diff --git a/Documentation/devicetree/bindings/dma/qcom_bam_dma.txt b/Documentation/devicetree/bindings/dma/qcom_bam_dma.txt
index cf5b9e44432c..6e9a5497b3f2 100644
--- a/Documentation/devicetree/bindings/dma/qcom_bam_dma.txt
+++ b/Documentation/devicetree/bindings/dma/qcom_bam_dma.txt
@@ -15,6 +15,8 @@ Required properties:
   the secure world.
 - qcom,controlled-remotely : optional, indicates that the bam is controlled by
   remote proccessor i.e. execution environment.
+- qcom,powered-remotely : optional, indicates that the bam is powered up by
+  a remote processor but must be initialized by the local processor.
 - num-channels : optional, indicates supported number of DMA channels in a
   remotely controlled bam.
 - qcom,num-ees : optional, indicates supported number of Execution Environments
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 80c2c03cb014..6bcdb4e6a0d1 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -717,7 +717,7 @@ config XILINX_DMA
 
 config XILINX_ZYNQMP_DMA
 	tristate "Xilinx ZynqMP DMA Engine"
-	depends on (ARCH_ZYNQ || MICROBLAZE || ARM64)
+	depends on ARCH_ZYNQ || MICROBLAZE || ARM64 || COMPILE_TEST
 	select DMA_ENGINE
 	help
 	  Enable support for Xilinx ZynqMP DMA controller.
diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c
index 5a2c7573b692..f5b885d69cd3 100644
--- a/drivers/dma/altera-msgdma.c
+++ b/drivers/dma/altera-msgdma.c
@@ -585,16 +585,14 @@ static void msgdma_chan_desc_cleanup(struct msgdma_device *mdev)
 	struct msgdma_sw_desc *desc, *next;
 
 	list_for_each_entry_safe(desc, next, &mdev->done_list, node) {
-		dma_async_tx_callback callback;
-		void *callback_param;
+		struct dmaengine_desc_callback cb;
 
 		list_del(&desc->node);
 
-		callback = desc->async_tx.callback;
-		callback_param = desc->async_tx.callback_param;
-		if (callback) {
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
+		if (dmaengine_desc_callback_valid(&cb)) {
 			spin_unlock(&mdev->lock);
-			callback(callback_param);
+			dmaengine_desc_callback_invoke(&cb, NULL);
 			spin_lock(&mdev->lock);
 		}
 
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index ab78e0f6afd7..275a76f188ae 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -155,7 +155,7 @@
 #define		AT_XDMAC_CC_WRIP	(0x1 << 23)	/* Write in Progress (read only) */
 #define			AT_XDMAC_CC_WRIP_DONE		(0x0 << 23)
 #define			AT_XDMAC_CC_WRIP_IN_PROGRESS	(0x1 << 23)
-#define		AT_XDMAC_CC_PERID(i)	(0x7f & (i) << 24)	/* Channel Peripheral Identifier */
+#define		AT_XDMAC_CC_PERID(i)	((0x7f & (i)) << 24)	/* Channel Peripheral Identifier */
 #define AT_XDMAC_CDS_MSP	0x2C	/* Channel Data Stride Memory Set Pattern */
 #define AT_XDMAC_CSUS		0x30	/* Channel Source Microblock Stride */
 #define AT_XDMAC_CDUS		0x34	/* Channel Destination Microblock Stride */
@@ -1926,8 +1926,31 @@ static void at_xdmac_free_chan_resources(struct dma_chan *chan)
 	return;
 }
 
-#ifdef CONFIG_PM
-static int atmel_xdmac_prepare(struct device *dev)
+static void at_xdmac_axi_config(struct platform_device *pdev)
+{
+	struct at_xdmac	*atxdmac = (struct at_xdmac *)platform_get_drvdata(pdev);
+	bool dev_m2m = false;
+	u32 dma_requests;
+
+	if (!atxdmac->layout->axi_config)
+		return; /* Not supported */
+
+	if (!of_property_read_u32(pdev->dev.of_node, "dma-requests",
+				  &dma_requests)) {
+		dev_info(&pdev->dev, "controller in mem2mem mode.\n");
+		dev_m2m = true;
+	}
+
+	if (dev_m2m) {
+		at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_M2M);
+		at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_M2M);
+	} else {
+		at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_P2M);
+		at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_P2M);
+	}
+}
+
+static int __maybe_unused atmel_xdmac_prepare(struct device *dev)
 {
 	struct at_xdmac		*atxdmac = dev_get_drvdata(dev);
 	struct dma_chan		*chan, *_chan;
@@ -1941,12 +1964,8 @@ static int atmel_xdmac_prepare(struct device *dev)
 	}
 	return 0;
 }
-#else
-#	define atmel_xdmac_prepare NULL
-#endif
 
-#ifdef CONFIG_PM_SLEEP
-static int atmel_xdmac_suspend(struct device *dev)
+static int __maybe_unused atmel_xdmac_suspend(struct device *dev)
 {
 	struct at_xdmac		*atxdmac = dev_get_drvdata(dev);
 	struct dma_chan		*chan, *_chan;
@@ -1970,11 +1989,12 @@ static int atmel_xdmac_suspend(struct device *dev)
 	return 0;
 }
 
-static int atmel_xdmac_resume(struct device *dev)
+static int __maybe_unused atmel_xdmac_resume(struct device *dev)
 {
 	struct at_xdmac		*atxdmac = dev_get_drvdata(dev);
 	struct at_xdmac_chan	*atchan;
 	struct dma_chan		*chan, *_chan;
+	struct platform_device	*pdev = container_of(dev, struct platform_device, dev);
 	int			i;
 	int ret;
 
@@ -1982,6 +2002,8 @@ static int atmel_xdmac_resume(struct device *dev)
 	if (ret)
 		return ret;
 
+	at_xdmac_axi_config(pdev);
+
 	/* Clear pending interrupts. */
 	for (i = 0; i < atxdmac->dma.chancnt; i++) {
 		atchan = &atxdmac->chan[i];
@@ -2005,31 +2027,6 @@ static int atmel_xdmac_resume(struct device *dev)
 	}
 	return 0;
 }
-#endif /* CONFIG_PM_SLEEP */
-
-static void at_xdmac_axi_config(struct platform_device *pdev)
-{
-	struct at_xdmac	*atxdmac = (struct at_xdmac *)platform_get_drvdata(pdev);
-	bool dev_m2m = false;
-	u32 dma_requests;
-
-	if (!atxdmac->layout->axi_config)
-		return; /* Not supported */
-
-	if (!of_property_read_u32(pdev->dev.of_node, "dma-requests",
-				  &dma_requests)) {
-		dev_info(&pdev->dev, "controller in mem2mem mode.\n");
-		dev_m2m = true;
-	}
-
-	if (dev_m2m) {
-		at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_M2M);
-		at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_M2M);
-	} else {
-		at_xdmac_write(atxdmac, AT_XDMAC_GCFG, AT_XDMAC_GCFG_P2M);
-		at_xdmac_write(atxdmac, AT_XDMAC_GWAC, AT_XDMAC_GWAC_P2M);
-	}
-}
 
 static int at_xdmac_probe(struct platform_device *pdev)
 {
@@ -2210,7 +2207,7 @@ static int at_xdmac_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct dev_pm_ops atmel_xdmac_dev_pm_ops = {
+static const struct dev_pm_ops __maybe_unused atmel_xdmac_dev_pm_ops = {
 	.prepare	= atmel_xdmac_prepare,
 	SET_LATE_SYSTEM_SLEEP_PM_OPS(atmel_xdmac_suspend, atmel_xdmac_resume)
 };
@@ -2234,7 +2231,7 @@ static struct platform_driver at_xdmac_driver = {
 	.driver = {
 		.name		= "at_xdmac",
 		.of_match_table	= of_match_ptr(atmel_xdmac_dt_ids),
-		.pm		= &atmel_xdmac_dev_pm_ops,
+		.pm		= pm_ptr(&atmel_xdmac_dev_pm_ops),
 	}
 };
 
diff --git a/drivers/dma/bestcomm/ata.c b/drivers/dma/bestcomm/ata.c
index 2fd87f83cf90..e169f18da551 100644
--- a/drivers/dma/bestcomm/ata.c
+++ b/drivers/dma/bestcomm/ata.c
@@ -133,7 +133,7 @@ void bcom_ata_reset_bd(struct bcom_task *tsk)
 	struct bcom_ata_var *var;
 
 	/* Reset all BD */
-	memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
+	memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
 
 	tsk->index = 0;
 	tsk->outdex = 0;
diff --git a/drivers/dma/bestcomm/bestcomm.c b/drivers/dma/bestcomm/bestcomm.c
index d91cbbe7a48f..8c42e5ca00a9 100644
--- a/drivers/dma/bestcomm/bestcomm.c
+++ b/drivers/dma/bestcomm/bestcomm.c
@@ -95,7 +95,7 @@ bcom_task_alloc(int bd_count, int bd_size, int priv_size)
 		tsk->bd = bcom_sram_alloc(bd_count * bd_size, 4, &tsk->bd_pa);
 		if (!tsk->bd)
 			goto error;
-		memset(tsk->bd, 0x00, bd_count * bd_size);
+		memset_io(tsk->bd, 0x00, bd_count * bd_size);
 
 		tsk->num_bd = bd_count;
 		tsk->bd_size = bd_size;
@@ -186,16 +186,16 @@ bcom_load_image(int task, u32 *task_image)
 	inc = bcom_task_inc(task);
 
 	/* Clear & copy */
-	memset(var, 0x00, BCOM_VAR_SIZE);
-	memset(inc, 0x00, BCOM_INC_SIZE);
+	memset_io(var, 0x00, BCOM_VAR_SIZE);
+	memset_io(inc, 0x00, BCOM_INC_SIZE);
 
 	desc_src = (u32 *)(hdr + 1);
 	var_src = desc_src + hdr->desc_size;
 	inc_src = var_src + hdr->var_size;
 
-	memcpy(desc, desc_src, hdr->desc_size * sizeof(u32));
-	memcpy(var + hdr->first_var, var_src, hdr->var_size * sizeof(u32));
-	memcpy(inc, inc_src, hdr->inc_size * sizeof(u32));
+	memcpy_toio(desc, desc_src, hdr->desc_size * sizeof(u32));
+	memcpy_toio(var + hdr->first_var, var_src, hdr->var_size * sizeof(u32));
+	memcpy_toio(inc, inc_src, hdr->inc_size * sizeof(u32));
 
 	return 0;
 }
@@ -302,13 +302,13 @@ static int bcom_engine_init(void)
 		return -ENOMEM;
 	}
 
-	memset(bcom_eng->tdt, 0x00, tdt_size);
-	memset(bcom_eng->ctx, 0x00, ctx_size);
-	memset(bcom_eng->var, 0x00, var_size);
-	memset(bcom_eng->fdt, 0x00, fdt_size);
+	memset_io(bcom_eng->tdt, 0x00, tdt_size);
+	memset_io(bcom_eng->ctx, 0x00, ctx_size);
+	memset_io(bcom_eng->var, 0x00, var_size);
+	memset_io(bcom_eng->fdt, 0x00, fdt_size);
 
 	/* Copy the FDT for the EU#3 */
-	memcpy(&bcom_eng->fdt[48], fdt_ops, sizeof(fdt_ops));
+	memcpy_toio(&bcom_eng->fdt[48], fdt_ops, sizeof(fdt_ops));
 
