM32_DMA_SCR_EN))
+				dev_err(chan2dev(chan), "FIFO Error\n");
+			else
+				dev_dbg(chan2dev(chan), "FIFO over/underrun\n");
+		}
 	}
 	if (status) {
 		stm32_dma_irq_clear(chan, status);
@@ -1112,15 +1116,14 @@ static int stm32_dma_alloc_chan_resources(struct dma_chan *c)
 	int ret;
 
 	chan->config_init = false;
-	ret = clk_prepare_enable(dmadev->clk);
-	if (ret < 0) {
-		dev_err(chan2dev(chan), "clk_prepare_enable failed: %d\n", ret);
+
+	ret = pm_runtime_get_sync(dmadev->ddev.dev);
+	if (ret < 0)
 		return ret;
-	}
 
 	ret = stm32_dma_disable_chan(chan);
 	if (ret < 0)
-		clk_disable_unprepare(dmadev->clk);
+		pm_runtime_put(dmadev->ddev.dev);
 
 	return ret;
 }
@@ -1140,7 +1143,7 @@ static void stm32_dma_free_chan_resources(struct dma_chan *c)
 		spin_unlock_irqrestore(&chan->vchan.lock, flags);
 	}
 
-	clk_disable_unprepare(dmadev->clk);
+	pm_runtime_put(dmadev->ddev.dev);
 
 	vchan_free_chan_resources(to_virt_chan(c));
 }
@@ -1240,6 +1243,12 @@ static int stm32_dma_probe(struct platform_device *pdev)
 		return PTR_ERR(dmadev->clk);
 	}
 
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "clk_prep_enable error: %d\n", ret);
+		return ret;
+	}
+
 	dmadev->mem2mem = of_property_read_bool(pdev->dev.of_node,
 						"st,mem2mem");
 
@@ -1289,7 +1298,7 @@ static int stm32_dma_probe(struct platform_device *pdev)
 
 	ret = dma_async_device_register(dd);
 	if (ret)
-		return ret;
+		goto clk_free;
 
 	for (i = 0; i < STM32_DMA_MAX_CHANNELS; i++) {
 		chan = &dmadev->chan[i];
@@ -1321,20 +1330,58 @@ static int stm32_dma_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, dmadev);
 
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_put(&pdev->dev);
+
 	dev_info(&pdev->dev, "STM32 DMA driver registered\n");
 
 	return 0;
 
 err_unregister:
 	dma_async_device_unregister(dd);
+clk_free:
+	clk_disable_unprepare(dmadev->clk);
 
 	return ret;
 }
 
+#ifdef CONFIG_PM
+static int stm32_dma_runtime_suspend(struct device *dev)
+{
+	struct stm32_dma_device *dmadev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(dmadev->clk);
+
+	return 0;
+}
+
+static int stm32_dma_runtime_resume(struct device *dev)
+{
+	struct stm32_dma_device *dmadev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret) {
+		dev_err(dev, "failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_dma_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_dma_runtime_suspend,
+			   stm32_dma_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_dma_driver = {
 	.driver = {
 		.name = "stm32-dma",
 		.of_match_table = stm32_dma_of_match,
+		.pm = &stm32_dma_pm_ops,
 	},
 };
 

drivers/dma/stm32-dmamux.c

@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -79,8 +80,7 @@ static void stm32_dmamux_free(struct device *dev, void *route_data)
 	stm32_dmamux_write(dmamux->iomem, STM32_DMAMUX_CCR(mux->chan_id), 0);
 	clear_bit(mux->chan_id, dmamux->dma_inuse);
 
-	if (!IS_ERR(dmamux->clk))
-		clk_disable(dmamux->clk);
+	pm_runtime_put_sync(dev);
 
 	spin_unlock_irqrestore(&dmamux->lock, flags);
 
@@ -146,13 +146,10 @@ static void *stm32_dmamux_route_allocate(struct of_phandle_args *dma_spec,
 
