Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 7af874b..a32d0d7 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -59,6 +59,7 @@
 #devices
 config ALTERA_MSGDMA
 	tristate "Altera / Intel mSGDMA Engine"
+	depends on HAS_IOMEM
 	select DMA_ENGINE
 	help
 	  Enable support for Altera / Intel mSGDMA controller.
diff --git a/drivers/dma/acpi-dma.c b/drivers/dma/acpi-dma.c
index 8a05db3..dcbcb71 100644
--- a/drivers/dma/acpi-dma.c
+++ b/drivers/dma/acpi-dma.c
@@ -135,11 +135,13 @@
 		if (ret < 0) {
 			dev_warn(&adev->dev,
 				 "error in parsing resource group\n");
-			return;
+			break;
 		}
 
 		grp = (struct acpi_csrt_group *)((void *)grp + grp->length);
 	}
+
+	acpi_put_table((struct acpi_table_header *)csrt);
 }
 
 /**
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 672c73b..303bc3e 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -1667,13 +1667,17 @@
 		return NULL;
 
 	dmac_pdev = of_find_device_by_node(dma_spec->np);
+	if (!dmac_pdev)
+		return NULL;
 
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_SLAVE, mask);
 
-	atslave = kzalloc(sizeof(*atslave), GFP_KERNEL);
-	if (!atslave)
+	atslave = kmalloc(sizeof(*atslave), GFP_KERNEL);
+	if (!atslave) {
+		put_device(&dmac_pdev->dev);
 		return NULL;
+	}
 
 	atslave->cfg = ATC_DST_H2SEL_HW | ATC_SRC_H2SEL_HW;
 	/*
@@ -1702,8 +1706,11 @@
 	atslave->dma_dev = &dmac_pdev->dev;
 
 	chan = dma_request_channel(mask, at_dma_filter, atslave);
-	if (!chan)
+	if (!chan) {
+		put_device(&dmac_pdev->dev);
+		kfree(atslave);
 		return NULL;
+	}
 
 	atchan = to_at_dma_chan(chan);
 	atchan->per_if = dma_spec->args[0] & 0xff;
diff --git a/drivers/dma/coh901318.c b/drivers/dma/coh901318.c
index e51d836..1092d4c 100644
--- a/drivers/dma/coh901318.c
+++ b/drivers/dma/coh901318.c
@@ -1947,8 +1947,6 @@
 		return;
 	}
 
-	spin_lock(&cohc->lock);
-
 	/*
 	 * When we reach this point, at least one queue item
 	 * should have been moved over from cohc->queue to
@@ -1969,8 +1967,6 @@
 	if (coh901318_queue_start(cohc) == NULL)
 		cohc->busy = 0;
 
-	spin_unlock(&cohc->lock);
-
 	/*
 	 * This tasklet will remove items from cohc->active
 	 * and thus terminates them.
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index a0ee404..f1d149e 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -830,6 +830,7 @@
 	struct dma_device *dma_dev;
 	struct axi_dmac *dmac;
 	struct resource *res;
+	struct regmap *regmap;
 	int ret;
 
 	dmac = devm_kzalloc(&pdev->dev, sizeof(*dmac), GFP_KERNEL);
@@ -921,10 +922,17 @@
 
 	platform_set_drvdata(pdev, dmac);
 
-	devm_regmap_init_mmio(&pdev->dev, dmac->base, &axi_dmac_regmap_config);
+	regmap = devm_regmap_init_mmio(&pdev->dev, dmac->base,
+		 &axi_dmac_regmap_config);
+	if (IS_ERR(regmap)) {
+		ret = PTR_ERR(regmap);
+		goto err_free_irq;
+	}
 
 	return 0;
 
+err_free_irq:
+	free_irq(dmac->irq, dmac);
 err_unregister_of:
 	of_dma_controller_free(pdev->dev.of_node);
 err_unregister_device:
diff --git a/drivers/dma/dma-jz4780.c b/drivers/dma/dma-jz4780.c
index cafb1cc..e270434 100644
--- a/drivers/dma/dma-jz4780.c
+++ b/drivers/dma/dma-jz4780.c
@@ -639,11 +639,11 @@
 	unsigned long flags;
 	unsigned long residue = 0;
 
+	spin_lock_irqsave(&jzchan->vchan.lock, flags);
+
 	status = dma_cookie_status(chan, cookie, txstate);
 	if ((status == DMA_COMPLETE) || (txstate == NULL))
-		return status;
-
-	spin_lock_irqsave(&jzchan->vchan.lock, flags);
+		goto out_unlock_irqrestore;
 
 	vdesc = vchan_find_desc(&jzchan->vchan, cookie);
 	if (vdesc) {
@@ -660,6 +660,7 @@
 	    && jzchan->desc->status & (JZ_DMA_DCS_AR | JZ_DMA_DCS_HLT))
 		status = DMA_ERROR;
 
+out_unlock_irqrestore:
 	spin_unlock_irqrestore(&jzchan->vchan.lock, flags);
 	return status;
 }
@@ -885,24 +886,11 @@
 		return -EINVAL;
 	}
 
-	ret = platform_get_irq(pdev, 0);
-	if (ret < 0)
-		return ret;
-
-	jzdma->irq = ret;
-
-	ret = request_irq(jzdma->irq, jz4780_dma_irq_handler, 0, dev_name(dev),
-			  jzdma);
-	if (ret) {
-		dev_err(dev, "failed to request IRQ %u!\n", jzdma->irq);
-		return ret;
-	}
-
 	jzdma->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(jzdma->clk)) {
 		dev_err(dev, "failed to get clock\n");
 		ret = PTR_ERR(jzdma->clk);
-		goto err_free_irq;
+		return ret;
 	}
 
 	clk_prepare_enable(jzdma->clk);
@@ -955,10 +943,23 @@
 		jzchan->vchan.desc_free = jz4780_dma_desc_free;
 	}
 
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		goto err_disable_clk;
+
+	jzdma->irq = ret;
+
+	ret = request_irq(jzdma->irq, jz4780_dma_irq_handler, 0, dev_name(dev),
+			  jzdma);
+	if (ret) {
+		dev_err(dev, "failed to request IRQ %u!\n", jzdma->irq);
+		goto err_disable_clk;
+	}
+
 	ret = dmaenginem_async_device_register(dd);
 	if (ret) {
 		dev_err(dev, "failed to register device\n");
-		goto err_disable_clk;
+		goto err_free_irq;
 	}
 
 	/* Register with OF DMA helpers. */
@@ -966,17 +967,17 @@
 					 jzdma);
 	if (ret) {
 		dev_err(dev, "failed to register OF DMA controller\n");
-		goto err_disable_clk;
+		goto err_free_irq;
 	}
 
 	dev_info(dev, "JZ4780 DMA controller initialised\n");
 	return 0;
 
-err_disable_clk:
-	clk_disable_unprepare(jzdma->clk);
-
 err_free_irq:
 	free_irq(jzdma->irq, jzdma);
+
+err_disable_clk:
+	clk_disable_unprepare(jzdma->clk);
 	return ret;
 }
 
@@ -1004,7 +1005,8 @@
 static const struct jz4780_dma_soc_data jz4725b_dma_soc_data = {
 	.nb_channels = 6,
 	.transfer_ord_max = 5,
-	.flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC,
+	.flags = JZ_SOC_DATA_PER_CHAN_PM | JZ_SOC_DATA_NO_DCKES_DCKEC |
+		 JZ_SOC_DATA_BREAK_LINKS,
 };
 
 static const struct jz4780_dma_soc_data jz4770_dma_soc_data = {
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 03ac4b9..4b60408 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -179,7 +179,7 @@
 
 static struct module *dma_chan_to_owner(struct dma_chan *chan)
 {
-	return chan->device->dev->driver->owner;
+	return chan->device->owner;
 }
 