 	/* Initialize Task base structure */
 	for (task=0; task<BCOM_MAX_TASKS; task++)
diff --git a/drivers/dma/bestcomm/fec.c b/drivers/dma/bestcomm/fec.c
index 7f1fb1c999e4..d203618ac11f 100644
--- a/drivers/dma/bestcomm/fec.c
+++ b/drivers/dma/bestcomm/fec.c
@@ -140,7 +140,7 @@ bcom_fec_rx_reset(struct bcom_task *tsk)
 	tsk->index = 0;
 	tsk->outdex = 0;
 
-	memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
+	memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
 
 	/* Configure some stuff */
 	bcom_set_task_pragma(tsk->tasknum, BCOM_FEC_RX_BD_PRAGMA);
@@ -241,7 +241,7 @@ bcom_fec_tx_reset(struct bcom_task *tsk)
 	tsk->index = 0;
 	tsk->outdex = 0;
 
-	memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
+	memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
 
 	/* Configure some stuff */
 	bcom_set_task_pragma(tsk->tasknum, BCOM_FEC_TX_BD_PRAGMA);
diff --git a/drivers/dma/bestcomm/gen_bd.c b/drivers/dma/bestcomm/gen_bd.c
index 906ddba6a6f5..8a24a5cbc263 100644
--- a/drivers/dma/bestcomm/gen_bd.c
+++ b/drivers/dma/bestcomm/gen_bd.c
@@ -142,7 +142,7 @@ bcom_gen_bd_rx_reset(struct bcom_task *tsk)
 	tsk->index = 0;
 	tsk->outdex = 0;
 
-	memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
+	memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
 
 	/* Configure some stuff */
 	bcom_set_task_pragma(tsk->tasknum, BCOM_GEN_RX_BD_PRAGMA);
@@ -226,7 +226,7 @@ bcom_gen_bd_tx_reset(struct bcom_task *tsk)
 	tsk->index = 0;
 	tsk->outdex = 0;
 
-	memset(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
+	memset_io(tsk->bd, 0x00, tsk->num_bd * tsk->bd_size);
 
 	/* Configure some stuff */
 	bcom_set_task_pragma(tsk->tasknum, BCOM_GEN_TX_BD_PRAGMA);
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index ebee94dbd630..96701dedcac8 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -915,6 +915,7 @@ static int jz4780_dma_probe(struct platform_device *pdev)
 	dd->dst_addr_widths = JZ_DMA_BUSWIDTHS;
 	dd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 	dd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	dd->max_sg_burst = JZ_DMA_MAX_DESC;
 
 	/*
 	 * Enable DMA controller, mark all channels as not programmable.
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index af3ee288bc11..d9f7c097cfd6 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -695,13 +695,12 @@ static struct dma_chan *find_candidate(struct dma_device *device,
  */
 struct dma_chan *dma_get_slave_channel(struct dma_chan *chan)
 {
-	int err = -EBUSY;
-
 	/* lock against __dma_request_channel */
 	mutex_lock(&dma_list_mutex);
 
 	if (chan->client_count == 0) {
 		struct dma_device *device = chan->device;
+		int err;
 
 		dma_cap_set(DMA_PRIVATE, device->cap_mask);
 		device->privatecnt++;
diff --git a/drivers/dma/dmaengine.h b/drivers/dma/dmaengine.h
index 1bfbd64b1371..53f16d3f0029 100644
--- a/drivers/dma/dmaengine.h
+++ b/drivers/dma/dmaengine.h
@@ -176,7 +176,7 @@ dmaengine_desc_get_callback_invoke(struct dma_async_tx_descriptor *tx,
 static inline bool
 dmaengine_desc_callback_valid(struct dmaengine_desc_callback *cb)
 {
-	return (cb->callback) ? true : false;
+	return cb->callback || cb->callback_result;
 }
 
 struct dma_chan *dma_get_slave_channel(struct dma_chan *chan);
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
index 35993ab92154..cd0d745eb071 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c
@@ -79,6 +79,32 @@ axi_chan_iowrite64(struct axi_dma_chan *chan, u32 reg, u64 val)
 	iowrite32(upper_32_bits(val), chan->chan_regs + reg + 4);
 }
 
+static inline void axi_chan_config_write(struct axi_dma_chan *chan,
+					 struct axi_dma_chan_config *config)
+{
+	u32 cfg_lo, cfg_hi;
+
+	cfg_lo = (config->dst_multblk_type << CH_CFG_L_DST_MULTBLK_TYPE_POS |
+		  config->src_multblk_type << CH_CFG_L_SRC_MULTBLK_TYPE_POS);
+	if (chan->chip->dw->hdata->reg_map_8_channels) {
+		cfg_hi = config->tt_fc << CH_CFG_H_TT_FC_POS |
+			 config->hs_sel_src << CH_CFG_H_HS_SEL_SRC_POS |
+			 config->hs_sel_dst << CH_CFG_H_HS_SEL_DST_POS |
+			 config->src_per << CH_CFG_H_SRC_PER_POS |
+			 config->dst_per << CH_CFG_H_DST_PER_POS |
+			 config->prior << CH_CFG_H_PRIORITY_POS;
+	} else {
+		cfg_lo |= config->src_per << CH_CFG2_L_SRC_PER_POS |
+			  config->dst_per << CH_CFG2_L_DST_PER_POS;
+		cfg_hi = config->tt_fc << CH_CFG2_H_TT_FC_POS |
+			 config->hs_sel_src << CH_CFG2_H_HS_SEL_SRC_POS |
+			 config->hs_sel_dst << CH_CFG2_H_HS_SEL_DST_POS |
+			 config->prior << CH_CFG2_H_PRIORITY_POS;
+	}
+	axi_chan_iowrite32(chan, CH_CFG_L, cfg_lo);
+	axi_chan_iowrite32(chan, CH_CFG_H, cfg_hi);
+}
+
 static inline void axi_dma_disable(struct axi_dma_chip *chip)
 {
 	u32 val;
@@ -154,7 +180,10 @@ static inline void axi_chan_disable(struct axi_dma_chan *chan)
 
 	val = axi_dma_ioread32(chan->chip, DMAC_CHEN);
 	val &= ~(BIT(chan->id) << DMAC_CHAN_EN_SHIFT);
-	val |=   BIT(chan->id) << DMAC_CHAN_EN_WE_SHIFT;
+	if (chan->chip->dw->hdata->reg_map_8_channels)
+		val |=   BIT(chan->id) << DMAC_CHAN_EN_WE_SHIFT;
+	else
+		val |=   BIT(chan->id) << DMAC_CHAN_EN2_WE_SHIFT;
 	axi_dma_iowrite32(chan->chip, DMAC_CHEN, val);
 }
 
@@ -163,8 +192,12 @@ static inline void axi_chan_enable(struct axi_dma_chan *chan)
 	u32 val;
 
 	val = axi_dma_ioread32(chan->chip, DMAC_CHEN);
-	val |= BIT(chan->id) << DMAC_CHAN_EN_SHIFT |
-	       BIT(chan->id) << DMAC_CHAN_EN_WE_SHIFT;
+	if (chan->chip->dw->hdata->reg_map_8_channels)
+		val |= BIT(chan->id) << DMAC_CHAN_EN_SHIFT |
+			BIT(chan->id) << DMAC_CHAN_EN_WE_SHIFT;
+	else
+		val |= BIT(chan->id) << DMAC_CHAN_EN_SHIFT |
+			BIT(chan->id) << DMAC_CHAN_EN2_WE_SHIFT;
 	axi_dma_iowrite32(chan->chip, DMAC_CHEN, val);
 }
 
@@ -179,12 +212,16 @@ static inline bool axi_chan_is_hw_enable(struct axi_dma_chan *chan)
 
 static void axi_dma_hw_init(struct axi_dma_chip *chip)
 {
+	int ret;
 	u32 i;
 
 	for (i = 0; i < chip->dw->hdata->nr_channels; i++) {
 		axi_chan_irq_disable(&chip->dw->chan[i], DWAXIDMAC_IRQ_ALL);
 		axi_chan_disable(&chip->dw->chan[i]);
 	}
+	ret = dma_set_mask_and_coherent(chip->dev, DMA_BIT_MASK(64));
+	if (ret)
+		dev_warn(chip->dev, "Unable to set coherent mask\n");
 }
 
 static u32 axi_chan_get_xfer_width(struct axi_dma_chan *chan, dma_addr_t src,
@@ -336,7 +373,8 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan,
 				      struct axi_dma_desc *first)
 {
 	u32 priority = chan->chip->dw->hdata->priority[chan->id];
-	u32 reg, irq_mask;
+	struct axi_dma_chan_config config;
+	u32 irq_mask;
 	u8 lms = 0; /* Select AXI0 master for LLI fetching */
 
 	if (unlikely(axi_chan_is_hw_enable(chan))) {
@@ -348,36 +386,36 @@ static void axi_chan_block_xfer_start(struct axi_dma_chan *chan,
 
 	axi_dma_enable(chan->chip);
 
-	reg = (DWAXIDMAC_MBLK_TYPE_LL << CH_CFG_L_DST_MULTBLK_TYPE_POS |
-	       DWAXIDMAC_MBLK_TYPE_LL << CH_CFG_L_SRC_MULTBLK_TYPE_POS);
-	axi_chan_iowrite32(chan, CH_CFG_L, reg);
-
-	reg = (DWAXIDMAC_TT_FC_MEM_TO_MEM_DMAC << CH_CFG_H_TT_FC_POS |
-	       priority << CH_CFG_H_PRIORITY_POS |
-	       DWAXIDMAC_HS_SEL_HW << CH_CFG_H_HS_SEL_DST_POS |
-	       DWAXIDMAC_HS_SEL_HW << CH_CFG_H_HS_SEL_SRC_POS);
+	config.dst_multblk_type = DWAXIDMAC_MBLK_TYPE_LL;
+	config.src_multblk_type = DWAXIDMAC_MBLK_TYPE_LL;
+	config.tt_fc = DWAXIDMAC_TT_FC_MEM_TO_MEM_DMAC;
+	config.prior = priority;
+	config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW;
+	config.hs_sel_dst = DWAXIDMAC_HS_SEL_HW;
 	switch (chan->direction) {
 	case DMA_MEM_TO_DEV:
 		dw_axi_dma_set_byte_halfword(chan, true);
-		reg |= (chan->config.device_fc ?
-			DWAXIDMAC_TT_FC_MEM_TO_PER_DST :
-			DWAXIDMAC_TT_FC_MEM_TO_PER_DMAC)
-			<< CH_CFG_H_TT_FC_POS;
+		config.tt_fc = chan->config.device_fc ?
+				DWAXIDMAC_TT_FC_MEM_TO_PER_DST :
+				DWAXIDMAC_TT_FC_MEM_TO_PER_DMAC;
 		if (chan->chip->apb_regs)
-			reg |= (chan->id << CH_CFG_H_DST_PER_POS);
+			config.dst_per = chan->id;
+		else
+			config.dst_per = chan->hw_handshake_num;
 		break;
 	case DMA_DEV_TO_MEM:
-		reg |= (chan->config.device_fc ?
-			DWAXIDMAC_TT_FC_PER_TO_MEM_SRC :
-			DWAXIDMAC_TT_FC_PER_TO_MEM_DMAC)
-			<< CH_CFG_H_TT_FC_POS;
+		config.tt_fc = chan->config.device_fc ?
+				DWAXIDMAC_TT_FC_PER_TO_MEM_SRC :
+				DWAXIDMAC_TT_FC_PER_TO_MEM_DMAC;
 		if (chan->chip->apb_regs)
-			reg |= (chan->id << CH_CFG_H_SRC_PER_POS);
+			config.src_per = chan->id;
+		else
+			config.src_per = chan->hw_handshake_num;
 		break;
 	default:
 		break;
 	}
-	axi_chan_iowrite32(chan, CH_CFG_H, reg);
+	axi_chan_config_write(chan, &config);
 
 	write_chan_llp(chan, first->hw_desc[0].llp | lms);
 