 	/* Set dma request */
 	spin_lock_irqsave(&dmamux->lock, flags);
-	if (!IS_ERR(dmamux->clk)) {
-		ret = clk_enable(dmamux->clk);
-		if (ret < 0) {
-			spin_unlock_irqrestore(&dmamux->lock, flags);
-			dev_err(&pdev->dev, "clk_prep_enable issue: %d\n", ret);
-			goto error;
-		}
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		spin_unlock_irqrestore(&dmamux->lock, flags);
+		goto error;
 	}
 	spin_unlock_irqrestore(&dmamux->lock, flags);
 
@@ -254,6 +251,7 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 		dev_warn(&pdev->dev, "DMAMUX defaulting on %u requests\n",
 			 stm32_dmamux->dmamux_requests);
 	}
+	pm_runtime_get_noresume(&pdev->dev);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	iomem = devm_ioremap_resource(&pdev->dev, res);
@@ -282,6 +280,8 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 	stm32_dmamux->dmarouter.route_free = stm32_dmamux_free;
 
 	platform_set_drvdata(pdev, stm32_dmamux);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 
 	if (!IS_ERR(stm32_dmamux->clk)) {
 		ret = clk_prepare_enable(stm32_dmamux->clk);
@@ -291,17 +291,52 @@ static int stm32_dmamux_probe(struct platform_device *pdev)
 		}
 	}
 
+	pm_runtime_get_noresume(&pdev->dev);
+
 	/* Reset the dmamux */
 	for (i = 0; i < stm32_dmamux->dma_requests; i++)
 		stm32_dmamux_write(stm32_dmamux->iomem, STM32_DMAMUX_CCR(i), 0);
 
-	if (!IS_ERR(stm32_dmamux->clk))
-		clk_disable(stm32_dmamux->clk);
+	pm_runtime_put(&pdev->dev);
 
 	return of_dma_router_register(node, stm32_dmamux_route_allocate,
 				     &stm32_dmamux->dmarouter);
 }
 
+#ifdef CONFIG_PM
+static int stm32_dmamux_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev =
+		container_of(dev, struct platform_device, dev);
+	struct stm32_dmamux_data *stm32_dmamux = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(stm32_dmamux->clk);
+
+	return 0;
+}
+
+static int stm32_dmamux_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev =
+		container_of(dev, struct platform_device, dev);
+	struct stm32_dmamux_data *stm32_dmamux = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = clk_prepare_enable(stm32_dmamux->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_dmamux_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_dmamux_runtime_suspend,
+			   stm32_dmamux_runtime_resume, NULL)
+};
+
 static const struct of_device_id stm32_dmamux_match[] = {
 	{ .compatible = "st,stm32h7-dmamux" },
 	{},
@@ -312,6 +347,7 @@ static struct platform_driver stm32_dmamux_driver = {
 	.driver = {
 		.name = "stm32-dmamux",
 		.of_match_table = stm32_dmamux_match,
+		.pm = &stm32_dmamux_pm_ops,
 	},
 };
 

drivers/dma/stm32-mdma.c

@@ -37,6 +37,7 @@
 #include <linux/of_device.h>
 #include <linux/of_dma.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/slab.h>
 
@@ -1456,15 +1457,13 @@ static int stm32_mdma_alloc_chan_resources(struct dma_chan *c)
 		return -ENOMEM;
 	}
 
-	ret = clk_prepare_enable(dmadev->clk);
-	if (ret < 0) {
-		dev_err(chan2dev(chan), "clk_prepare_enable failed: %d\n", ret);
+	ret = pm_runtime_get_sync(dmadev->ddev.dev);
+	if (ret < 0)
 		return ret;
-	}
 
 	ret = stm32_mdma_disable_chan(chan);
 	if (ret < 0)
-		clk_disable_unprepare(dmadev->clk);
+		pm_runtime_put(dmadev->ddev.dev);
 
 	return ret;
 }
@@ -1484,7 +1483,7 @@ static void stm32_mdma_free_chan_resources(struct dma_chan *c)
 		spin_unlock_irqrestore(&chan->vchan.lock, flags);
 	}
 
