Merge branch 'tracking-qcomlt-sdcc' into integration-linux-qcomlt

* tracking-qcomlt-sdcc:
  mmc: mmci: Add qcom dml support to the driver.
  mmc: mmci: Add Qualcomm Id to amba id table
  mmc: mmci: Add Qcom specific rx_fifocnt logic.
  mmc: mmci: add explicit clk control
  mmc: mmci: add f_max to variant structure
  mmc: mmci: Add support to data commands via variant structure.
  mmc: mmci: add edge support to data and command out in variant data.
  mmc: mmci: add 8bit bus support in variant data
  mmc: mmci: add ddrmode mask to variant data
  mmc: mmci: Add Qcom datactrl register variant
  mmc: mmci: Add enough delay between writes to CMD register.
  mmc: mmci: Add Qualcomm specific register defines.
  mmc: mmci: use NSEC_PER_SEC macro

6 files changed, 352 insertions, 13 deletions

diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index a5652548230a..2f210a5a1d24 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -14,6 +14,17 @@ config MMC_ARMMMCI
 
 	  If unsure, say N.
 
+config MMC_QCOM_DML
+	tristate "Qualcomm Data Mover for SD Card Controller"
+	depends on MMC_ARMMMCI
+	default y
+	help
+	  This selects the Qualcomm Data Mover lite/local on SD Card controller.
+	  This option will enable the dma to work correctly, if you are using
+	  Qcom SOCs and MMC, you would probably need this option to get DMA working.
+
+	  if unsure, say N.
+
 config MMC_PXA
 	tristate "Intel PXA25x/26x/27x Multimedia Card Interface support"
 	depends on ARCH_PXA
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index 7f81ddf1dd2c..e6a14ac7075e 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -3,6 +3,7 @@
 #
 
 obj-$(CONFIG_MMC_ARMMMCI)	+= mmci.o
+obj-$(CONFIG_MMC_QCOM_DML)	+= qcom_dml.o
 obj-$(CONFIG_MMC_PXA)		+= pxamci.o
 obj-$(CONFIG_MMC_MXC)		+= mxcmmc.o
 obj-$(CONFIG_MMC_MXS)		+= mxs-mmc.o
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 7ad463e9741c..ca9bb6de4379 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -43,6 +43,7 @@
 #include <asm/sizes.h>
 
 #include "mmci.h"
+#include "qcom_dml.h"
 
 #define DRIVER_NAME "mmci-pl18x"
 
@@ -52,34 +53,53 @@ static unsigned int fmax = 515633;
  * struct variant_data - MMCI variant-specific quirks
  * @clkreg: default value for MCICLOCK register
  * @clkreg_enable: enable value for MMCICLOCK register
+ * @clkreg_8bit_bus_enable: enable value for 8 bit bus
+ * @clkreg_neg_edge_enable: enable value for inverted data/cmd output
  * @datalength_bits: number of bits in the MMCIDATALENGTH register
  * @fifosize: number of bytes that can be written when MMCI_TXFIFOEMPTY
  *	      is asserted (likewise for RX)
  * @fifohalfsize: number of bytes that can be written when MCI_TXFIFOHALFEMPTY
  *		  is asserted (likewise for RX)
+ * @data_cmd_enable: enable value for data commands.
  * @sdio: variant supports SDIO
  * @st_clkdiv: true if using a ST-specific clock divider algorithm
+ * @datactrl_mask_ddrmode: ddr mode mask in datactrl register.
  * @blksz_datactrl16: true if Block size is at b16..b30 position in datactrl register
+ * @blksz_datactrl4: true if Block size is at b4..b16 position in datactrl
+ *		     register
  * @pwrreg_powerup: power up value for MMCIPOWER register
+ * @f_max: maximum clk frequency supported by the controller.
  * @signal_direction: input/out direction of bus signals can be indicated
  * @pwrreg_clkgate: MMCIPOWER register must be used to gate the clock
  * @busy_detect: true if busy detection on dat0 is supported
  * @pwrreg_nopower: bits in MMCIPOWER don't controls ext. power supply
+ * @explicit_mclk_control: enable explicit mclk control in driver.
+ * @qcom_fifo: enables qcom specific fifo pio read logic.
+ * @qcom_dml: enables qcom specific dml glue for dma transfers.
  */
 struct variant_data {
 	unsigned int		clkreg;
 	unsigned int		clkreg_enable;
+	unsigned int		clkreg_8bit_bus_enable;
+	unsigned int		clkreg_neg_edge_enable;
 	unsigned int		datalength_bits;
 	unsigned int		fifosize;
 	unsigned int		fifohalfsize;
+	unsigned int		data_cmd_enable;
+	unsigned int		datactrl_mask_ddrmode;
 	bool			sdio;
 	bool			st_clkdiv;
 	bool			blksz_datactrl16;
+	bool			blksz_datactrl4;
 	u32			pwrreg_powerup;
+	u32			f_max;
 	bool			signal_direction;
 	bool			pwrreg_clkgate;
 	bool			busy_detect;
 	bool			pwrreg_nopower;
+	bool			explicit_mclk_control;
+	bool			qcom_fifo;
+	bool			qcom_dml;
 };
 
