Merge branch 'topic/intel' into for-linus

4 files changed, 223 insertions, 67 deletions

diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index e5adf5d1c34f..e500950dad82 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -138,16 +138,32 @@ static void dwc_desc_put(struct dw_dma_chan *dwc, struct dw_desc *desc)
 	dwc->descs_allocated--;
 }
 
-static void dwc_initialize(struct dw_dma_chan *dwc)
+static void dwc_initialize_chan_idma32(struct dw_dma_chan *dwc)
+{
+	u32 cfghi = 0;
+	u32 cfglo = 0;
+
+	/* Set default burst alignment */
+	cfglo |= IDMA32C_CFGL_DST_BURST_ALIGN | IDMA32C_CFGL_SRC_BURST_ALIGN;
+
+	/* Low 4 bits of the request lines */
+	cfghi |= IDMA32C_CFGH_DST_PER(dwc->dws.dst_id & 0xf);
+	cfghi |= IDMA32C_CFGH_SRC_PER(dwc->dws.src_id & 0xf);
+
+	/* Request line extension (2 bits) */
+	cfghi |= IDMA32C_CFGH_DST_PER_EXT(dwc->dws.dst_id >> 4 & 0x3);
+	cfghi |= IDMA32C_CFGH_SRC_PER_EXT(dwc->dws.src_id >> 4 & 0x3);
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void dwc_initialize_chan_dw(struct dw_dma_chan *dwc)
 {
-	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 	u32 cfghi = DWC_CFGH_FIFO_MODE;
 	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
 	bool hs_polarity = dwc->dws.hs_polarity;
 
-	if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags))
-		return;
-
 	cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id);
 	cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id);
 
@@ -156,6 +172,19 @@ static void dwc_initialize(struct dw_dma_chan *dwc)
 
 	channel_writel(dwc, CFG_LO, cfglo);
 	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void dwc_initialize(struct dw_dma_chan *dwc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+
+	if (test_bit(DW_DMA_IS_INITIALIZED, &dwc->flags))
+		return;
+
+	if (dw->pdata->is_idma32)
+		dwc_initialize_chan_idma32(dwc);
+	else
+		dwc_initialize_chan_dw(dwc);
 
 	/* Enable interrupts */
 	channel_set_bit(dw, MASK.XFER, dwc->mask);
@@ -184,6 +213,37 @@ static inline void dwc_chan_disable(struct dw_dma *dw, struct dw_dma_chan *dwc)
 		cpu_relax();
 }
 
+static u32 bytes2block(struct dw_dma_chan *dwc, size_t bytes,
+			  unsigned int width, size_t *len)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	u32 block;
+
+	/* Always in bytes for iDMA 32-bit */
+	if (dw->pdata->is_idma32)
+		width = 0;
+
+	if ((bytes >> width) > dwc->block_size) {
+		block = dwc->block_size;
+		*len = block << width;
+	} else {
+		block = bytes >> width;
+		*len = bytes;
+	}
+
+	return block;
+}
+
+static size_t block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+
+	if (dw->pdata->is_idma32)
+		return IDMA32C_CTLH_BLOCK_TS(block);
+
+	return DWC_CTLH_BLOCK_TS(block) << width;
+}
+
 /*----------------------------------------------------------------------*/
 
 /* Perform single block transfer */
@@ -332,7 +392,7 @@ static inline u32 dwc_get_sent(struct dw_dma_chan *dwc)
 	u32 ctlhi = channel_readl(dwc, CTL_HI);
 	u32 ctllo = channel_readl(dwc, CTL_LO);
 
-	return (ctlhi & DWC_CTLH_BLOCK_TS_MASK) * (1 << (ctllo >> 4 & 7));
+	return block2bytes(dwc, ctlhi, ctllo >> 4 & 7);
 }
 
 static void dwc_scan_descriptors(struct dw_dma *dw, struct dw_dma_chan *dwc)
@@ -692,10 +752,7 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 			| DWC_CTLL_FC_M2M;
 	prev = first = NULL;
 