-	clk_disable_unprepare(dmadev->clk);
+	pm_runtime_put(dmadev->ddev.dev);
 	vchan_free_chan_resources(to_virt_chan(c));
 	dmam_pool_destroy(chan->desc_pool);
 	chan->desc_pool = NULL;
@@ -1579,9 +1578,11 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 
 	dmadev->nr_channels = nr_channels;
 	dmadev->nr_requests = nr_requests;
-	device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks",
+	ret = device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks",
 				       dmadev->ahb_addr_masks,
 				       count);
+	if (ret)
+		return ret;
 	dmadev->nr_ahb_addr_masks = count;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1597,6 +1598,12 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "clk_prep_enable error: %d\n", ret);
+		return ret;
+	}
+
 	dmadev->rst = devm_reset_control_get(&pdev->dev, NULL);
 	if (!IS_ERR(dmadev->rst)) {
 		reset_control_assert(dmadev->rst);
@@ -1668,6 +1675,10 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, dmadev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_put(&pdev->dev);
 
 	dev_info(&pdev->dev, "STM32 MDMA driver registered\n");
 
@@ -1677,11 +1688,42 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 	return ret;
 }
 
+#ifdef CONFIG_PM
+static int stm32_mdma_runtime_suspend(struct device *dev)
+{
+	struct stm32_mdma_device *dmadev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(dmadev->clk);
+
+	return 0;
+}
+
+static int stm32_mdma_runtime_resume(struct device *dev)
+{
+	struct stm32_mdma_device *dmadev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(dmadev->clk);
+	if (ret) {
+		dev_err(dev, "failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_mdma_pm_ops = {
+	SET_RUNTIME_PM_OPS(stm32_mdma_runtime_suspend,
+			   stm32_mdma_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_mdma_driver = {
 	.probe = stm32_mdma_probe,
 	.driver = {
 		.name = "stm32-mdma",
 		.of_match_table = stm32_mdma_of_match,
+		.pm = &stm32_mdma_pm_ops,
 	},
 };
 

drivers/dma/tegra20-apb-dma.c

@@ -38,6 +38,9 @@
 
 #include "dmaengine.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/tegra_apb_dma.h>
+
 #define TEGRA_APBDMA_GENERAL			0x0
 #define TEGRA_APBDMA_GENERAL_ENABLE		BIT(31)
 
@@ -146,7 +149,7 @@ struct tegra_dma_channel_regs {
 };
 
 /*
- * tegra_dma_sg_req: Dma request details to configure hardware. This
+ * tegra_dma_sg_req: DMA request details to configure hardware. This
  * contains the details for one transfer to configure DMA hw.
  * The client's request for data transfer can be broken into multiple
  * sub-transfer as per requester details and hw support.
@@ -155,7 +158,7 @@ struct tegra_dma_channel_regs {
  */
 struct tegra_dma_sg_req {
 	struct tegra_dma_channel_regs	ch_regs;
-	int				req_len;
+	unsigned int			req_len;
 	bool				configured;
 	bool				last_sg;
 	struct list_head		node;
@@ -169,8 +172,8 @@ struct tegra_dma_sg_req {
  */
 struct tegra_dma_desc {
 	struct dma_async_tx_descriptor	txd;
-	int				bytes_requested;
-	int				bytes_transferred;
+	unsigned int			bytes_requested;
+	unsigned int			bytes_transferred;
 	enum dma_status			dma_status;
 	struct list_head		node;
 	struct list_head		tx_list;
@@ -186,7 +189,7 @@ typedef void (*dma_isr_handler)(struct tegra_dma_channel *tdc,
 /* tegra_dma_channel: Channel specific information */
 struct tegra_dma_channel {
 	struct dma_chan		dma_chan;
-	char			name[30];
+	char			name[12];
 	bool			config_init;
 	int			id;
 	int			irq;
@@ -574,7 +577,7 @@ static bool handle_continuous_head_request(struct tegra_dma_channel *tdc,
 	struct tegra_dma_sg_req *hsgreq = NULL;
 