@@ -1120,10 +1158,16 @@ static int dma_chan_pause(struct dma_chan *dchan)
 
 	spin_lock_irqsave(&chan->vc.lock, flags);
 
-	val = axi_dma_ioread32(chan->chip, DMAC_CHEN);
-	val |= BIT(chan->id) << DMAC_CHAN_SUSP_SHIFT |
-	       BIT(chan->id) << DMAC_CHAN_SUSP_WE_SHIFT;
-	axi_dma_iowrite32(chan->chip, DMAC_CHEN, val);
+	if (chan->chip->dw->hdata->reg_map_8_channels) {
+		val = axi_dma_ioread32(chan->chip, DMAC_CHEN);
+		val |= BIT(chan->id) << DMAC_CHAN_SUSP_SHIFT |
+			BIT(chan->id) << DMAC_CHAN_SUSP_WE_SHIFT;
+		axi_dma_iowrite32(chan->chip, DMAC_CHEN, val);
+	} else {
+		val = BIT(chan->id) << DMAC_CHAN_SUSP2_SHIFT |
+		      BIT(chan->id) << DMAC_CHAN_SUSP2_WE_SHIFT;
+		axi_dma_iowrite32(chan->chip, DMAC_CHSUSPREG, val);
+	}
 
 	do  {
 		if (axi_chan_irq_read(chan) & DWAXIDMAC_IRQ_SUSPENDED)
@@ -1147,9 +1191,15 @@ static inline void axi_chan_resume(struct axi_dma_chan *chan)
 	u32 val;
 
 	val = axi_dma_ioread32(chan->chip, DMAC_CHEN);
-	val &= ~(BIT(chan->id) << DMAC_CHAN_SUSP_SHIFT);
-	val |=  (BIT(chan->id) << DMAC_CHAN_SUSP_WE_SHIFT);
-	axi_dma_iowrite32(chan->chip, DMAC_CHEN, val);
+	if (chan->chip->dw->hdata->reg_map_8_channels) {
+		val &= ~(BIT(chan->id) << DMAC_CHAN_SUSP_SHIFT);
+		val |=  (BIT(chan->id) << DMAC_CHAN_SUSP_WE_SHIFT);
+		axi_dma_iowrite32(chan->chip, DMAC_CHEN, val);
+	} else {
+		val &= ~(BIT(chan->id) << DMAC_CHAN_SUSP2_SHIFT);
+		val |=  (BIT(chan->id) << DMAC_CHAN_SUSP2_WE_SHIFT);
+		axi_dma_iowrite32(chan->chip, DMAC_CHSUSPREG, val);
+	}
 
 	chan->is_paused = false;
 }
@@ -1241,6 +1291,8 @@ static int parse_device_properties(struct axi_dma_chip *chip)
 		return -EINVAL;
 
 	chip->dw->hdata->nr_channels = tmp;
+	if (tmp <= DMA_REG_MAP_CH_REF)
+		chip->dw->hdata->reg_map_8_channels = true;
 
 	ret = device_property_read_u32(dev, "snps,dma-masters", &tmp);
 	if (ret)
diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h
index 380005afde16..be69a0b76860 100644
--- a/drivers/dma/dw-axi-dmac/dw-axi-dmac.h
+++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac.h
@@ -18,7 +18,7 @@
 
 #include "../virt-dma.h"
 
-#define DMAC_MAX_CHANNELS	8
+#define DMAC_MAX_CHANNELS	16
 #define DMAC_MAX_MASTERS	2
 #define DMAC_MAX_BLK_SIZE	0x200000
 
@@ -30,6 +30,8 @@ struct dw_axi_dma_hcfg {
 	u32	priority[DMAC_MAX_CHANNELS];
 	/* maximum supported axi burst length */
 	u32	axi_rw_burst_len;
+	/* Register map for DMAX_NUM_CHANNELS <= 8 */
+	bool	reg_map_8_channels;
 	bool	restrict_axi_burst_len;
 };
 
@@ -103,6 +105,17 @@ struct axi_dma_desc {
 	u32				period_len;
 };
 
+struct axi_dma_chan_config {
+	u8 dst_multblk_type;
+	u8 src_multblk_type;
+	u8 dst_per;
+	u8 src_per;
+	u8 tt_fc;
+	u8 prior;
+	u8 hs_sel_dst;
+	u8 hs_sel_src;
+};
+
 static inline struct device *dchan2dev(struct dma_chan *dchan)
 {
 	return &dchan->dev->device;
@@ -139,6 +152,8 @@ static inline struct axi_dma_chan *dchan_to_axi_dma_chan(struct dma_chan *dchan)
 #define DMAC_CHEN		0x018 /* R/W DMAC Channel Enable */
 #define DMAC_CHEN_L		0x018 /* R/W DMAC Channel Enable 00-31 */
 #define DMAC_CHEN_H		0x01C /* R/W DMAC Channel Enable 32-63 */
+#define DMAC_CHSUSPREG		0x020 /* R/W DMAC Channel Suspend */
+#define DMAC_CHABORTREG		0x028 /* R/W DMAC Channel Abort */
 #define DMAC_INTSTATUS		0x030 /* R DMAC Interrupt Status */
 #define DMAC_COMMON_INTCLEAR	0x038 /* W DMAC Interrupt Clear */
 #define DMAC_COMMON_INTSTATUS_ENA 0x040 /* R DMAC Interrupt Status Enable */
@@ -187,6 +202,7 @@ static inline struct axi_dma_chan *dchan_to_axi_dma_chan(struct dma_chan *dchan)
 #define DMA_APB_HS_SEL_BIT_SIZE	0x08 /* HW handshake bits per channel */
 #define DMA_APB_HS_SEL_MASK	0xFF /* HW handshake select masks */
 #define MAX_BLOCK_SIZE		0x1000 /* 1024 blocks * 4 bytes data width */
+#define DMA_REG_MAP_CH_REF	0x08 /* Channel count to choose register map */
 
 /* DMAC_CFG */
 #define DMAC_EN_POS			0
@@ -195,12 +211,20 @@ static inline struct axi_dma_chan *dchan_to_axi_dma_chan(struct dma_chan *dchan)
 #define INT_EN_POS			1
 #define INT_EN_MASK			BIT(INT_EN_POS)
 
+/* DMAC_CHEN */
 #define DMAC_CHAN_EN_SHIFT		0
 #define DMAC_CHAN_EN_WE_SHIFT		8
 
 #define DMAC_CHAN_SUSP_SHIFT		16
 #define DMAC_CHAN_SUSP_WE_SHIFT		24
 
+/* DMAC_CHEN2 */
+#define DMAC_CHAN_EN2_WE_SHIFT		16
+
+/* DMAC_CHSUSP */
+#define DMAC_CHAN_SUSP2_SHIFT		0
+#define DMAC_CHAN_SUSP2_WE_SHIFT	16
+
 /* CH_CTL_H */
 #define CH_CTL_H_ARLEN_EN		BIT(6)
 #define CH_CTL_H_ARLEN_POS		7
@@ -289,6 +313,15 @@ enum {
 	DWAXIDMAC_MBLK_TYPE_LL
 };
 
+/* CH_CFG2 */
+#define CH_CFG2_L_SRC_PER_POS		4
+#define CH_CFG2_L_DST_PER_POS		11
+
+#define CH_CFG2_H_TT_FC_POS		0
+#define CH_CFG2_H_HS_SEL_SRC_POS	3
+#define CH_CFG2_H_HS_SEL_DST_POS	4
+#define CH_CFG2_H_PRIORITY_POS		20
+
 /**
  * DW AXI DMA channel interrupts
  *
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 53289927dd0d..468d1097a1ec 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -249,7 +249,6 @@ static int dw_edma_device_terminate_all(struct dma_chan *dchan)
 {
 	struct dw_edma_chan *chan = dchan2dw_edma_chan(dchan);
 	int err = 0;
-	LIST_HEAD(head);
 
 	if (!chan->configured) {
 		/* Do nothing */
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index 44f6e09bdb53..198f6cd8ac1b 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -186,27 +186,18 @@ static int dw_edma_pcie_probe(struct pci_dev *pdev,
 	pci_set_master(pdev);
 
 	/* DMA configuration */
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (!err) {
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-		if (err) {
-			pci_err(pdev, "consistent DMA mask 64 set failed\n");
-			return err;
-		}
+		pci_err(pdev, "DMA mask 64 set failed\n");
+		return err;
 	} else {
 		pci_err(pdev, "DMA mask 64 set failed\n");
 
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			pci_err(pdev, "DMA mask 32 set failed\n");
 			return err;
 		}
-
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (err) {
-			pci_err(pdev, "consistent DMA mask 32 set failed\n");
-			return err;
-		}
 	}
 
 	/* Data structure allocation */
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index 26a3f926da02..ad2d4d012cf7 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -32,11 +32,7 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 	pci_set_master(pdev);
 	pci_try_set_mwi(pdev);
 
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (ret)
-		return ret;
-
-	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (ret)
 		return ret;
 
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index 930ae268c497..3ae05d1446a5 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -348,6 +348,7 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 	struct fsl_edma_engine *edma = fsl_chan->edma;
 	struct edma_regs *regs = &fsl_chan->edma->regs;
 	u32 ch = fsl_chan->vchan.chan.chan_id;
+	u16 csr = 0;
 
 	/*
 	 * TCD parameters are stored in struct fsl_edma_hw_tcd in little
@@ -373,6 +374,12 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan,
 	edma_writel(edma, (s32)tcd->dlast_sga,
 			&regs->tcd[ch].dlast_sga);
 
+	if (fsl_chan->is_sw) {
+		csr = le16_to_cpu(tcd->csr);
+		csr |= EDMA_TCD_CSR_START;
+		tcd->csr = cpu_to_le16(csr);
+	}
+
 	edma_writew(edma, (s16)tcd->csr, &regs->tcd[ch].csr);
 }
 
@@ -587,6 +594,29 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 }
 EXPORT_SYMBOL_GPL(fsl_edma_prep_slave_sg);
 
+struct dma_async_tx_descriptor *fsl_edma_prep_memcpy(struct dma_chan *chan,
+						     dma_addr_t dma_dst, dma_addr_t dma_src,
+						     size_t len, unsigned long flags)
+{
+	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct fsl_edma_desc *fsl_desc;
+
+	fsl_desc = fsl_edma_alloc_desc(fsl_chan, 1);
+	if (!fsl_desc)
+		return NULL;
+	fsl_desc->iscyclic = false;
+
+	fsl_chan->is_sw = true;
+
+	/* To match with copy_align and max_seg_size so 1 tcd is enough */
+	fsl_edma_fill_tcd(fsl_desc->tcd[0].vtcd, dma_src, dma_dst,
+			EDMA_TCD_ATTR_SSIZE_32BYTE | EDMA_TCD_ATTR_DSIZE_32BYTE,
+			32, len, 0, 1, 1, 32, 0, true, true, false);
+
+	return vchan_tx_prep(&fsl_chan->vchan, &fsl_desc->vdesc, flags);
+}
+EXPORT_SYMBOL_GPL(fsl_edma_prep_memcpy);
+
 void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan)
 {
 	struct virt_dma_desc *vdesc;
@@ -638,12 +668,14 @@ EXPORT_SYMBOL_GPL(fsl_edma_alloc_chan_resources);
 void fsl_edma_free_chan_resources(struct dma_chan *chan)
 {
 	struct fsl_edma_chan *fsl_chan = to_fsl_edma_chan(chan);
+	struct fsl_edma_engine *edma = fsl_chan->edma;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&fsl_chan->vchan.lock, flags);
 	fsl_edma_disable_request(fsl_chan);
-	fsl_edma_chan_mux(fsl_chan, 0, false);
+	if (edma->drvdata->dmamuxs)
+		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);
@@ -652,6 +684,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
 	dma_pool_destroy(fsl_chan->tcd_pool);
 	fsl_chan->tcd_pool = NULL;
+	fsl_chan->is_sw = false;
 }
 EXPORT_SYMBOL_GPL(fsl_edma_free_chan_resources);
 