-	for (offset = 0; offset < len; offset += xfer_count << src_width) {
-		xfer_count = min_t(size_t, (len - offset) >> src_width,
-					   dwc->block_size);
-
+	for (offset = 0; offset < len; offset += xfer_count) {
 		desc = dwc_desc_get(dwc);
 		if (!desc)
 			goto err_desc_get;
@@ -703,8 +760,8 @@ dwc_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
 		lli_write(desc, sar, src + offset);
 		lli_write(desc, dar, dest + offset);
 		lli_write(desc, ctllo, ctllo);
-		lli_write(desc, ctlhi, xfer_count);
-		desc->len = xfer_count << src_width;
+		lli_write(desc, ctlhi, bytes2block(dwc, len - offset, src_width, &xfer_count));
+		desc->len = xfer_count;
 
 		if (!first) {
 			first = desc;
@@ -775,7 +832,8 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
 
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
-			u32		len, dlen, mem;
+			u32		len, mem;
+			size_t		dlen;
 
 			mem = sg_dma_address(sg);
 			len = sg_dma_len(sg);
@@ -789,17 +847,8 @@ slave_sg_todev_fill_desc:
 
 			lli_write(desc, sar, mem);
 			lli_write(desc, dar, reg);
+			lli_write(desc, ctlhi, bytes2block(dwc, len, mem_width, &dlen));
 			lli_write(desc, ctllo, ctllo | DWC_CTLL_SRC_WIDTH(mem_width));
-			if ((len >> mem_width) > dwc->block_size) {
-				dlen = dwc->block_size << mem_width;
-				mem += dlen;
-				len -= dlen;
-			} else {
-				dlen = len;
-				len = 0;
-			}
-
-			lli_write(desc, ctlhi, dlen >> mem_width);
 			desc->len = dlen;
 
 			if (!first) {
@@ -809,6 +858,9 @@ slave_sg_todev_fill_desc:
 				list_add_tail(&desc->desc_node, &first->tx_list);
 			}
 			prev = desc;
+
+			mem += dlen;
+			len -= dlen;
 			total_len += dlen;
 
 			if (len)
@@ -828,13 +880,12 @@ slave_sg_todev_fill_desc:
 
 		for_each_sg(sgl, sg, sg_len, i) {
 			struct dw_desc	*desc;
-			u32		len, dlen, mem;
+			u32		len, mem;
+			size_t		dlen;
 
 			mem = sg_dma_address(sg);
 			len = sg_dma_len(sg);
 
-			mem_width = __ffs(data_width | mem | len);
-
 slave_sg_fromdev_fill_desc:
 			desc = dwc_desc_get(dwc);
 			if (!desc)
@@ -842,16 +893,9 @@ slave_sg_fromdev_fill_desc:
 
 			lli_write(desc, sar, reg);
 			lli_write(desc, dar, mem);
+			lli_write(desc, ctlhi, bytes2block(dwc, len, reg_width, &dlen));
+			mem_width = __ffs(data_width | mem | dlen);
 			lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width));
-			if ((len >> reg_width) > dwc->block_size) {
-				dlen = dwc->block_size << reg_width;
-				mem += dlen;
-				len -= dlen;
-			} else {
-				dlen = len;
-				len = 0;
-			}
-			lli_write(desc, ctlhi, dlen >> reg_width);
 			desc->len = dlen;
 
 			if (!first) {
@@ -861,6 +905,9 @@ slave_sg_fromdev_fill_desc:
 				list_add_tail(&desc->desc_node, &first->tx_list);
 			}
 			prev = desc;
+
+			mem += dlen;
+			len -= dlen;
 			total_len += dlen;
 
 			if (len)
@@ -903,25 +950,20 @@ bool dw_dma_filter(struct dma_chan *chan, void *param)
 }
 EXPORT_SYMBOL_GPL(dw_dma_filter);
 
-/*
- * Fix sconfig's burst size according to dw_dmac. We need to convert them as:
- * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
- *
- * NOTE: burst size 2 is not supported by controller.
- *
- * This can be done by finding least significant bit set: n & (n - 1)
- */
-static inline void convert_burst(u32 *maxburst)
-{
-	if (*maxburst > 1)
-		*maxburst = fls(*maxburst) - 2;
-	else
-		*maxburst = 0;
-}
-
 static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 {
 	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	struct dma_slave_config *sc = &dwc->dma_sconfig;
+	struct dw_dma *dw = to_dw_dma(chan->device);
+	/*
+	 * Fix sconfig's burst size according to dw_dmac. We need to convert
+	 * them as:
+	 * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
+	 *
+	 * NOTE: burst size 2 is not supported by DesignWare controller.
+	 *       iDMA 32-bit supports it.
+	 */
+	u32 s = dw->pdata->is_idma32 ? 1 : 2;
 