 static struct variant_data variant_arm = {
@@ -87,6 +107,7 @@ static struct variant_data variant_arm = {
 	.fifohalfsize		= 8 * 4,
 	.datalength_bits	= 16,
 	.pwrreg_powerup		= MCI_PWR_UP,
+	.f_max			= 100000000,
 };
 
 static struct variant_data variant_arm_extended_fifo = {
@@ -94,6 +115,7 @@ static struct variant_data variant_arm_extended_fifo = {
 	.fifohalfsize		= 64 * 4,
 	.datalength_bits	= 16,
 	.pwrreg_powerup		= MCI_PWR_UP,
+	.f_max			= 100000000,
 };
 
 static struct variant_data variant_arm_extended_fifo_hwfc = {
@@ -102,15 +124,18 @@ static struct variant_data variant_arm_extended_fifo_hwfc = {
 	.clkreg_enable		= MCI_ARM_HWFCEN,
 	.datalength_bits	= 16,
 	.pwrreg_powerup		= MCI_PWR_UP,
+	.f_max			= 100000000,
 };
 
 static struct variant_data variant_u300 = {
 	.fifosize		= 16 * 4,
 	.fifohalfsize		= 8 * 4,
 	.clkreg_enable		= MCI_ST_U300_HWFCEN,
+	.clkreg_8bit_bus_enable = MCI_ST_8BIT_BUS,
 	.datalength_bits	= 16,
 	.sdio			= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
+	.f_max			= 100000000,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
 	.pwrreg_nopower		= true,
@@ -124,6 +149,7 @@ static struct variant_data variant_nomadik = {
 	.sdio			= true,
 	.st_clkdiv		= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
+	.f_max			= 100000000,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
 	.pwrreg_nopower		= true,
@@ -134,10 +160,13 @@ static struct variant_data variant_ux500 = {
 	.fifohalfsize		= 8 * 4,
 	.clkreg			= MCI_CLK_ENABLE,
 	.clkreg_enable		= MCI_ST_UX500_HWFCEN,
+	.clkreg_8bit_bus_enable = MCI_ST_8BIT_BUS,
+	.clkreg_neg_edge_enable	= MCI_ST_UX500_NEG_EDGE,
 	.datalength_bits	= 24,
 	.sdio			= true,
 	.st_clkdiv		= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
+	.f_max			= 100000000,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
 	.busy_detect		= true,
@@ -149,17 +178,39 @@ static struct variant_data variant_ux500v2 = {
 	.fifohalfsize		= 8 * 4,
 	.clkreg			= MCI_CLK_ENABLE,
 	.clkreg_enable		= MCI_ST_UX500_HWFCEN,
+	.clkreg_8bit_bus_enable = MCI_ST_8BIT_BUS,
+	.clkreg_neg_edge_enable	= MCI_ST_UX500_NEG_EDGE,
+	.datactrl_mask_ddrmode	= MCI_ST_DPSM_DDRMODE,
 	.datalength_bits	= 24,
 	.sdio			= true,
 	.st_clkdiv		= true,
 	.blksz_datactrl16	= true,
 	.pwrreg_powerup		= MCI_PWR_ON,
+	.f_max			= 100000000,
 	.signal_direction	= true,
 	.pwrreg_clkgate		= true,
 	.busy_detect		= true,
 	.pwrreg_nopower		= true,
 };
 
