dma: pdma: cyclic, residue, DMA_PRIVATE

index 579f79a..9929f85 100644
@@ -710,25 +710,32 @@ static void dma_do_tasklet(unsigned long data)
 
 	spin_lock_irqsave(&chan->desc_lock, flags);
 
-	/* update the cookie if we have some descriptors to cleanup */
-	if (!list_empty(&chan->chain_running)) {
-		dma_cookie_t cookie;
-
-		desc = to_mmp_pdma_desc(chan->chain_running.prev);
-		cookie = desc->async_tx.cookie;
-		dma_cookie_complete(&desc->async_tx);
+	list_for_each_entry_safe(desc, _desc, &chan->chain_running, node) {
+		/*
+		 * move the descriptors to a temporary list so we can drop
+		 * the lock during the entire cleanup operation
+		 */
+		list_del(&desc->node);
+		list_add(&desc->node, &chain_cleanup);
 
-		dev_dbg(chan->dev, "completed_cookie=%d\n", cookie);
+		/*
+		 * Look for the first list entry which has the ENDIRQEN flag
+		 * set. That is the descriptor we got an interrupt for, so
+		 * complete that transaction and its cookie.
+		 */
+		if (desc->desc.dcmd & DCMD_ENDIRQEN) {
+			dma_cookie_t cookie = desc->async_tx.cookie;
+			dma_cookie_complete(&desc->async_tx);
+			dev_dbg(chan->dev, "completed_cookie=%d\n", cookie);
+			break;
+		}
 	}
 
 	/*
-	 * move the descriptors to a temporary list so we can drop the lock
-	 * during the entire cleanup operation
+	 * The hardware is idle and ready for more when the
+	 * chain_running list is empty.
 	 */
-	list_splice_tail_init(&chan->chain_running, &chain_cleanup);
-
-	/* the hardware is now idle and ready for more */
-	chan->idle = true;
+	chan->idle = list_empty(&chan->chain_running);
 
 	/* Start any pending transactions automatically */
 	start_pending_queue(chan);

index 9929f85..31e9a71 100644
@@ -279,25 +279,6 @@ static void mmp_pdma_free_phy(struct mmp_pdma_chan *pchan)
 	spin_unlock_irqrestore(&pdev->phy_lock, flags);
 }
 
-/* desc->tx_list ==> pending list */
-static void append_pending_queue(struct mmp_pdma_chan *chan,
-					struct mmp_pdma_desc_sw *desc)
-{
-	struct mmp_pdma_desc_sw *tail =
-				to_mmp_pdma_desc(chan->chain_pending.prev);
-
-	if (list_empty(&chan->chain_pending))
-		goto out_splice;
-
-	/* one irq per queue, even appended */
-	tail->desc.ddadr = desc->async_tx.phys;
-	tail->desc.dcmd &= ~DCMD_ENDIRQEN;
-
-	/* softly link to pending list */
-out_splice:
-	list_splice_tail_init(&desc->tx_list, &chan->chain_pending);
-}
-
 /**
  * start_pending_queue - transfer any pending transactions
  * pending list ==> running list

@@ -360,7 +341,8 @@ static dma_cookie_t mmp_pdma_tx_submit(struct dma_async_tx_descriptor *tx)
 		cookie = dma_cookie_assign(&child->async_tx);
 	}
 
-	append_pending_queue(chan, desc);
+	/* softly link to pending list - desc->tx_list ==> pending list */
+	list_splice_tail_init(&desc->tx_list, &chan->chain_pending);
 
 	spin_unlock_irqrestore(&chan->desc_lock, flags);
 

index 31e9a71..d82a4f6 100644
@@ -98,6 +98,9 @@ struct mmp_pdma_chan {
 	struct mmp_pdma_phy *phy;
 	enum dma_transfer_direction dir;
 
+	struct mmp_pdma_desc_sw *cyclic_first;	/* first desc_sw if channel
+						 * is in cyclic mode */
+
 	/* channel's basic info */
 	struct tasklet_struct tasklet;
 	u32 dcmd;

@@ -499,6 +502,8 @@ mmp_pdma_prep_memcpy(struct dma_chan *dchan,
 	new->desc.ddadr = DDADR_STOP;
 	new->desc.dcmd |= DCMD_ENDIRQEN;
 
+	chan->cyclic_first = NULL;
+
 	return &first->async_tx;
 
 fail:

@@ -574,6 +579,94 @@ mmp_pdma_prep_slave_sg(struct dma_chan *dchan, struct scatterlist *sgl,
 	new->desc.ddadr = DDADR_STOP;
 	new->desc.dcmd |= DCMD_ENDIRQEN;
 