 	/* Check if chan will be configured for slave transfers */
 	if (!is_slave_direction(sconfig->direction))
@@ -930,28 +972,39 @@ static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
 	memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
 	dwc->direction = sconfig->direction;
 
-	convert_burst(&dwc->dma_sconfig.src_maxburst);
-	convert_burst(&dwc->dma_sconfig.dst_maxburst);
+	sc->src_maxburst = sc->src_maxburst > 1 ? fls(sc->src_maxburst) - s : 0;
+	sc->dst_maxburst = sc->dst_maxburst > 1 ? fls(sc->dst_maxburst) - s : 0;
 
 	return 0;
 }
 
-static int dwc_pause(struct dma_chan *chan)
+static void dwc_chan_pause(struct dw_dma_chan *dwc, bool drain)
 {
-	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
-	unsigned long		flags;
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
 	unsigned int		count = 20;	/* timeout iterations */
 	u32			cfglo;
 
-	spin_lock_irqsave(&dwc->lock, flags);
-
 	cfglo = channel_readl(dwc, CFG_LO);
+	if (dw->pdata->is_idma32) {
+		if (drain)
+			cfglo |= IDMA32C_CFGL_CH_DRAIN;
+		else
+			cfglo &= ~IDMA32C_CFGL_CH_DRAIN;
+	}
 	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
 	while (!(channel_readl(dwc, CFG_LO) & DWC_CFGL_FIFO_EMPTY) && count--)
 		udelay(2);
 
 	set_bit(DW_DMA_IS_PAUSED, &dwc->flags);
+}
 
+static int dwc_pause(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	unsigned long		flags;
+
+	spin_lock_irqsave(&dwc->lock, flags);
+	dwc_chan_pause(dwc, false);
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
 	return 0;
@@ -993,6 +1046,8 @@ static int dwc_terminate_all(struct dma_chan *chan)
 
 	clear_bit(DW_DMA_IS_SOFT_LLP, &dwc->flags);
 
+	dwc_chan_pause(dwc, true);
+
 	dwc_chan_disable(dw, dwc);
 
 	dwc_chan_resume(dwc);
@@ -1085,6 +1140,32 @@ static void dwc_issue_pending(struct dma_chan *chan)
 
 /*----------------------------------------------------------------------*/
 
+/*
+ * Program FIFO size of channels.
+ *
+ * By default full FIFO (1024 bytes) is assigned to channel 0. Here we
+ * slice FIFO on equal parts between channels.
+ */
+static void idma32_fifo_partition(struct dw_dma *dw)
+{
+	u64 value = IDMA32C_FP_PSIZE_CH0(128) | IDMA32C_FP_PSIZE_CH1(128) |
+		    IDMA32C_FP_UPDATE;
+	u64 fifo_partition = 0;
+
+	if (!dw->pdata->is_idma32)
+		return;
+
+	/* Fill FIFO_PARTITION low bits (Channels 0..1, 4..5) */
+	fifo_partition |= value << 0;
+
+	/* Fill FIFO_PARTITION high bits (Channels 2..3, 6..7) */
+	fifo_partition |= value << 32;
+
+	/* Program FIFO Partition registers - 128 bytes for each channel */
+	idma32_writeq(dw, FIFO_PARTITION1, fifo_partition);
+	idma32_writeq(dw, FIFO_PARTITION0, fifo_partition);
+}
+
 static void dw_dma_off(struct dw_dma *dw)
 {
 	unsigned int i;
@@ -1504,8 +1585,16 @@ int dw_dma_probe(struct dw_dma_chip *chip)
 	/* Force dma off, just in case */
 	dw_dma_off(dw);
 
+	idma32_fifo_partition(dw);
+
+	/* Device and instance ID for IRQ and DMA pool */
+	if (pdata->is_idma32)
+		snprintf(dw->name, sizeof(dw->name), "idma32:dmac%d", chip->id);
+	else
+		snprintf(dw->name, sizeof(dw->name), "dw:dmac%d", chip->id);
+
 	/* Create a pool of consistent memory blocks for hardware descriptors */
-	dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", chip->dev,
+	dw->desc_pool = dmam_pool_create(dw->name, chip->dev,
 					 sizeof(struct dw_desc), 4, 0);
 	if (!dw->desc_pool) {
 		dev_err(chip->dev, "No memory for descriptors dma pool\n");
@@ -1516,7 +1605,7 @@ int dw_dma_probe(struct dw_dma_chip *chip)
 	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
 
 	err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
-			  "dw_dmac", dw);
+			  dw->name, dw);
 	if (err)
 		goto err_pdata;
 
