1 files changed, 208 insertions, 51 deletions

diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 59892126d175..58d406230d89 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -48,6 +48,8 @@
 	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |\
 	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
 
+#define ATC_MAX_DSCR_TRIALS	10
+
 /*
  * Initial number of descriptors to allocate for each channel. This could
  * be increased during dma usage.
@@ -285,28 +287,19 @@ static struct at_desc *atc_get_desc_by_cookie(struct at_dma_chan *atchan,
  *
  * @current_len: the number of bytes left before reading CTRLA
  * @ctrla: the value of CTRLA
- * @desc: the descriptor containing the transfer width
  */
-static inline int atc_calc_bytes_left(int current_len, u32 ctrla,
-					struct at_desc *desc)
+static inline int atc_calc_bytes_left(int current_len, u32 ctrla)
 {
-	return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width);
-}
+	u32 btsize = (ctrla & ATC_BTSIZE_MAX);
+	u32 src_width = ATC_REG_TO_SRC_WIDTH(ctrla);
 
-/**
- * atc_calc_bytes_left_from_reg - calculates the number of bytes left according
- * to the current value of CTRLA.
- *
- * @current_len: the number of bytes left before reading CTRLA
- * @atchan: the channel to read CTRLA for
- * @desc: the descriptor containing the transfer width
- */
-static inline int atc_calc_bytes_left_from_reg(int current_len,
-			struct at_dma_chan *atchan, struct at_desc *desc)
-{
-	u32 ctrla = channel_readl(atchan, CTRLA);
-
-	return atc_calc_bytes_left(current_len, ctrla, desc);
+	/*
+	 * According to the datasheet, when reading the Control A Register
+	 * (ctrla), the Buffer Transfer Size (btsize) bitfield refers to the
+	 * number of transfers completed on the Source Interface.
+	 * So btsize is always a number of source width transfers.
+	 */
+	return current_len - (btsize << src_width);
 }
 
 /**
@@ -320,7 +313,7 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 	struct at_desc *desc_first = atc_first_active(atchan);
 	struct at_desc *desc;
 	int ret;
-	u32 ctrla, dscr;
+	u32 ctrla, dscr, trials;
 
 	/*
 	 * If the cookie doesn't match to the currently running transfer then
@@ -346,15 +339,82 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 		 * the channel's DSCR register and compare it against the value
 		 * of the hardware linked list structure of each child
 		 * descriptor.
+		 *
+		 * The CTRLA register provides us with the amount of data
+		 * already read from the source for the current child
+		 * descriptor. So we can compute a more accurate residue by also
+		 * removing the number of bytes corresponding to this amount of
+		 * data.
+		 *
+		 * However, the DSCR and CTRLA registers cannot be read both
+		 * atomically. Hence a race condition may occur: the first read
+		 * register may refer to one child descriptor whereas the second
+		 * read may refer to a later child descriptor in the list
+		 * because of the DMA transfer progression inbetween the two
+		 * reads.
+		 *
+		 * One solution could have been to pause the DMA transfer, read
+		 * the DSCR and CTRLA then resume the DMA transfer. Nonetheless,
+		 * this approach presents some drawbacks:
+		 * - If the DMA transfer is paused, RX overruns or TX underruns
+		 *   are more likey to occur depending on the system latency.
+		 *   Taking the USART driver as an example, it uses a cyclic DMA
+		 *   transfer to read data from the Receive Holding Register
+		 *   (RHR) to avoid RX overruns since the RHR is not protected
+		 *   by any FIFO on most Atmel SoCs. So pausing the DMA transfer
+		 *   to compute the residue would break the USART driver design.
+		 * - The atc_pause() function masks interrupts but we'd rather
+		 *   avoid to do so for system latency purpose.
+		 *
+		 * Then we'd rather use another solution: the DSCR is read a
+		 * first time, the CTRLA is read in turn, next the DSCR is read
+		 * a second time. If the two consecutive read values of the DSCR
+		 * are the same then we assume both refers to the very same
+		 * child descriptor as well as the CTRLA value read inbetween
+		 * does. For cyclic tranfers, the assumption is that a full loop
+		 * is "not so fast".
+		 * If the two DSCR values are different, we read again the CTRLA
+		 * then the DSCR till two consecutive read values from DSCR are
+		 * equal or till the maxium trials is reach.
+		 * This algorithm is very unlikely not to find a stable value for
+		 * DSCR.
 		 */
 