 /**
@@ -919,6 +919,8 @@
 		return -EIO;
 	}
 
+	device->owner = device->dev->driver->owner;
+
 	if (dma_has_cap(DMA_MEMCPY, device->cap_mask) && !device->device_prep_dma_memcpy) {
 		dev_err(device->dev,
 			"Device claims capability %s, but op is not defined\n",
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index a2cadfa..238936e 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -240,7 +240,7 @@
 		struct dmatest_thread *thread;
 
 		list_for_each_entry(thread, &dtc->threads, node) {
-			if (!thread->done)
+			if (!thread->done && !thread->pending)
 				return true;
 		}
 	}
@@ -662,8 +662,8 @@
 		flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
 
 	ktime = ktime_get();
-	while (!kthread_should_stop()
-	       && !(params->iterations && total_tests >= params->iterations)) {
+	while (!(kthread_should_stop() ||
+	       (params->iterations && total_tests >= params->iterations))) {
 		struct dma_async_tx_descriptor *tx = NULL;
 		struct dmaengine_unmap_data *um;
 		dma_addr_t *dsts;
@@ -1166,10 +1166,13 @@
 		mutex_unlock(&info->lock);
 		return ret;
 	} else if (dmatest_run) {
-		if (is_threaded_test_pending(info))
-			start_threaded_tests(info);
-		else
-			pr_info("Could not start test, no channels configured\n");
+		if (!is_threaded_test_pending(info)) {
+			pr_info("No channels configured, continue with any\n");
+			if (!is_threaded_test_run(info))
+				stop_threaded_test(info);
+			add_threaded_test(info);
+		}
+		start_threaded_tests(info);
 	} else {
 		stop_threaded_test(info);
 	}
@@ -1215,15 +1218,14 @@
 	add_threaded_test(info);
 
 	/* Check if channel was added successfully */
-	dtc = list_last_entry(&info->channels, struct dmatest_chan, node);
-
-	if (dtc->chan) {
+	if (!list_empty(&info->channels)) {
 		/*
 		 * if new channel was not successfully added, revert the
 		 * "test_channel" string to the name of the last successfully
 		 * added channel. exception for when users issues empty string
 		 * to channel parameter.
 		 */
+		dtc = list_last_entry(&info->channels, struct dmatest_chan, node);
 		if ((strcmp(dma_chan_name(dtc->chan), strim(test_channel)) != 0)
 		    && (strcmp("", strim(test_channel)) != 0)) {
 			ret = -EINVAL;
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index ff392c0..afbd1a4 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -85,12 +85,12 @@
 
 	if (desc->chunk) {
 		/* Create and add new element into the linked list */
-		desc->chunks_alloc++;
-		list_add_tail(&chunk->list, &desc->chunk->list);
 		if (!dw_edma_alloc_burst(chunk)) {
 			kfree(chunk);
 			return NULL;
 		}
+		desc->chunks_alloc++;
+		list_add_tail(&chunk->list, &desc->chunk->list);
 	} else {
 		/* List head */
 		chunk->burst = NULL;
@@ -391,7 +391,7 @@
 			if (xfer->cyclic) {
 				burst->dar = xfer->xfer.cyclic.paddr;
 			} else {
-				burst->dar = sg_dma_address(sg);
+				burst->dar = dst_addr;
 				/* Unlike the typical assumption by other
 				 * drivers/IPs the peripheral memory isn't
 				 * a FIFO memory, in this case, it's a
@@ -399,14 +399,13 @@
 				 * and destination addresses are increased
 				 * by the same portion (data length)
 				 */
-				src_addr += sg_dma_len(sg);
 			}
 		} else {
 			burst->dar = dst_addr;
 			if (xfer->cyclic) {
 				burst->sar = xfer->xfer.cyclic.paddr;
 			} else {
-				burst->sar = sg_dma_address(sg);
+				burst->sar = src_addr;
 				/* Unlike the typical assumption by other
 				 * drivers/IPs the peripheral memory isn't
 				 * a FIFO memory, in this case, it's a
@@ -414,12 +413,14 @@
 				 * and destination addresses are increased
 				 * by the same portion (data length)
 				 */
-				dst_addr += sg_dma_len(sg);
 			}
 		}
 
-		if (!xfer->cyclic)
+		if (!xfer->cyclic) {
+			src_addr += sg_dma_len(sg);
+			dst_addr += sg_dma_len(sg);
 			sg = sg_next(sg);
+		}
 	}
 
 	return vchan_tx_prep(&chan->vc, &desc->vd, xfer->flags);
@@ -909,21 +910,20 @@
 	/* Power management */
 	pm_runtime_disable(dev);
 
-	list_for_each_entry_safe(chan, _chan, &dw->wr_edma.channels,
-				 vc.chan.device_node) {
-		list_del(&chan->vc.chan.device_node);
-		tasklet_kill(&chan->vc.task);
-	}
-
-	list_for_each_entry_safe(chan, _chan, &dw->rd_edma.channels,
-				 vc.chan.device_node) {
-		list_del(&chan->vc.chan.device_node);
-		tasklet_kill(&chan->vc.task);
-	}
-
 	/* Deregister eDMA device */
 	dma_async_device_unregister(&dw->wr_edma);
+	list_for_each_entry_safe(chan, _chan, &dw->wr_edma.channels,
+				 vc.chan.device_node) {
+		tasklet_kill(&chan->vc.task);
+		list_del(&chan->vc.chan.device_node);
+	}
+
 	dma_async_device_unregister(&dw->rd_edma);
+	list_for_each_entry_safe(chan, _chan, &dw->rd_edma.channels,
+				 vc.chan.device_node) {
+		tasklet_kill(&chan->vc.task);
+		list_del(&chan->vc.chan.device_node);
+	}
 
 	/* Turn debugfs off */
 	dw_edma_v0_core_debugfs_off();
diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig
index e516269..db25f9b 100644
--- a/drivers/dma/dw/Kconfig
+++ b/drivers/dma/dw/Kconfig
@@ -10,6 +10,7 @@
 
 config DW_DMAC
 	tristate "Synopsys DesignWare AHB DMA platform driver"
+	depends on HAS_IOMEM
 	select DW_DMAC_CORE
 	help
 	  Support the Synopsys DesignWare AHB DMA controller. This
@@ -18,6 +19,7 @@
 config DW_DMAC_PCI
 	tristate "Synopsys DesignWare AHB DMA PCI driver"
 	depends on PCI
+	depends on HAS_IOMEM
 	select DW_DMAC_CORE
 	help
 	  Support the Synopsys DesignWare AHB DMA controller on the
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 21cb2a5..5e7fdc0 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -118,16 +118,11 @@
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 
-	if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags))
-		return;
-
 	dw->initialize_chan(dwc);
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
 	channel_set_bit(dw, MASK.ERROR, dwc->mask);
-
-	set_bit(DW_DMA_IS_INITIALIZED, &dwc->flags);
 }
 
 /*----------------------------------------------------------------------*/
@@ -777,6 +772,10 @@
 	if (dws->dma_dev != chan->device->dev)
 		return false;
 
+	/* permit channels in accordance with the channels mask */
+	if (dws->channels && !(dws->channels & dwc->mask))
+		return false;
+
 	/* We have to copy data since dws can be temporary storage */
 	memcpy(&dwc->dws, dws, sizeof(struct dw_dma_slave));
 
@@ -954,8 +953,6 @@
 
 void do_dw_dma_off(struct dw_dma *dw)
 {
-	unsigned int i;
-
 	dma_writel(dw, CFG, 0);
 
 	channel_clear_bit(dw, MASK.XFER, dw->all_chan_mask);
@@ -966,9 +963,6 @@
 
 	while (dma_readl(dw, CFG) & DW_CFG_DMA_EN)
 		cpu_relax();
-
-	for (i = 0; i < dw->dma.chancnt; i++)
-		clear_bit(DW_DMA_IS_INITIALIZED, &dw->chan[i].flags);
 }
 
 void do_dw_dma_on(struct dw_dma *dw)
@@ -1032,8 +1026,6 @@
 	/* Clear custom channel configuration */
 	memset(&dwc->dws, 0, sizeof(struct dw_dma_slave));
 