@@ -1665,6 +1754,8 @@ int dw_dma_enable(struct dw_dma_chip *chip)
 {
 	struct dw_dma *dw = chip->dw;
 
+	idma32_fifo_partition(dw);
+
 	dw_dma_on(dw);
 	return 0;
 }
diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c
index 0ae6c3b1d34e..7778ed705a1a 100644
--- a/drivers/dma/dw/pci.c
+++ b/drivers/dma/dw/pci.c
@@ -15,6 +15,18 @@
 
 #include "internal.h"
 
+static struct dw_dma_platform_data mrfld_pdata = {
+	.nr_channels = 8,
+	.is_private = true,
+	.is_memcpy = true,
+	.is_idma32 = true,
+	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
+	.chan_priority = CHAN_PRIORITY_ASCENDING,
+	.block_size = 131071,
+	.nr_masters = 1,
+	.data_width = {4},
+};
+
 static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 {
 	const struct dw_dma_platform_data *pdata = (void *)pid->driver_data;
@@ -47,6 +59,7 @@ static int dw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *pid)
 		return -ENOMEM;
 
 	chip->dev = &pdev->dev;
+	chip->id = pdev->devfn;
 	chip->regs = pcim_iomap_table(pdev)[0];
 	chip->irq = pdev->irq;
 	chip->pdata = pdata;
@@ -95,14 +108,16 @@ static const struct dev_pm_ops dw_pci_dev_pm_ops = {
 };
 
 static const struct pci_device_id dw_pci_id_table[] = {
-	/* Medfield */
+	/* Medfield (GPDMA) */
 	{ PCI_VDEVICE(INTEL, 0x0827) },
-	{ PCI_VDEVICE(INTEL, 0x0830) },
 
 	/* BayTrail */
 	{ PCI_VDEVICE(INTEL, 0x0f06) },
 	{ PCI_VDEVICE(INTEL, 0x0f40) },
 
+	/* Merrifield iDMA 32-bit (GPDMA) */
+	{ PCI_VDEVICE(INTEL, 0x11a2), (kernel_ulong_t)&mrfld_pdata },
+
 	/* Braswell */
 	{ PCI_VDEVICE(INTEL, 0x2286) },
 	{ PCI_VDEVICE(INTEL, 0x22c0) },
diff --git a/drivers/dma/dw/platform.c b/drivers/dma/dw/platform.c
index b1655e40cfa2..c639c60b825a 100644
--- a/drivers/dma/dw/platform.c
+++ b/drivers/dma/dw/platform.c
@@ -202,6 +202,7 @@ static int dw_probe(struct platform_device *pdev)
 		pdata = dw_dma_parse_dt(pdev);
 
 	chip->dev = dev;
+	chip->id = pdev->id;
 	chip->pdata = pdata;
 
 	chip->clk = devm_clk_get(chip->dev, "hclk");
diff --git a/drivers/dma/dw/regs.h b/drivers/dma/dw/regs.h
index 4e0128c62704..32a328721c88 100644
--- a/drivers/dma/dw/regs.h
+++ b/drivers/dma/dw/regs.h
@@ -3,15 +3,19 @@
  *
  * Copyright (C) 2005-2007 Atmel Corporation
  * Copyright (C) 2010-2011 ST Microelectronics
+ * Copyright (C) 2016 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
 
+#include <linux/bitops.h>
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
 
+#include <linux/io-64-nonatomic-hi-lo.h>
+
 #include "internal.h"
 
 #define DW_DMA_MAX_NR_REQUESTS	16
@@ -85,9 +89,9 @@ struct dw_dma_regs {
 	DW_REG(ID);
 	DW_REG(TEST);
 
-	/* reserved */
-	DW_REG(__reserved0);
-	DW_REG(__reserved1);
+	/* iDMA 32-bit support */
+	DW_REG(CLASS_PRIORITY0);
+	DW_REG(CLASS_PRIORITY1);
 
 	/* optional encoded params, 0x3c8..0x3f7 */
 	u32	__reserved;
@@ -99,6 +103,17 @@ struct dw_dma_regs {
 