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index ec1169741de1..004ec4a6bc86 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -121,6 +121,7 @@ struct fsl_edma_chan {
 	struct fsl_edma_desc		*edesc;
 	struct dma_slave_config		cfg;
 	u32				attr;
+	bool                            is_sw;
 	struct dma_pool			*tcd_pool;
 	dma_addr_t			dma_dev_addr;
 	u32				dma_dev_size;
@@ -240,6 +241,9 @@ struct dma_async_tx_descriptor *fsl_edma_prep_slave_sg(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
 		unsigned long flags, void *context);
+struct dma_async_tx_descriptor *fsl_edma_prep_memcpy(
+		struct dma_chan *chan, dma_addr_t dma_dst, dma_addr_t dma_src,
+		size_t len, unsigned long flags);
 void fsl_edma_xfer_desc(struct fsl_edma_chan *fsl_chan);
 void fsl_edma_issue_pending(struct dma_chan *chan);
 int fsl_edma_alloc_chan_resources(struct dma_chan *chan);
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index 90bb72af306c..76cbf54aec58 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -17,6 +17,7 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_dma.h>
+#include <linux/dma-mapping.h>
 
 #include "fsl-edma-common.h"
 
@@ -372,6 +373,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_PRIVATE, fsl_edma->dma_dev.cap_mask);
 	dma_cap_set(DMA_SLAVE, fsl_edma->dma_dev.cap_mask);
 	dma_cap_set(DMA_CYCLIC, fsl_edma->dma_dev.cap_mask);
+	dma_cap_set(DMA_MEMCPY, fsl_edma->dma_dev.cap_mask);
 
 	fsl_edma->dma_dev.dev = &pdev->dev;
 	fsl_edma->dma_dev.device_alloc_chan_resources
@@ -381,6 +383,7 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	fsl_edma->dma_dev.device_tx_status = fsl_edma_tx_status;
 	fsl_edma->dma_dev.device_prep_slave_sg = fsl_edma_prep_slave_sg;
 	fsl_edma->dma_dev.device_prep_dma_cyclic = fsl_edma_prep_dma_cyclic;
+	fsl_edma->dma_dev.device_prep_dma_memcpy = fsl_edma_prep_memcpy;
 	fsl_edma->dma_dev.device_config = fsl_edma_slave_config;
 	fsl_edma->dma_dev.device_pause = fsl_edma_pause;
 	fsl_edma->dma_dev.device_resume = fsl_edma_resume;
@@ -392,6 +395,10 @@ static int fsl_edma_probe(struct platform_device *pdev)
 	fsl_edma->dma_dev.dst_addr_widths = FSL_EDMA_BUSWIDTHS;
 	fsl_edma->dma_dev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
 
+	fsl_edma->dma_dev.copy_align = DMAENGINE_ALIGN_32_BYTES;
+	/* Per worst case 'nbytes = 1' take CITER as the max_seg_size */
+	dma_set_max_seg_size(fsl_edma->dma_dev.dev, 0x3fff);
+
 	platform_set_drvdata(pdev, fsl_edma);
 
 	ret = dma_async_device_register(&fsl_edma->dma_dev);
diff --git a/drivers/dma/hisi_dma.c b/drivers/dma/hisi_dma.c
index c855a0e4f9ff..97c87a7cba87 100644
--- a/drivers/dma/hisi_dma.c
+++ b/drivers/dma/hisi_dma.c
@@ -519,11 +519,7 @@ static int hisi_dma_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return ret;
 	}
 
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (ret)
-		return ret;
-
-	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (ret)
 		return ret;
 
diff --git a/drivers/dma/hsu/pci.c b/drivers/dma/hsu/pci.c
index 9045a6f7f589..6a2df3dd78d0 100644
--- a/drivers/dma/hsu/pci.c
+++ b/drivers/dma/hsu/pci.c
@@ -65,11 +65,7 @@ static int hsu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	pci_set_master(pdev);
 	pci_try_set_mwi(pdev);
 
-	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (ret)
-		return ret;
-
-	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+	ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (ret)
 		return ret;
 
diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c
index 83a5ff2ecf2a..fab412349f7f 100644
--- a/drivers/dma/idxd/device.c
+++ b/drivers/dma/idxd/device.c
@@ -135,8 +135,6 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 	struct idxd_device *idxd = wq->idxd;
 	struct device *dev = &idxd->pdev->dev;
 	int rc, num_descs, i;
-	int align;
-	u64 tmp;
 
 	if (wq->type != IDXD_WQT_KERNEL)
 		return 0;
@@ -148,21 +146,13 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
 	if (rc < 0)
 		return rc;
 
-	align = idxd->data->align;
-	wq->compls_size = num_descs * idxd->data->compl_size + align;
-	wq->compls_raw = dma_alloc_coherent(dev, wq->compls_size,
-					    &wq->compls_addr_raw, GFP_KERNEL);
-	if (!wq->compls_raw) {
+	wq->compls_size = num_descs * idxd->data->compl_size;
+	wq->compls = dma_alloc_coherent(dev, wq->compls_size, &wq->compls_addr, GFP_KERNEL);
+	if (!wq->compls) {
 		rc = -ENOMEM;
 		goto fail_alloc_compls;
 	}
 
-	/* Adjust alignment */
-	wq->compls_addr = (wq->compls_addr_raw + (align - 1)) & ~(align - 1);
-	tmp = (u64)wq->compls_raw;
-	tmp = (tmp + (align - 1)) & ~(align - 1);
-	wq->compls = (struct dsa_completion_record *)tmp;
-
 	rc = alloc_descs(wq, num_descs);
 	if (rc < 0)
 		goto fail_alloc_descs;
@@ -191,8 +181,7 @@ int idxd_wq_alloc_resources(struct idxd_wq *wq)
  fail_sbitmap_init:
 	free_descs(wq);
  fail_alloc_descs:
-	dma_free_coherent(dev, wq->compls_size, wq->compls_raw,
-			  wq->compls_addr_raw);
+	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
  fail_alloc_compls:
 	free_hw_descs(wq);
 	return rc;
@@ -207,8 +196,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq)
 
 	free_hw_descs(wq);
 	free_descs(wq);
-	dma_free_coherent(dev, wq->compls_size, wq->compls_raw,
-			  wq->compls_addr_raw);
+	dma_free_coherent(dev, wq->compls_size, wq->compls, wq->compls_addr);
 	sbitmap_queue_free(&wq->sbq);
 }
 
@@ -427,7 +415,6 @@ void idxd_wq_quiesce(struct idxd_wq *wq)
 {
 	percpu_ref_kill(&wq->wq_active);
 	wait_for_completion(&wq->wq_dead);
-	percpu_ref_exit(&wq->wq_active);
 }
 
 /* Device control bits */
@@ -584,6 +571,8 @@ void idxd_device_reset(struct idxd_device *idxd)
 	spin_lock(&idxd->dev_lock);
 	idxd_device_clear_state(idxd);
 	idxd->state = IDXD_DEV_DISABLED;
+	idxd_unmask_error_interrupts(idxd);
+	idxd_msix_perm_setup(idxd);
 	spin_unlock(&idxd->dev_lock);
 }
 
@@ -792,7 +781,7 @@ static int idxd_groups_config_write(struct idxd_device *idxd)
 	struct device *dev = &idxd->pdev->dev;
 
 	/* Setup bandwidth token limit */
-	if (idxd->token_limit) {
+	if (idxd->hw.gen_cap.config_en && idxd->token_limit) {
 		reg.bits = ioread32(idxd->reg_base + IDXD_GENCFG_OFFSET);
 		reg.token_limit = idxd->token_limit;
 		iowrite32(reg.bits, idxd->reg_base + IDXD_GENCFG_OFFSET);
@@ -1051,8 +1040,6 @@ static int idxd_wq_load_config(struct idxd_wq *wq)
 
 	wq->size = wq->wqcfg->wq_size;
 	wq->threshold = wq->wqcfg->wq_thresh;
-	if (wq->wqcfg->priv)
-		wq->type = IDXD_WQT_KERNEL;
 
 	/* The driver does not support shared WQ mode in read-only config yet */
 	if (wq->wqcfg->mode == 0 || wq->wqcfg->pasid_en)
diff --git a/drivers/dma/idxd/dma.c b/drivers/dma/idxd/dma.c
index e0f056c1d1f5..c39e9483206a 100644
--- a/drivers/dma/idxd/dma.c
+++ b/drivers/dma/idxd/dma.c
@@ -311,6 +311,7 @@ static int idxd_dmaengine_drv_probe(struct idxd_dev *idxd_dev)
 
 err_dma:
 	idxd_wq_quiesce(wq);
+	percpu_ref_exit(&wq->wq_active);
 err_ref:
 	idxd_wq_free_resources(wq);
 err_res_alloc:
@@ -328,9 +329,9 @@ static void idxd_dmaengine_drv_remove(struct idxd_dev *idxd_dev)
 	mutex_lock(&wq->wq_lock);
 	idxd_wq_quiesce(wq);
 	idxd_unregister_dma_channel(wq);
-	__drv_disable_wq(wq);
 	idxd_wq_free_resources(wq);
-	wq->type = IDXD_WQT_NONE;
+	__drv_disable_wq(wq);
+	percpu_ref_exit(&wq->wq_active);
 	mutex_unlock(&wq->wq_lock);
 }
 
diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h
index bfcb03329f77..0cf8d3145870 100644
--- a/drivers/dma/idxd/idxd.h
+++ b/drivers/dma/idxd/idxd.h
@@ -187,9 +187,7 @@ struct idxd_wq {
 		struct dsa_completion_record *compls;
 		struct iax_completion_record *iax_compls;
 	};
-	void *compls_raw;
 	dma_addr_t compls_addr;
-	dma_addr_t compls_addr_raw;
 	int compls_size;
 	struct idxd_desc **descs;
 	struct sbitmap_queue sbq;
diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index eb09bc591c31..7bf03f371ce1 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -797,11 +797,19 @@ static void idxd_remove(struct pci_dev *pdev)
 	int msixcnt = pci_msix_vec_count(pdev);
 	int i;
 
