Merge tag 'dmaengine-5.4-rc1' of git://git.infradead.org/users/vkoul/slave-dma

Pull dmaengine updates from Vinod Koul:

 - Move Dmaengine DT bindings to YAML and convert Allwinner to schema.

 - FSL dma device_synchronize implementation

 - DW split acpi and of helpers and updates to driver and support for
   Elkhart Lake

 - Move filter fn as private for omap-dma and edma drivers and
   improvements to these drivers

 - Mark expected switch fall-through in couple of drivers

 - Renames of shdma and nbpfaxi binding document

 - Minor updates to bunch of drivers

* tag 'dmaengine-5.4-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (55 commits)
  dmaengine: ti: edma: Use bitmap_set() instead of open coded edma_set_bits()
  dmaengine: ti: edma: Only reset region0 access registers
  dmaengine: ti: edma: Do not reset reserved paRAM slots
  dmaengine: iop-adma.c: fix printk format warning
  dmaengine: stm32-dma: Use struct_size() helper
  dt-bindings: dmaengine: dma-common: Fix the dma-channel-mask property
  dmanegine: ioat/dca: Use struct_size() helper
  dmaengine: iop-adma: remove set but not used variable 'slots_per_op'
  dmaengine: dmatest: Add support for completion polling
  dmaengine: ti: omap-dma: Remove variable override in omap_dma_tx_status()
  dmaengine: ti: omap-dma: Remove 'Assignment in if condition'
  dmaengine: ti: edma: Remove 'Assignment in if condition'
  dmaengine: dw: platform: Split OF helpers to separate module
  dmaengine: dw: platform: Split ACPI helpers to separate module
  dmaengine: dw: platform: Move handle check to dw_dma_acpi_controller_register()
  dmaengine: dw: platform: Switch to acpi_dma_controller_register()
  dmaengine: dw: platform: Use devm_platform_ioremap_resource()
  dmaengine: dw: platform: Enable iDMA 32-bit on Intel Elkhart Lake
  dmaengine: dw: platform: Use struct dw_dma_chip_pdata
  dmaengine: dw: Export struct dw_dma_chip_pdata for wider use
  ...

2 files changed, 183 insertions, 107 deletions

diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c
index ceabdea40ae0..ba7c4f07fcd6 100644
--- a/drivers/dma/ti/edma.c
+++ b/drivers/dma/ti/edma.c
@@ -15,7 +15,7 @@
 
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
-#include <linux/edma.h>
+#include <linux/bitmap.h>
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -133,6 +133,17 @@
 #define EDMA_CONT_PARAMS_FIXED_EXACT	 1002
 #define EDMA_CONT_PARAMS_FIXED_NOT_EXACT 1003
 
+/*
+ * 64bit array registers are split into two 32bit registers:
+ * reg0: channel/event 0-31
+ * reg1: channel/event 32-63
+ *
+ * bit 5 in the channel number tells the array index (0/1)
+ * bit 0-4 (0x1f) is the bit offset within the register
+ */
+#define EDMA_REG_ARRAY_INDEX(channel)	((channel) >> 5)
+#define EDMA_CHANNEL_BIT(channel)	(BIT((channel) & 0x1f))
+
 /* PaRAM slots are laid out like this */
 struct edmacc_param {
 	u32 opt;
@@ -169,6 +180,7 @@ struct edma_desc {
 	struct list_head		node;
 	enum dma_transfer_direction	direction;
 	int				cyclic;
+	bool				polled;
 	int				absync;
 	int				pset_nr;
 	struct edma_chan		*echan;
@@ -412,12 +424,6 @@ static inline void edma_param_or(struct edma_cc *ecc, int offset, int param_no,
 	edma_or(ecc, EDMA_PARM + offset + (param_no << 5), or);
 }
 
