diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 5ad0ec1f0e29f750eee5c70889df5427d7413556..97199b3c25a22cd907c1a73648c76a96a594b370 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -130,26 +130,14 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 static void dwc_initialize(struct dw_dma_chan *dwc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
-	struct dw_dma_slave *dws = dwc->chan.private;
 	u32 cfghi = DWC_CFGH_FIFO_MODE;
 	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
 
 	if (dwc->initialized == true)
 		return;
 
-	if (dws) {
-		/*
-		 * We need controller-specific data to set up slave
-		 * transfers.
-		 */
-		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
-
-		cfghi |= DWC_CFGH_DST_PER(dws->dst_id);
-		cfghi |= DWC_CFGH_SRC_PER(dws->src_id);
-	} else {
-		cfghi |= DWC_CFGH_DST_PER(dwc->dst_id);
-		cfghi |= DWC_CFGH_SRC_PER(dwc->src_id);
-	}
+	cfghi |= DWC_CFGH_DST_PER(dwc->dst_id);
+	cfghi |= DWC_CFGH_SRC_PER(dwc->src_id);
 
 	channel_writel(dwc, CFG_LO, cfglo);
 	channel_writel(dwc, CFG_HI, cfghi);
@@ -941,7 +929,7 @@ bool dw_dma_filter(struct dma_chan *chan, void *param)
 	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
 	struct dw_dma_slave *dws = param;
 
-	if (!dws || dws->dma_dev != chan->device->dev)
+	if (dws->dma_dev != chan->device->dev)
 		return false;
 
 	/* We have to copy data since dws can be temporary storage */
@@ -1165,6 +1153,14 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	 * doesn't mean what you think it means), and status writeback.
 	 */
 
+	/*
+	 * We need controller-specific data to set up slave transfers.
+	 */
+	if (chan->private && !dw_dma_filter(chan, chan->private)) {
+		dev_warn(chan2dev(chan), "Wrong controller-specific data\n");
+		return -EINVAL;
+	}
+
 	/* Enable controller here if needed */
 	if (!dw->in_use)
 		dw_dma_on(dw);
@@ -1226,6 +1222,14 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	spin_lock_irqsave(&dwc->lock, flags);
 	list_splice_init(&dwc->free_list, &list);
 	dwc->descs_allocated = 0;
+
+	/* Clear custom channel configuration */
+	dwc->src_id = 0;
+	dwc->dst_id = 0;
+
+	dwc->src_master = 0;
+	dwc->dst_master = 0;
+
 	dwc->initialized = false;
 
 	/* Disable interrupts */
diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c
index ee3463e774f8e4dc5c46e2614719f9d0723cfd06..04070baab78ab0cc7772085dd70828741317dd5a 100644
--- a/drivers/dma/edma.c
+++ b/drivers/dma/edma.c
@@ -1238,6 +1238,7 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 	struct edma_desc *edesc;
 	dma_addr_t src_addr, dst_addr;
 	enum dma_slave_buswidth dev_width;
+	bool use_intermediate = false;
 	u32 burst;
 	int i, ret, nslots;
 
@@ -1279,8 +1280,21 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 	 * but the synchronization is difficult to achieve with Cyclic and
 	 * cannot be guaranteed, so we error out early.
 	 */
-	if (nslots > MAX_NR_SG)
-		return NULL;
+	if (nslots > MAX_NR_SG) {
+		/*
+		 * If the burst and period sizes are the same, we can put
+		 * the full buffer into a single period and activate
+		 * intermediate interrupts. This will produce interrupts
+		 * after each burst, which is also after each desired period.
+		 */
+		if (burst == period_len) {
+			period_len = buf_len;
+			nslots = 2;
+			use_intermediate = true;
+		} else {
+			return NULL;
+		}
+	}
 
 	edesc = kzalloc(sizeof(*edesc) + nslots * sizeof(edesc->pset[0]),
 			GFP_ATOMIC);
@@ -1358,8 +1372,13 @@ static struct dma_async_tx_descriptor *edma_prep_dma_cyclic(
 		/*
 		 * Enable period interrupt only if it is requested
 		 */
-		if (tx_flags & DMA_PREP_INTERRUPT)
+		if (tx_flags & DMA_PREP_INTERRUPT) {
 			edesc->pset[i].param.opt |= TCINTEN;
+
+			/* Also enable intermediate interrupts if necessary */
+			if (use_intermediate)
+				edesc->pset[i].param.opt |= ITCINTEN;
+		}
 	}
 