-		ctrla = channel_readl(atchan, CTRLA);
-		rmb(); /* ensure CTRLA is read before DSCR */
 		dscr = channel_readl(atchan, DSCR);
+		rmb(); /* ensure DSCR is read before CTRLA */
+		ctrla = channel_readl(atchan, CTRLA);
+		for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) {
+			u32 new_dscr;
+
+			rmb(); /* ensure DSCR is read after CTRLA */
+			new_dscr = channel_readl(atchan, DSCR);
+
+			/*
+			 * If the DSCR register value has not changed inside the
+			 * DMA controller since the previous read, we assume
+			 * that both the dscr and ctrla values refers to the
+			 * very same descriptor.
+			 */
+			if (likely(new_dscr == dscr))
+				break;
+
+			/*
+			 * DSCR has changed inside the DMA controller, so the
+			 * previouly read value of CTRLA may refer to an already
+			 * processed descriptor hence could be outdated.
+			 * We need to update ctrla to match the current
+			 * descriptor.
+			 */
+			dscr = new_dscr;
+			rmb(); /* ensure DSCR is read before CTRLA */
+			ctrla = channel_readl(atchan, CTRLA);
+		}
+		if (unlikely(trials >= ATC_MAX_DSCR_TRIALS))
+			return -ETIMEDOUT;
 
 		/* for the first descriptor we can be more accurate */
 		if (desc_first->lli.dscr == dscr)
-			return atc_calc_bytes_left(ret, ctrla, desc_first);
+			return atc_calc_bytes_left(ret, ctrla);
 
 		ret -= desc_first->len;
 		list_for_each_entry(desc, &desc_first->tx_list, desc_node) {
@@ -365,16 +425,14 @@ static int atc_get_bytes_left(struct dma_chan *chan, dma_cookie_t cookie)
 		}
 
 		/*
-		 * For the last descriptor in the chain we can calculate
+		 * For the current descriptor in the chain we can calculate
 		 * the remaining bytes using the channel's register.
-		 * Note that the transfer width of the first and last
-		 * descriptor may differ.
 		 */
-		if (!desc->lli.dscr)
-			ret = atc_calc_bytes_left_from_reg(ret, atchan, desc);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	} else {
 		/* single transfer */
-		ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first);
+		ctrla = channel_readl(atchan, CTRLA);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	}
 
 	return ret;
@@ -390,6 +448,7 @@ static void
 atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 {
 	struct dma_async_tx_descriptor	*txd = &desc->txd;
+	struct at_dma			*atdma = to_at_dma(atchan->chan_common.device);
 
 	dev_vdbg(chan2dev(&atchan->chan_common),
 		"descriptor %u complete\n", txd->cookie);
@@ -398,6 +457,13 @@ atc_chain_complete(struct at_dma_chan *atchan, struct at_desc *desc)
 	if (!atc_chan_is_cyclic(atchan))
 		dma_cookie_complete(txd);
 
+	/* If the transfer was a memset, free our temporary buffer */
+	if (desc->memset) {
+		dma_pool_free(atdma->memset_pool, desc->memset_vaddr,
+			      desc->memset_paddr);
+		desc->memset = false;
+	}
+
 	/* move children to free_list */
 	list_splice_init(&desc->tx_list, &atchan->free_list);
 	/* move myself to free_list */
@@ -659,14 +725,14 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 	size_t			len = 0;
 	int			i;
 
+	if (unlikely(!xt || xt->numf != 1 || !xt->frame_size))
+		return NULL;
+
 	dev_info(chan2dev(chan),
 		 "%s: src=0x%08x, dest=0x%08x, numf=%d, frame_size=%d, flags=0x%lx\n",
 		__func__, xt->src_start, xt->dst_start, xt->numf,
 		xt->frame_size, flags);
 