-static inline void edma_set_bits(int offset, int len, unsigned long *p)
-{
-	for (; len > 0; len--)
-		set_bit(offset + (len - 1), p);
-}
-
 static void edma_assign_priority_to_queue(struct edma_cc *ecc, int queue_no,
 					  int priority)
 {
@@ -441,15 +447,14 @@ static void edma_setup_interrupt(struct edma_chan *echan, bool enable)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
 	if (enable) {
-		edma_shadow0_write_array(ecc, SH_ICR, channel >> 5,
-					 BIT(channel & 0x1f));
-		edma_shadow0_write_array(ecc, SH_IESR, channel >> 5,
-					 BIT(channel & 0x1f));
+		edma_shadow0_write_array(ecc, SH_ICR, idx, ch_bit);
+		edma_shadow0_write_array(ecc, SH_IESR, idx, ch_bit);
 	} else {
-		edma_shadow0_write_array(ecc, SH_IECR, channel >> 5,
-					 BIT(channel & 0x1f));
+		edma_shadow0_write_array(ecc, SH_IECR, idx, ch_bit);
 	}
 }
 
@@ -587,26 +592,26 @@ static void edma_start(struct edma_chan *echan)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	int j = (channel >> 5);
-	unsigned int mask = BIT(channel & 0x1f);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
 	if (!echan->hw_triggered) {
 		/* EDMA channels without event association */
-		dev_dbg(ecc->dev, "ESR%d %08x\n", j,
-			edma_shadow0_read_array(ecc, SH_ESR, j));
-		edma_shadow0_write_array(ecc, SH_ESR, j, mask);
+		dev_dbg(ecc->dev, "ESR%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_ESR, idx));
+		edma_shadow0_write_array(ecc, SH_ESR, idx, ch_bit);
 	} else {
 		/* EDMA channel with event association */
-		dev_dbg(ecc->dev, "ER%d %08x\n", j,
-			edma_shadow0_read_array(ecc, SH_ER, j));
+		dev_dbg(ecc->dev, "ER%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_ER, idx));
 		/* Clear any pending event or error */
-		edma_write_array(ecc, EDMA_ECR, j, mask);
-		edma_write_array(ecc, EDMA_EMCR, j, mask);
+		edma_write_array(ecc, EDMA_ECR, idx, ch_bit);
+		edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
 		/* Clear any SER */
-		edma_shadow0_write_array(ecc, SH_SECR, j, mask);
-		edma_shadow0_write_array(ecc, SH_EESR, j, mask);
-		dev_dbg(ecc->dev, "EER%d %08x\n", j,
-			edma_shadow0_read_array(ecc, SH_EER, j));
+		edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
+		edma_shadow0_write_array(ecc, SH_EESR, idx, ch_bit);
+		dev_dbg(ecc->dev, "EER%d %08x\n", idx,
+			edma_shadow0_read_array(ecc, SH_EER, idx));
 	}
 }
 
@@ -614,19 +619,19 @@ static void edma_stop(struct edma_chan *echan)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	int j = (channel >> 5);
-	unsigned int mask = BIT(channel & 0x1f);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
-	edma_shadow0_write_array(ecc, SH_EECR, j, mask);
-	edma_shadow0_write_array(ecc, SH_ECR, j, mask);
-	edma_shadow0_write_array(ecc, SH_SECR, j, mask);
-	edma_write_array(ecc, EDMA_EMCR, j, mask);
+	edma_shadow0_write_array(ecc, SH_EECR, idx, ch_bit);
+	edma_shadow0_write_array(ecc, SH_ECR, idx, ch_bit);
+	edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
+	edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
 
 	/* clear possibly pending completion interrupt */
-	edma_shadow0_write_array(ecc, SH_ICR, j, mask);
+	edma_shadow0_write_array(ecc, SH_ICR, idx, ch_bit);
 
-	dev_dbg(ecc->dev, "EER%d %08x\n", j,
-		edma_shadow0_read_array(ecc, SH_EER, j));
+	dev_dbg(ecc->dev, "EER%d %08x\n", idx,
+		edma_shadow0_read_array(ecc, SH_EER, idx));
 
 	/* REVISIT:  consider guarding against inappropriate event
 	 * chaining by overwriting with dummy_paramset.
@@ -640,45 +645,49 @@ static void edma_stop(struct edma_chan *echan)
 static void edma_pause(struct edma_chan *echan)
 {
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	unsigned int mask = BIT(channel & 0x1f);
 
-	edma_shadow0_write_array(echan->ecc, SH_EECR, channel >> 5, mask);
+	edma_shadow0_write_array(echan->ecc, SH_EECR,
+				 EDMA_REG_ARRAY_INDEX(channel),
+				 EDMA_CHANNEL_BIT(channel));
 }
 
