Merge remote-tracking branch 'spi/topic/qspi' into spi-next

14 files changed, 710 insertions, 134 deletions

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 8aad2c1dc33d..f552c89abdd4 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -306,6 +306,14 @@ config SPI_OMAP24XX
 	  SPI master controller for OMAP24XX and later Multichannel SPI
 	  (McSPI) modules.
 
+config SPI_TI_QSPI
+	tristate "DRA7xxx QSPI controller support"
+	depends on ARCH_OMAP2PLUS || COMPILE_TEST
+	help
+	  QSPI master controller for DRA7xxx used for flash devices.
+	  This device supports single, dual and quad read support, while
+	  it only supports single write mode.
+
 config SPI_OMAP_100K
 	tristate "OMAP SPI 100K"
 	depends on ARCH_OMAP850 || ARCH_OMAP730 || COMPILE_TEST
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 985d7bad7932..ab8d8644af0e 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -49,6 +49,7 @@ obj-$(CONFIG_SPI_OCTEON)		+= spi-octeon.o
 obj-$(CONFIG_SPI_OMAP_UWIRE)		+= spi-omap-uwire.o
 obj-$(CONFIG_SPI_OMAP_100K)		+= spi-omap-100k.o
 obj-$(CONFIG_SPI_OMAP24XX)		+= spi-omap2-mcspi.o
+obj-$(CONFIG_SPI_TI_QSPI)		+= spi-ti-qspi.o
 obj-$(CONFIG_SPI_ORION)			+= spi-orion.o
 obj-$(CONFIG_SPI_PL022)			+= spi-pl022.o
 obj-$(CONFIG_SPI_PPC4xx)		+= spi-ppc4xx.o
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index de197f72e082..536b0e363826 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -231,24 +231,6 @@ static int bcm63xx_txrx_bufs(struct spi_device *spi, struct spi_transfer *first,
 	return 0;
 }
 
-static int bcm63xx_spi_prepare_transfer(struct spi_master *master)
-{
-	struct bcm63xx_spi *bs = spi_master_get_devdata(master);
-
-	pm_runtime_get_sync(&bs->pdev->dev);
-
-	return 0;
-}
-
-static int bcm63xx_spi_unprepare_transfer(struct spi_master *master)
-{
-	struct bcm63xx_spi *bs = spi_master_get_devdata(master);
-
-	pm_runtime_put(&bs->pdev->dev);
-
-	return 0;
-}
-
 static int bcm63xx_spi_transfer_one(struct spi_master *master,
 					struct spi_message *m)
 {
@@ -406,11 +388,10 @@ static int bcm63xx_spi_probe(struct platform_device *pdev)
 
 	master->bus_num = pdata->bus_num;
 	master->num_chipselect = pdata->num_chipselect;
-	master->prepare_transfer_hardware = bcm63xx_spi_prepare_transfer;
-	master->unprepare_transfer_hardware = bcm63xx_spi_unprepare_transfer;
 	master->transfer_one_message = bcm63xx_spi_transfer_one;
 	master->mode_bits = MODEBITS;
 	master->bits_per_word_mask = SPI_BPW_MASK(8);
+	master->auto_runtime_pm = true;
 	bs->msg_type_shift = pdata->msg_type_shift;
 	bs->msg_ctl_width = pdata->msg_ctl_width;
 	bs->tx_io = (u8 *)(bs->regs + bcm63xx_spireg(SPI_MSG_DATA));
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index 8e07928cadb3..cc5b75d10c38 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -354,24 +354,6 @@ static int mcfqspi_transfer_one_message(struct spi_master *master,
 
 }
 
-static int mcfqspi_prepare_transfer_hw(struct spi_master *master)
-{
-	struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
-
-	pm_runtime_get_sync(mcfqspi->dev);
-
-	return 0;
-}
-
-static int mcfqspi_unprepare_transfer_hw(struct spi_master *master)
-{
-	struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
-
-	pm_runtime_put_sync(mcfqspi->dev);
-
-	return 0;
-}
-
 static int mcfqspi_setup(struct spi_device *spi)
 {
 	if (spi->chip_select >= spi->master->num_chipselect) {
@@ -473,8 +455,7 @@ static int mcfqspi_probe(struct platform_device *pdev)
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 16);
 	master->setup = mcfqspi_setup;
 	master->transfer_one_message = mcfqspi_transfer_one_message;
-	master->prepare_transfer_hardware = mcfqspi_prepare_transfer_hw;
-	master->unprepare_transfer_hardware = mcfqspi_unprepare_transfer_hw;
+	master->auto_runtime_pm = true;
 
 	platform_set_drvdata(pdev, master);
 
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index fc190a5a0bad..ed4af4708d9a 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -335,23 +335,6 @@ static void omap2_mcspi_restore_ctx(struct omap2_mcspi *mcspi)
 		__raw_writel(cs->chconf0, cs->base + OMAP2_MCSPI_CHCONF0);
 }
 