-	dev_dbg(&pdev->dev, "%s called\n", __func__);
+	idxd_unregister_devices(idxd);
+	/*
+	 * When ->release() is called for the idxd->conf_dev, it frees all the memory related
+	 * to the idxd context. The driver still needs those bits in order to do the rest of
+	 * the cleanup. However, we do need to unbound the idxd sub-driver. So take a ref
+	 * on the device here to hold off the freeing while allowing the idxd sub-driver
+	 * to unbind.
+	 */
+	get_device(idxd_confdev(idxd));
+	device_unregister(idxd_confdev(idxd));
 	idxd_shutdown(pdev);
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
-	idxd_unregister_devices(idxd);
 
 	for (i = 0; i < msixcnt; i++) {
 		irq_entry = &idxd->irq_entries[i];
@@ -815,7 +823,7 @@ static void idxd_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 	destroy_workqueue(idxd->wq);
 	perfmon_pmu_remove(idxd);
-	device_unregister(idxd_confdev(idxd));
+	put_device(idxd_confdev(idxd));
 }
 
 static struct pci_driver idxd_pci_driver = {
diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c
index ca88fa7a328e..17f2f8a31b63 100644
--- a/drivers/dma/idxd/irq.c
+++ b/drivers/dma/idxd/irq.c
@@ -63,6 +63,9 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 	int i;
 	bool err = false;
 
+	if (cause & IDXD_INTC_HALT_STATE)
+		goto halt;
+
 	if (cause & IDXD_INTC_ERR) {
 		spin_lock(&idxd->dev_lock);
 		for (i = 0; i < 4; i++)
@@ -121,6 +124,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 	if (!err)
 		return 0;
 
+halt:
 	gensts.bits = ioread32(idxd->reg_base + IDXD_GENSTATS_OFFSET);
 	if (gensts.state == IDXD_DEVICE_STATE_HALT) {
 		idxd->state = IDXD_DEV_HALTED;
@@ -134,6 +138,7 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause)
 			queue_work(idxd->wq, &idxd->work);
 		} else {
 			spin_lock(&idxd->dev_lock);
+			idxd->state = IDXD_DEV_HALTED;
 			idxd_wqs_quiesce(idxd);
 			idxd_wqs_unmap_portal(idxd);
 			idxd_device_clear_state(idxd);
@@ -221,8 +226,7 @@ static void irq_process_work_list(struct idxd_irq_entry *irq_entry)
 
 	list_for_each_entry_safe(desc, n, &irq_entry->work_list, list) {
 		if (desc->completion->status) {
-			list_del(&desc->list);
-			list_add_tail(&desc->list, &flist);
+			list_move_tail(&desc->list, &flist);
 		}
 	}
 
diff --git a/drivers/dma/idxd/registers.h b/drivers/dma/idxd/registers.h
index ffc7550a77ee..262c8220adbd 100644
--- a/drivers/dma/idxd/registers.h
+++ b/drivers/dma/idxd/registers.h
@@ -36,8 +36,7 @@ union gen_cap_reg {
 		u64 max_batch_shift:4;
 		u64 max_ims_mult:6;
 		u64 config_en:1;
-		u64 max_descs_per_engine:8;
-		u64 rsvd3:24;
+		u64 rsvd3:32;
 	};
 	u64 bits;
 } __packed;
@@ -158,6 +157,7 @@ enum idxd_device_reset_type {
 #define IDXD_INTC_CMD			0x02
 #define IDXD_INTC_OCCUPY			0x04
 #define IDXD_INTC_PERFMON_OVFL		0x08
+#define IDXD_INTC_HALT_STATE		0x10
 
 #define IDXD_CMD_OFFSET			0xa0
 union idxd_command_reg {
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index cacc725ca545..75ec0754d4ad 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -741,9 +741,8 @@ static int sdma_load_script(struct sdma_engine *sdma, void *buf, int size,
 	unsigned long flags;
 
 	buf_virt = dma_alloc_coherent(sdma->dev, size, &buf_phys, GFP_KERNEL);
-	if (!buf_virt) {
+	if (!buf_virt)
 		return -ENOMEM;
-	}
 
 	spin_lock_irqsave(&sdma->channel_0_lock, flags);
 
@@ -1227,8 +1226,9 @@ static int sdma_config_channel(struct dma_chan *chan)
 			if (sdmac->peripheral_type == IMX_DMATYPE_ASRC_SP ||
 			    sdmac->peripheral_type == IMX_DMATYPE_ASRC)
 				sdma_set_watermarklevel_for_p2p(sdmac);
-		} else
+		} else {
 			__set_bit(sdmac->event_id0, sdmac->event_mask);
+		}
 
 		/* Address */
 		sdmac->shp_addr = sdmac->per_address;
@@ -1241,7 +1241,7 @@ static int sdma_config_channel(struct dma_chan *chan)
 }
 
 static int sdma_set_channel_priority(struct sdma_channel *sdmac,
-		unsigned int priority)
+				     unsigned int priority)
 {
 	struct sdma_engine *sdma = sdmac->sdma;
 	int channel = sdmac->channel;
@@ -1261,7 +1261,7 @@ static int sdma_request_channel0(struct sdma_engine *sdma)
 	int ret = -EBUSY;
 
 	sdma->bd0 = dma_alloc_coherent(sdma->dev, PAGE_SIZE, &sdma->bd0_phys,
-					GFP_NOWAIT);
+				       GFP_NOWAIT);
 	if (!sdma->bd0) {
 		ret = -ENOMEM;
 		goto out;
@@ -1284,7 +1284,7 @@ static int sdma_alloc_bd(struct sdma_desc *desc)
 	int ret = 0;
 
 	desc->bd = dma_alloc_coherent(desc->sdmac->sdma->dev, bd_size,
-				       &desc->bd_phys, GFP_NOWAIT);
+				      &desc->bd_phys, GFP_NOWAIT);
 	if (!desc->bd) {
 		ret = -ENOMEM;
 		goto out;
@@ -1757,7 +1757,7 @@ static void sdma_issue_pending(struct dma_chan *chan)
 #define SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V4	46
 
 static void sdma_add_scripts(struct sdma_engine *sdma,
-		const struct sdma_script_start_addrs *addr)
+			     const struct sdma_script_start_addrs *addr)
 {
 	s32 *addr_arr = (u32 *)addr;
 	s32 *saddr_arr = (u32 *)sdma->script_addrs;
@@ -1840,8 +1840,8 @@ static void sdma_load_firmware(const struct firmware *fw, void *context)
 	clk_enable(sdma->clk_ahb);
 	/* download the RAM image for SDMA */
 	sdma_load_script(sdma, ram_code,
-			header->ram_code_size,
-			addr->ram_code_start_addr);
+			 header->ram_code_size,
+			 addr->ram_code_start_addr);
 	clk_disable(sdma->clk_ipg);
 	clk_disable(sdma->clk_ahb);
 
@@ -1850,8 +1850,8 @@ static void sdma_load_firmware(const struct firmware *fw, void *context)
 	sdma->fw_loaded = true;
 
 	dev_info(sdma->dev, "loaded firmware %d.%d\n",
-			header->version_major,
-			header->version_minor);
+		 header->version_major,
+		 header->version_minor);
 
 err_firmware:
 	release_firmware(fw);
@@ -1955,7 +1955,7 @@ static int sdma_init(struct sdma_engine *sdma)
 	writel_relaxed(0, sdma->regs + SDMA_H_C0PTR);
 
 	sdma->channel_control = dma_alloc_coherent(sdma->dev,
-			MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control) +
+			MAX_DMA_CHANNELS * sizeof(struct sdma_channel_control) +
 			sizeof(struct sdma_context_data),
 			&ccb_phys, GFP_KERNEL);
 
@@ -1965,9 +1965,9 @@ static int sdma_init(struct sdma_engine *sdma)
 	}
 
 	sdma->context = (void *)sdma->channel_control +
-		MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control);
+		MAX_DMA_CHANNELS * sizeof(struct sdma_channel_control);
 	sdma->context_phys = ccb_phys +
-		MAX_DMA_CHANNELS * sizeof (struct sdma_channel_control);
+		MAX_DMA_CHANNELS * sizeof(struct sdma_channel_control);
 
 	/* disable all channels */
 	for (i = 0; i < sdma->drvdata->num_events; i++)
diff --git a/drivers/dma/ioat/init.c b/drivers/dma/ioat/init.c
index 191b59279007..373b8dac6c9b 100644
--- a/drivers/dma/ioat/init.c
+++ b/drivers/dma/ioat/init.c
@@ -1363,15 +1363,9 @@ static int ioat_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (!iomap)
 		return -ENOMEM;
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
 	if (err)
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (err)
-		return err;
-
-	err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (err)
 		return err;
 
diff --git a/drivers/dma/milbeaut-hdmac.c b/drivers/dma/milbeaut-hdmac.c
index a8cfb59f6efe..1b0a95892627 100644
--- a/drivers/dma/milbeaut-hdmac.c
+++ b/drivers/dma/milbeaut-hdmac.c
@@ -269,7 +269,7 @@ milbeaut_hdmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	if (!md)
 		return NULL;
 
-	md->sgl = kzalloc(sizeof(*sgl) * sg_len, GFP_NOWAIT);
+	md->sgl = kcalloc(sg_len, sizeof(*sgl), GFP_NOWAIT);
 	if (!md->sgl) {
 		kfree(md);
 		return NULL;
diff --git a/drivers/dma/mmp_pdma.c b/drivers/dma/mmp_pdma.c
index 89f1814ff27a..a23563cd118b 100644
--- a/drivers/dma/mmp_pdma.c
+++ b/drivers/dma/mmp_pdma.c
@@ -1123,6 +1123,7 @@ static int mmp_pdma_probe(struct platform_device *op)
 						 mmp_pdma_dma_xlate, pdev);
 		if (ret < 0) {
 			dev_err(&op->dev, "of_dma_controller_register failed\n");
+			dma_async_device_unregister(&pdev->device);
 			return ret;
 		}
 	}
diff --git a/drivers/dma/plx_dma.c b/drivers/dma/plx_dma.c
index 166934544161..1ffcb5ca9788 100644
--- a/drivers/dma/plx_dma.c
+++ b/drivers/dma/plx_dma.c
@@ -563,15 +563,9 @@ static int plx_dma_probe(struct pci_dev *pdev,
 	if (rc)
 		return rc;
 
-	rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(48));
+	rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(48));
 	if (rc)
-		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-	if (rc)
-		return rc;
-
-	rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(48));
-	if (rc)
-		rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
+		rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
 	if (rc)
 		return rc;
 
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index c8a77b428b52..87f6ca1541cf 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -388,6 +388,8 @@ struct bam_device {
 	/* execution environment ID, from DT */
 	u32 ee;
 	bool controlled_remotely;
+	bool powered_remotely;
+	u32 active_channels;
 
 	const struct reg_offset_data *layout;
 
@@ -415,6 +417,44 @@ static inline void __iomem *bam_addr(struct bam_device *bdev, u32 pipe,
 		r.ee_mult * bdev->ee;
 }
 
+/**
+ * bam_reset() - reset and initialize BAM registers
+ * @bdev: bam device
+ */
+static void bam_reset(struct bam_device *bdev)
+{
+	u32 val;
+
+	/* s/w reset bam */
+	/* after reset all pipes are disabled and idle */
+	val = readl_relaxed(bam_addr(bdev, 0, BAM_CTRL));
+	val |= BAM_SW_RST;
+	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
+	val &= ~BAM_SW_RST;
+	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
+
+	/* make sure previous stores are visible before enabling BAM */
+	wmb();
+
+	/* enable bam */
+	val |= BAM_EN;
+	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
+
+	/* set descriptor threshhold, start with 4 bytes */
+	writel_relaxed(DEFAULT_CNT_THRSHLD,
+			bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
+
+	/* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */
+	writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS));
+
+	/* enable irqs for errors */
+	writel_relaxed(BAM_ERROR_EN | BAM_HRESP_ERR_EN,
+			bam_addr(bdev, 0, BAM_IRQ_EN));
+
+	/* unmask global bam interrupt */
+	writel_relaxed(BAM_IRQ_MSK, bam_addr(bdev, 0, BAM_IRQ_SRCS_MSK_EE));
+}
+
 /**
  * bam_reset_channel - Reset individual BAM DMA channel
  * @bchan: bam channel
@@ -512,6 +552,9 @@ static int bam_alloc_chan(struct dma_chan *chan)
 		return -ENOMEM;
 	}
 