 /* Re-enable EDMA hardware events on the specified channel.  */
 static void edma_resume(struct edma_chan *echan)
 {
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	unsigned int mask = BIT(channel & 0x1f);
 
-	edma_shadow0_write_array(echan->ecc, SH_EESR, channel >> 5, mask);
+	edma_shadow0_write_array(echan->ecc, SH_EESR,
+				 EDMA_REG_ARRAY_INDEX(channel),
+				 EDMA_CHANNEL_BIT(channel));
 }
 
 static void edma_trigger_channel(struct edma_chan *echan)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	unsigned int mask = BIT(channel & 0x1f);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
-	edma_shadow0_write_array(ecc, SH_ESR, (channel >> 5), mask);
+	edma_shadow0_write_array(ecc, SH_ESR, idx, ch_bit);
 
-	dev_dbg(ecc->dev, "ESR%d %08x\n", (channel >> 5),
-		edma_shadow0_read_array(ecc, SH_ESR, (channel >> 5)));
+	dev_dbg(ecc->dev, "ESR%d %08x\n", idx,
+		edma_shadow0_read_array(ecc, SH_ESR, idx));
 }
 
 static void edma_clean_channel(struct edma_chan *echan)
 {
 	struct edma_cc *ecc = echan->ecc;
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
-	int j = (channel >> 5);
-	unsigned int mask = BIT(channel & 0x1f);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
 
-	dev_dbg(ecc->dev, "EMR%d %08x\n", j, edma_read_array(ecc, EDMA_EMR, j));
-	edma_shadow0_write_array(ecc, SH_ECR, j, mask);
+	dev_dbg(ecc->dev, "EMR%d %08x\n", idx,
+		edma_read_array(ecc, EDMA_EMR, idx));
+	edma_shadow0_write_array(ecc, SH_ECR, idx, ch_bit);
 	/* Clear the corresponding EMR bits */
-	edma_write_array(ecc, EDMA_EMCR, j, mask);
+	edma_write_array(ecc, EDMA_EMCR, idx, ch_bit);
 	/* Clear any SER */
-	edma_shadow0_write_array(ecc, SH_SECR, j, mask);
+	edma_shadow0_write_array(ecc, SH_SECR, idx, ch_bit);
 	edma_write(ecc, EDMA_CCERRCLR, BIT(16) | BIT(1) | BIT(0));
 }
 
@@ -708,7 +717,8 @@ static int edma_alloc_channel(struct edma_chan *echan,
 	int channel = EDMA_CHAN_SLOT(echan->ch_num);
 
 	/* ensure access through shadow region 0 */
-	edma_or_array2(ecc, EDMA_DRAE, 0, channel >> 5, BIT(channel & 0x1f));
+	edma_or_array2(ecc, EDMA_DRAE, 0, EDMA_REG_ARRAY_INDEX(channel),
+		       EDMA_CHANNEL_BIT(channel));
 
 	/* ensure no events are pending */
 	edma_stop(echan);
@@ -1011,6 +1021,7 @@ static int edma_config_pset(struct dma_chan *chan, struct edma_pset *epset,
 		src_cidx = cidx;
 		dst_bidx = acnt;
 		dst_cidx = cidx;
+		epset->addr = src_addr;
 	} else {
 		dev_err(dev, "%s: direction not implemented yet\n", __func__);
 		return -EINVAL;
@@ -1211,8 +1222,9 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
 
 	edesc->pset[0].param.opt |= ITCCHEN;
 	if (nslots == 1) {
-		/* Enable transfer complete interrupt */
-		edesc->pset[0].param.opt |= TCINTEN;
+		/* Enable transfer complete interrupt if requested */
+		if (tx_flags & DMA_PREP_INTERRUPT)
+			edesc->pset[0].param.opt |= TCINTEN;
 	} else {
 		/* Enable transfer complete chaining for the first slot */
 		edesc->pset[0].param.opt |= TCCHEN;
@@ -1239,9 +1251,14 @@ static struct dma_async_tx_descriptor *edma_prep_dma_memcpy(
 		}
 
 		edesc->pset[1].param.opt |= ITCCHEN;
-		edesc->pset[1].param.opt |= TCINTEN;
+		/* Enable transfer complete interrupt if requested */
+		if (tx_flags & DMA_PREP_INTERRUPT)
+			edesc->pset[1].param.opt |= TCINTEN;
 	}
 