-static int omap2_prepare_transfer(struct spi_master *master)
-{
-	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
-
-	pm_runtime_get_sync(mcspi->dev);
-	return 0;
-}
-
-static int omap2_unprepare_transfer(struct spi_master *master)
-{
-	struct omap2_mcspi *mcspi = spi_master_get_devdata(master);
-
-	pm_runtime_mark_last_busy(mcspi->dev);
-	pm_runtime_put_autosuspend(mcspi->dev);
-	return 0;
-}
-
 static int mcspi_wait_for_reg_bit(void __iomem *reg, unsigned long bit)
 {
 	unsigned long timeout;
@@ -1318,8 +1301,7 @@ static int omap2_mcspi_probe(struct platform_device *pdev)
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	master->setup = omap2_mcspi_setup;
-	master->prepare_transfer_hardware = omap2_prepare_transfer;
-	master->unprepare_transfer_hardware = omap2_unprepare_transfer;
+	master->auto_runtime_pm = true;
 	master->transfer_one_message = omap2_mcspi_transfer_one_message;
 	master->cleanup = omap2_mcspi_cleanup;
 	master->dev.of_node = node;
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 5a9e05e20bb5..9c511a954d21 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -1555,18 +1555,6 @@ static int pl022_transfer_one_message(struct spi_master *master,
 	return 0;
 }
 
-static int pl022_prepare_transfer_hardware(struct spi_master *master)
-{
-	struct pl022 *pl022 = spi_master_get_devdata(master);
-
-	/*
-	 * Just make sure we have all we need to run the transfer by syncing
-	 * with the runtime PM framework.
-	 */
-	pm_runtime_get_sync(&pl022->adev->dev);
-	return 0;
-}
-
 static int pl022_unprepare_transfer_hardware(struct spi_master *master)
 {
 	struct pl022 *pl022 = spi_master_get_devdata(master);
@@ -1575,13 +1563,6 @@ static int pl022_unprepare_transfer_hardware(struct spi_master *master)
 	writew((readw(SSP_CR1(pl022->virtbase)) &
 		(~SSP_CR1_MASK_SSE)), SSP_CR1(pl022->virtbase));
 
-	if (pl022->master_info->autosuspend_delay > 0) {
-		pm_runtime_mark_last_busy(&pl022->adev->dev);
-		pm_runtime_put_autosuspend(&pl022->adev->dev);
-	} else {
-		pm_runtime_put(&pl022->adev->dev);
-	}
-
 	return 0;
 }
 
@@ -2140,7 +2121,7 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id)
 	master->num_chipselect = num_cs;
 	master->cleanup = pl022_cleanup;
 	master->setup = pl022_setup;
-	master->prepare_transfer_hardware = pl022_prepare_transfer_hardware;
+	master->auto_runtime_pm = true;
 	master->transfer_one_message = pl022_transfer_one_message;
 	master->unprepare_transfer_hardware = pl022_unprepare_transfer_hardware;
 	master->rt = platform_info->rt;
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index e0fd6f63c93e..2eb06ee0b326 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -811,14 +811,6 @@ static int pxa2xx_spi_transfer_one_message(struct spi_master *master,
 	return 0;
 }
 
-static int pxa2xx_spi_prepare_transfer(struct spi_master *master)
-{
-	struct driver_data *drv_data = spi_master_get_devdata(master);
-
-	pm_runtime_get_sync(&drv_data->pdev->dev);
-	return 0;
-}
-
 static int pxa2xx_spi_unprepare_transfer(struct spi_master *master)
 {
 	struct driver_data *drv_data = spi_master_get_devdata(master);
@@ -827,8 +819,6 @@ static int pxa2xx_spi_unprepare_transfer(struct spi_master *master)
 	write_SSCR0(read_SSCR0(drv_data->ioaddr) & ~SSCR0_SSE,
 		    drv_data->ioaddr);
 
-	pm_runtime_mark_last_busy(&drv_data->pdev->dev);
-	pm_runtime_put_autosuspend(&drv_data->pdev->dev);
 	return 0;
 }
 
@@ -1141,8 +1131,8 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	master->cleanup = cleanup;
 	master->setup = setup;
 	master->transfer_one_message = pxa2xx_spi_transfer_one_message;
-	master->prepare_transfer_hardware = pxa2xx_spi_prepare_transfer;
 	master->unprepare_transfer_hardware = pxa2xx_spi_unprepare_transfer;
+	master->auto_runtime_pm = true;
 
 	drv_data->ssp_type = ssp->type;
 	drv_data->null_dma_buf = (u32 *)PTR_ALIGN(&drv_data[1], DMA_ALIGNMENT);
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 2465d6d35b06..c5bc96123c1b 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -356,8 +356,6 @@ static int s3c64xx_spi_prepare_transfer(struct spi_master *spi)
 	while (!is_polling(sdd) && !acquire_dma(sdd))
 		usleep_range(10000, 11000);
 
