[PATCH V2 17/20] dmaengine/amba-pl08x: Pass flow controller information with slave channel data

[Viresh Kumar <viresh.kumar@st.com>]

At least, on SPEAr platforms there is one peripheral, JPEG, which can be flow
controller for DMA transfer. Currently DMA controller driver didn't support
peripheral flow controller configurations.

This patch adds device_fc field in struct pl08x_channel_data, which will be used
only for slave transfers and is not used in case of mem2mem transfers.

Signed-off-by: Viresh Kumar <viresh.kumar@st.com>
---
 drivers/dma/amba-pl08x.c   |   61 ++++++++++++++++++++++++++++++++++++++------
 include/linux/amba/pl08x.h |    4 +++
 2 files changed, 57 insertions(+), 8 deletions(-)

diff --git a/drivers/dma/amba-pl08x.c b/drivers/dma/amba-pl08x.c
index c969309..d573dc2 100644
--- a/drivers/dma/amba-pl08x.c
+++ b/drivers/dma/amba-pl08x.c
@@ -66,11 +66,6 @@
  *    after the final transfer signalled by LBREQ or LSREQ.  The DMAC
  *    will then move to the next LLI entry.
  *
- * Only the former works sanely with scatter lists, so we only implement
- * the DMAC flow control method.  However, peripherals which use the LBREQ
- * and LSREQ signals (eg, MMCI) are unable to use this mode, which through
- * these hardware restrictions prevents them from using scatter DMA.
- *
  * Global TODO:
  * - Break out common code from arch/arm/mach-s3c64xx and share
  */
@@ -615,6 +610,49 @@ static int pl08x_fill_llis_for_desc(struct pl08x_driver_data *pl08x,
 		 sbus == &bd.srcbus ? "src" : "dst");
 
 	/*
+	 * Zero length is only allowed if all these requirements are met:
+	 * - flow controller is peripheral.
+	 * - src.addr is aligned to src.width
+	 * - dst.addr is aligned to dst.width
+	 *
+	 * sg_len == 1 should be true, as there can be two cases here:
+	 * - Memory addresses are contiguous and are not scattered. Here, Only
+	 * one sg will be passed by user driver, with memory address and zero
+	 * length. We pass this to controller and after the transfer it will
+	 * receive the last burst request from peripheral and so transfer
+	 * finishes.
+	 *
+	 * - Memory addresses are scattered and are not contiguous. Here,
+	 * Obviously as DMA controller doesn't know when a lli's transfer gets
+	 * over, it can't load next lli. So in this case, there has to be an
+	 * assumption that only one lli is supported. Thus, we can't have
+	 * scattered addresses.
+	 */
+	if (!bd.remainder) {
+		u32 fc = (txd->ccfg & PL080_CONFIG_FLOW_CONTROL_MASK) >>
+			PL080_CONFIG_FLOW_CONTROL_SHIFT;
+		if (!((fc >= PL080_FLOW_SRC2DST_DST) &&
+					(fc <= PL080_FLOW_SRC2DST_SRC))) {
+			dev_err(&pl08x->adev->dev, "%s sg len can't be zero",
+				__func__);
+			return 0;
+		}
+
+		if ((bd.srcbus.addr % bd.srcbus.buswidth) ||
+				(bd.srcbus.addr % bd.srcbus.buswidth)) {
+			dev_err(&pl08x->adev->dev,
+				"%s src & dst address must be aligned to src"
+				" & dst width if peripheral is flow controller",
+				__func__);
+			return 0;
+		}
+
+		cctl = pl08x_cctl_bits(cctl, bd.srcbus.buswidth,
+				bd.dstbus.buswidth, 0);
+		pl08x_fill_lli_for_desc(&bd, num_llis++, 0, cctl);
+	}
+
+	/*
 	 * Send byte by byte for following cases
 	 * - Less than a bus width available
 	 * - until master bus is aligned
@@ -1255,7 +1293,7 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 	struct pl08x_dma_chan *plchan = to_pl08x_chan(chan);
 	struct pl08x_driver_data *pl08x = plchan->host;
 	struct pl08x_txd *txd;
-	int ret;
+	int ret, tmp;
 
 	/*
 	 * Current implementation ASSUMES only one sg
@@ -1289,12 +1327,10 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 	txd->len = sgl->length;
 
 	if (direction == DMA_TO_DEVICE) {
-		txd->ccfg |= PL080_FLOW_MEM2PER << PL080_CONFIG_FLOW_CONTROL_SHIFT;
 		txd->cctl = plchan->dst_cctl;
 		txd->src_addr = sgl->dma_address;
 		txd->dst_addr = plchan->dst_addr;
 	} else if (direction == DMA_FROM_DEVICE) {
-		txd->ccfg |= PL080_FLOW_PER2MEM << PL080_CONFIG_FLOW_CONTROL_SHIFT;
 		txd->cctl = plchan->src_cctl;
 		txd->src_addr = plchan->src_addr;
 		txd->dst_addr = sgl->dma_address;
@@ -1304,6 +1340,15 @@ static struct dma_async_tx_descriptor *pl08x_prep_slave_sg(
 		return NULL;
 	}
 
+	if (plchan->cd->device_fc)
+		tmp = (direction == DMA_TO_DEVICE) ? PL080_FLOW_MEM2PER_PER :
+			PL080_FLOW_PER2MEM_PER;
+	else
+		tmp = (direction == DMA_TO_DEVICE) ? PL080_FLOW_MEM2PER :
+			PL080_FLOW_PER2MEM;
+
+	txd->ccfg |= tmp << PL080_CONFIG_FLOW_CONTROL_SHIFT;
+
 	ret = pl08x_prep_channel_resources(plchan, txd);
 	if (ret)
 		return NULL;
diff --git a/include/linux/amba/pl08x.h b/include/linux/amba/pl08x.h
index ecd17f5..a22662c 100644
--- a/include/linux/amba/pl08x.h
+++ b/include/linux/amba/pl08x.h
@@ -47,6 +47,9 @@ enum {
  * @muxval: a number usually used to poke into some mux regiser to
  * mux in the signal to this channel
  * @cctl_opt: default options for the channel control register
+ * @device_fc: Flow Controller Settings for ccfg register. Only valid for slave
+ * channels. Fill with 'true' if peripheral should be flow controller. Direction
+ * will be selected at Runtime.
  * @addr: source/target address in physical memory for this DMA channel,
  * can be the address of a FIFO register for burst requests for example.
  * This can be left undefined if the PrimeCell API is used for configuring
@@ -65,6 +68,7 @@ struct pl08x_channel_data {
 	int max_signal;
 	u32 muxval;
 	u32 cctl;
+	bool device_fc;
 	dma_addr_t addr;
 	bool circular_buffer;
 	bool single;
-- 
1.7.2.2