Merge tag 'v4.4.12' into toradex_vf_4.4-next

This is the 4.4.12 stable release

5 files changed, 90 insertions, 30 deletions

diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index fa00f3a186da..02f9aa4ebe05 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -176,6 +176,7 @@
 #define AT_XDMAC_MAX_CHAN	0x20
 #define AT_XDMAC_MAX_CSIZE	16	/* 16 data */
 #define AT_XDMAC_MAX_DWIDTH	8	/* 64 bits */
+#define AT_XDMAC_RESIDUE_MAX_RETRIES	5
 
 #define AT_XDMAC_DMA_BUSWIDTHS\
 	(BIT(DMA_SLAVE_BUSWIDTH_UNDEFINED) |\
@@ -1383,8 +1384,8 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 	struct at_xdmac_desc	*desc, *_desc;
 	struct list_head	*descs_list;
 	enum dma_status		ret;
-	int			residue;
-	u32			cur_nda, mask, value;
+	int			residue, retry;
+	u32			cur_nda, check_nda, cur_ubc, mask, value;
 	u8			dwidth = 0;
 	unsigned long		flags;
 
@@ -1421,7 +1422,42 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 			cpu_relax();
 	}
 
+	/*
+	 * When processing the residue, we need to read two registers but we
+	 * can't do it in an atomic way. AT_XDMAC_CNDA is used to find where
+	 * we stand in the descriptor list and AT_XDMAC_CUBC is used
+	 * to know how many data are remaining for the current descriptor.
+	 * Since the dma channel is not paused to not loose data, between the
+	 * AT_XDMAC_CNDA and AT_XDMAC_CUBC read, we may have change of
+	 * descriptor.
+	 * For that reason, after reading AT_XDMAC_CUBC, we check if we are
+	 * still using the same descriptor by reading a second time
+	 * AT_XDMAC_CNDA. If AT_XDMAC_CNDA has changed, it means we have to
+	 * read again AT_XDMAC_CUBC.
+	 * Memory barriers are used to ensure the read order of the registers.
+	 * A max number of retries is set because unlikely it can never ends if
+	 * we are transferring a lot of data with small buffers.
+	 */
 	cur_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+	rmb();
+	cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+	for (retry = 0; retry < AT_XDMAC_RESIDUE_MAX_RETRIES; retry++) {
+		rmb();
+		check_nda = at_xdmac_chan_read(atchan, AT_XDMAC_CNDA) & 0xfffffffc;
+
+		if (likely(cur_nda == check_nda))
+			break;
+
+		cur_nda = check_nda;
+		rmb();
+		cur_ubc = at_xdmac_chan_read(atchan, AT_XDMAC_CUBC);
+	}
+
+	if (unlikely(retry >= AT_XDMAC_RESIDUE_MAX_RETRIES)) {
+		ret = DMA_ERROR;
+		goto spin_unlock;
+	}
+
 	/*
 	 * Remove size of all microblocks already transferred and the current
 	 * one. Then add the remaining size to transfer of the current
@@ -1434,7 +1470,7 @@ at_xdmac_tx_status(struct dma_chan *chan, dma_cookie_t cookie,
 		if ((desc->lld.mbr_nda & 0xfffffffc) == cur_nda)
 			break;
 	}
-	residue += at_xdmac_chan_read(atchan, AT_XDMAC_CUBC) << dwidth;
+	residue += cur_ubc << dwidth;
 
 	dma_set_residue(txstate, residue);
 
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 4f099ea29f83..c66133b5e852 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -130,26 +130,14 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 static void dwc_initialize(struct dw_dma_chan *dwc)
 {
 	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
-	struct dw_dma_slave *dws = dwc->chan.private;
 	u32 cfghi = DWC_CFGH_FIFO_MODE;
 	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
 
 	if (dwc->initialized == true)
 		return;
 
-	if (dws) {
-		/*
-		 * We need controller-specific data to set up slave
-		 * transfers.
-		 */
-		BUG_ON(!dws->dma_dev || dws->dma_dev != dw->dma.dev);
-
-		cfghi |= DWC_CFGH_DST_PER(dws->dst_id);
-		cfghi |= DWC_CFGH_SRC_PER(dws->src_id);
-	} else {
-		cfghi |= DWC_CFGH_DST_PER(dwc->dst_id);
-		cfghi |= DWC_CFGH_SRC_PER(dwc->src_id);
-	}
+	cfghi |= DWC_CFGH_DST_PER(dwc->dst_id);
+	cfghi |= DWC_CFGH_SRC_PER(dwc->src_id);
 
 	channel_writel(dwc, CFG_LO, cfglo);
 	channel_writel(dwc, CFG_HI, cfghi);
@@ -936,7 +924,7 @@ bool dw_dma_filter(struct dma_chan *chan, void *param)
 	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
 	struct dw_dma_slave *dws = param;
 