-	clear_bit(DW_DMA_IS_INITIALIZED, &dwc->flags);
-
 	/* Disable interrupts */
 	channel_clear_bit(dw, MASK.XFER, dwc->mask);
 	channel_clear_bit(dw, MASK.BLOCK, dwc->mask);
diff --git a/drivers/dma/dw/dw.c b/drivers/dma/dw/dw.c
index 7a085b3..d981098 100644
--- a/drivers/dma/dw/dw.c
+++ b/drivers/dma/dw/dw.c
@@ -14,7 +14,7 @@
 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 cfghi = is_slave_direction(dwc->direction) ? 0 : DWC_CFGH_FIFO_MODE;
 	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
 	bool hs_polarity = dwc->dws.hs_polarity;
 
diff --git a/drivers/dma/dw/of.c b/drivers/dma/dw/of.c
index 9e27831..43e975f 100644
--- a/drivers/dma/dw/of.c
+++ b/drivers/dma/dw/of.c
@@ -22,18 +22,21 @@
 	};
 	dma_cap_mask_t cap;
 
-	if (dma_spec->args_count != 3)
+	if (dma_spec->args_count < 3 || dma_spec->args_count > 4)
 		return NULL;
 
 	slave.src_id = dma_spec->args[0];
 	slave.dst_id = dma_spec->args[0];
 	slave.m_master = dma_spec->args[1];
 	slave.p_master = dma_spec->args[2];
+	if (dma_spec->args_count >= 4)
+		slave.channels = dma_spec->args[3];
 
 	if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS ||
 		    slave.dst_id >= DW_DMA_MAX_NR_REQUESTS ||
 		    slave.m_master >= dw->pdata->nr_masters ||
-		    slave.p_master >= dw->pdata->nr_masters))
+		    slave.p_master >= dw->pdata->nr_masters ||
+		    slave.channels >= BIT(dw->pdata->nr_channels)))
 		return NULL;
 
 	dma_cap_zero(cap);
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index c90c798..0585d74 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -66,7 +66,7 @@
 
 	data->chip = chip;
 
-	chip->clk = devm_clk_get(chip->dev, "hclk");
+	chip->clk = devm_clk_get_optional(chip->dev, "hclk");
 	if (IS_ERR(chip->clk))
 		return PTR_ERR(chip->clk);
 	err = clk_prepare_enable(chip->clk);
diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
index b1a7ca9..d601048 100644
--- a/drivers/dma/fsl-edma-common.c
+++ b/drivers/dma/fsl-edma-common.c
@@ -347,26 +347,28 @@
 	/*
 	 * TCD parameters are stored in struct fsl_edma_hw_tcd in little
 	 * endian format. However, we need to load the TCD registers in
-	 * big- or little-endian obeying the eDMA engine model endian.
+	 * big- or little-endian obeying the eDMA engine model endian,
+	 * and this is performed from specific edma_write functions
 	 */
 	edma_writew(edma, 0,  &regs->tcd[ch].csr);
-	edma_writel(edma, le32_to_cpu(tcd->saddr), &regs->tcd[ch].saddr);
-	edma_writel(edma, le32_to_cpu(tcd->daddr), &regs->tcd[ch].daddr);
 
-	edma_writew(edma, le16_to_cpu(tcd->attr), &regs->tcd[ch].attr);
-	edma_writew(edma, le16_to_cpu(tcd->soff), &regs->tcd[ch].soff);
+	edma_writel(edma, (s32)tcd->saddr, &regs->tcd[ch].saddr);
+	edma_writel(edma, (s32)tcd->daddr, &regs->tcd[ch].daddr);
 
-	edma_writel(edma, le32_to_cpu(tcd->nbytes), &regs->tcd[ch].nbytes);
-	edma_writel(edma, le32_to_cpu(tcd->slast), &regs->tcd[ch].slast);
+	edma_writew(edma, (s16)tcd->attr, &regs->tcd[ch].attr);
+	edma_writew(edma, tcd->soff, &regs->tcd[ch].soff);
 
-	edma_writew(edma, le16_to_cpu(tcd->citer), &regs->tcd[ch].citer);
-	edma_writew(edma, le16_to_cpu(tcd->biter), &regs->tcd[ch].biter);
-	edma_writew(edma, le16_to_cpu(tcd->doff), &regs->tcd[ch].doff);
+	edma_writel(edma, (s32)tcd->nbytes, &regs->tcd[ch].nbytes);
+	edma_writel(edma, (s32)tcd->slast, &regs->tcd[ch].slast);
 
-	edma_writel(edma, le32_to_cpu(tcd->dlast_sga),
+	edma_writew(edma, (s16)tcd->citer, &regs->tcd[ch].citer);
+	edma_writew(edma, (s16)tcd->biter, &regs->tcd[ch].biter);
+	edma_writew(edma, (s16)tcd->doff, &regs->tcd[ch].doff);
+
+	edma_writel(edma, (s32)tcd->dlast_sga,
 			&regs->tcd[ch].dlast_sga);
 
-	edma_writew(edma, le16_to_cpu(tcd->csr), &regs->tcd[ch].csr);
+	edma_writew(edma, (s16)tcd->csr, &regs->tcd[ch].csr);
 }
 
 static inline
diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
index 5eaa290..6ff7063 100644
--- a/drivers/dma/fsl-edma-common.h
+++ b/drivers/dma/fsl-edma-common.h
@@ -33,7 +33,7 @@
 #define EDMA_TCD_ATTR_DSIZE_16BIT	BIT(0)
 #define EDMA_TCD_ATTR_DSIZE_32BIT	BIT(1)
 #define EDMA_TCD_ATTR_DSIZE_64BIT	(BIT(0) | BIT(1))
-#define EDMA_TCD_ATTR_DSIZE_32BYTE	(BIT(3) | BIT(0))
+#define EDMA_TCD_ATTR_DSIZE_32BYTE	(BIT(2) | BIT(0))
 #define EDMA_TCD_ATTR_SSIZE_8BIT	0
 #define EDMA_TCD_ATTR_SSIZE_16BIT	(EDMA_TCD_ATTR_DSIZE_16BIT << 8)
 #define EDMA_TCD_ATTR_SSIZE_32BIT	(EDMA_TCD_ATTR_DSIZE_32BIT << 8)
diff --git a/drivers/dma/fsl-edma.c b/drivers/dma/fsl-edma.c
index b626c06..6760ae4 100644
--- a/drivers/dma/fsl-edma.c
+++ b/drivers/dma/fsl-edma.c
@@ -45,6 +45,13 @@
 			fsl_chan = &fsl_edma->chans[ch];
 
 			spin_lock(&fsl_chan->vchan.lock);
+
+			if (!fsl_chan->edesc) {
+				/* terminate_all called before */
+				spin_unlock(&fsl_chan->vchan.lock);
+				continue;
+			}
+
 			if (!fsl_chan->edesc->iscyclic) {
 				list_del(&fsl_chan->edesc->vdesc.node);
 				vchan_cookie_complete(&fsl_chan->edesc->vdesc);
diff --git a/drivers/dma/fsl-qdma.c b/drivers/dma/fsl-qdma.c
index 06664fb..f5a1ae1 100644
--- a/drivers/dma/fsl-qdma.c
+++ b/drivers/dma/fsl-qdma.c
@@ -304,7 +304,7 @@
 
 	vchan_dma_desc_free_list(&fsl_chan->vchan, &head);
 