 	if (list_empty(&tdc->pending_sg_req)) {
-		dev_err(tdc2dev(tdc), "Dma is running without req\n");
+		dev_err(tdc2dev(tdc), "DMA is running without req\n");
 		tegra_dma_stop(tdc);
 		return false;
 	}
@@ -587,7 +590,7 @@ static bool handle_continuous_head_request(struct tegra_dma_channel *tdc,
 	hsgreq = list_first_entry(&tdc->pending_sg_req, typeof(*hsgreq), node);
 	if (!hsgreq->configured) {
 		tegra_dma_stop(tdc);
-		dev_err(tdc2dev(tdc), "Error in dma transfer, aborting dma\n");
+		dev_err(tdc2dev(tdc), "Error in DMA transfer, aborting DMA\n");
 		tegra_dma_abort_all(tdc);
 		return false;
 	}
@@ -636,7 +639,10 @@ static void handle_cont_sngl_cycle_dma_done(struct tegra_dma_channel *tdc,
 
 	sgreq = list_first_entry(&tdc->pending_sg_req, typeof(*sgreq), node);
 	dma_desc = sgreq->dma_desc;
-	dma_desc->bytes_transferred += sgreq->req_len;
+	/* if we dma for long enough the transfer count will wrap */
+	dma_desc->bytes_transferred =
+		(dma_desc->bytes_transferred + sgreq->req_len) %
+		dma_desc->bytes_requested;
 
 	/* Callback need to be call */
 	if (!dma_desc->cb_count)
@@ -669,6 +675,8 @@ static void tegra_dma_tasklet(unsigned long data)
 		dmaengine_desc_get_callback(&dma_desc->txd, &cb);
 		cb_count = dma_desc->cb_count;
 		dma_desc->cb_count = 0;
+		trace_tegra_dma_complete_cb(&tdc->dma_chan, cb_count,
+					    cb.callback);
 		spin_unlock_irqrestore(&tdc->lock, flags);
 		while (cb_count--)
 			dmaengine_desc_callback_invoke(&cb, NULL);
@@ -685,6 +693,7 @@ static irqreturn_t tegra_dma_isr(int irq, void *dev_id)
 
 	spin_lock_irqsave(&tdc->lock, flags);
 
+	trace_tegra_dma_isr(&tdc->dma_chan, irq);
 	status = tdc_read(tdc, TEGRA_APBDMA_CHAN_STATUS);
 	if (status & TEGRA_APBDMA_STATUS_ISE_EOC) {
 		tdc_write(tdc, TEGRA_APBDMA_CHAN_STATUS, status);
@@ -843,6 +852,7 @@ static enum dma_status tegra_dma_tx_status(struct dma_chan *dc,
 		dma_set_residue(txstate, residual);
 	}
 
+	trace_tegra_dma_tx_status(&tdc->dma_chan, cookie, txstate);
 	spin_unlock_irqrestore(&tdc->lock, flags);
 	return ret;
 }
@@ -919,7 +929,7 @@ static int get_transfer_param(struct tegra_dma_channel *tdc,
 		return 0;
 
 	default:
-		dev_err(tdc2dev(tdc), "Dma direction is not supported\n");
+		dev_err(tdc2dev(tdc), "DMA direction is not supported\n");
 		return -EINVAL;
 	}
 	return -EINVAL;
@@ -952,7 +962,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 	enum dma_slave_buswidth slave_bw;
 
 	if (!tdc->config_init) {
-		dev_err(tdc2dev(tdc), "dma channel is not configured\n");
+		dev_err(tdc2dev(tdc), "DMA channel is not configured\n");
 		return NULL;
 	}
 	if (sg_len < 1) {
@@ -985,7 +995,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 
 	dma_desc = tegra_dma_desc_get(tdc);
 	if (!dma_desc) {
-		dev_err(tdc2dev(tdc), "Dma descriptors not available\n");
+		dev_err(tdc2dev(tdc), "DMA descriptors not available\n");
 		return NULL;
 	}
 	INIT_LIST_HEAD(&dma_desc->tx_list);
@@ -1005,14 +1015,14 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_slave_sg(
 		if ((len & 3) || (mem & 3) ||
 				(len > tdc->tdma->chip_data->max_dma_count)) {
 			dev_err(tdc2dev(tdc),
-				"Dma length/memory address is not supported\n");
+				"DMA length/memory address is not supported\n");
 			tegra_dma_desc_put(tdc, dma_desc);
 			return NULL;
 		}
 
