dmaengine: at_hdmac: Add support for memory to memory sg transfers

This patch adds support for memory to memory scatter-gather transfers.

Changes from V1:
   * Fixed coding style of the multi-line comments.

Changes from V2:
   * Added setup of 'desc->tx_width' that is needed to calculate the
     residue.
Signed-off-by: Torsten Fleischer <torfl6749@gmail.com>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>

drivers/dma/at_hdmac.c

@@ -65,6 +65,21 @@ static void atc_issue_pending(struct dma_chan *chan);
 
 /*----------------------------------------------------------------------*/
 
+static inline unsigned int atc_get_xfer_width(dma_addr_t src, dma_addr_t dst,
+						size_t len)
+{
+	unsigned int width;
+
+	if (!((src | dst  | len) & 3))
+		width = 2;
+	else if (!((src | dst | len) & 1))
+		width = 1;
+	else
+		width = 0;
+
+	return width;
+}
+
 static struct at_desc *atc_first_active(struct at_dma_chan *atchan)
 {
 	return list_first_entry(&atchan->active_list,
@@ -628,16 +643,10 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	 * We can be a lot more clever here, but this should take care
 	 * of the most common optimization.
 	 */
-	if (!((src | dest  | len) & 3)) {
-		ctrla = ATC_SRC_WIDTH_WORD | ATC_DST_WIDTH_WORD;
-		src_width = dst_width = 2;
-	} else if (!((src | dest | len) & 1)) {
-		ctrla = ATC_SRC_WIDTH_HALFWORD | ATC_DST_WIDTH_HALFWORD;
-		src_width = dst_width = 1;
-	} else {
-		ctrla = ATC_SRC_WIDTH_BYTE | ATC_DST_WIDTH_BYTE;
-		src_width = dst_width = 0;
-	}
+	src_width = dst_width = atc_get_xfer_width(src, dest, len);
+
+	ctrla = ATC_SRC_WIDTH(src_width) |
+		ATC_DST_WIDTH(dst_width);
 
 	for (offset = 0; offset < len; offset += xfer_count << src_width) {
 		xfer_count = min_t(size_t, (len - offset) >> src_width,
@@ -821,6 +830,144 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	return NULL;
 }
 