 	/* top-level parameters */
 	u32	DW_PARAMS;
+
+	/* component ID */
+	u32	COMP_TYPE;
+	u32	COMP_VERSION;
+
+	/* iDMA 32-bit support */
+	DW_REG(FIFO_PARTITION0);
+	DW_REG(FIFO_PARTITION1);
+
+	DW_REG(SAI_ERR);
+	DW_REG(GLOBAL_CFG);
 };
 
 /*
@@ -170,8 +185,9 @@ enum dw_dma_msize {
 #define DWC_CTLL_LLP_S_EN	(1 << 28)	/* src block chain */
 
 /* Bitfields in CTL_HI */
-#define DWC_CTLH_DONE		0x00001000
-#define DWC_CTLH_BLOCK_TS_MASK	0x00000fff
+#define DWC_CTLH_BLOCK_TS_MASK	GENMASK(11, 0)
+#define DWC_CTLH_BLOCK_TS(x)	((x) & DWC_CTLH_BLOCK_TS_MASK)
+#define DWC_CTLH_DONE		(1 << 12)
 
 /* Bitfields in CFG_LO */
 #define DWC_CFGL_CH_PRIOR_MASK	(0x7 << 5)	/* priority mask */
@@ -214,6 +230,33 @@ enum dw_dma_msize {
 /* Bitfields in CFG */
 #define DW_CFG_DMA_EN		(1 << 0)
 
+/* iDMA 32-bit support */
+
+/* Bitfields in CTL_HI */
+#define IDMA32C_CTLH_BLOCK_TS_MASK	GENMASK(16, 0)
+#define IDMA32C_CTLH_BLOCK_TS(x)	((x) & IDMA32C_CTLH_BLOCK_TS_MASK)
+#define IDMA32C_CTLH_DONE		(1 << 17)
+
+/* Bitfields in CFG_LO */
+#define IDMA32C_CFGL_DST_BURST_ALIGN	(1 << 0)	/* dst burst align */
+#define IDMA32C_CFGL_SRC_BURST_ALIGN	(1 << 1)	/* src burst align */
+#define IDMA32C_CFGL_CH_DRAIN		(1 << 10)	/* drain FIFO */
+#define IDMA32C_CFGL_DST_OPT_BL		(1 << 20)	/* optimize dst burst length */
+#define IDMA32C_CFGL_SRC_OPT_BL		(1 << 21)	/* optimize src burst length */
+
+/* Bitfields in CFG_HI */
+#define IDMA32C_CFGH_SRC_PER(x)		((x) << 0)
+#define IDMA32C_CFGH_DST_PER(x)		((x) << 4)
+#define IDMA32C_CFGH_RD_ISSUE_THD(x)	((x) << 8)
+#define IDMA32C_CFGH_RW_ISSUE_THD(x)	((x) << 18)
+#define IDMA32C_CFGH_SRC_PER_EXT(x)	((x) << 28)	/* src peripheral extension */
+#define IDMA32C_CFGH_DST_PER_EXT(x)	((x) << 30)	/* dst peripheral extension */
+
+/* Bitfields in FIFO_PARTITION */
+#define IDMA32C_FP_PSIZE_CH0(x)		((x) << 0)
+#define IDMA32C_FP_PSIZE_CH1(x)		((x) << 13)
+#define IDMA32C_FP_UPDATE		(1 << 26)
+
 enum dw_dmac_flags {
 	DW_DMA_IS_CYCLIC = 0,
 	DW_DMA_IS_SOFT_LLP = 1,
@@ -270,6 +313,7 @@ static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
 
 struct dw_dma {
 	struct dma_device	dma;
+	char			name[20];
 	void __iomem		*regs;
 	struct dma_pool		*desc_pool;
 	struct tasklet_struct	tasklet;
@@ -293,6 +337,11 @@ static inline struct dw_dma_regs __iomem *__dw_regs(struct dw_dma *dw)
 #define dma_writel(dw, name, val) \
 	dma_writel_native((val), &(__dw_regs(dw)->name))
 
+#define idma32_readq(dw, name)				\
+	hi_lo_readq(&(__dw_regs(dw)->name))
+#define idma32_writeq(dw, name, val)			\
+	hi_lo_writeq((val), &(__dw_regs(dw)->name))
+
 #define channel_set_bit(dw, reg, mask) \
 	dma_writel(dw, reg, ((mask) << 8) | (mask))
 #define channel_clear_bit(dw, reg, mask) \