 		sg_req = tegra_dma_sg_req_get(tdc);
 		if (!sg_req) {
-			dev_err(tdc2dev(tdc), "Dma sg-req not available\n");
+			dev_err(tdc2dev(tdc), "DMA sg-req not available\n");
 			tegra_dma_desc_put(tdc, dma_desc);
 			return NULL;
 		}
@@ -1087,7 +1097,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 	 * terminating the DMA.
 	 */
 	if (tdc->busy) {
-		dev_err(tdc2dev(tdc), "Request not allowed when dma running\n");
+		dev_err(tdc2dev(tdc), "Request not allowed when DMA running\n");
 		return NULL;
 	}
 
@@ -1144,7 +1154,7 @@ static struct dma_async_tx_descriptor *tegra_dma_prep_dma_cyclic(
 	while (remain_len) {
 		sg_req = tegra_dma_sg_req_get(tdc);
 		if (!sg_req) {
-			dev_err(tdc2dev(tdc), "Dma sg-req not available\n");
+			dev_err(tdc2dev(tdc), "DMA sg-req not available\n");
 			tegra_dma_desc_put(tdc, dma_desc);
 			return NULL;
 		}
@@ -1319,8 +1329,9 @@ static int tegra_dma_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	tdma = devm_kzalloc(&pdev->dev, sizeof(*tdma) + cdata->nr_channels *
-			sizeof(struct tegra_dma_channel), GFP_KERNEL);
+	tdma = devm_kzalloc(&pdev->dev,
+			    struct_size(tdma, channels, cdata->nr_channels),
+			    GFP_KERNEL);
 	if (!tdma)
 		return -ENOMEM;
 

drivers/dma/tegra210-adma.c

@@ -678,8 +678,9 @@ static int tegra_adma_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	tdma = devm_kzalloc(&pdev->dev, sizeof(*tdma) + cdata->nr_channels *
-			    sizeof(struct tegra_adma_chan), GFP_KERNEL);
+	tdma = devm_kzalloc(&pdev->dev,
+			    struct_size(tdma, channels, cdata->nr_channels),
+			    GFP_KERNEL);
 	if (!tdma)
 		return -ENOMEM;
 

drivers/dma/timb_dma.c

@@ -643,8 +643,8 @@ static int td_probe(struct platform_device *pdev)
 		DRIVER_NAME))
 		return -EBUSY;
 
-	td  = kzalloc(sizeof(struct timb_dma) +
-		sizeof(struct timb_dma_chan) * pdata->nr_channels, GFP_KERNEL);
+	td  = kzalloc(struct_size(td, channels, pdata->nr_channels),
+		      GFP_KERNEL);
 	if (!td) {
 		err = -ENOMEM;
 		goto err_release_region;

drivers/tty/serial/8250/8250_lpss.c

@@ -153,7 +153,6 @@ static int byt_serial_setup(struct lpss8250 *lpss, struct uart_port *port)
 #ifdef CONFIG_SERIAL_8250_DMA
 static const struct dw_dma_platform_data qrk_serial_dma_pdata = {
 	.nr_channels = 2,
-	.is_private = true,
 	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
 	.chan_priority = CHAN_PRIORITY_ASCENDING,
 	.block_size = 4095,

include/linux/dma/dw.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2007 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
  * Copyright (C) 2014 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef _DMA_DW_H
 #define _DMA_DW_H
@@ -45,9 +42,13 @@ struct dw_dma_chip {
 #if IS_ENABLED(CONFIG_DW_DMAC_CORE)
 int dw_dma_probe(struct dw_dma_chip *chip);
 int dw_dma_remove(struct dw_dma_chip *chip);
+int idma32_dma_probe(struct dw_dma_chip *chip);
+int idma32_dma_remove(struct dw_dma_chip *chip);
 #else
 static inline int dw_dma_probe(struct dw_dma_chip *chip) { return -ENODEV; }
 static inline int dw_dma_remove(struct dw_dma_chip *chip) { return 0; }
+static inline int idma32_dma_probe(struct dw_dma_chip *chip) { return -ENODEV; }
+static inline int idma32_dma_remove(struct dw_dma_chip *chip) { return 0; }
 #endif /* CONFIG_DW_DMAC_CORE */
 