-	if (!fsl_queue->comp_pool && !fsl_queue->comp_pool)
+	if (!fsl_queue->comp_pool && !fsl_queue->desc_pool)
 		return;
 
 	list_for_each_entry_safe(comp_temp, _comp_temp,
@@ -1155,6 +1155,9 @@
 		return ret;
 
 	fsl_qdma->irq_base = platform_get_irq_byname(pdev, "qdma-queue0");
+	if (fsl_qdma->irq_base < 0)
+		return fsl_qdma->irq_base;
+
 	fsl_qdma->feature = of_property_read_bool(np, "big-endian");
 	INIT_LIST_HEAD(&fsl_qdma->dma_dev.channels);
 
@@ -1181,7 +1184,11 @@
 	fsl_qdma->dma_dev.device_synchronize = fsl_qdma_synchronize;
 	fsl_qdma->dma_dev.device_terminate_all = fsl_qdma_terminate_all;
 
-	dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+	ret = dma_set_mask(&pdev->dev, DMA_BIT_MASK(40));
+	if (ret) {
+		dev_err(&pdev->dev, "dma_set_mask failure.\n");
+		return ret;
+	}
 
 	platform_set_drvdata(pdev, fsl_qdma);
 
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index ad72b3f..eae385a 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -1214,6 +1214,7 @@
 {
 	struct fsldma_device *fdev;
 	struct device_node *child;
+	unsigned int i;
 	int err;
 
 	fdev = kzalloc(sizeof(*fdev), GFP_KERNEL);
@@ -1292,6 +1293,10 @@
 	return 0;
 
 out_free_fdev:
+	for (i = 0; i < FSL_DMA_MAX_CHANS_PER_DEVICE; i++) {
+		if (fdev->chan[i])
+			fsl_dma_chan_remove(fdev->chan[i]);
+	}
 	irq_dispose_mapping(fdev->irq);
 	iounmap(fdev->regs);
 out_free:
@@ -1314,6 +1319,7 @@
 		if (fdev->chan[i])
 			fsl_dma_chan_remove(fdev->chan[i]);
 	}
+	irq_dispose_mapping(fdev->irq);
 
 	iounmap(fdev->regs);
 	kfree(fdev);
diff --git a/drivers/dma/fsldma.h b/drivers/dma/fsldma.h
index 56f18ae..308bed0 100644
--- a/drivers/dma/fsldma.h
+++ b/drivers/dma/fsldma.h
@@ -205,10 +205,10 @@
 #else
 static u64 fsl_ioread64(const u64 __iomem *addr)
 {
-	u32 fsl_addr = lower_32_bits(addr);
-	u64 fsl_addr_hi = (u64)in_le32((u32 *)(fsl_addr + 1)) << 32;
+	u32 val_lo = in_le32((u32 __iomem *)addr);
+	u32 val_hi = in_le32((u32 __iomem *)addr + 1);
 
-	return fsl_addr_hi | in_le32((u32 *)fsl_addr);
+	return ((u64)val_hi << 32) + val_lo;
 }
 
 static void fsl_iowrite64(u64 val, u64 __iomem *addr)
@@ -219,10 +219,10 @@
 
 static u64 fsl_ioread64be(const u64 __iomem *addr)
 {
-	u32 fsl_addr = lower_32_bits(addr);
-	u64 fsl_addr_hi = (u64)in_be32((u32 *)fsl_addr) << 32;
+	u32 val_hi = in_be32((u32 __iomem *)addr);
+	u32 val_lo = in_be32((u32 __iomem *)addr + 1);
 
-	return fsl_addr_hi | in_be32((u32 *)(fsl_addr + 1));
+	return ((u64)val_hi << 32) + val_lo;
 }
 
 static void fsl_iowrite64be(u64 val, u64 __iomem *addr)
diff --git a/drivers/dma/hsu/pci.c b/drivers/dma/hsu/pci.c
index 07cc732..9045a6f 100644
--- a/drivers/dma/hsu/pci.c
+++ b/drivers/dma/hsu/pci.c
@@ -26,22 +26,12 @@
 static irqreturn_t hsu_pci_irq(int irq, void *dev)
 {
 	struct hsu_dma_chip *chip = dev;
-	struct pci_dev *pdev = to_pci_dev(chip->dev);
 	u32 dmaisr;
 	u32 status;
 	unsigned short i;
 	int ret = 0;
 	int err;
 
-	/*
-	 * On Intel Tangier B0 and Anniedale the interrupt line, disregarding
-	 * to have different numbers, is shared between HSU DMA and UART IPs.
-	 * Thus on such SoCs we are expecting that IRQ handler is called in
-	 * UART driver only.
-	 */
-	if (pdev->device == PCI_DEVICE_ID_INTEL_MRFLD_HSU_DMA)
-		return IRQ_HANDLED;
-
 	dmaisr = readl(chip->regs + HSU_PCI_DMAISR);
 	for (i = 0; i < chip->hsu->nr_channels; i++) {
 		if (dmaisr & 0x1) {
@@ -105,6 +95,17 @@
 	if (ret)
 		goto err_register_irq;
 
+	/*
+	 * On Intel Tangier B0 and Anniedale the interrupt line, disregarding
+	 * to have different numbers, is shared between HSU DMA and UART IPs.
+	 * Thus on such SoCs we are expecting that IRQ handler is called in
+	 * UART driver only. Instead of handling the spurious interrupt
+	 * from HSU DMA here and waste CPU time and delay HSU UART interrupt
+	 * handling, disable the interrupt entirely.
+	 */
+	if (pdev->device == PCI_DEVICE_ID_INTEL_MRFLD_HSU_DMA)
+		disable_irq_nosync(chip->irq);
+
 	pci_set_drvdata(pdev, chip);
 
 	return 0;
diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c
index 5c0fb31..5265182 100644
--- a/drivers/dma/imx-dma.c
+++ b/drivers/dma/imx-dma.c
@@ -832,6 +832,8 @@
 		dma_length += sg_dma_len(sg);
 	}
 
+	imxdma_config_write(chan, &imxdmac->config, direction);
+
 	switch (imxdmac->word_size) {
 	case DMA_SLAVE_BUSWIDTH_4_BYTES:
 		if (sg_dma_len(sgl) & 3 || sgl->dma_address & 3)
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index c27e206..cc70da0 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -377,7 +377,6 @@
 	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;
 };
@@ -988,9 +987,6 @@
 	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)
@@ -1033,8 +1029,6 @@
 
 	spin_unlock_irqrestore(&sdma->channel_0_lock, flags);
 
-	sdmac->context_loaded = true;
-
 	return ret;
 }
 
@@ -1074,7 +1068,6 @@
 	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)
@@ -1141,7 +1134,6 @@
 static int sdma_config_channel(struct dma_chan *chan)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
-	int ret;
 
 	sdma_disable_channel(chan);
 
@@ -1181,9 +1173,7 @@
 		sdmac->watermark_level = 0; /* FIXME: M3_BASE_ADDRESS */
 	}
 
-	ret = sdma_load_context(sdmac);
-
-	return ret;
+	return 0;
 }
 
 static int sdma_set_channel_priority(struct sdma_channel *sdmac,
@@ -1328,7 +1318,7 @@
 
 	sdma_channel_synchronize(chan);
 
-	if (sdmac->event_id0)
+	if (sdmac->event_id0 >= 0)
 		sdma_event_disable(sdmac, sdmac->event_id0);
 	if (sdmac->event_id1)
 		sdma_event_disable(sdmac, sdmac->event_id1);
@@ -1628,7 +1618,7 @@
 	memcpy(&sdmac->slave_config, dmaengine_cfg, sizeof(*dmaengine_cfg));
 