 	/* Place the cyclic channel to highest priority queue */
@@ -1570,32 +1589,6 @@ static irqreturn_t dma_ccerr_handler(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void edma_tc_set_pm_state(struct edma_tc *tc, bool enable)
-{
-	struct platform_device *tc_pdev;
-	int ret;
-
-	if (!IS_ENABLED(CONFIG_OF) || !tc)
-		return;
-
-	tc_pdev = of_find_device_by_node(tc->node);
-	if (!tc_pdev) {
-		pr_err("%s: TPTC device is not found\n", __func__);
-		return;
-	}
-	if (!pm_runtime_enabled(&tc_pdev->dev))
-		pm_runtime_enable(&tc_pdev->dev);
-
-	if (enable)
-		ret = pm_runtime_get_sync(&tc_pdev->dev);
-	else
-		ret = pm_runtime_put_sync(&tc_pdev->dev);
-
-	if (ret < 0)
-		pr_err("%s: pm_runtime_%s_sync() failed for %s\n", __func__,
-		       enable ? "get" : "put", dev_name(&tc_pdev->dev));
-}
-
 /* Alloc channel resources */
 static int edma_alloc_chan_resources(struct dma_chan *chan)
 {
@@ -1632,8 +1625,6 @@ static int edma_alloc_chan_resources(struct dma_chan *chan)
 		EDMA_CHAN_SLOT(echan->ch_num), chan->chan_id,
 		echan->hw_triggered ? "HW" : "SW");
 
-	edma_tc_set_pm_state(echan->tc, true);
-
 	return 0;
 
 err_slot:
@@ -1670,7 +1661,6 @@ static void edma_free_chan_resources(struct dma_chan *chan)
 		echan->alloced = false;
 	}
 
-	edma_tc_set_pm_state(echan->tc, false);
 	echan->tc = NULL;
 	echan->hw_triggered = false;
 
@@ -2417,10 +2407,8 @@ static int edma_pm_suspend(struct device *dev)
 	int i;
 
 	for (i = 0; i < ecc->num_channels; i++) {
-		if (echan[i].alloced) {
+		if (echan[i].alloced)
 			edma_setup_interrupt(&echan[i], false);
-			edma_tc_set_pm_state(echan[i].tc, false);
-		}
 	}
 
 	return 0;
@@ -2450,8 +2438,6 @@ static int edma_pm_resume(struct device *dev)
 
 			/* Set up channel -> slot mapping for the entry slot */
 			edma_set_chmap(&echan[i], echan[i].slot[0]);
-
-			edma_tc_set_pm_state(echan[i].tc, true);
 		}
 	}
 
@@ -2475,7 +2461,8 @@ static struct platform_driver edma_driver = {
 
 static int edma_tptc_probe(struct platform_device *pdev)
 {
-	return 0;
+	pm_runtime_enable(&pdev->dev);
+	return pm_runtime_get_sync(&pdev->dev);
 }
 
 static struct platform_driver edma_tptc_driver = {
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index eef145edb936816f3686d343742a709392a5dffa..ee510515ce187af75d3ba873b65d5de26cc3acb4 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -64,10 +64,10 @@ static void hsu_dma_chan_start(struct hsu_dma_chan *hsuc)
 
 	if (hsuc->direction == DMA_MEM_TO_DEV) {
 		bsr = config->dst_maxburst;
-		mtsr = config->dst_addr_width;
+		mtsr = config->src_addr_width;
 	} else if (hsuc->direction == DMA_DEV_TO_MEM) {
 		bsr = config->src_maxburst;
-		mtsr = config->src_addr_width;
+		mtsr = config->dst_addr_width;
 	}
 
 	hsu_chan_disable(hsuc);
@@ -135,7 +135,7 @@ static u32 hsu_dma_chan_get_sr(struct hsu_dma_chan *hsuc)
 	sr = hsu_chan_readl(hsuc, HSU_CH_SR);
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
 
-	return sr;
+	return sr & ~(HSU_CH_SR_DESCE_ANY | HSU_CH_SR_CDESC_ANY);
 }
 
 irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr)
@@ -254,10 +254,13 @@ static void hsu_dma_issue_pending(struct dma_chan *chan)
 static size_t hsu_dma_active_desc_size(struct hsu_dma_chan *hsuc)
 {
 	struct hsu_dma_desc *desc = hsuc->desc;
-	size_t bytes = desc->length;
+	size_t bytes = 0;
 	int i;
 