 #endif /* _DMA_DW_H */

include/linux/platform_data/dma-dw.h

+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Driver for the Synopsys DesignWare DMA Controller
  *
  * Copyright (C) 2007 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #ifndef _PLATFORM_DATA_DMA_DW_H
 #define _PLATFORM_DATA_DMA_DW_H
@@ -38,10 +35,6 @@ struct dw_dma_slave {
 /**
  * struct dw_dma_platform_data - Controller configuration parameters
  * @nr_channels: Number of channels supported by hardware (max 8)
- * @is_private: The device channels should be marked as private and not for
- *	by the general purpose DMA channel allocator.
- * @is_memcpy: The device channels do support memory-to-memory transfers.
- * @is_idma32: The type of the DMA controller is iDMA32
  * @chan_allocation_order: Allocate channels starting from 0 or 7
  * @chan_priority: Set channel priority increasing from 0 to 7 or 7 to 0.
  * @block_size: Maximum block size supported by the controller
@@ -53,9 +46,6 @@ struct dw_dma_slave {
  */
 struct dw_dma_platform_data {
 	unsigned int	nr_channels;
-	bool		is_private;
-	bool		is_memcpy;
-	bool		is_idma32;
 #define CHAN_ALLOCATION_ASCENDING	0	/* zero to seven */
 #define CHAN_ALLOCATION_DESCENDING	1	/* seven to zero */
 	unsigned char	chan_allocation_order;

include/linux/platform_data/dma-imx.h

@@ -55,6 +55,7 @@ struct imx_dma_data {
 	int dma_request2; /* secondary DMA request line */
 	enum sdma_peripheral_type peripheral_type;
 	int priority;
+	struct device_node *of_node;
 };
 
 static inline int imx_dma_is_ipu(struct dma_chan *chan)

include/trace/events/tegra_apb_dma.h

+#if !defined(_TRACE_TEGRA_APB_DMA_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TEGRA_APM_DMA_H
+
+#include <linux/tracepoint.h>
+#include <linux/dmaengine.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM tegra_apb_dma
+
+TRACE_EVENT(tegra_dma_tx_status,
+	TP_PROTO(struct dma_chan *dc, dma_cookie_t cookie, struct dma_tx_state *state),
+	TP_ARGS(dc, cookie, state),
+	TP_STRUCT__entry(
+		__string(chan,	dev_name(&dc->dev->device))
+		__field(dma_cookie_t, cookie)
+		__field(__u32,	residue)
+	),
+	TP_fast_assign(
+		__assign_str(chan, dev_name(&dc->dev->device));
+		__entry->cookie = cookie;
+		__entry->residue = state ? state->residue : (u32)-1;
+	),
+	TP_printk("channel %s: dma cookie %d, residue %u",
+		  __get_str(chan), __entry->cookie, __entry->residue)
+);
+
+TRACE_EVENT(tegra_dma_complete_cb,
+	TP_PROTO(struct dma_chan *dc, int count, void *ptr),
+	TP_ARGS(dc, count, ptr),
+	TP_STRUCT__entry(
+		__string(chan,	dev_name(&dc->dev->device))
+		__field(int,	count)
+		__field(void *,	ptr)
+		),
+	TP_fast_assign(
+		__assign_str(chan, dev_name(&dc->dev->device));
+		__entry->count = count;
+		__entry->ptr = ptr;
+		),
+	TP_printk("channel %s: done %d, ptr %p",
+		  __get_str(chan), __entry->count, __entry->ptr)
+);
+
+TRACE_EVENT(tegra_dma_isr,
+	TP_PROTO(struct dma_chan *dc, int irq),
+	TP_ARGS(dc, irq),
+	TP_STRUCT__entry(
+		__string(chan,	dev_name(&dc->dev->device))
+		__field(int,	irq)
+	),
+	TP_fast_assign(
+		__assign_str(chan, dev_name(&dc->dev->device));
+		__entry->irq = irq;
+	),
+	TP_printk("%s: irq %d\n",  __get_str(chan), __entry->irq)
+);
+
+#endif /*  _TRACE_TEGRADMA_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>