 	/* Set ENBLn earlier to make sure dma request triggered after that */
-	if (sdmac->event_id0) {
+	if (sdmac->event_id0 >= 0) {
 		if (sdmac->event_id0 >= sdmac->sdma->drvdata->num_events)
 			return -EINVAL;
 		sdma_event_enable(sdmac, sdmac->event_id0);
diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c
index 1a422a8..8e2a4d1 100644
--- a/drivers/dma/ioat/dma.c
+++ b/drivers/dma/ioat/dma.c
@@ -26,6 +26,18 @@
 
 #include "../dmaengine.h"
 
+int completion_timeout = 200;
+module_param(completion_timeout, int, 0644);
+MODULE_PARM_DESC(completion_timeout,
+		"set ioat completion timeout [msec] (default 200 [msec])");
+int idle_timeout = 2000;
+module_param(idle_timeout, int, 0644);
+MODULE_PARM_DESC(idle_timeout,
+		"set ioat idel timeout [msec] (default 2000 [msec])");
+
+#define IDLE_TIMEOUT msecs_to_jiffies(idle_timeout)
+#define COMPLETION_TIMEOUT msecs_to_jiffies(completion_timeout)
+
 static char *chanerr_str[] = {
 	"DMA Transfer Source Address Error",
 	"DMA Transfer Destination Address Error",
@@ -377,10 +389,11 @@
 
 		descs->virt = dma_alloc_coherent(to_dev(ioat_chan),
 						 SZ_2M, &descs->hw, flags);
-		if (!descs->virt && (i > 0)) {
+		if (!descs->virt) {
 			int idx;
 
 			for (idx = 0; idx < i; idx++) {
+				descs = &ioat_chan->descs[idx];
 				dma_free_coherent(to_dev(ioat_chan), SZ_2M,
 						  descs->virt, descs->hw);
 				descs->virt = NULL;
diff --git a/drivers/dma/ioat/dma.h b/drivers/dma/ioat/dma.h
index b8e8e0b..4ac9134 100644
--- a/drivers/dma/ioat/dma.h
+++ b/drivers/dma/ioat/dma.h
@@ -99,8 +99,6 @@
 	#define IOAT_RUN 5
 	#define IOAT_CHAN_ACTIVE 6
 	struct timer_list timer;
-	#define COMPLETION_TIMEOUT msecs_to_jiffies(100)
-	#define IDLE_TIMEOUT msecs_to_jiffies(2000)
 	#define RESET_DELAY msecs_to_jiffies(100)
 	struct ioatdma_device *ioat_dma;
 	dma_addr_t completion_dma;
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index 4b36c88..d054716 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -229,9 +229,11 @@
 			c = p->vchan;
 			if (c && (tc1 & BIT(i))) {
 				spin_lock_irqsave(&c->vc.lock, flags);
-				vchan_cookie_complete(&p->ds_run->vd);
-				p->ds_done = p->ds_run;
-				p->ds_run = NULL;
+				if (p->ds_run != NULL) {
+					vchan_cookie_complete(&p->ds_run->vd);
+					p->ds_done = p->ds_run;
+					p->ds_run = NULL;
+				}
 				spin_unlock_irqrestore(&c->vc.lock, flags);
 			}
 			if (c && (tc2 & BIT(i))) {
@@ -271,6 +273,10 @@
 	if (BIT(c->phy->idx) & k3_dma_get_chan_stat(d))
 		return -EAGAIN;
 
+	/* Avoid losing track of  ds_run if a transaction is in flight */
+	if (c->phy->ds_run)
+		return -EAGAIN;
+
 	if (vd) {
 		struct k3_dma_desc_sw *ds =
 			container_of(vd, struct k3_dma_desc_sw, vd);
diff --git a/drivers/dma/mcf-edma.c b/drivers/dma/mcf-edma.c
index e15bd15..e12b754 100644
--- a/drivers/dma/mcf-edma.c
+++ b/drivers/dma/mcf-edma.c
@@ -35,6 +35,13 @@
 			mcf_chan = &mcf_edma->chans[ch];
 
 			spin_lock(&mcf_chan->vchan.lock);
+
+			if (!mcf_chan->edesc) {
+				/* terminate_all called before */
+				spin_unlock(&mcf_chan->vchan.lock);
+				continue;
+			}
+
 			if (!mcf_chan->edesc->iscyclic) {
 				list_del(&mcf_chan->edesc->vdesc.node);
 				vchan_cookie_complete(&mcf_chan->edesc->vdesc);
diff --git a/drivers/dma/mediatek/mtk-hsdma.c b/drivers/dma/mediatek/mtk-hsdma.c
index 1a2028e..04d89ee 100644
--- a/drivers/dma/mediatek/mtk-hsdma.c
+++ b/drivers/dma/mediatek/mtk-hsdma.c
@@ -997,7 +997,7 @@
 	if (err) {
 		dev_err(&pdev->dev,
 			"request_irq failed with err %d\n", err);
-		goto err_unregister;
+		goto err_free;
 	}
 
 	platform_set_drvdata(pdev, hsdma);
@@ -1006,6 +1006,9 @@
 
 	return 0;
 
+err_free:
+	mtk_hsdma_hw_deinit(hsdma);
+	of_dma_controller_free(pdev->dev.of_node);
 err_unregister:
 	dma_async_device_unregister(dd);
 
diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c
index f40051d..9c0ea13 100644
--- a/drivers/dma/mediatek/mtk-uart-apdma.c
+++ b/drivers/dma/mediatek/mtk-uart-apdma.c
@@ -131,10 +131,7 @@
 
 static void mtk_uart_apdma_desc_free(struct virt_dma_desc *vd)
 {
-	struct dma_chan *chan = vd->tx.chan;
-	struct mtk_chan *c = to_mtk_uart_apdma_chan(chan);
-
-	kfree(c->desc);
+	kfree(container_of(vd, struct mtk_uart_apdma_desc, vd));
 }
 
 static void mtk_uart_apdma_start_tx(struct mtk_chan *c)
@@ -207,14 +204,9 @@
 
 static void mtk_uart_apdma_tx_handler(struct mtk_chan *c)
 {
-	struct mtk_uart_apdma_desc *d = c->desc;
-
 	mtk_uart_apdma_write(c, VFF_INT_FLAG, VFF_TX_INT_CLR_B);
 	mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B);
 	mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B);
-
-	list_del(&d->vd.node);
-	vchan_cookie_complete(&d->vd);
 }
 
 static void mtk_uart_apdma_rx_handler(struct mtk_chan *c)
@@ -245,9 +237,17 @@
 
 	c->rx_status = d->avail_len - cnt;
 	mtk_uart_apdma_write(c, VFF_RPT, wg);
+}
 
-	list_del(&d->vd.node);
-	vchan_cookie_complete(&d->vd);
+static void mtk_uart_apdma_chan_complete_handler(struct mtk_chan *c)
+{
+	struct mtk_uart_apdma_desc *d = c->desc;
+
+	if (d) {
+		list_del(&d->vd.node);
+		vchan_cookie_complete(&d->vd);
+		c->desc = NULL;
+	}
 }
 
 static irqreturn_t mtk_uart_apdma_irq_handler(int irq, void *dev_id)
@@ -261,6 +261,7 @@
 		mtk_uart_apdma_rx_handler(c);
 	else if (c->dir == DMA_MEM_TO_DEV)
 		mtk_uart_apdma_tx_handler(c);
+	mtk_uart_apdma_chan_complete_handler(c);
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 
 	return IRQ_HANDLED;
@@ -348,7 +349,7 @@
 		return NULL;
 
 	/* Now allocate and setup the descriptor */
-	d = kzalloc(sizeof(*d), GFP_ATOMIC);
+	d = kzalloc(sizeof(*d), GFP_NOWAIT);
 	if (!d)
 		return NULL;
 