-	if (unlikely(!xt || xt->numf != 1 || !xt->frame_size))
-		return NULL;
-
 	/*
 	 * The controller can only "skip" X bytes every Y bytes, so we
 	 * need to make sure we are given a template that fit that
@@ -726,7 +792,6 @@ atc_prep_dma_interleaved(struct dma_chan *chan,
 
 	desc->txd.cookie = -EBUSY;
 	desc->total_len = desc->len = len;
-	desc->tx_width = dwidth;
 
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
@@ -804,10 +869,6 @@ atc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 	first->txd.cookie = -EBUSY;
 	first->total_len = len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = src_width;
-	prev->tx_width = src_width;
-
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
 
@@ -820,6 +881,93 @@ err_desc_get:
 	return NULL;
 }
 
+/**
+ * atc_prep_dma_memset - prepare a memcpy operation
+ * @chan: the channel to prepare operation on
+ * @dest: operation virtual destination address
+ * @value: value to set memory buffer to
+ * @len: operation length
+ * @flags: tx descriptor status flags
+ */
+static struct dma_async_tx_descriptor *
+atc_prep_dma_memset(struct dma_chan *chan, dma_addr_t dest, int value,
+		    size_t len, unsigned long flags)
+{
+	struct at_dma_chan	*atchan = to_at_dma_chan(chan);
+	struct at_dma		*atdma = to_at_dma(chan->device);
+	struct at_desc		*desc = NULL;
+	size_t			xfer_count;
+	u32			ctrla;
+	u32			ctrlb;
+
+	dev_vdbg(chan2dev(chan), "%s: d0x%x v0x%x l0x%zx f0x%lx\n", __func__,
+		dest, value, len, flags);
+
+	if (unlikely(!len)) {
+		dev_dbg(chan2dev(chan), "%s: length is zero!\n", __func__);
+		return NULL;
+	}
+
+	if (!is_dma_fill_aligned(chan->device, dest, 0, len)) {
+		dev_dbg(chan2dev(chan), "%s: buffer is not aligned\n",
+			__func__);
+		return NULL;
+	}
+
+	xfer_count = len >> 2;
+	if (xfer_count > ATC_BTSIZE_MAX) {
+		dev_err(chan2dev(chan), "%s: buffer is too big\n",
+			__func__);
+		return NULL;
+	}
+
+	ctrlb =   ATC_DEFAULT_CTRLB | ATC_IEN
+		| ATC_SRC_ADDR_MODE_FIXED
+		| ATC_DST_ADDR_MODE_INCR
+		| ATC_FC_MEM2MEM;
+
+	ctrla = ATC_SRC_WIDTH(2) |
+		ATC_DST_WIDTH(2);
+
+	desc = atc_desc_get(atchan);
+	if (!desc) {
+		dev_err(chan2dev(chan), "%s: can't get a descriptor\n",
+			__func__);
+		return NULL;
+	}
+
+	desc->memset_vaddr = dma_pool_alloc(atdma->memset_pool, GFP_ATOMIC,
+					    &desc->memset_paddr);
+	if (!desc->memset_vaddr) {
+		dev_err(chan2dev(chan), "%s: couldn't allocate buffer\n",
+			__func__);
+		goto err_put_desc;
+	}
+
+	*desc->memset_vaddr = value;
+	desc->memset = true;
+
+	desc->lli.saddr = desc->memset_paddr;
+	desc->lli.daddr = dest;
+	desc->lli.ctrla = ctrla | xfer_count;
+	desc->lli.ctrlb = ctrlb;
+
+	desc->txd.cookie = -EBUSY;
+	desc->len = len;
+	desc->total_len = len;
+
+	/* set end-of-link on the descriptor */
+	set_desc_eol(desc);
+
+	desc->txd.flags = flags;
+
+	return &desc->txd;
+
+err_put_desc:
+	atc_desc_put(atchan, desc);
+	return NULL;
+}
+
 
 /**
  * atc_prep_slave_sg - prepare descriptors for a DMA_SLAVE transaction
@@ -956,10 +1104,6 @@ atc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 	first->txd.cookie = -EBUSY;
 	first->total_len = total_len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = reg_width;
-	prev->tx_width = reg_width;
-
 	/* first link descriptor of list is responsible of flags */
 	first->txd.flags = flags; /* client is in control of this ack */
 