+static struct variant_data variant_qcom = {
+	.fifosize		= 16 * 4,
+	.fifohalfsize		= 8 * 4,
+	.clkreg			= MCI_CLK_ENABLE,
+	.clkreg_enable		= MCI_QCOM_CLK_FLOWENA |
+				  MCI_QCOM_CLK_SELECT_IN_FBCLK,
+	.clkreg_8bit_bus_enable = MCI_QCOM_CLK_WIDEBUS_8,
+	.datactrl_mask_ddrmode	= MCI_QCOM_CLK_SELECT_IN_DDR_MODE,
+	.data_cmd_enable	= MCI_QCOM_CSPM_DATCMD,
+	.blksz_datactrl4	= true,
+	.datalength_bits	= 24,
+	.pwrreg_powerup		= MCI_PWR_UP,
+	.f_max			= 208000000,
+	.explicit_mclk_control	= true,
+	.qcom_fifo		= true,
+	.qcom_dml		= true,
+};
+
 static int mmci_card_busy(struct mmc_host *mmc)
 {
 	struct mmci_host *host = mmc_priv(mmc);
@@ -260,7 +311,9 @@ static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 	host->cclk = 0;
 
 	if (desired) {
-		if (desired >= host->mclk) {
+		if (variant->explicit_mclk_control) {
+			host->cclk = host->mclk;
+		} else if (desired >= host->mclk) {
 			clk = MCI_CLK_BYPASS;
 			if (variant->st_clkdiv)
 				clk |= MCI_ST_UX500_NEG_EDGE;
@@ -299,11 +352,11 @@ static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_4)
 		clk |= MCI_4BIT_BUS;
 	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_8)
-		clk |= MCI_ST_8BIT_BUS;
+		clk |= variant->clkreg_8bit_bus_enable;
 
 	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50 ||
 	    host->mmc->ios.timing == MMC_TIMING_MMC_DDR52)
-		clk |= MCI_ST_UX500_NEG_EDGE;
+		clk |= variant->clkreg_neg_edge_enable;
 
 	mmci_write_clkreg(host, clk);
 }
@@ -520,6 +573,7 @@ static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 	struct dma_async_tx_descriptor *desc;
 	enum dma_data_direction buffer_dirn;
 	int nr_sg;
+	u32 flags = DMA_CTRL_ACK;
 
 	if (data->flags & MMC_DATA_READ) {
 		conf.direction = DMA_DEV_TO_MEM;
@@ -544,9 +598,12 @@ static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
 	if (nr_sg == 0)
 		return -EINVAL;
 
+	if (host->variant->qcom_dml)
+		flags |= DMA_PREP_INTERRUPT;
+
 	dmaengine_slave_config(chan, &conf);
 	desc = dmaengine_prep_slave_sg(chan, data->sg, nr_sg,
-					    conf.direction, DMA_CTRL_ACK);
+					    conf.direction, flags);
 	if (!desc)
 		goto unmap_exit;
 
@@ -595,6 +652,9 @@ static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
 	dmaengine_submit(host->dma_desc_current);
 	dma_async_issue_pending(host->dma_current);
 
+	if (host->variant->qcom_dml)
+		dml_start_xfer(host, data);
+
 	datactrl |= MCI_DPSM_DMAENABLE;
 
 	/* Trigger the DMA transfer */
@@ -719,7 +779,7 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 	data->bytes_xfered = 0;
 
 	clks = (unsigned long long)data->timeout_ns * host->cclk;
-	do_div(clks, 1000000000UL);
+	do_div(clks, NSEC_PER_SEC);
 
 	timeout = data->timeout_clks + (unsigned int)clks;
 
@@ -732,6 +792,8 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 
 	if (variant->blksz_datactrl16)
 		datactrl = MCI_DPSM_ENABLE | (data->blksz << 16);
+	else if (variant->blksz_datactrl4)
+		datactrl = MCI_DPSM_ENABLE | (data->blksz << 4);
 	else
 		datactrl = MCI_DPSM_ENABLE | blksz_bits << 4;
 
@@ -767,7 +829,7 @@ static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
 
 	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50 ||
 	    host->mmc->ios.timing == MMC_TIMING_MMC_DDR52)
-		datactrl |= MCI_ST_DPSM_DDRMODE;
+		datactrl |= variant->datactrl_mask_ddrmode;
 