@@ -366,7 +367,7 @@
 	unsigned long flags;
 
 	spin_lock_irqsave(&c->vc.lock, flags);
-	if (vchan_issue_pending(&c->vc)) {
+	if (vchan_issue_pending(&c->vc) && !c->desc) {
 		vd = vchan_next_desc(&c->vc);
 		c->desc = to_mtk_uart_apdma_desc(&vd->tx);
 
diff --git a/drivers/dma/mmp_tdma.c b/drivers/dma/mmp_tdma.c
index e7d1e12..89d90c4 100644
--- a/drivers/dma/mmp_tdma.c
+++ b/drivers/dma/mmp_tdma.c
@@ -363,6 +363,8 @@
 		gen_pool_free(gpool, (unsigned long)tdmac->desc_arr,
 				size);
 	tdmac->desc_arr = NULL;
+	if (tdmac->status == DMA_ERROR)
+		tdmac->status = DMA_COMPLETE;
 
 	return;
 }
@@ -443,7 +445,8 @@
 	if (!desc)
 		goto err_out;
 
-	mmp_tdma_config_write(chan, direction, &tdmac->slave_config);
+	if (mmp_tdma_config_write(chan, direction, &tdmac->slave_config))
+		goto err_out;
 
 	while (buf < buf_len) {
 		desc = &tdmac->desc_arr[i];
diff --git a/drivers/dma/mv_xor_v2.c b/drivers/dma/mv_xor_v2.c
index e3850f0..889a94a 100644
--- a/drivers/dma/mv_xor_v2.c
+++ b/drivers/dma/mv_xor_v2.c
@@ -766,8 +766,10 @@
 		goto disable_clk;
 
 	msi_desc = first_msi_entry(&pdev->dev);
-	if (!msi_desc)
+	if (!msi_desc) {
+		ret = -ENODEV;
 		goto free_msi_irqs;
+	}
 	xor_dev->msi_desc = msi_desc;
 
 	ret = devm_request_irq(&pdev->dev, msi_desc->irq,
diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c
index c2d779d..e3f1d4a 100644
--- a/drivers/dma/of-dma.c
+++ b/drivers/dma/of-dma.c
@@ -65,18 +65,23 @@
 		return NULL;
 
 	ofdma_target = of_dma_find_controller(&dma_spec_target);
-	if (!ofdma_target)
-		return NULL;
-
-	chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target);
-	if (chan) {
-		chan->router = ofdma->dma_router;
-		chan->route_data = route_data;
-	} else {
+	if (!ofdma_target) {
 		ofdma->dma_router->route_free(ofdma->dma_router->dev,
 					      route_data);
+		chan = ERR_PTR(-EPROBE_DEFER);
+		goto err;
 	}
 
+	chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target);
+	if (IS_ERR_OR_NULL(chan)) {
+		ofdma->dma_router->route_free(ofdma->dma_router->dev,
+					      route_data);
+	} else {
+		chan->router = ofdma->dma_router;
+		chan->route_data = route_data;
+	}
+
+err:
 	/*
 	 * Need to put the node back since the ofdma->of_dma_route_allocate
 	 * has taken it for generating the new, translated dma_spec
diff --git a/drivers/dma/owl-dma.c b/drivers/dma/owl-dma.c
index 90bbcef..bb9c361 100644
--- a/drivers/dma/owl-dma.c
+++ b/drivers/dma/owl-dma.c
@@ -175,13 +175,11 @@
  * @id: physical index to this channel
  * @base: virtual memory base for the dma channel
  * @vchan: the virtual channel currently being served by this physical channel
- * @lock: a lock to use when altering an instance of this struct
  */
 struct owl_dma_pchan {
 	u32			id;
 	void __iomem		*base;
 	struct owl_dma_vchan	*vchan;
-	spinlock_t		lock;
 };
 
 /**
@@ -437,14 +435,14 @@
 	for (i = 0; i < od->nr_pchans; i++) {
 		pchan = &od->pchans[i];
 
-		spin_lock_irqsave(&pchan->lock, flags);
+		spin_lock_irqsave(&od->lock, flags);
 		if (!pchan->vchan) {
 			pchan->vchan = vchan;
-			spin_unlock_irqrestore(&pchan->lock, flags);
+			spin_unlock_irqrestore(&od->lock, flags);
 			break;
 		}
 
-		spin_unlock_irqrestore(&pchan->lock, flags);
+		spin_unlock_irqrestore(&od->lock, flags);
 	}
 
 	return pchan;
@@ -1203,6 +1201,7 @@
 	owl_dma_free(od);
 
 	clk_disable_unprepare(od->clk);
+	dma_pool_destroy(od->lli_pool);
 
 	return 0;
 }
diff --git a/drivers/dma/pch_dma.c b/drivers/dma/pch_dma.c
index 581e7a2..a3b0b4c 100644
--- a/drivers/dma/pch_dma.c
+++ b/drivers/dma/pch_dma.c
@@ -865,6 +865,7 @@
 	}
 
 	pci_set_master(pdev);
+	pd->dma.dev = &pdev->dev;
 
 	err = request_irq(pdev->irq, pd_irq, IRQF_SHARED, DRV_NAME, pd);
 	if (err) {
@@ -880,7 +881,6 @@
 		goto err_free_irq;
 	}
 
-	pd->dma.dev = &pdev->dev;
 
 	INIT_LIST_HEAD(&pd->dma.channels);
 
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index 6cce9ef..9a94d5b 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2690,13 +2690,15 @@
 	for (i = 0; i < len / period_len; i++) {
 		desc = pl330_get_desc(pch);
 		if (!desc) {
+			unsigned long iflags;
+
 			dev_err(pch->dmac->ddma.dev, "%s:%d Unable to fetch desc\n",
 				__func__, __LINE__);
 
 			if (!first)
 				return NULL;
 
-			spin_lock_irqsave(&pl330->pool_lock, flags);
+			spin_lock_irqsave(&pl330->pool_lock, iflags);
 
 			while (!list_empty(&first->node)) {
 				desc = list_entry(first->node.next,
@@ -2706,7 +2708,7 @@
 
 			list_move_tail(&first->node, &pl330->desc_pool);
 
-			spin_unlock_irqrestore(&pl330->pool_lock, flags);
+			spin_unlock_irqrestore(&pl330->pool_lock, iflags);
 
 			return NULL;
 		}
@@ -2788,14 +2790,14 @@
 	while (burst != (1 << desc->rqcfg.brst_size))
 		desc->rqcfg.brst_size++;
 
+	desc->rqcfg.brst_len = get_burst_len(desc, len);
 	/*
 	 * If burst size is smaller than bus width then make sure we only
 	 * transfer one at a time to avoid a burst stradling an MFIFO entry.
 	 */
-	if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width)
+	if (burst * 8 < pl330->pcfg.data_bus_width)
 		desc->rqcfg.brst_len = 1;
 
-	desc->rqcfg.brst_len = get_burst_len(desc, len);
 	desc->bytes_requested = len;
 
 	desc->txd.flags = flags;
diff --git a/drivers/dma/qcom/Kconfig b/drivers/dma/qcom/Kconfig
index 1d18943..bef309e 100644
--- a/drivers/dma/qcom/Kconfig
+++ b/drivers/dma/qcom/Kconfig
@@ -10,6 +10,7 @@
 
 config QCOM_HIDMA_MGMT
 	tristate "Qualcomm Technologies HIDMA Management support"
+	depends on HAS_IOMEM
 	select DMA_ENGINE
 	help
 	  Enable support for the Qualcomm Technologies HIDMA Management.
diff --git a/drivers/dma/qcom/hidma_mgmt.c b/drivers/dma/qcom/hidma_mgmt.c
index 806ca02..6202660 100644
--- a/drivers/dma/qcom/hidma_mgmt.c
+++ b/drivers/dma/qcom/hidma_mgmt.c
@@ -418,8 +418,23 @@
 		hidma_mgmt_of_populate_channels(child);
 	}
 #endif
-	return platform_driver_register(&hidma_mgmt_driver);
+	/*
+	 * We do not check for return value here, as it is assumed that
+	 * platform_driver_register must not fail. The reason for this is that
+	 * the (potential) hidma_mgmt_of_populate_channels calls above are not
+	 * cleaned up if it does fail, and to do this work is quite
+	 * complicated. In particular, various calls of of_address_to_resource,
+	 * of_irq_to_resource, platform_device_register_full, of_dma_configure,
+	 * and of_msi_configure which then call other functions and so on, must
+	 * be cleaned up - this is not a trivial exercise.
+	 *
+	 * Currently, this module is not intended to be unloaded, and there is
+	 * no module_exit function defined which does the needed cleanup. For
+	 * this reason, we have to assume success here.
+	 */
+	platform_driver_register(&hidma_mgmt_driver);
 