@@ -1077,12 +1221,6 @@ atc_prep_dma_sg(struct dma_chan *chan,
 		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 */
@@ -1256,7 +1394,6 @@ atc_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr, size_t buf_len,
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
 	first->total_len = buf_len;
-	first->tx_width = reg_width;
 
 	return &first->txd;
 
@@ -1713,6 +1850,8 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	dma_cap_set(DMA_SG, at91sam9rl_config.cap_mask);
 	dma_cap_set(DMA_INTERLEAVE, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_MEMCPY, at91sam9g45_config.cap_mask);
+	dma_cap_set(DMA_MEMSET, at91sam9g45_config.cap_mask);
+	dma_cap_set(DMA_PRIVATE, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_SLAVE, at91sam9g45_config.cap_mask);
 	dma_cap_set(DMA_SG, at91sam9g45_config.cap_mask);
 
@@ -1776,7 +1915,16 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	if (!atdma->dma_desc_pool) {
 		dev_err(&pdev->dev, "No memory for descriptors dma pool\n");
 		err = -ENOMEM;
-		goto err_pool_create;
+		goto err_desc_pool_create;
+	}
+
+	/* create a pool of consistent memory blocks for memset blocks */
+	atdma->memset_pool = dma_pool_create("at_hdmac_memset_pool",
+					     &pdev->dev, sizeof(int), 4, 0);
+	if (!atdma->memset_pool) {
+		dev_err(&pdev->dev, "No memory for memset dma pool\n");
+		err = -ENOMEM;
+		goto err_memset_pool_create;
 	}
 
 	/* clear any pending interrupt */
@@ -1822,6 +1970,11 @@ static int __init at_dma_probe(struct platform_device *pdev)
 	if (dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask))
 		atdma->dma_common.device_prep_dma_memcpy = atc_prep_dma_memcpy;
 
+	if (dma_has_cap(DMA_MEMSET, atdma->dma_common.cap_mask)) {
+		atdma->dma_common.device_prep_dma_memset = atc_prep_dma_memset;
+		atdma->dma_common.fill_align = DMAENGINE_ALIGN_4_BYTES;
+	}
+
 	if (dma_has_cap(DMA_SLAVE, atdma->dma_common.cap_mask)) {
 		atdma->dma_common.device_prep_slave_sg = atc_prep_slave_sg;
 		/* controller can do slave DMA: can trigger cyclic transfers */
@@ -1842,8 +1995,9 @@ static int __init at_dma_probe(struct platform_device *pdev)
 
 	dma_writel(atdma, EN, AT_DMA_ENABLE);
 
-	dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s%s), %d channels\n",
+	dev_info(&pdev->dev, "Atmel AHB DMA Controller ( %s%s%s%s), %d channels\n",
 	  dma_has_cap(DMA_MEMCPY, atdma->dma_common.cap_mask) ? "cpy " : "",
+	  dma_has_cap(DMA_MEMSET, atdma->dma_common.cap_mask) ? "set " : "",
 	  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);
@@ -1868,8 +2022,10 @@ static int __init at_dma_probe(struct platform_device *pdev)
 
 err_of_dma_controller_register:
 	dma_async_device_unregister(&atdma->dma_common);
+	dma_pool_destroy(atdma->memset_pool);
+err_memset_pool_create:
 	dma_pool_destroy(atdma->dma_desc_pool);
-err_pool_create:
+err_desc_pool_create:
 	free_irq(platform_get_irq(pdev, 0), atdma);
 err_irq:
 	clk_disable_unprepare(atdma->clk);
@@ -1894,6 +2050,7 @@ static int at_dma_remove(struct platform_device *pdev)
 	at_dma_off(atdma);
 	dma_async_device_unregister(&atdma->dma_common);
 
+	dma_pool_destroy(atdma->memset_pool);
 	dma_pool_destroy(atdma->dma_desc_pool);
 	free_irq(platform_get_irq(pdev, 0), atdma);