 	/*
 	 * Attempt to use DMA operation mode, if this
@@ -812,7 +874,7 @@ mmci_start_command(struct mmci_host *host, struct mmc_command *cmd, u32 c)
 
 	if (readl(base + MMCICOMMAND) & MCI_CPSM_ENABLE) {
 		writel(0, base + MMCICOMMAND);
-		udelay(1);
+		mmci_reg_delay(host);
 	}
 
 	c |= cmd->opcode | MCI_CPSM_ENABLE;
@@ -824,6 +886,9 @@ mmci_start_command(struct mmci_host *host, struct mmc_command *cmd, u32 c)
 	if (/*interrupt*/0)
 		c |= MCI_CPSM_INTERRUPT;
 
+	if (mmc_cmd_type(cmd) == MMC_CMD_ADTC)
+		c |= host->variant->data_cmd_enable;
+
 	host->cmd = cmd;
 
 	writel(cmd->arg, base + MMCIARGUMENT);
@@ -957,15 +1022,34 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
 	}
 }
 
+static int mmci_get_rx_fifocnt(struct mmci_host *host, u32 status, int remain)
+{
+	return remain - (readl(host->base + MMCIFIFOCNT) << 2);
+}
+
+static int mmci_qcom_get_rx_fifocnt(struct mmci_host *host, u32 status, int r)
+{
+	/*
+	 * on qcom SDCC4 only 8 words are used in each burst so only 8 addresses
+	 * from the fifo range should be used
+	 */
+	if (status & MCI_RXFIFOHALFFULL)
+		return host->variant->fifohalfsize;
+	else if (status & MCI_RXDATAAVLBL)
+		return 4;
+
+	return 0;
+}
+
 static int mmci_pio_read(struct mmci_host *host, char *buffer, unsigned int remain)
 {
 	void __iomem *base = host->base;
 	char *ptr = buffer;
-	u32 status;
+	u32 status = readl(host->base + MMCISTATUS);
 	int host_remain = host->size;
 
 	do {
-		int count = host_remain - (readl(base + MMCIFIFOCNT) << 2);
+		int count = host->get_rx_fifocnt(host, status, host_remain);
 
 		if (count > remain)
 			count = remain;
@@ -1296,6 +1380,18 @@ static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (!ios->clock && variant->pwrreg_clkgate)
 		pwr &= ~MCI_PWR_ON;
 
+	if (host->variant->explicit_mclk_control &&
+	    ios->clock != host->clock_cache) {
+		int rc = clk_set_rate(host->clk, ios->clock);
+		if (rc < 0) {
+			dev_err(mmc_dev(host->mmc),
+				"Error setting clock rate (%d)\n", rc);
+		} else {
+			host->mclk = clk_get_rate(host->clk);
+			host->clock_cache = ios->clock;
+		}
+	}
+
 	spin_lock_irqsave(&host->lock, flags);
 
 	mmci_set_clkreg(host, ios->clock);
@@ -1443,6 +1539,11 @@ static int mmci_probe(struct amba_device *dev,
 	if (ret)
 		goto host_free;
 
+	if (variant->qcom_fifo)
+		host->get_rx_fifocnt = mmci_qcom_get_rx_fifocnt;
+	else
+		host->get_rx_fifocnt = mmci_get_rx_fifocnt;
+
 	host->plat = plat;
 	host->variant = variant;
 	host->mclk = clk_get_rate(host->clk);
@@ -1451,8 +1552,8 @@ static int mmci_probe(struct amba_device *dev,
 	 * so we try to adjust the clock down to this,
 	 * (if possible).
 	 */
-	if (host->mclk > 100000000) {
-		ret = clk_set_rate(host->clk, 100000000);
+	if (host->mclk > variant->f_max) {
+		ret = clk_set_rate(host->clk, variant->f_max);
 		if (ret < 0)
 			goto clk_disable;
 		host->mclk = clk_get_rate(host->clk);
@@ -1471,9 +1572,12 @@ static int mmci_probe(struct amba_device *dev,
 	 * The ARM and ST versions of the block have slightly different
 	 * clock divider equations which means that the minimum divider
 	 * differs too.
+	 * on Qualcomm like controllers get the nearest minimum clock to 100Khz
 	 */
 	if (variant->st_clkdiv)
 		mmc->f_min = DIV_ROUND_UP(host->mclk, 257);
+	else if (variant->explicit_mclk_control)
+		mmc->f_min = clk_round_rate(host->clk, 100000);
 	else
 		mmc->f_min = DIV_ROUND_UP(host->mclk, 512);
 	/*
@@ -1483,9 +1587,14 @@ static int mmci_probe(struct amba_device *dev,
 	 * the block, of course.
 	 */
 	if (mmc->f_max)
-		mmc->f_max = min(host->mclk, mmc->f_max);
+		mmc->f_max = variant->explicit_mclk_control ?
+				min(variant->f_max, mmc->f_max) :
+				min(host->mclk, mmc->f_max);
 	else
-		mmc->f_max = min(host->mclk, fmax);
+		mmc->f_max = variant->explicit_mclk_control ?
+				fmax : min(host->mclk, fmax);
+
+
 	dev_dbg(mmc_dev(mmc), "clocking block at %u Hz\n", mmc->f_max);
 