+	return 0;
 }
 module_init(hidma_mgmt_init);
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 3993ab6..89eb9ea 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1855,7 +1855,7 @@
 
 	/* Enable runtime PM and initialize the device. */
 	pm_runtime_enable(&pdev->dev);
-	ret = pm_runtime_get_sync(&pdev->dev);
+	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;
diff --git a/drivers/dma/sh/usb-dmac.c b/drivers/dma/sh/usb-dmac.c
index b218a01..1cc0690 100644
--- a/drivers/dma/sh/usb-dmac.c
+++ b/drivers/dma/sh/usb-dmac.c
@@ -586,6 +586,8 @@
 		desc->residue = usb_dmac_get_current_residue(chan, desc,
 							desc->sg_index - 1);
 		desc->done_cookie = desc->vd.tx.cookie;
+		desc->vd.tx_result.result = DMA_TRANS_NOERROR;
+		desc->vd.tx_result.residue = desc->residue;
 		vchan_cookie_complete(&desc->vd);
 
 		/* Restart the next transfer if this driver has a next desc */
@@ -853,8 +855,8 @@
 
 error:
 	of_dma_controller_free(pdev->dev.of_node);
-	pm_runtime_put(&pdev->dev);
 error_pm:
+	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	return ret;
 }
diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c
index de8bfd9..6671bfe 100644
--- a/drivers/dma/ste_dma40.c
+++ b/drivers/dma/ste_dma40.c
@@ -3678,6 +3678,9 @@
 
 	kfree(base->lcla_pool.base_unaligned);
 
+	if (base->lcpa_base)
+		iounmap(base->lcpa_base);
+
 	if (base->phy_lcpa)
 		release_mem_region(base->phy_lcpa,
 				   base->lcpa_size);
diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c
index 5989b08..6c5771d 100644
--- a/drivers/dma/stm32-dma.c
+++ b/drivers/dma/stm32-dma.c
@@ -488,8 +488,10 @@
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
 
-	if (chan->busy) {
-		stm32_dma_stop(chan);
+	if (chan->desc) {
+		vchan_terminate_vdesc(&chan->desc->vdesc);
+		if (chan->busy)
+			stm32_dma_stop(chan);
 		chan->desc = NULL;
 	}
 
@@ -545,6 +547,8 @@
 		if (!vdesc)
 			return;
 
+		list_del(&vdesc->node);
+
 		chan->desc = to_stm32_dma_desc(vdesc);
 		chan->next_sg = 0;
 	}
@@ -622,7 +626,6 @@
 		} else {
 			chan->busy = false;
 			if (chan->next_sg == chan->desc->num_sgs) {
-				list_del(&chan->desc->vdesc.node);
 				vchan_cookie_complete(&chan->desc->vdesc);
 				chan->desc = NULL;
 			}
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 5838311..ee1cbf3 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -1127,6 +1127,8 @@
 		return;
 	}
 
+	list_del(&vdesc->node);
+
 	chan->desc = to_stm32_mdma_desc(vdesc);
 	hwdesc = chan->desc->node[0].hwdesc;
 	chan->curr_hwdesc = 0;
@@ -1242,8 +1244,10 @@
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&chan->vchan.lock, flags);
-	if (chan->busy) {
-		stm32_mdma_stop(chan);
+	if (chan->desc) {
+		vchan_terminate_vdesc(&chan->desc->vdesc);
+		if (chan->busy)
+			stm32_mdma_stop(chan);
 		chan->desc = NULL;
 	}
 	vchan_get_all_descriptors(&chan->vchan, &head);
@@ -1331,7 +1335,6 @@
 
 static void stm32_mdma_xfer_end(struct stm32_mdma_chan *chan)
 {
-	list_del(&chan->desc->vdesc.node);
 	vchan_cookie_complete(&chan->desc->vdesc);
 	chan->desc = NULL;
 	chan->busy = false;
diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c
index 3a45079..3fe27db 100644
--- a/drivers/dma/tegra20-apb-dma.c
+++ b/drivers/dma/tegra20-apb-dma.c
@@ -281,7 +281,7 @@
 
 	/* Do not allocate if desc are waiting for ack */
 	list_for_each_entry(dma_desc, &tdc->free_dma_desc, node) {
-		if (async_tx_test_ack(&dma_desc->txd)) {
+		if (async_tx_test_ack(&dma_desc->txd) && !dma_desc->cb_count) {
 			list_del(&dma_desc->node);
 			spin_unlock_irqrestore(&tdc->lock, flags);
 			dma_desc->txd.flags = 0;
@@ -756,10 +756,6 @@
 	bool was_busy;
 
 	spin_lock_irqsave(&tdc->lock, flags);
-	if (list_empty(&tdc->pending_sg_req)) {
-		spin_unlock_irqrestore(&tdc->lock, flags);
-		return 0;
-	}
 
 	if (!tdc->busy)
 		goto skip_dma_stop;
@@ -1291,8 +1287,7 @@
 
 	dev_dbg(tdc2dev(tdc), "Freeing channel %d\n", tdc->id);
 
-	if (tdc->busy)
-		tegra_dma_terminate_all(dc);
+	tegra_dma_terminate_all(dc);
 
 	spin_lock_irqsave(&tdc->lock, flags);
 	list_splice_init(&tdc->pending_sg_req, &sg_req_list);
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 6e12685..9068591 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -658,6 +658,7 @@
 
 	ret = pm_runtime_get_sync(tdc2dev(tdc));
 	if (ret < 0) {
+		pm_runtime_put_noidle(tdc2dev(tdc));
 		free_irq(tdc->irq, tdc);
 		return ret;
 	}
@@ -869,8 +870,10 @@
 	pm_runtime_enable(&pdev->dev);
 
 	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0)
+	if (ret < 0) {
+		pm_runtime_put_noidle(&pdev->dev);
 		goto rpm_disable;
+	}
 
 	ret = tegra_adma_init(tdma);
 	if (ret)
@@ -900,7 +903,7 @@
 	ret = dma_async_device_register(&tdma->dma_dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "ADMA registration failed: %d\n", ret);
-		goto irq_dispose;
+		goto rpm_put;
 	}
 
 	ret = of_dma_controller_register(pdev->dev.of_node,
diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index ba7c4f0..80b780e 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -2403,8 +2403,10 @@
 
 		ecc->tc_list = devm_kcalloc(dev, ecc->num_tc,
 					    sizeof(*ecc->tc_list), GFP_KERNEL);
-		if (!ecc->tc_list)
-			return -ENOMEM;
+		if (!ecc->tc_list) {
+			ret = -ENOMEM;
+			goto err_reg1;
+		}
 
 		for (i = 0;; i++) {
 			ret = of_parse_phandle_with_fixed_args(node, "ti,tptcs",
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index ec4adf4..256fc66 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -104,9 +104,8 @@
 		dmaengine_desc_get_callback(&vd->tx, &cb);
 
 		list_del(&vd->node);
-		vchan_vdesc_fini(vd);
-
 		dmaengine_desc_callback_invoke(&cb, &vd->tx_result);
+		vchan_vdesc_fini(vd);
 	}
 }
 