+	chan->dir = dir;
+	chan->cyclic_first = NULL;
+
+	return &first->async_tx;
+
+fail:
+	if (first)
+		mmp_pdma_free_desc_list(chan, &first->tx_list);
+	return NULL;
+}
+
+static struct dma_async_tx_descriptor *mmp_pdma_prep_dma_cyclic(
+	struct dma_chan *dchan, dma_addr_t buf_addr, size_t len,
+	size_t period_len, enum dma_transfer_direction direction,
+	unsigned long flags, void *context)
+{
+	struct mmp_pdma_chan *chan;
+	struct mmp_pdma_desc_sw *first = NULL, *prev = NULL, *new;
+	dma_addr_t dma_src, dma_dst;
+
+	if (!dchan || !len || !period_len)
+		return NULL;
+
+	/* the buffer length must be a multiple of period_len */
+	if (len % period_len != 0)
+		return NULL;
+
+	if (period_len > PDMA_MAX_DESC_BYTES)
+		return NULL;
+
+	chan = to_mmp_pdma_chan(dchan);
+
+	switch (direction) {
+	case DMA_MEM_TO_DEV:
+		dma_src = buf_addr;
+		dma_dst = chan->dev_addr;
+		break;
+	case DMA_DEV_TO_MEM:
+		dma_dst = buf_addr;
+		dma_src = chan->dev_addr;
+		break;
+	default:
+		dev_err(chan->dev, "Unsupported direction for cyclic DMA\n");
+		return NULL;
+	}
+
+	chan->dir = direction;
+
+	do {
+		/* Allocate the link descriptor from DMA pool */
+		new = mmp_pdma_alloc_descriptor(chan);
+		if (!new) {
+			dev_err(chan->dev, "no memory for desc\n");
+			goto fail;
+		}
+
+		new->desc.dcmd = chan->dcmd | DCMD_ENDIRQEN |
+					(DCMD_LENGTH & period_len);
+		new->desc.dsadr = dma_src;
+		new->desc.dtadr = dma_dst;
+
+		if (!first)
+			first = new;
+		else
+			prev->desc.ddadr = new->async_tx.phys;
+
+		new->async_tx.cookie = 0;
+		async_tx_ack(&new->async_tx);
+
+		prev = new;
+		len -= period_len;
+
+		if (chan->dir == DMA_MEM_TO_DEV)
+			dma_src += period_len;
+		else
+			dma_dst += period_len;
+
+		/* Insert the link descriptor to the LD ring */
+		list_add_tail(&new->node, &first->tx_list);
+	} while (len);
+
+	first->async_tx.flags = flags; /* client is in control of this ack */
+	first->async_tx.cookie = -EBUSY;
+
+	/* make the cyclic link */
+	new->desc.ddadr = first->async_tx.phys;
+	chan->cyclic_first = first;
+
 	return &first->async_tx;
 
 fail:

@@ -688,8 +781,23 @@ static void dma_do_tasklet(unsigned long data)
 	LIST_HEAD(chain_cleanup);
 	unsigned long flags;
 
-	/* submit pending list; callback for each desc; free desc */
+	if (chan->cyclic_first) {
+		dma_async_tx_callback cb = NULL;
+		void *cb_data = NULL;
 
+		spin_lock_irqsave(&chan->desc_lock, flags);
+		desc = chan->cyclic_first;
+		cb = desc->async_tx.callback;
+		cb_data = desc->async_tx.callback_param;
+		spin_unlock_irqrestore(&chan->desc_lock, flags);
+
+		if (cb)
+			cb(cb_data);
+
+		return;
+	}
+
+	/* submit pending list; callback for each desc; free desc */
 	spin_lock_irqsave(&chan->desc_lock, flags);
 
 	list_for_each_entry_safe(desc, _desc, &chan->chain_running, node) {

@@ -886,12 +994,14 @@ static int mmp_pdma_probe(struct platform_device *op)
 
 	dma_cap_set(DMA_SLAVE, pdev->device.cap_mask);
 	dma_cap_set(DMA_MEMCPY, pdev->device.cap_mask);
+	dma_cap_set(DMA_CYCLIC, pdev->device.cap_mask);
 	pdev->device.dev = &op->dev;
 	pdev->device.device_alloc_chan_resources = mmp_pdma_alloc_chan_resources;
 	pdev->device.device_free_chan_resources = mmp_pdma_free_chan_resources;
 	pdev->device.device_tx_status = mmp_pdma_tx_status;
 	pdev->device.device_prep_dma_memcpy = mmp_pdma_prep_memcpy;
 	pdev->device.device_prep_slave_sg = mmp_pdma_prep_slave_sg;
+	pdev->device.device_prep_dma_cyclic = mmp_pdma_prep_dma_cyclic;
 	pdev->device.device_issue_pending = mmp_pdma_issue_pending;
 	pdev->device.device_control = mmp_pdma_control;
 	pdev->device.copy_align = PDMA_ALIGNMENT;

index d82a4f6..efb583f 100644
@@ -28,8 +28,8 @@
 #define DALGN		0x00a0
 #define DINT		0x00f0
 #define DDADR		0x0200
-#define DSADR		0x0204
-#define DTADR		0x0208
+#define DSADR(n)	(0x0204 + ((n) << 4))
+#define DTADR(n)	(0x0208 + ((n) << 4))
 #define DCMD		0x020c
 