 	/* Get regulators and the supported OCR mask */
@@ -1589,6 +1698,11 @@ static int mmci_probe(struct amba_device *dev,
 
 	mmci_dma_setup(host);
 
+	if (variant->qcom_dml && host->dma_rx_channel && host->dma_tx_channel) {
+		if (dml_hw_init(host, np))
+			variant->qcom_dml = false;
+	}
+
 	pm_runtime_set_autosuspend_delay(&dev->dev, 50);
 	pm_runtime_use_autosuspend(&dev->dev);
 	pm_runtime_put(&dev->dev);
@@ -1752,6 +1866,12 @@ static struct amba_id mmci_ids[] = {
 		.mask   = 0xf0ffffff,
 		.data	= &variant_ux500v2,
 	},
+	/* Qualcomm variants */
+	{
+		.id     = 0x00051180,
+		.mask	= 0x000fffff,
+		.data	= &variant_qcom,
+	},
 	{ 0, 0 },
 };
 
diff --git a/drivers/mmc/host/mmci.h b/drivers/mmc/host/mmci.h
index 347d942d740b..a1f5e4f49e2a 100644
--- a/drivers/mmc/host/mmci.h
+++ b/drivers/mmc/host/mmci.h
@@ -41,6 +41,15 @@
 /* Modified PL180 on Versatile Express platform */
 #define MCI_ARM_HWFCEN		(1 << 12)
 
+/* Modified on Qualcomm Integrations */
+#define MCI_QCOM_CLK_WIDEBUS_8	(BIT(10) | BIT(11))
+#define MCI_QCOM_CLK_FLOWENA	BIT(12)
+#define MCI_QCOM_CLK_INVERTOUT	BIT(13)
+
+/* select in latch data and command in */
+#define MCI_QCOM_CLK_SELECT_IN_FBCLK	BIT(15)
+#define MCI_QCOM_CLK_SELECT_IN_DDR_MODE	(BIT(14) | BIT(15))
+
 #define MMCIARGUMENT		0x008
 #define MMCICOMMAND		0x00c
 #define MCI_CPSM_RESPONSE	(1 << 6)
@@ -54,6 +63,14 @@
 #define MCI_ST_NIEN		(1 << 13)
 #define MCI_ST_CE_ATACMD	(1 << 14)
 
+/* Modified on Qualcomm Integrations */
+#define MCI_QCOM_CSPM_DATCMD		BIT(12)
+#define MCI_QCOM_CSPM_MCIABORT		BIT(13)
+#define MCI_QCOM_CSPM_CCSENABLE		BIT(14)
+#define MCI_QCOM_CSPM_CCSDISABLE	BIT(15)
+#define MCI_QCOM_CSPM_AUTO_CMD19	BIT(16)
+#define MCI_QCOM_CSPM_AUTO_CMD21	BIT(21)
+
 #define MMCIRESPCMD		0x010
 #define MMCIRESPONSE0		0x014
 #define MMCIRESPONSE1		0x018
@@ -191,6 +208,8 @@ struct mmci_host {
 	spinlock_t		lock;
 
 	unsigned int		mclk;
+	/* cached value of requested clk in set_ios */
+	unsigned int		clock_cache;
 	unsigned int		cclk;
 	u32			pwr_reg;
 	u32			pwr_reg_add;
@@ -210,6 +229,7 @@ struct mmci_host {
 	/* pio stuff */
 	struct sg_mapping_iter	sg_miter;
 	unsigned int		size;
+	int (*get_rx_fifocnt)(struct mmci_host *h, u32 status, int remain);
 