+	if (!(tx_flags & DMA_PREP_INTERRUPT))
+		edesc->polled = true;
+
 	return vchan_tx_prep(&echan->vchan, &edesc->vdesc, tx_flags);
 }
 
@@ -1721,7 +1738,11 @@ static u32 edma_residue(struct edma_desc *edesc)
 	int loop_count = EDMA_MAX_TR_WAIT_LOOPS;
 	struct edma_chan *echan = edesc->echan;
 	struct edma_pset *pset = edesc->pset;
-	dma_addr_t done, pos;
+	dma_addr_t done, pos, pos_old;
+	int channel = EDMA_CHAN_SLOT(echan->ch_num);
+	int idx = EDMA_REG_ARRAY_INDEX(channel);
+	int ch_bit = EDMA_CHANNEL_BIT(channel);
+	int event_reg;
 	int i;
 
 	/*
@@ -1734,16 +1755,20 @@ static u32 edma_residue(struct edma_desc *edesc)
 	 * "pos" may represent a transfer request that is still being
 	 * processed by the EDMACC or EDMATC. We will busy wait until
 	 * any one of the situations occurs:
-	 *   1. the DMA hardware is idle
-	 *   2. a new transfer request is setup
+	 *   1. while and event is pending for the channel
+	 *   2. a position updated
 	 *   3. we hit the loop limit
 	 */
-	while (edma_read(echan->ecc, EDMA_CCSTAT) & EDMA_CCSTAT_ACTV) {
-		/* check if a new transfer request is setup */
-		if (edma_get_position(echan->ecc,
-				      echan->slot[0], dst) != pos) {
+	if (is_slave_direction(edesc->direction))
+		event_reg = SH_ER;
+	else
+		event_reg = SH_ESR;
+
+	pos_old = pos;
+	while (edma_shadow0_read_array(echan->ecc, event_reg, idx) & ch_bit) {
+		pos = edma_get_position(echan->ecc, echan->slot[0], dst);
+		if (pos != pos_old)
 			break;
-		}
 
 		if (!--loop_count) {
 			dev_dbg_ratelimited(echan->vchan.chan.device->dev,
@@ -1769,6 +1794,12 @@ static u32 edma_residue(struct edma_desc *edesc)
 	}
 
 	/*
+	 * If the position is 0, then EDMA loaded the closing dummy slot, the
+	 * transfer is completed
+	 */
+	if (!pos)
+		return 0;
+	/*
 	 * For SG operation we catch up with the last processed
 	 * status.
 	 */
@@ -1796,19 +1827,46 @@ static enum dma_status edma_tx_status(struct dma_chan *chan,
 				      struct dma_tx_state *txstate)
 {
 	struct edma_chan *echan = to_edma_chan(chan);
-	struct virt_dma_desc *vdesc;
+	struct dma_tx_state txstate_tmp;
 	enum dma_status ret;
 	unsigned long flags;
 
 	ret = dma_cookie_status(chan, cookie, txstate);
-	if (ret == DMA_COMPLETE || !txstate)
+
+	if (ret == DMA_COMPLETE)
 		return ret;
 
+	/* Provide a dummy dma_tx_state for completion checking */
+	if (!txstate)
+		txstate = &txstate_tmp;
+
 	spin_lock_irqsave(&echan->vchan.lock, flags);
-	if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie)
+	if (echan->edesc && echan->edesc->vdesc.tx.cookie == cookie) {
 		txstate->residue = edma_residue(echan->edesc);
-	else if ((vdesc = vchan_find_desc(&echan->vchan, cookie)))
-		txstate->residue = to_edma_desc(&vdesc->tx)->residue;
+	} else {
+		struct virt_dma_desc *vdesc = vchan_find_desc(&echan->vchan,
+							      cookie);
+
+		if (vdesc)
+			txstate->residue = to_edma_desc(&vdesc->tx)->residue;
+		else
+			txstate->residue = 0;
+	}
+
+	/*
+	 * Mark the cookie completed if the residue is 0 for non cyclic
+	 * transfers
+	 */
+	if (ret != DMA_COMPLETE && !txstate->residue &&
+	    echan->edesc && echan->edesc->polled &&
+	    echan->edesc->vdesc.tx.cookie == cookie) {
+		edma_stop(echan);
+		vchan_cookie_complete(&echan->edesc->vdesc);
+		echan->edesc = NULL;
+		edma_execute(echan);
+		ret = DMA_COMPLETE;
+	}
+
 	spin_unlock_irqrestore(&echan->vchan.lock, flags);
 