+/**
+ * atc_prep_dma_sg - prepare memory to memory scather-gather operation
+ * @chan: the channel to prepare operation on
+ * @dst_sg: destination scatterlist
+ * @dst_nents: number of destination scatterlist entries
+ * @src_sg: source scatterlist
+ * @src_nents: number of source scatterlist entries
+ * @flags: tx descriptor status flags
+ */
+static struct dma_async_tx_descriptor *
+atc_prep_dma_sg(struct dma_chan *chan,
+		struct scatterlist *dst_sg, unsigned int dst_nents,
+		struct scatterlist *src_sg, unsigned int src_nents,
+		unsigned long flags)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_desc		*desc = NULL;
+	struct at_desc		*first = NULL;
+	struct at_desc		*prev = NULL;
+	unsigned int		src_width;
+	unsigned int		dst_width;
+	size_t			xfer_count;
+	u32			ctrla;
+	u32			ctrlb;
+	size_t			dst_len = 0, src_len = 0;
+	dma_addr_t		dst = 0, src = 0;
+	size_t			len = 0, total_len = 0;
+
+	if (unlikely(dst_nents == 0 || src_nents == 0))
+		return NULL;
+
+	if (unlikely(dst_sg == NULL || src_sg == NULL))
+		return NULL;
+
+	ctrlb =   ATC_DEFAULT_CTRLB | ATC_IEN
+		| ATC_SRC_ADDR_MODE_INCR
+		| ATC_DST_ADDR_MODE_INCR
+		| ATC_FC_MEM2MEM;
+
+	/*
+	 * loop until there is either no more source or no more destination
+	 * scatterlist entry
+	 */
+	while (true) {
+
+		/* prepare the next transfer */
+		if (dst_len == 0) {
+
+			/* no more destination scatterlist entries */
+			if (!dst_sg || !dst_nents)
+				break;
+
+			dst = sg_dma_address(dst_sg);
+			dst_len = sg_dma_len(dst_sg);
+
+			dst_sg = sg_next(dst_sg);
+			dst_nents--;
+		}
+
+		if (src_len == 0) {
+
+			/* no more source scatterlist entries */
+			if (!src_sg || !src_nents)
+				break;
+
+			src = sg_dma_address(src_sg);
+			src_len = sg_dma_len(src_sg);
+
+			src_sg = sg_next(src_sg);
+			src_nents--;
+		}
+
+		len = min_t(size_t, src_len, dst_len);
+		if (len == 0)
+			continue;
+
+		/* take care for the alignment */
+		src_width = dst_width = atc_get_xfer_width(src, dst, len);
+
+		ctrla = ATC_SRC_WIDTH(src_width) |
+			ATC_DST_WIDTH(dst_width);
+
+		/*
+		 * The number of transfers to set up refer to the source width
+		 * that depends on the alignment.
+		 */
+		xfer_count = len >> src_width;
+		if (xfer_count > ATC_BTSIZE_MAX) {
+			xfer_count = ATC_BTSIZE_MAX;
+			len = ATC_BTSIZE_MAX << src_width;
+		}
+
+		/* create the transfer */
+		desc = atc_desc_get(atchan);
+		if (!desc)
+			goto err_desc_get;
+
+		desc->lli.saddr = src;
+		desc->lli.daddr = dst;
+		desc->lli.ctrla = ctrla | xfer_count;
+		desc->lli.ctrlb = ctrlb;
+
+		desc->txd.cookie = 0;
+		desc->len = len;
+
+		/*
+		 * Although we only need the transfer width for the first and
+		 * the last descriptor, its easier to set it to all descriptors.
+		 */
+		desc->tx_width = src_width;
+
+		atc_desc_chain(&first, &prev, desc);
+
+		/* update the lengths and addresses for the next loop cycle */
+		dst_len -= len;
+		src_len -= len;
+		dst += len;
+		src += len;
+
+		total_len += len;
+	}
+
+	/* First descriptor of the chain embedds additional information */
+	first->txd.cookie = -EBUSY;
+	first->total_len = total_len;
+
+	/* set end-of-link to the last link descriptor of list*/
+	set_desc_eol(desc);
+
+	first->txd.flags = flags; /* client is in control of this ack */
+
+	return &first->txd;
+
+err_desc_get:
+	atc_desc_put(atchan, first);
+	return NULL;
+}
+
 /**
  * atc_dma_cyclic_check_values
  * Check for too big/unaligned periods and unaligned DMA buffer
@@ -1421,8 +1568,10 @@ static int __init at_dma_probe(struct platform_device *pdev)
 
 	/* setup platform data for each SoC */
 	dma_cap_set(DMA_MEMCPY, at91sam9rl_config.cap_mask);
+	dma_cap_set(DMA_SG, at91sam9rl_config.cap_mask);
 	dma_cap_set(DMA_MEMCPY, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_SLAVE, at91sam9g45_config.cap_mask);
+	dma_cap_set(DMA_SG, at91sam9g45_config.cap_mask);
 
 	/* get DMA parameters from controller type */
 	plat_dat = at_dma_get_driver_data(pdev);
@@ -1542,11 +1691,15 @@ static int __init at_dma_probe(struct platform_device *pdev)
 		atdma->dma_common.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	}
 
+	if (dma_has_cap(DMA_SG, atdma->dma_common.cap_mask))
+		atdma->dma_common.device_prep_dma_sg = atc_prep_dma_sg;
+
 	dma_writel(atdma, EN, AT_DMA_ENABLE);
 
-	dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s), %d channels\n",
+	dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s%s), %d channels\n",
 	  dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask) ? "cpy " : "",
 	  dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)  ? "slave " : "",
+	  dma_has_cap(DMA_SG, atdma->dma_common.cap_mask)  ? "sg-cpy " : "",
 	  plat_dat->nr_channels);
 
 	dma_async_device_register(&atdma->dma_common);