+	if (bdev->active_channels++ == 0 && bdev->powered_remotely)
+		bam_reset(bdev);
+
 	return 0;
 }
 
@@ -565,6 +608,13 @@ static void bam_free_chan(struct dma_chan *chan)
 	/* disable irq */
 	writel_relaxed(0, bam_addr(bdev, bchan->id, BAM_P_IRQ_EN));
 
+	if (--bdev->active_channels == 0 && bdev->powered_remotely) {
+		/* s/w reset bam */
+		val = readl_relaxed(bam_addr(bdev, 0, BAM_CTRL));
+		val |= BAM_SW_RST;
+		writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
+	}
+
 err:
 	pm_runtime_mark_last_busy(bdev->dev);
 	pm_runtime_put_autosuspend(bdev->dev);
@@ -1164,37 +1214,9 @@ static int bam_init(struct bam_device *bdev)
 		bdev->num_channels = val & BAM_NUM_PIPES_MASK;
 	}
 
-	if (bdev->controlled_remotely)
-		return 0;
-
-	/* s/w reset bam */
-	/* after reset all pipes are disabled and idle */
-	val = readl_relaxed(bam_addr(bdev, 0, BAM_CTRL));
-	val |= BAM_SW_RST;
-	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
-	val &= ~BAM_SW_RST;
-	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
-
-	/* make sure previous stores are visible before enabling BAM */
-	wmb();
-
-	/* enable bam */
-	val |= BAM_EN;
-	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
-
-	/* set descriptor threshhold, start with 4 bytes */
-	writel_relaxed(DEFAULT_CNT_THRSHLD,
-			bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
-
-	/* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */
-	writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS));
-
-	/* enable irqs for errors */
-	writel_relaxed(BAM_ERROR_EN | BAM_HRESP_ERR_EN,
-			bam_addr(bdev, 0, BAM_IRQ_EN));
-
-	/* unmask global bam interrupt */
-	writel_relaxed(BAM_IRQ_MSK, bam_addr(bdev, 0, BAM_IRQ_SRCS_MSK_EE));
+	/* Reset BAM now if fully controlled locally */
+	if (!bdev->controlled_remotely && !bdev->powered_remotely)
+		bam_reset(bdev);
 
 	return 0;
 }
@@ -1257,8 +1279,10 @@ static int bam_dma_probe(struct platform_device *pdev)
 
 	bdev->controlled_remotely = of_property_read_bool(pdev->dev.of_node,
 						"qcom,controlled-remotely");
+	bdev->powered_remotely = of_property_read_bool(pdev->dev.of_node,
+						"qcom,powered-remotely");
 
-	if (bdev->controlled_remotely) {
+	if (bdev->controlled_remotely || bdev->powered_remotely) {
 		ret = of_property_read_u32(pdev->dev.of_node, "num-channels",
 					   &bdev->num_channels);
 		if (ret)
@@ -1270,7 +1294,7 @@ static int bam_dma_probe(struct platform_device *pdev)
 			dev_err(bdev->dev, "num-ees unspecified in dt\n");
 	}
 
-	if (bdev->controlled_remotely)
+	if (bdev->controlled_remotely || bdev->powered_remotely)
 		bdev->bamclk = devm_clk_get_optional(bdev->dev, "bam_clk");
 	else
 		bdev->bamclk = devm_clk_get(bdev->dev, "bam_clk");
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
index 1e918e284fc0..a29c13cae716 100644
--- a/drivers/dma/sa11x0-dma.c
+++ b/drivers/dma/sa11x0-dma.c
@@ -1001,7 +1001,7 @@ static int sa11x0_dma_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int sa11x0_dma_suspend(struct device *dev)
+static __maybe_unused int sa11x0_dma_suspend(struct device *dev)
 {
 	struct sa11x0_dma_dev *d = dev_get_drvdata(dev);
 	unsigned pch;
@@ -1039,7 +1039,7 @@ static int sa11x0_dma_suspend(struct device *dev)
 	return 0;
 }
 
-static int sa11x0_dma_resume(struct device *dev)
+static __maybe_unused int sa11x0_dma_resume(struct device *dev)
 {
 	struct sa11x0_dma_dev *d = dev_get_drvdata(dev);
 	unsigned pch;
@@ -1072,12 +1072,7 @@ static int sa11x0_dma_resume(struct device *dev)
 }
 
 static const struct dev_pm_ops sa11x0_dma_pm_ops = {
-	.suspend_noirq = sa11x0_dma_suspend,
-	.resume_noirq = sa11x0_dma_resume,
-	.freeze_noirq = sa11x0_dma_suspend,
-	.thaw_noirq = sa11x0_dma_resume,
-	.poweroff_noirq = sa11x0_dma_suspend,
-	.restore_noirq = sa11x0_dma_resume,
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(sa11x0_dma_suspend, sa11x0_dma_resume)
 };
 
 static struct platform_driver sa11x0_dma_driver = {
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 6885b3dcd7a9..5c7716fd6bc5 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1916,7 +1916,7 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 	ret = pm_runtime_resume_and_get(&pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret);
-		return ret;
+		goto err_pm_disable;
 	}
 
 	ret = rcar_dmac_init(dmac);
@@ -1924,7 +1924,7 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 
 	if (ret) {
 		dev_err(&pdev->dev, "failed to reset device\n");
-		goto error;
+		goto err_pm_disable;
 	}
 
 	/* Initialize engine */
@@ -1958,14 +1958,14 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 	for_each_rcar_dmac_chan(i, dmac, chan) {
 		ret = rcar_dmac_chan_probe(dmac, chan);
 		if (ret < 0)
-			goto error;
+			goto err_pm_disable;
 	}
 
 	/* Register the DMAC as a DMA provider for DT. */
 	ret = of_dma_controller_register(pdev->dev.of_node, rcar_dmac_of_xlate,
 					 NULL);
 	if (ret < 0)
-		goto error;
+		goto err_pm_disable;
 
 	/*
 	 * Register the DMA engine device.
@@ -1974,12 +1974,13 @@ static int rcar_dmac_probe(struct platform_device *pdev)
 	 */
 	ret = dma_async_device_register(engine);
 	if (ret < 0)
-		goto error;
+		goto err_dma_free;
 
 	return 0;
 
-error:
+err_dma_free:
 	of_dma_controller_free(pdev->dev.of_node);
+err_pm_disable:
 	pm_runtime_disable(&pdev->dev);
 	return ret;
 }
diff --git a/drivers/dma/sh/rz-dmac.c b/drivers/dma/sh/rz-dmac.c
index f9f30cbeccbe..ee2872e7d64c 100644
--- a/drivers/dma/sh/rz-dmac.c
+++ b/drivers/dma/sh/rz-dmac.c
@@ -18,6 +18,7 @@
 #include <linux/of_dma.h>
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
@@ -573,7 +574,7 @@ static void rz_dmac_issue_pending(struct dma_chan *chan)
 static u8 rz_dmac_ds_to_val_mapping(enum dma_slave_buswidth ds)
 {
 	u8 i;
-	const enum dma_slave_buswidth ds_lut[] = {
+	static const enum dma_slave_buswidth ds_lut[] = {
 		DMA_SLAVE_BUSWIDTH_1_BYTE,
 		DMA_SLAVE_BUSWIDTH_2_BYTES,
 		DMA_SLAVE_BUSWIDTH_4_BYTES,
@@ -872,6 +873,13 @@ static int rz_dmac_probe(struct platform_device *pdev)
 	/* Initialize the channels. */
 	INIT_LIST_HEAD(&dmac->engine.channels);
 
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_runtime_resume_and_get(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "pm_runtime_resume_and_get failed\n");
+		goto err_pm_disable;
+	}
+
 	for (i = 0; i < dmac->n_channels; i++) {
 		ret = rz_dmac_chan_probe(dmac, &dmac->channels[i], i);
 		if (ret < 0)
@@ -925,6 +933,10 @@ err:
 				  channel->lmdesc.base_dma);
 	}
 
+	pm_runtime_put(&pdev->dev);
+err_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+
 	return ret;
 }
 
@@ -943,6 +955,8 @@ static int rz_dmac_remove(struct platform_device *pdev)
 	}
 	of_dma_controller_free(pdev->dev.of_node);
 	dma_async_device_unregister(&dmac->engine);
+	pm_runtime_put(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
 
 	return 0;
 }
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 9063c727962e..83a37a6955a3 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -270,7 +270,6 @@ static enum dma_slave_buswidth stm32_dma_get_max_width(u32 buf_len,
 						       u32 threshold)
 {
 	enum dma_slave_buswidth max_width;
-	u64 addr = buf_addr;
 
 	if (threshold == STM32_DMA_FIFO_THRESHOLD_FULL)
 		max_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -281,7 +280,7 @@ static enum dma_slave_buswidth stm32_dma_get_max_width(u32 buf_len,
 	       max_width > DMA_SLAVE_BUSWIDTH_1_BYTE)
 		max_width = max_width >> 1;
 
-	if (do_div(addr, max_width))
+	if (buf_addr & (max_width - 1))
 		max_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
 
 	return max_width;
@@ -497,6 +496,7 @@ static int stm32_dma_terminate_all(struct dma_chan *c)
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 
 	if (chan->desc) {
+		dma_cookie_complete(&chan->desc->vdesc.tx);
 		vchan_terminate_vdesc(&chan->desc->vdesc);
 		if (chan->busy)
 			stm32_dma_stop(chan);
@@ -753,8 +753,14 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 		if (src_bus_width < 0)
 			return src_bus_width;
 
-		/* Set memory burst size */
-		src_maxburst = STM32_DMA_MAX_BURST;
+		/*
+		 * Set memory burst size - burst not possible if address is not aligned on
+		 * the address boundary equal to the size of the transfer
+		 */
+		if (buf_addr & (buf_len - 1))
+			src_maxburst = 1;
+		else
+			src_maxburst = STM32_DMA_MAX_BURST;
 		src_best_burst = stm32_dma_get_best_burst(buf_len,
 							  src_maxburst,
 							  fifoth,
@@ -803,8 +809,14 @@ static int stm32_dma_set_xfer_param(struct stm32_dma_chan *chan,
 		if (dst_bus_width < 0)
 			return dst_bus_width;
 
-		/* Set memory burst size */
-		dst_maxburst = STM32_DMA_MAX_BURST;
+		/*
+		 * Set memory burst size - burst not possible if address is not aligned on
+		 * the address boundary equal to the size of the transfer
+		 */
+		if (buf_addr & (buf_len - 1))
+			dst_maxburst = 1;
+		else
+			dst_maxburst = STM32_DMA_MAX_BURST;
 		dst_best_burst = stm32_dma_get_best_burst(buf_len,
 							  dst_maxburst,
 							  fifoth,
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 18cbd1e43c2e..d30a4a28d3bf 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -1566,7 +1566,8 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 	if (count < 0)
 		count = 0;
 
-	dmadev = devm_kzalloc(&pdev->dev, sizeof(*dmadev) + sizeof(u32) * count,
+	dmadev = devm_kzalloc(&pdev->dev,
+			      struct_size(dmadev, ahb_addr_masks, count),
 			      GFP_KERNEL);
 	if (!dmadev)
 		return -ENOMEM;
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index b1115a6d1935..ae39b52012b2 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -43,10 +43,8 @@
 #define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs)	(reqs << 4)
 