-	if (!dws || dws->dma_dev != chan->device->dev)
+	if (dws->dma_dev != chan->device->dev)
 		return false;
 
 	/* We have to copy data since dws can be temporary storage */
@@ -1160,6 +1148,14 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 	 * doesn't mean what you think it means), and status writeback.
 	 */
 
+	/*
+	 * We need controller-specific data to set up slave transfers.
+	 */
+	if (chan->private && !dw_dma_filter(chan, chan->private)) {
+		dev_warn(chan2dev(chan), "Wrong controller-specific data\n");
+		return -EINVAL;
+	}
+
 	/* Enable controller here if needed */
 	if (!dw->in_use)
 		dw_dma_on(dw);
@@ -1221,6 +1217,14 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	spin_lock_irqsave(&dwc->lock, flags);
 	list_splice_init(&dwc->free_list, &list);
 	dwc->descs_allocated = 0;
+
+	/* Clear custom channel configuration */
+	dwc->src_id = 0;
+	dwc->dst_id = 0;
+
+	dwc->src_master = 0;
+	dwc->dst_master = 0;
+
 	dwc->initialized = false;
 
 	/* Disable interrupts */
diff --git a/drivers/dma/hsu/hsu.c b/drivers/dma/hsu/hsu.c
index 823ad728aecf..efc02b98e6ba 100644
--- a/drivers/dma/hsu/hsu.c
+++ b/drivers/dma/hsu/hsu.c
@@ -135,7 +135,7 @@ static u32 hsu_dma_chan_get_sr(struct hsu_dma_chan *hsuc)
 	sr = hsu_chan_readl(hsuc, HSU_CH_SR);
 	spin_unlock_irqrestore(&hsuc->vchan.lock, flags);
 
-	return sr;
+	return sr & ~(HSU_CH_SR_DESCE_ANY | HSU_CH_SR_CDESC_ANY);
 }
 
 irqreturn_t hsu_dma_irq(struct hsu_dma_chip *chip, unsigned short nr)
diff --git a/drivers/dma/hsu/hsu.h b/drivers/dma/hsu/hsu.h
index f06579c6d548..26da2865b025 100644
--- a/drivers/dma/hsu/hsu.h
+++ b/drivers/dma/hsu/hsu.h
@@ -41,6 +41,9 @@
 #define HSU_CH_SR_DESCTO(x)	BIT(8 + (x))
 #define HSU_CH_SR_DESCTO_ANY	(BIT(11) | BIT(10) | BIT(9) | BIT(8))
 #define HSU_CH_SR_CHE		BIT(15)
+#define HSU_CH_SR_DESCE(x)	BIT(16 + (x))
+#define HSU_CH_SR_DESCE_ANY	(BIT(19) | BIT(18) | BIT(17) | BIT(16))
+#define HSU_CH_SR_CDESC_ANY	(BIT(31) | BIT(30))
 
 /* Bits in HSU_CH_CR */
 #define HSU_CH_CR_CHA		BIT(0)
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index a59061e4221a..55f5d33f6dc7 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -122,6 +122,7 @@ struct pxad_chan {
 struct pxad_device {
 	struct dma_device		slave;
 	int				nr_chans;
+	int				nr_requestors;
 	void __iomem			*base;
 	struct pxad_phy			*phys;
 	spinlock_t			phy_lock;	/* Phy association */
@@ -473,7 +474,7 @@ static void pxad_free_phy(struct pxad_chan *chan)
 		return;
 
 	/* clear the channel mapping in DRCMR */
-	if (chan->drcmr <= DRCMR_CHLNUM) {
+	if (chan->drcmr <= pdev->nr_requestors) {
 		reg = pxad_drcmr(chan->drcmr);
 		writel_relaxed(0, chan->phy->base + reg);
 	}
@@ -509,6 +510,7 @@ static bool is_running_chan_misaligned(struct pxad_chan *chan)
 
 static void phy_enable(struct pxad_phy *phy, bool misaligned)
 {
+	struct pxad_device *pdev;
 	u32 reg, dalgn;
 
 	if (!phy->vchan)
@@ -518,7 +520,8 @@ static void phy_enable(struct pxad_phy *phy, bool misaligned)
 		"%s(); phy=%p(%d) misaligned=%d\n", __func__,
 		phy, phy->idx, misaligned);
 
-	if (phy->vchan->drcmr <= DRCMR_CHLNUM) {
+	pdev = to_pxad_dev(phy->vchan->vc.chan.device);
+	if (phy->vchan->drcmr <= pdev->nr_requestors) {
 		reg = pxad_drcmr(phy->vchan->drcmr);
 		writel_relaxed(DRCMR_MAPVLD | phy->idx, phy->base + reg);
 	}
@@ -914,6 +917,7 @@ static void pxad_get_config(struct pxad_chan *chan,
 {
 	u32 maxburst = 0, dev_addr = 0;
 	enum dma_slave_buswidth width = DMA_SLAVE_BUSWIDTH_UNDEFINED;
+	struct pxad_device *pdev = to_pxad_dev(chan->vc.chan.device);
 