 #ifdef CONFIG_DMA_ENGINE
 	/* DMA stuff */
diff --git a/drivers/mmc/host/qcom_dml.c b/drivers/mmc/host/qcom_dml.c
new file mode 100644
index 000000000000..5d61e4ce13ea
--- /dev/null
+++ b/drivers/mmc/host/qcom_dml.c
@@ -0,0 +1,170 @@
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/mmc/host.h>
+#include <linux/mmc/card.h>
+#include "mmci.h"
+
+/* DML config register defination */
+#define DML_CONFIG			0x00
+#define PRODUCER_CRCI_DIS		0x00
+#define PRODUCER_CRCI_X_SEL		0x01
+#define PRODUCER_CRCI_Y_SEL		0x02
+#define PRODUCER_CRCI_MSK		0x3
+#define CONSUMER_CRCI_DIS		(0x00 << 2)
+#define CONSUMER_CRCI_X_SEL		(0x01 << 2)
+#define CONSUMER_CRCI_Y_SEL		(0x02 << 2)
+#define CONSUMER_CRCI_MSK		(0x3 << 2)
+#define PRODUCER_TRANS_END_EN		(1 << 4)
+#define BYPASS				(1 << 16)
+#define DIRECT_MODE			(1 << 17)
+#define INFINITE_CONS_TRANS		(1 << 18)
+
+#define DML_SW_RESET			0x08
+#define DML_PRODUCER_START		0x0C
+#define DML_CONSUMER_START		0x10
+#define DML_PRODUCER_PIPE_LOGICAL_SIZE	0x14
+#define DML_CONSUMER_PIPE_LOGICAL_SIZE	0x18
+#define DML_PIPE_ID			0x1C
+#define DML_PRODUCER_BAM_BLOCK_SIZE	0x24
+#define DML_PRODUCER_BAM_TRANS_SIZE	0x28
+#define PRODUCER_PIPE_ID_SHFT		0
+#define PRODUCER_PIPE_ID_MSK		0x1f
+#define CONSUMER_PIPE_ID_SHFT		16
+#define CONSUMER_PIPE_ID_MSK		(0x1f << 16)
+/* other definations */
+#define PRODUCER_PIPE_LOGICAL_SIZE	4096
+#define CONSUMER_PIPE_LOGICAL_SIZE	4096
+
+#define DML_OFFSET			0x800
+
+void dml_start_xfer(struct mmci_host *host, struct mmc_data *data)
+{
+	u32 config;
+	void __iomem *dml_base;
+	dml_base = host->base + DML_OFFSET;
+
+	if (data->flags & MMC_DATA_READ) {
+		/* Read operation: configure DML for producer operation */
+		/* Set producer CRCI-x and disable consumer CRCI */
+		config = readl(dml_base + DML_CONFIG);
+		config = (config & ~PRODUCER_CRCI_MSK) | PRODUCER_CRCI_X_SEL;
+		config = (config & ~CONSUMER_CRCI_MSK) | CONSUMER_CRCI_DIS;
+		writel(config, (dml_base + DML_CONFIG));
+
+		/* Set the Producer BAM block size */
+		writel(data->blksz, (dml_base +
+					DML_PRODUCER_BAM_BLOCK_SIZE));
+
+		/* Set Producer BAM Transaction size */
+		writel(data->blocks * data->blksz,
+			(dml_base + DML_PRODUCER_BAM_TRANS_SIZE));
+		/* Set Producer Transaction End bit */
+		writel((readl_relaxed(dml_base + DML_CONFIG)
+			| PRODUCER_TRANS_END_EN),
+			(dml_base + DML_CONFIG));
+		/* Trigger producer */
+		writel(1, (dml_base + DML_PRODUCER_START));
+	} else {
+		/* Write operation: configure DML for consumer operation */
+		/* Set consumer CRCI-x and disable producer CRCI*/
+		config = readl(dml_base + DML_CONFIG);
+		config = (config & ~CONSUMER_CRCI_MSK) | CONSUMER_CRCI_X_SEL;
+		config = (config & ~PRODUCER_CRCI_MSK) | PRODUCER_CRCI_DIS;
+
+		config = 0x4;
+		writel(config, (dml_base + DML_CONFIG));
+		/* Clear Producer Transaction End bit */
+		writel((readl_relaxed(dml_base + DML_CONFIG)
+			& ~PRODUCER_TRANS_END_EN),
+			(dml_base + DML_CONFIG));
+		/* Trigger consumer */