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index 5d56f1e..ce18bca 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -333,6 +333,7 @@
  * @genlock: Support genlock mode
  * @err: Channel has errors
  * @idle: Check for channel idle
+ * @terminating: Check for channel being synchronized by user
  * @tasklet: Cleanup work after irq
  * @config: Device configuration info
  * @flush_on_fsync: Flush on Frame sync
@@ -370,6 +371,7 @@
 	bool genlock;
 	bool err;
 	bool idle;
+	bool terminating;
 	struct tasklet_struct tasklet;
 	struct xilinx_vdma_config config;
 	bool flush_on_fsync;
@@ -454,8 +456,8 @@
 #define to_dma_tx_descriptor(tx) \
 	container_of(tx, struct xilinx_dma_tx_descriptor, async_tx)
 #define xilinx_dma_poll_timeout(chan, reg, val, cond, delay_us, timeout_us) \
-	readl_poll_timeout(chan->xdev->regs + chan->ctrl_offset + reg, val, \
-			   cond, delay_us, timeout_us)
+	readl_poll_timeout_atomic(chan->xdev->regs + chan->ctrl_offset + reg, \
+				  val, cond, delay_us, timeout_us)
 
 /* IO accessors */
 static inline u32 dma_read(struct xilinx_dma_chan *chan, u32 reg)
@@ -844,6 +846,13 @@
 		/* Run any dependencies, then free the descriptor */
 		dma_run_dependencies(&desc->async_tx);
 		xilinx_dma_free_tx_descriptor(chan, desc);
+
+		/*
+		 * While we ran a callback the user called a terminate function,
+		 * which takes care of cleaning up any remaining descriptors
+		 */
+		if (chan->terminating)
+			break;
 	}
 
 	spin_unlock_irqrestore(&chan->lock, flags);
@@ -1433,6 +1442,7 @@
 
 	chan->err = false;
 	chan->idle = true;
+	chan->desc_pendingcount = 0;
 	chan->desc_submitcount = 0;
 
 	return err;
@@ -1617,6 +1627,8 @@
 	if (desc->cyclic)
 		chan->cyclic = true;
 
+	chan->terminating = false;
+
 	spin_unlock_irqrestore(&chan->lock, flags);
 
 	return cookie;
@@ -2073,6 +2085,7 @@
 	}
 
 	/* Remove and free all of the descriptors in the lists */
+	chan->terminating = true;
 	xilinx_dma_free_descriptors(chan);
 	chan->idle = true;
 
@@ -2430,7 +2443,7 @@
 		has_dre = false;
 
 	if (!has_dre)
-		xdev->common.copy_align = fls(width - 1);
+		xdev->common.copy_align = (enum dmaengine_alignment)fls(width - 1);
 
 	if (of_device_is_compatible(node, "xlnx,axi-vdma-mm2s-channel") ||
 	    of_device_is_compatible(node, "xlnx,axi-dma-mm2s-channel") ||
@@ -2542,7 +2555,8 @@
 static int xilinx_dma_child_probe(struct xilinx_dma_device *xdev,
 				    struct device_node *node)
 {
-	int ret, i, nr_channels = 1;
+	int ret, i;
+	u32 nr_channels = 1;
 
 	ret = of_property_read_u32(node, "dma-channels", &nr_channels);
 	if ((ret < 0) && xdev->mcdma)
@@ -2741,7 +2755,11 @@
 	}
 
 	/* Register the DMA engine with the core */
-	dma_async_device_register(&xdev->common);
+	err = dma_async_device_register(&xdev->common);
+	if (err) {
+		dev_err(xdev->dev, "failed to register the dma device\n");
+		goto error;
+	}
 
 	err = of_dma_controller_register(node, of_dma_xilinx_xlate,
 					 xdev);
diff --git a/drivers/dma/xilinx/zynqmp_dma.c b/drivers/dma/xilinx/zynqmp_dma.c
index 9c845c0..84009c5 100644
--- a/drivers/dma/xilinx/zynqmp_dma.c
+++ b/drivers/dma/xilinx/zynqmp_dma.c
@@ -123,10 +123,12 @@
 /* Max transfer size per descriptor */
 #define ZYNQMP_DMA_MAX_TRANS_LEN	0x40000000
 
+/* Max burst lengths */
+#define ZYNQMP_DMA_MAX_DST_BURST_LEN    32768U
+#define ZYNQMP_DMA_MAX_SRC_BURST_LEN    32768U
+
 /* Reset values for data attributes */
 #define ZYNQMP_DMA_AXCACHE_VAL		0xF
-#define ZYNQMP_DMA_ARLEN_RST_VAL	0xF
-#define ZYNQMP_DMA_AWLEN_RST_VAL	0xF
 
 #define ZYNQMP_DMA_SRC_ISSUE_RST_VAL	0x1F
 
@@ -465,7 +467,7 @@
 	struct zynqmp_dma_desc_sw *desc;
 	int i, ret;
 
-	ret = pm_runtime_get_sync(chan->dev);
+	ret = pm_runtime_resume_and_get(chan->dev);
 	if (ret < 0)
 		return ret;
 
@@ -534,17 +536,19 @@
 
 static void zynqmp_dma_config(struct zynqmp_dma_chan *chan)
 {
-	u32 val;
+	u32 val, burst_val;
 
 	val = readl(chan->regs + ZYNQMP_DMA_CTRL0);
 	val |= ZYNQMP_DMA_POINT_TYPE_SG;
 	writel(val, chan->regs + ZYNQMP_DMA_CTRL0);
 
 	val = readl(chan->regs + ZYNQMP_DMA_DATA_ATTR);
+	burst_val = __ilog2_u32(chan->src_burst_len);
 	val = (val & ~ZYNQMP_DMA_ARLEN) |
-		(chan->src_burst_len << ZYNQMP_DMA_ARLEN_OFST);
+		((burst_val << ZYNQMP_DMA_ARLEN_OFST) & ZYNQMP_DMA_ARLEN);
+	burst_val = __ilog2_u32(chan->dst_burst_len);
 	val = (val & ~ZYNQMP_DMA_AWLEN) |
-		(chan->dst_burst_len << ZYNQMP_DMA_AWLEN_OFST);
+		((burst_val << ZYNQMP_DMA_AWLEN_OFST) & ZYNQMP_DMA_AWLEN);
 	writel(val, chan->regs + ZYNQMP_DMA_DATA_ATTR);
 }
 
@@ -560,8 +564,10 @@
 {
 	struct zynqmp_dma_chan *chan = to_chan(dchan);
 
-	chan->src_burst_len = config->src_maxburst;
-	chan->dst_burst_len = config->dst_maxburst;
+	chan->src_burst_len = clamp(config->src_maxburst, 1U,
+		ZYNQMP_DMA_MAX_SRC_BURST_LEN);
+	chan->dst_burst_len = clamp(config->dst_maxburst, 1U,
+		ZYNQMP_DMA_MAX_DST_BURST_LEN);
 
 	return 0;
 }
@@ -887,8 +893,8 @@
 		return PTR_ERR(chan->regs);
 
 	chan->bus_width = ZYNQMP_DMA_BUS_WIDTH_64;
-	chan->dst_burst_len = ZYNQMP_DMA_AWLEN_RST_VAL;
-	chan->src_burst_len = ZYNQMP_DMA_ARLEN_RST_VAL;
+	chan->dst_burst_len = ZYNQMP_DMA_MAX_DST_BURST_LEN;
+	chan->src_burst_len = ZYNQMP_DMA_MAX_SRC_BURST_LEN;
 	err = of_property_read_u32(node, "xlnx,bus-width", &chan->bus_width);
 	if (err < 0) {
 		dev_err(&pdev->dev, "missing xlnx,bus-width property\n");