 	*dcmd = 0;
 	if (dir == DMA_DEV_TO_MEM) {
@@ -922,7 +926,7 @@ static void pxad_get_config(struct pxad_chan *chan,
 		dev_addr = chan->cfg.src_addr;
 		*dev_src = dev_addr;
 		*dcmd |= PXA_DCMD_INCTRGADDR;
-		if (chan->drcmr <= DRCMR_CHLNUM)
+		if (chan->drcmr <= pdev->nr_requestors)
 			*dcmd |= PXA_DCMD_FLOWSRC;
 	}
 	if (dir == DMA_MEM_TO_DEV) {
@@ -931,7 +935,7 @@ static void pxad_get_config(struct pxad_chan *chan,
 		dev_addr = chan->cfg.dst_addr;
 		*dev_dst = dev_addr;
 		*dcmd |= PXA_DCMD_INCSRCADDR;
-		if (chan->drcmr <= DRCMR_CHLNUM)
+		if (chan->drcmr <= pdev->nr_requestors)
 			*dcmd |= PXA_DCMD_FLOWTRG;
 	}
 	if (dir == DMA_MEM_TO_MEM)
@@ -1341,13 +1345,15 @@ static struct dma_chan *pxad_dma_xlate(struct of_phandle_args *dma_spec,
 
 static int pxad_init_dmadev(struct platform_device *op,
 			    struct pxad_device *pdev,
-			    unsigned int nr_phy_chans)
+			    unsigned int nr_phy_chans,
+			    unsigned int nr_requestors)
 {
 	int ret;
 	unsigned int i;
 	struct pxad_chan *c;
 
 	pdev->nr_chans = nr_phy_chans;
+	pdev->nr_requestors = nr_requestors;
 	INIT_LIST_HEAD(&pdev->slave.channels);
 	pdev->slave.device_alloc_chan_resources = pxad_alloc_chan_resources;
 	pdev->slave.device_free_chan_resources = pxad_free_chan_resources;
@@ -1382,7 +1388,7 @@ static int pxad_probe(struct platform_device *op)
 	const struct of_device_id *of_id;
 	struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev);
 	struct resource *iores;
-	int ret, dma_channels = 0;
+	int ret, dma_channels = 0, nb_requestors = 0;
 	const enum dma_slave_buswidth widths =
 		DMA_SLAVE_BUSWIDTH_1_BYTE   | DMA_SLAVE_BUSWIDTH_2_BYTES |
 		DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -1399,13 +1405,23 @@ static int pxad_probe(struct platform_device *op)
 		return PTR_ERR(pdev->base);
 
 	of_id = of_match_device(pxad_dt_ids, &op->dev);
-	if (of_id)
+	if (of_id) {
 		of_property_read_u32(op->dev.of_node, "#dma-channels",
 				     &dma_channels);
-	else if (pdata && pdata->dma_channels)
+		ret = of_property_read_u32(op->dev.of_node, "#dma-requests",
+					   &nb_requestors);
+		if (ret) {
+			dev_warn(pdev->slave.dev,
+				 "#dma-requests set to default 32 as missing in OF: %d",
+				 ret);
+			nb_requestors = 32;
+		};
+	} else if (pdata && pdata->dma_channels) {
 		dma_channels = pdata->dma_channels;
-	else
+		nb_requestors = pdata->nb_requestors;
+	} else {
 		dma_channels = 32;	/* default 32 channel */
+	}
 
 	dma_cap_set(DMA_SLAVE, pdev->slave.cap_mask);
 	dma_cap_set(DMA_MEMCPY, pdev->slave.cap_mask);
@@ -1422,7 +1438,7 @@ static int pxad_probe(struct platform_device *op)
 	pdev->slave.residue_granularity = DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
 
 	pdev->slave.dev = &op->dev;
-	ret = pxad_init_dmadev(op, pdev, dma_channels);
+	ret = pxad_init_dmadev(op, pdev, dma_channels, nb_requestors);
 	if (ret) {
 		dev_err(pdev->slave.dev, "unable to register\n");
 		return ret;
@@ -1441,7 +1457,8 @@ static int pxad_probe(struct platform_device *op)
 
 	platform_set_drvdata(op, pdev);
 	pxad_init_debugfs(pdev);
-	dev_info(pdev->slave.dev, "initialized %d channels\n", dma_channels);
+	dev_info(pdev->slave.dev, "initialized %d channels on %d requestors\n",
+		 dma_channels, nb_requestors);
 	return 0;
 }