+		writel(1, (dml_base + DML_CONSUMER_START));
+	}
+}
+
+static int of_get_dml_pipe_index(struct device_node *np, const char *name)
+{
+	int count, i;
+	const char *s;
+	struct of_phandle_args	dma_spec;
+
+	if (!np || !name)
+		return -ENODEV;
+
+	count = of_property_count_strings(np, "dma-names");
+	if (count < 0)
+		return -ENODEV;
+
+	for (i = 0; i < count; i++) {
+
+		if (of_property_read_string_index(np, "dma-names", i, &s))
+			continue;
+
+		if (strcmp(name, s))
+			continue;
+
+		if (of_parse_phandle_with_args(np, "dmas", "#dma-cells", i,
+				       &dma_spec))
+			continue;
+
+		if (dma_spec.args_count)
+			return dma_spec.args[0];
+	}
+
+	return -ENODEV;
+}
+
+/* Initialize the dml hardware connectd to SD Card controller */
+int dml_hw_init(struct mmci_host *host, struct device_node *np)
+{
+	u32 config = 0;
+	void __iomem *dml_base;
+	u32 consumer_id = 0, producer_id = 0;
+
+	consumer_id = of_get_dml_pipe_index(np, "tx");
+	producer_id = of_get_dml_pipe_index(np, "rx");
+
+	if (IS_ERR_VALUE(producer_id) || IS_ERR_VALUE(consumer_id))
+		return -ENODEV;
+
+	dml_base = host->base + DML_OFFSET;
+
+	/* Reset the DML block */
+	writel(1, (dml_base + DML_SW_RESET));
+
+	/* Disable the producer and consumer CRCI */
+	config = (PRODUCER_CRCI_DIS | CONSUMER_CRCI_DIS);
+	/*
+	 * Disable the bypass mode. Bypass mode will only be used
+	 * if data transfer is to happen in PIO mode and don't
+	 * want the BAM interface to connect with SDCC-DML.
+	 */
+	config &= ~BYPASS;
+	/*
+	 * Disable direct mode as we don't DML to MASTER the AHB bus.
+	 * BAM connected with DML should MASTER the AHB bus.
+	 */
+	config &= ~DIRECT_MODE;
+	/*
+	 * Disable infinite mode transfer as we won't be doing any
+	 * infinite size data transfers. All data transfer will be
+	 * of finite data size.
+	 */
+	config &= ~INFINITE_CONS_TRANS;
+	writel(config, (dml_base + DML_CONFIG));
+
+	/*
+	 * Initialize the logical BAM pipe size for producer
+	 * and consumer.
+	 */
+	writel(PRODUCER_PIPE_LOGICAL_SIZE,
+		(dml_base + DML_PRODUCER_PIPE_LOGICAL_SIZE));
+	writel(CONSUMER_PIPE_LOGICAL_SIZE,
+		(dml_base + DML_CONSUMER_PIPE_LOGICAL_SIZE));
+
+	/* Initialize Producer/consumer pipe id */
+	writel(producer_id | (consumer_id << CONSUMER_PIPE_ID_SHFT),
+		(dml_base + DML_PIPE_ID));
+
+	return 0;
+}
diff --git a/drivers/mmc/host/qcom_dml.h b/drivers/mmc/host/qcom_dml.h
new file mode 100644
index 000000000000..d2c5aa45b20a
--- /dev/null
+++ b/drivers/mmc/host/qcom_dml.h
@@ -0,0 +1,17 @@
+#ifndef __MMC_QCOM_DML_H__
+#define __MMC_QCOM_DML_H__
+
+#ifdef CONFIG_MMC_QCOM_DML
+int dml_hw_init(struct mmci_host *host, struct device_node *np);
+void dml_start_xfer(struct mmci_host *host, struct mmc_data *data);
+#else
+static inline int dml_hw_init(struct mmci_host *host, struct device_node *np)
+{
+	return -ENOSYS;
+}
+static inline void dml_start_xfer(struct mmci_host *host, struct mmc_data *data)
+{
+}
+#endif /* CONFIG_MMC_QCOM_DML */
+
+#endif /* __MMC_QCOM_DML_H__ */