 	return ret;
@@ -2185,11 +2243,13 @@ static struct dma_chan *of_edma_xlate(struct of_phandle_args *dma_spec,
 }
 #endif
 
+static bool edma_filter_fn(struct dma_chan *chan, void *param);
+
 static int edma_probe(struct platform_device *pdev)
 {
 	struct edma_soc_info	*info = pdev->dev.platform_data;
 	s8			(*queue_priority_mapping)[2];
-	int			i, off, ln;
+	int			i, off;
 	const s16		(*rsv_slots)[2];
 	const s16		(*xbar_chans)[2];
 	int			irq;
@@ -2273,21 +2333,22 @@ static int edma_probe(struct platform_device *pdev)
 
 	ecc->default_queue = info->default_queue;
 
-	for (i = 0; i < ecc->num_slots; i++)
-		edma_write_slot(ecc, i, &dummy_paramset);
-
 	if (info->rsv) {
 		/* Set the reserved slots in inuse list */
 		rsv_slots = info->rsv->rsv_slots;
 		if (rsv_slots) {
-			for (i = 0; rsv_slots[i][0] != -1; i++) {
-				off = rsv_slots[i][0];
-				ln = rsv_slots[i][1];
-				edma_set_bits(off, ln, ecc->slot_inuse);
-			}
+			for (i = 0; rsv_slots[i][0] != -1; i++)
+				bitmap_set(ecc->slot_inuse, rsv_slots[i][0],
+					   rsv_slots[i][1]);
 		}
 	}
 
+	for (i = 0; i < ecc->num_slots; i++) {
+		/* Reset only unused - not reserved - paRAM slots */
+		if (!test_bit(i, ecc->slot_inuse))
+			edma_write_slot(ecc, i, &dummy_paramset);
+	}
+
 	/* Clear the xbar mapped channels in unused list */
 	xbar_chans = info->xbar_chans;
 	if (xbar_chans) {
@@ -2366,11 +2427,10 @@ static int edma_probe(struct platform_device *pdev)
 		edma_assign_priority_to_queue(ecc, queue_priority_mapping[i][0],
 					      queue_priority_mapping[i][1]);
 
-	for (i = 0; i < ecc->num_region; i++) {
-		edma_write_array2(ecc, EDMA_DRAE, i, 0, 0x0);
-		edma_write_array2(ecc, EDMA_DRAE, i, 1, 0x0);
-		edma_write_array(ecc, EDMA_QRAE, i, 0x0);
-	}
+	edma_write_array2(ecc, EDMA_DRAE, 0, 0, 0x0);
+	edma_write_array2(ecc, EDMA_DRAE, 0, 1, 0x0);
+	edma_write_array(ecc, EDMA_QRAE, 0, 0x0);
+
 	ecc->info = info;
 
 	/* Init the dma device and channels */
@@ -2482,8 +2542,9 @@ static int edma_pm_resume(struct device *dev)
 	for (i = 0; i < ecc->num_channels; i++) {
 		if (echan[i].alloced) {
 			/* ensure access through shadow region 0 */
-			edma_or_array2(ecc, EDMA_DRAE, 0, i >> 5,
-				       BIT(i & 0x1f));
+			edma_or_array2(ecc, EDMA_DRAE, 0,
+				       EDMA_REG_ARRAY_INDEX(i),
+				       EDMA_CHANNEL_BIT(i));
 
 			edma_setup_interrupt(&echan[i], true);
 
@@ -2524,7 +2585,7 @@ static struct platform_driver edma_tptc_driver = {
 	},
 };
 
-bool edma_filter_fn(struct dma_chan *chan, void *param)
+static bool edma_filter_fn(struct dma_chan *chan, void *param)
 {
 	bool match = false;
 