 #define ADMA_CH_FIFO_CTRL				0x2c
-#define TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(val)		(((val) & 0xf) << 8)
-#define TEGRA210_ADMA_CH_FIFO_CTRL_RXSIZE(val)		((val) & 0xf)
-#define TEGRA186_ADMA_CH_FIFO_CTRL_TXSIZE(val)		(((val) & 0x1f) << 8)
-#define TEGRA186_ADMA_CH_FIFO_CTRL_RXSIZE(val)		((val) & 0x1f)
+#define ADMA_CH_TX_FIFO_SIZE_SHIFT			8
+#define ADMA_CH_RX_FIFO_SIZE_SHIFT			0
 
 #define ADMA_CH_LOWER_SRC_ADDR				0x34
 #define ADMA_CH_LOWER_TRG_ADDR				0x3c
@@ -61,29 +59,26 @@
 
 #define TEGRA_ADMA_BURST_COMPLETE_TIME			20
 
-#define TEGRA210_FIFO_CTRL_DEFAULT (TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(3) | \
-				    TEGRA210_ADMA_CH_FIFO_CTRL_RXSIZE(3))
-
-#define TEGRA186_FIFO_CTRL_DEFAULT (TEGRA186_ADMA_CH_FIFO_CTRL_TXSIZE(3) | \
-				    TEGRA186_ADMA_CH_FIFO_CTRL_RXSIZE(3))
-
 #define ADMA_CH_REG_FIELD_VAL(val, mask, shift)	(((val) & mask) << shift)
 
 struct tegra_adma;
 
 /*
  * struct tegra_adma_chip_data - Tegra chip specific data
+ * @adma_get_burst_config: Function callback used to set DMA burst size.
  * @global_reg_offset: Register offset of DMA global register.
  * @global_int_clear: Register offset of DMA global interrupt clear.
  * @ch_req_tx_shift: Register offset for AHUB transmit channel select.
  * @ch_req_rx_shift: Register offset for AHUB receive channel select.
  * @ch_base_offset: Register offset of DMA channel registers.
- * @has_outstanding_reqs: If DMA channel can have outstanding requests.
  * @ch_fifo_ctrl: Default value for channel FIFO CTRL register.
  * @ch_req_mask: Mask for Tx or Rx channel select.
  * @ch_req_max: Maximum number of Tx or Rx channels available.
  * @ch_reg_size: Size of DMA channel register space.
  * @nr_channels: Number of DMA channels available.
+ * @ch_fifo_size_mask: Mask for FIFO size field.
+ * @sreq_index_offset: Slave channel index offset.
+ * @has_outstanding_reqs: If DMA channel can have outstanding requests.
  */
 struct tegra_adma_chip_data {
 	unsigned int (*adma_get_burst_config)(unsigned int burst_size);
@@ -97,6 +92,8 @@ struct tegra_adma_chip_data {
 	unsigned int ch_req_max;
 	unsigned int ch_reg_size;
 	unsigned int nr_channels;
+	unsigned int ch_fifo_size_mask;
+	unsigned int sreq_index_offset;
 	bool has_outstanding_reqs;
 };
 
@@ -560,13 +557,14 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 {
 	struct tegra_adma_chan_regs *ch_regs = &desc->ch_regs;
 	const struct tegra_adma_chip_data *cdata = tdc->tdma->cdata;
-	unsigned int burst_size, adma_dir;
+	unsigned int burst_size, adma_dir, fifo_size_shift;
 
 	if (desc->num_periods > ADMA_CH_CONFIG_MAX_BUFS)
 		return -EINVAL;
 
 	switch (direction) {
 	case DMA_MEM_TO_DEV:
+		fifo_size_shift = ADMA_CH_TX_FIFO_SIZE_SHIFT;
 		adma_dir = ADMA_CH_CTRL_DIR_MEM2AHUB;
 		burst_size = tdc->sconfig.dst_maxburst;
 		ch_regs->config = ADMA_CH_CONFIG_SRC_BUF(desc->num_periods - 1);
@@ -577,6 +575,7 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 		break;
 
 	case DMA_DEV_TO_MEM:
+		fifo_size_shift = ADMA_CH_RX_FIFO_SIZE_SHIFT;
 		adma_dir = ADMA_CH_CTRL_DIR_AHUB2MEM;
 		burst_size = tdc->sconfig.src_maxburst;
 		ch_regs->config = ADMA_CH_CONFIG_TRG_BUF(desc->num_periods - 1);
@@ -598,7 +597,27 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 	ch_regs->config |= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1);
 	if (cdata->has_outstanding_reqs)
 		ch_regs->config |= TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8);
-	ch_regs->fifo_ctrl = cdata->ch_fifo_ctrl;
+
+	/*
+	 * 'sreq_index' represents the current ADMAIF channel number and as per
+	 * HW recommendation its FIFO size should match with the corresponding
+	 * ADMA channel.
+	 *
+	 * ADMA FIFO size is set as per below (based on default ADMAIF channel
+	 * FIFO sizes):
+	 *    fifo_size = 0x2 (sreq_index > sreq_index_offset)
+	 *    fifo_size = 0x3 (sreq_index <= sreq_index_offset)
+	 *
+	 */
+	if (tdc->sreq_index > cdata->sreq_index_offset)
+		ch_regs->fifo_ctrl =
+			ADMA_CH_REG_FIELD_VAL(2, cdata->ch_fifo_size_mask,
+					      fifo_size_shift);
+	else
+		ch_regs->fifo_ctrl =
+			ADMA_CH_REG_FIELD_VAL(3, cdata->ch_fifo_size_mask,
+					      fifo_size_shift);
+
 	ch_regs->tc = desc->period_len & ADMA_CH_TC_COUNT_MASK;
 
 	return tegra_adma_request_alloc(tdc, direction);
@@ -782,12 +801,13 @@ static const struct tegra_adma_chip_data tegra210_chip_data = {
 	.ch_req_tx_shift	= 28,
 	.ch_req_rx_shift	= 24,
 	.ch_base_offset		= 0,
-	.has_outstanding_reqs	= false,
-	.ch_fifo_ctrl		= TEGRA210_FIFO_CTRL_DEFAULT,
 	.ch_req_mask		= 0xf,
 	.ch_req_max		= 10,
 	.ch_reg_size		= 0x80,
 	.nr_channels		= 22,
+	.ch_fifo_size_mask	= 0xf,
+	.sreq_index_offset	= 2,
+	.has_outstanding_reqs	= false,
 };
 
 static const struct tegra_adma_chip_data tegra186_chip_data = {
@@ -797,12 +817,13 @@ static const struct tegra_adma_chip_data tegra186_chip_data = {
 	.ch_req_tx_shift	= 27,
 	.ch_req_rx_shift	= 22,
 	.ch_base_offset		= 0x10000,
-	.has_outstanding_reqs	= true,
-	.ch_fifo_ctrl		= TEGRA186_FIFO_CTRL_DEFAULT,
 	.ch_req_mask		= 0x1f,
 	.ch_req_max		= 20,
 	.ch_reg_size		= 0x100,
 	.nr_channels		= 32,
+	.ch_fifo_size_mask	= 0x1f,
+	.sreq_index_offset	= 4,
+	.has_outstanding_reqs	= true,
 };
 
 static const struct of_device_id tegra_adma_of_match[] = {
@@ -867,7 +888,7 @@ static int tegra_adma_probe(struct platform_device *pdev)
 
 	pm_runtime_enable(&pdev->dev);
 
-	ret = pm_runtime_get_sync(&pdev->dev);
+	ret = pm_runtime_resume_and_get(&pdev->dev);
 	if (ret < 0)
 		goto rpm_disable;
 
@@ -940,7 +961,6 @@ static int tegra_adma_remove(struct platform_device *pdev)
 	for (i = 0; i < tdma->nr_channels; ++i)
 		irq_dispose_mapping(tdma->channels[i].irq);
 
-	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
 	return 0;
diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
index a35858610780..041d8e32d630 100644
--- a/drivers/dma/ti/k3-udma.c
+++ b/drivers/dma/ti/k3-udma.c
@@ -1348,6 +1348,7 @@ static int bcdma_get_bchan(struct udma_chan *uc)
 {
 	struct udma_dev *ud = uc->ud;
 	enum udma_tp_level tpl;
+	int ret;
 
 	if (uc->bchan) {
 		dev_dbg(ud->dev, "chan%d: already have bchan%d allocated\n",
@@ -1365,8 +1366,11 @@ static int bcdma_get_bchan(struct udma_chan *uc)
 		tpl = ud->bchan_tpl.levels - 1;
 
 	uc->bchan = __udma_reserve_bchan(ud, tpl, -1);
-	if (IS_ERR(uc->bchan))
-		return PTR_ERR(uc->bchan);
+	if (IS_ERR(uc->bchan)) {
+		ret = PTR_ERR(uc->bchan);
+		uc->bchan = NULL;
+		return ret;
+	}
 
 	uc->tchan = uc->bchan;
 
@@ -1376,6 +1380,7 @@ static int bcdma_get_bchan(struct udma_chan *uc)
 static int udma_get_tchan(struct udma_chan *uc)
 {
 	struct udma_dev *ud = uc->ud;
+	int ret;
 
 	if (uc->tchan) {
 		dev_dbg(ud->dev, "chan%d: already have tchan%d allocated\n",
@@ -1390,8 +1395,11 @@ static int udma_get_tchan(struct udma_chan *uc)
 	 */
 	uc->tchan = __udma_reserve_tchan(ud, uc->config.channel_tpl,
 					 uc->config.mapped_channel_id);
-	if (IS_ERR(uc->tchan))
-		return PTR_ERR(uc->tchan);
+	if (IS_ERR(uc->tchan)) {
+		ret = PTR_ERR(uc->tchan);
+		uc->tchan = NULL;
+		return ret;
+	}
 
 	if (ud->tflow_cnt) {
 		int tflow_id;
@@ -1421,6 +1429,7 @@ static int udma_get_tchan(struct udma_chan *uc)
 static int udma_get_rchan(struct udma_chan *uc)
 {
 	struct udma_dev *ud = uc->ud;
+	int ret;
 
 	if (uc->rchan) {
 		dev_dbg(ud->dev, "chan%d: already have rchan%d allocated\n",
@@ -1435,8 +1444,13 @@ static int udma_get_rchan(struct udma_chan *uc)
 	 */
 	uc->rchan = __udma_reserve_rchan(ud, uc->config.channel_tpl,
 					 uc->config.mapped_channel_id);
+	if (IS_ERR(uc->rchan)) {
+		ret = PTR_ERR(uc->rchan);
+		uc->rchan = NULL;
+		return ret;
+	}
 
-	return PTR_ERR_OR_ZERO(uc->rchan);
+	return 0;
 }
 
 static int udma_get_chan_pair(struct udma_chan *uc)
@@ -1490,6 +1504,7 @@ static int udma_get_chan_pair(struct udma_chan *uc)
 static int udma_get_rflow(struct udma_chan *uc, int flow_id)
 {
 	struct udma_dev *ud = uc->ud;
+	int ret;
 
 	if (!uc->rchan) {
 		dev_err(ud->dev, "chan%d: does not have rchan??\n", uc->id);
@@ -1503,8 +1518,13 @@ static int udma_get_rflow(struct udma_chan *uc, int flow_id)
 	}
 
 	uc->rflow = __udma_get_rflow(ud, flow_id);
+	if (IS_ERR(uc->rflow)) {
+		ret = PTR_ERR(uc->rflow);
+		uc->rflow = NULL;
+		return ret;
+	}
 