 #define DCSR_RUN	(1 << 31)	/* Run Bit (read / write) */

@@ -741,6 +741,78 @@ static int mmp_pdma_control(struct dma_chan *dchan, enum dma_ctrl_cmd cmd,
 	return ret;
 }
 
+static unsigned int mmp_pdma_residue(struct mmp_pdma_chan *chan,
+				     dma_cookie_t cookie)
+{
+	struct mmp_pdma_desc_sw *sw;
+	u32 curr, residue = 0;
+	bool passed = false;
+	bool cyclic = chan->cyclic_first != NULL;
+
+	/*
+	 * If the channel does not have a phy pointer anymore, it has already
+	 * been completed. Therefore, its residue is 0.
+	 */
+	if (!chan->phy)
+		return 0;
+
+	if (chan->dir == DMA_DEV_TO_MEM)
+		curr = readl(chan->phy->base + DTADR(chan->phy->idx));
+	else
+		curr = readl(chan->phy->base + DSADR(chan->phy->idx));
+
+	list_for_each_entry(sw, &chan->chain_running, node) {
+		u32 start, end, len;
+
+		if (chan->dir == DMA_DEV_TO_MEM)
+			start = sw->desc.dtadr;
+		else
+			start = sw->desc.dsadr;
+
+		len = sw->desc.dcmd & DCMD_LENGTH;
+		end = start + len;
+
+		/*
+		 * 'passed' will be latched once we found the descriptor which
+		 * lies inside the boundaries of the curr pointer. All
+		 * descriptors that occur in the list _after_ we found that
+		 * partially handled descriptor are still to be processed and
+		 * are hence added to the residual bytes counter.
+		 */
+		if (passed) {
+			residue += len;
+		} else if (curr >= start && curr <= end) {
+			residue += end - curr;
+			passed = true;
+		}
+
+		/*
+		 * Descriptors that have the ENDIRQEN bit set mark the end of a
+		 * transaction chain, and the cookie assigned with it has been
+		 * returned previously from mmp_pdma_tx_submit().
+		 *
+		 * In case we have multiple transactions in the running chain,
+		 * and the cookie does not match the one the user asked us
+		 * about, reset the state variables and start over.
+		 *
+		 * This logic does not apply to cyclic transactions, where all
+		 * descriptors have the ENDIRQEN bit set, and for which we
+		 * can't have multiple transactions on one channel anyway.
+		 */
+		if (!cyclic && (sw->desc.dcmd & DCMD_ENDIRQEN)) {
+			if (sw->async_tx.cookie != cookie) {
+				residue = 0;
+				passed = false;
+			} else {
+				return residue;
+			}
+		}
+	}
+
+	/* We should only get here in case of cyclic transactions */
+	return residue;
+}
+
 static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan,
 			dma_cookie_t cookie, struct dma_tx_state *txstate)
 {

@@ -750,6 +822,7 @@ static enum dma_status mmp_pdma_tx_status(struct dma_chan *dchan,
 
 	spin_lock_irqsave(&chan->desc_lock, flags);
 	ret = dma_cookie_status(dchan, cookie, txstate);
+	txstate->residue = mmp_pdma_residue(chan, cookie);
 	spin_unlock_irqrestore(&chan->desc_lock, flags);
 
 	return ret;

index efb583f..3efde2d 100644
@@ -1068,6 +1068,7 @@ static int mmp_pdma_probe(struct platform_device *op)
 	dma_cap_set(DMA_SLAVE, pdev->device.cap_mask);
 	dma_cap_set(DMA_MEMCPY, pdev->device.cap_mask);
 	dma_cap_set(DMA_CYCLIC, pdev->device.cap_mask);
+	dma_cap_set(DMA_PRIVATE, pdev->device.cap_mask);
 	pdev->device.dev = &op->dev;
 	pdev->device.device_alloc_chan_resources = mmp_pdma_alloc_chan_resources;
 	pdev->device.device_free_chan_resources = mmp_pdma_free_chan_resources;