-	i = desc->active % HSU_DMA_CHAN_NR_DESC;
+	for (i = desc->active; i < desc->nents; i++)
+		bytes += desc->sg[i].len;
+
+	i = HSU_DMA_CHAN_NR_DESC - 1;
 	do {
 		bytes += hsu_chan_readl(hsuc, HSU_CH_DxTSR(i));
 	} while (--i >= 0);
diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h
index 578a8ee8cd054429b3e3fd6da2341b49020721cc..6b070c22b1dfc2bca1dc04ca12218de17d1f0d70 100644
--- a/drivers/dma/hsu/hsu.h
+++ b/drivers/dma/hsu/hsu.h
@@ -41,6 +41,9 @@
 #define HSU_CH_SR_DESCTO(x)	BIT(8 + (x))
 #define HSU_CH_SR_DESCTO_ANY	(BIT(11) | BIT(10) | BIT(9) | BIT(8))
 #define HSU_CH_SR_CHE		BIT(15)
+#define HSU_CH_SR_DESCE(x)	BIT(16 + (x))
+#define HSU_CH_SR_DESCE_ANY	(BIT(19) | BIT(18) | BIT(17) | BIT(16))
+#define HSU_CH_SR_CDESC_ANY	(BIT(31) | BIT(30))
 
 /* Bits in HSU_CH_CR */
 #define HSU_CH_CR_CHA		BIT(0)
diff --git a/drivers/dma/omap-dma.c b/drivers/dma/omap-dma.c
index 43bd5aee7ffe093d78e6f8c1f43b75084f8f1c8e..1e984e18c1266b74fc01c247fad36f3e132ad587 100644
--- a/drivers/dma/omap-dma.c
+++ b/drivers/dma/omap-dma.c
@@ -48,6 +48,7 @@ struct omap_chan {
 	unsigned dma_sig;
 	bool cyclic;
 	bool paused;
+	bool running;
 
 	int dma_ch;
 	struct omap_desc *desc;
@@ -294,6 +295,8 @@ static void omap_dma_start(struct omap_chan *c, struct omap_desc *d)
 
 	/* Enable channel */
 	omap_dma_chan_write(c, CCR, d->ccr | CCR_ENABLE);
+
+	c->running = true;
 }
 
 static void omap_dma_stop(struct omap_chan *c)
@@ -355,6 +358,8 @@ static void omap_dma_stop(struct omap_chan *c)
 
 		omap_dma_chan_write(c, CLNK_CTRL, val);
 	}
+
+	c->running = false;
 }
 
 static void omap_dma_start_sg(struct omap_chan *c, struct omap_desc *d,
@@ -673,15 +678,20 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 	struct omap_chan *c = to_omap_dma_chan(chan);
 	struct virt_dma_desc *vd;
 	enum dma_status ret;
-	uint32_t ccr;
 	unsigned long flags;
 
-	ccr = omap_dma_chan_read(c, CCR);
-	/* The channel is no longer active, handle the completion right away */
-	if (!(ccr & CCR_ENABLE))
-		omap_dma_callback(c->dma_ch, 0, c);
-
 	ret = dma_cookie_status(chan, cookie, txstate);
+
+	if (!c->paused && c->running) {
+		uint32_t ccr = omap_dma_chan_read(c, CCR);
+		/*
+		 * The channel is no longer active, set the return value
+		 * accordingly
+		 */
+		if (!(ccr & CCR_ENABLE))
+			ret = DMA_COMPLETE;
+	}
+
 	if (ret == DMA_COMPLETE || !txstate)
 		return ret;
 
@@ -945,9 +955,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_memcpy(
 	d->ccr = c->ccr;
 	d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_POSTINC;
 
-	d->cicr = CICR_DROP_IE;
-	if (tx_flags & DMA_PREP_INTERRUPT)
-		d->cicr |= CICR_FRAME_IE;
+	d->cicr = CICR_DROP_IE | CICR_FRAME_IE;
 
 	d->csdp = data_type;
 
diff --git a/drivers/dma/xilinx/xilinx_vdma.c b/drivers/dma/xilinx/xilinx_vdma.c
index 0ee0321868d36b3054acac0a02356e09cc0749a1..ef67f278e076da61c3e08428a70bffd0d8f9341c 100644
--- a/drivers/dma/xilinx/xilinx_vdma.c
+++ b/drivers/dma/xilinx/xilinx_vdma.c
@@ -1236,7 +1236,7 @@ static struct dma_chan *of_dma_xilinx_xlate(struct of_phandle_args *dma_spec,
 	struct xilinx_vdma_device *xdev = ofdma->of_dma_data;
 	int chan_id = dma_spec->args[0];
 
-	if (chan_id >= XILINX_VDMA_MAX_CHANS_PER_DEVICE)
+	if (chan_id >= XILINX_VDMA_MAX_CHANS_PER_DEVICE || !xdev->chan[chan_id])
 		return NULL;
 
 	return dma_get_slave_channel(&xdev->chan[chan_id]->common);