@@ -2539,7 +2600,6 @@ bool edma_filter_fn(struct dma_chan *chan, void *param)
 	}
 	return match;
 }
-EXPORT_SYMBOL(edma_filter_fn);
 
 static int edma_init(void)
 {
diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index d07c0d5de7a2..6b6ba238b81a 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -91,6 +91,7 @@ struct omap_desc {
 	bool using_ll;
 	enum dma_transfer_direction dir;
 	dma_addr_t dev_addr;
+	bool polled;
 
 	int32_t fi;		/* for OMAP_DMA_SYNC_PACKET / double indexing */
 	int16_t ei;		/* for double indexing */
@@ -202,6 +203,7 @@ static const unsigned es_bytes[] = {
 	[CSDP_DATA_TYPE_32] = 4,
 };
 
+static bool omap_dma_filter_fn(struct dma_chan *chan, void *param);
 static struct of_dma_filter_info omap_dma_info = {
 	.filter_fn = omap_dma_filter_fn,
 };
@@ -812,31 +814,22 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 	dma_cookie_t cookie, struct dma_tx_state *txstate)
 {
 	struct omap_chan *c = to_omap_dma_chan(chan);
-	struct virt_dma_desc *vd;
 	enum dma_status ret;
 	unsigned long flags;
+	struct omap_desc *d = NULL;
 
 	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)
+	if (ret == DMA_COMPLETE)
 		return ret;
 
 	spin_lock_irqsave(&c->vc.lock, flags);
-	vd = vchan_find_desc(&c->vc, cookie);
-	if (vd) {
-		txstate->residue = omap_dma_desc_size(to_omap_dma_desc(&vd->tx));
-	} else if (c->desc && c->desc->vd.tx.cookie == cookie) {
-		struct omap_desc *d = c->desc;
+	if (c->desc && c->desc->vd.tx.cookie == cookie)
+		d = c->desc;
+
+	if (!txstate)
+		goto out;
+
+	if (d) {
 		dma_addr_t pos;
 
 		if (d->dir == DMA_MEM_TO_DEV)
@@ -848,10 +841,31 @@ static enum dma_status omap_dma_tx_status(struct dma_chan *chan,
 
 		txstate->residue = omap_dma_desc_size_pos(d, pos);
 	} else {
-		txstate->residue = 0;
+		struct virt_dma_desc *vd = vchan_find_desc(&c->vc, cookie);
+
+		if (vd)
+			txstate->residue = omap_dma_desc_size(
+						to_omap_dma_desc(&vd->tx));
+		else
+			txstate->residue = 0;
 	}
-	if (ret == DMA_IN_PROGRESS && c->paused)
+
+out:
+	if (ret == DMA_IN_PROGRESS && c->paused) {
 		ret = DMA_PAUSED;
+	} else if (d && d->polled && c->running) {
+		uint32_t ccr = omap_dma_chan_read(c, CCR);
+		/*
+		 * The channel is no longer active, set the return value
+		 * accordingly and mark it as completed
+		 */
+		if (!(ccr & CCR_ENABLE)) {
+			ret = DMA_COMPLETE;
+			omap_dma_start_desc(c);
+			vchan_cookie_complete(&d->vd);
+		}
+	}
+
 	spin_unlock_irqrestore(&c->vc.lock, flags);
 
 	return ret;
@@ -1178,7 +1192,10 @@ 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 | CICR_FRAME_IE;
+	if (tx_flags & DMA_PREP_INTERRUPT)
+		d->cicr |= CICR_FRAME_IE;
+	else
+		d->polled = true;
 
 	d->csdp = data_type;
 
@@ -1639,7 +1656,7 @@ static struct platform_driver omap_dma_driver = {
 	},
 };
 
-bool omap_dma_filter_fn(struct dma_chan *chan, void *param)
+static bool omap_dma_filter_fn(struct dma_chan *chan, void *param)
 {
 	if (chan->device->dev->driver == &omap_dma_driver.driver) {
 		struct omap_dmadev *od = to_omap_dma_dev(chan->device);
@@ -1653,7 +1670,6 @@ bool omap_dma_filter_fn(struct dma_chan *chan, void *param)
 	}
 	return false;
 }
-EXPORT_SYMBOL_GPL(omap_dma_filter_fn);
 
 static int omap_dma_init(void)
 {