-	return PTR_ERR_OR_ZERO(uc->rflow);
+	return 0;
 }
 
 static void bcdma_put_bchan(struct udma_chan *uc)
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index a4450bc95466..4677ce08ed40 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -792,7 +792,7 @@ static void xilinx_vdma_free_tx_segment(struct xilinx_dma_chan *chan,
 }
 
 /**
- * xilinx_dma_tx_descriptor - Allocate transaction descriptor
+ * xilinx_dma_alloc_tx_descriptor - Allocate transaction descriptor
  * @chan: Driver specific DMA channel
  *
  * Return: The allocated descriptor on success and NULL on failure.
@@ -998,14 +998,12 @@ static void xilinx_dma_chan_handle_cyclic(struct xilinx_dma_chan *chan,
 					  struct xilinx_dma_tx_descriptor *desc,
 					  unsigned long *flags)
 {
-	dma_async_tx_callback callback;
-	void *callback_param;
+	struct dmaengine_desc_callback cb;
 
-	callback = desc->async_tx.callback;
-	callback_param = desc->async_tx.callback_param;
-	if (callback) {
+	dmaengine_desc_get_callback(&desc->async_tx, &cb);
+	if (dmaengine_desc_callback_valid(&cb)) {
 		spin_unlock_irqrestore(&chan->lock, *flags);
-		callback(callback_param);
+		dmaengine_desc_callback_invoke(&cb, NULL);
 		spin_lock_irqsave(&chan->lock, *flags);
 	}
 }
@@ -2483,7 +2481,7 @@ static void xilinx_dma_synchronize(struct dma_chan *dchan)
 }
 
 /**
- * xilinx_dma_channel_set_config - Configure VDMA channel
+ * xilinx_vdma_channel_set_config - Configure VDMA channel
  * Run-time configuration for Axi VDMA, supports:
  * . halt the channel
  * . configure interrupt coalescing and inter-packet delay threshold
diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c
index b280a53e8570..ce5c66e6897d 100644
--- a/drivers/dma/xilinx/xilinx_dpdma.c
+++ b/drivers/dma/xilinx/xilinx_dpdma.c
@@ -271,9 +271,6 @@ struct xilinx_dpdma_device {
 /* -----------------------------------------------------------------------------
  * DebugFS
  */
-
-#ifdef CONFIG_DEBUG_FS
-
 #define XILINX_DPDMA_DEBUGFS_READ_MAX_SIZE	32
 #define XILINX_DPDMA_DEBUGFS_UINT16_MAX_STR	"65535"
 
@@ -299,7 +296,7 @@ struct xilinx_dpdma_debugfs_request {
 
 static void xilinx_dpdma_debugfs_desc_done_irq(struct xilinx_dpdma_chan *chan)
 {
-	if (chan->id == dpdma_debugfs.chan_id)
+	if (IS_ENABLED(CONFIG_DEBUG_FS) && chan->id == dpdma_debugfs.chan_id)
 		dpdma_debugfs.xilinx_dpdma_irq_done_count++;
 }
 
@@ -462,16 +459,6 @@ static void xilinx_dpdma_debugfs_init(struct xilinx_dpdma_device *xdev)
 		dev_err(xdev->dev, "Failed to create debugfs testcase file\n");
 }
 
-#else
-static void xilinx_dpdma_debugfs_init(struct xilinx_dpdma_device *xdev)
-{
-}
-
-static void xilinx_dpdma_debugfs_desc_done_irq(struct xilinx_dpdma_chan *chan)
-{
-}
-#endif /* CONFIG_DEBUG_FS */
-
 /* -----------------------------------------------------------------------------
  * I/O Accessors
  */
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 97f02f8eb03a..7aa63b652027 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -6,15 +6,12 @@
  */
 
 #include <linux/bitops.h>
-#include <linux/dmapool.h>
-#include <linux/dma/xilinx_dma.h>
+#include <linux/dma-mapping.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
 #include <linux/of_dma.h>
-#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/slab.h>
 #include <linux/clk.h>
@@ -603,22 +600,25 @@ static void zynqmp_dma_start_transfer(struct zynqmp_dma_chan *chan)
 static void zynqmp_dma_chan_desc_cleanup(struct zynqmp_dma_chan *chan)
 {
 	struct zynqmp_dma_desc_sw *desc, *next;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&chan->lock, irqflags);
 
 	list_for_each_entry_safe(desc, next, &chan->done_list, node) {
-		dma_async_tx_callback callback;
-		void *callback_param;
+		struct dmaengine_desc_callback cb;
 
-		callback = desc->async_tx.callback;
-		callback_param = desc->async_tx.callback_param;
-		if (callback) {
-			spin_unlock(&chan->lock);
-			callback(callback_param);
-			spin_lock(&chan->lock);
+		dmaengine_desc_get_callback(&desc->async_tx, &cb);
+		if (dmaengine_desc_callback_valid(&cb)) {
+			spin_unlock_irqrestore(&chan->lock, irqflags);
+			dmaengine_desc_callback_invoke(&cb, NULL);
+			spin_lock_irqsave(&chan->lock, irqflags);
 		}
 
 		/* Run any dependencies, then free the descriptor */
 		zynqmp_dma_free_descriptor(chan, desc);
 	}
+
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 }
 
 /**
@@ -658,9 +658,13 @@ static void zynqmp_dma_issue_pending(struct dma_chan *dchan)
  */
 static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan)
 {
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&chan->lock, irqflags);
 	zynqmp_dma_free_desc_list(chan, &chan->active_list);
 	zynqmp_dma_free_desc_list(chan, &chan->pending_list);
 	zynqmp_dma_free_desc_list(chan, &chan->done_list);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 }
 
 /**
@@ -670,11 +674,8 @@ static void zynqmp_dma_free_descriptors(struct zynqmp_dma_chan *chan)
 static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
-	unsigned long irqflags;
 
-	spin_lock_irqsave(&chan->lock, irqflags);
 	zynqmp_dma_free_descriptors(chan);
-	spin_unlock_irqrestore(&chan->lock, irqflags);
 	dma_free_coherent(chan->dev,
 		(2 * ZYNQMP_DMA_DESC_SIZE(chan) * ZYNQMP_DMA_NUM_DESCS),
 		chan->desc_pool_v, chan->desc_pool_p);
@@ -689,11 +690,16 @@ static void zynqmp_dma_free_chan_resources(struct dma_chan *dchan)
  */
 static void zynqmp_dma_reset(struct zynqmp_dma_chan *chan)
 {
+	unsigned long irqflags;
+
 	writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS);
 
+	spin_lock_irqsave(&chan->lock, irqflags);
 	zynqmp_dma_complete_descriptor(chan);
+	spin_unlock_irqrestore(&chan->lock, irqflags);
 	zynqmp_dma_chan_desc_cleanup(chan);
 	zynqmp_dma_free_descriptors(chan);
+
 	zynqmp_dma_init(chan);
 }
 
@@ -749,27 +755,27 @@ static void zynqmp_dma_do_tasklet(struct tasklet_struct *t)
 	u32 count;
 	unsigned long irqflags;
 
-	spin_lock_irqsave(&chan->lock, irqflags);
-
 	if (chan->err) {
 		zynqmp_dma_reset(chan);
 		chan->err = false;
-		goto unlock;
+		return;
 	}
 
+	spin_lock_irqsave(&chan->lock, irqflags);
 	count = readl(chan->regs + ZYNQMP_DMA_IRQ_DST_ACCT);
-
 	while (count) {
 		zynqmp_dma_complete_descriptor(chan);
-		zynqmp_dma_chan_desc_cleanup(chan);
 		count--;
 	}
-
-	if (chan->idle)
-		zynqmp_dma_start_transfer(chan);
-
-unlock:
 	spin_unlock_irqrestore(&chan->lock, irqflags);
+
+	zynqmp_dma_chan_desc_cleanup(chan);
+
+	if (chan->idle) {
+		spin_lock_irqsave(&chan->lock, irqflags);
+		zynqmp_dma_start_transfer(chan);
+		spin_unlock_irqrestore(&chan->lock, irqflags);
+	}
 }
 
 /**
@@ -781,12 +787,9 @@ unlock:
 static int zynqmp_dma_device_terminate_all(struct dma_chan *dchan)
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
-	unsigned long irqflags;
 
-	spin_lock_irqsave(&chan->lock, irqflags);
 	writel(ZYNQMP_DMA_IDS_DEFAULT_MASK, chan->regs + ZYNQMP_DMA_IDS);
 	zynqmp_dma_free_descriptors(chan);
-	spin_unlock_irqrestore(&chan->lock, irqflags);
 
 	return 0;
 }
@@ -1061,16 +1064,14 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 	p->dev = &pdev->dev;
 
 	zdev->clk_main = devm_clk_get(&pdev->dev, "clk_main");
-	if (IS_ERR(zdev->clk_main)) {
-		dev_err(&pdev->dev, "main clock not found.\n");
-		return PTR_ERR(zdev->clk_main);
-	}
+	if (IS_ERR(zdev->clk_main))
+		return dev_err_probe(&pdev->dev, PTR_ERR(zdev->clk_main),
+				     "main clock not found.\n");
 
 	zdev->clk_apb = devm_clk_get(&pdev->dev, "clk_apb");
-	if (IS_ERR(zdev->clk_apb)) {
-		dev_err(&pdev->dev, "apb clock not found.\n");
-		return PTR_ERR(zdev->clk_apb);
-	}
+	if (IS_ERR(zdev->clk_apb))
+		return dev_err_probe(&pdev->dev, PTR_ERR(zdev->clk_apb),
+				     "apb clock not found.\n");
 
 	platform_set_drvdata(pdev, zdev);
 	pm_runtime_set_autosuspend_delay(zdev->dev, ZDMA_PM_TIMEOUT);
@@ -1085,7 +1086,7 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 
 	ret = zynqmp_dma_chan_probe(zdev, pdev);
 	if (ret) {
-		dev_err(&pdev->dev, "Probing channel failed\n");
+		dev_err_probe(&pdev->dev, ret, "Probing channel failed\n");
 		goto err_disable_pm;
 	}
 
@@ -1097,7 +1098,7 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 	ret = of_dma_controller_register(pdev->dev.of_node,
 					 of_zynqmp_dma_xlate, zdev);
 	if (ret) {
-		dev_err(&pdev->dev, "Unable to register DMA to DT\n");
+		dev_err_probe(&pdev->dev, ret, "Unable to register DMA to DT\n");
 		dma_async_device_unregister(&zdev->common);
 		goto free_chan_resources;
 	}
@@ -1105,8 +1106,6 @@ static int zynqmp_dma_probe(struct platform_device *pdev)
 	pm_runtime_mark_last_busy(zdev->dev);
 	pm_runtime_put_sync_autosuspend(zdev->dev);
 
-	dev_info(&pdev->dev, "ZynqMP DMA driver Probe success\n");
-
 	return 0;
 
 free_chan_resources:
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index e5c2c9e71bf1..9000f3ffce8b 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -944,10 +944,8 @@ struct dma_device {
 	void (*device_issue_pending)(struct dma_chan *chan);
 	void (*device_release)(struct dma_device *dev);
 	/* debugfs support */
-#ifdef CONFIG_DEBUG_FS
 	void (*dbg_summary_show)(struct seq_file *s, struct dma_device *dev);
 	struct dentry *dbg_dev_root;
-#endif
 };
 
 static inline int dmaengine_slave_config(struct dma_chan *chan,