-	pm_runtime_get_sync(&sdd->pdev->dev);
-
 	return 0;
 }
 
@@ -372,7 +370,6 @@ static int s3c64xx_spi_unprepare_transfer(struct spi_master *spi)
 		sdd->ops->release((enum dma_ch)sdd->tx_dma.ch,
 					&s3c64xx_spi_dma_client);
 	}
-	pm_runtime_put(&sdd->pdev->dev);
 
 	return 0;
 }
@@ -1395,6 +1392,7 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 					SPI_BPW_MASK(8);
 	/* the spi->mode bits understood by this driver: */
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	master->auto_runtime_pm = true;
 
 	sdd->regs = devm_ioremap_resource(&pdev->dev, mem_res);
 	if (IS_ERR(sdd->regs)) {
diff --git a/drivers/spi/spi-sh-hspi.c b/drivers/spi/spi-sh-hspi.c
index 716edf999538..b95d6a9fb80e 100644
--- a/drivers/spi/spi-sh-hspi.c
+++ b/drivers/spi/spi-sh-hspi.c
@@ -99,21 +99,6 @@ static int hspi_status_check_timeout(struct hspi_priv *hspi, u32 mask, u32 val)
 /*
  *		spi master function
  */
-static int hspi_prepare_transfer(struct spi_master *master)
-{
-	struct hspi_priv *hspi = spi_master_get_devdata(master);
-
-	pm_runtime_get_sync(hspi->dev);
-	return 0;
-}
-
-static int hspi_unprepare_transfer(struct spi_master *master)
-{
-	struct hspi_priv *hspi = spi_master_get_devdata(master);
-
-	pm_runtime_put_sync(hspi->dev);
-	return 0;
-}
 
 #define hspi_hw_cs_enable(hspi)		hspi_hw_cs_ctrl(hspi, 0)
 #define hspi_hw_cs_disable(hspi)	hspi_hw_cs_ctrl(hspi, 1)
@@ -316,9 +301,8 @@ static int hspi_probe(struct platform_device *pdev)
 	master->setup		= hspi_setup;
 	master->cleanup		= hspi_cleanup;
 	master->mode_bits	= SPI_CPOL | SPI_CPHA;
-	master->prepare_transfer_hardware	= hspi_prepare_transfer;
+	master->auto_runtime_pm = true;
 	master->transfer_one_message		= hspi_transfer_one_message;
-	master->unprepare_transfer_hardware	= hspi_unprepare_transfer;
 	ret = spi_register_master(master);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "spi_register_master error.\n");
diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c
index e8f542ab8935..c14e30c8af2e 100644
--- a/drivers/spi/spi-tegra114.c
+++ b/drivers/spi/spi-tegra114.c
@@ -816,14 +816,6 @@ static int tegra_spi_transfer_one_message(struct spi_master *master,
 	msg->status = 0;
 	msg->actual_length = 0;
 
-	ret = pm_runtime_get_sync(tspi->dev);
-	if (ret < 0) {
-		dev_err(tspi->dev, "runtime PM get failed: %d\n", ret);
-		msg->status = ret;
-		spi_finalize_current_message(master);
-		return ret;
-	}
-
 	single_xfer = list_is_singular(&msg->transfers);
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		INIT_COMPLETION(tspi->xfer_completion);
@@ -859,7 +851,6 @@ static int tegra_spi_transfer_one_message(struct spi_master *master,
 	ret = 0;
 exit:
 	tegra_spi_writel(tspi, tspi->def_command1_reg, SPI_COMMAND1);
-	pm_runtime_put(tspi->dev);
 	msg->status = ret;
 	spi_finalize_current_message(master);
 	return ret;
@@ -1053,6 +1044,7 @@ static int tegra_spi_probe(struct platform_device *pdev)
 	master->transfer_one_message = tegra_spi_transfer_one_message;
 	master->num_chipselect = MAX_CHIP_SELECT;
 	master->bus_num = -1;
+	master->auto_runtime_pm = true;
 
 	tspi->master = master;
 	tspi->dev = &pdev->dev;
diff --git a/drivers/spi/spi-tegra20-sflash.c b/drivers/spi/spi-tegra20-sflash.c
index c1d5d95e70ea..1d814dc6e000 100644
--- a/drivers/spi/spi-tegra20-sflash.c
+++ b/drivers/spi/spi-tegra20-sflash.c
@@ -335,12 +335,6 @@ static int tegra_sflash_transfer_one_message(struct spi_master *master,
 	struct spi_device *spi = msg->spi;
 	int ret;
 
-	ret = pm_runtime_get_sync(tsd->dev);
-	if (ret < 0) {
-		dev_err(tsd->dev, "pm_runtime_get() failed, err = %d\n", ret);
-		return ret;
-	}
-
 	msg->status = 0;
 	msg->actual_length = 0;
 	single_xfer = list_is_singular(&msg->transfers);
@@ -380,7 +374,6 @@ exit:
 	tegra_sflash_writel(tsd, tsd->def_command_reg, SPI_COMMAND);
 	msg->status = ret;
 	spi_finalize_current_message(master);
-	pm_runtime_put(tsd->dev);
 	return ret;
 }
 
@@ -477,6 +470,7 @@ static int tegra_sflash_probe(struct platform_device *pdev)
 	master->mode_bits = SPI_CPOL | SPI_CPHA;
 	master->setup = tegra_sflash_setup;
 	master->transfer_one_message = tegra_sflash_transfer_one_message;
+	master->auto_runtime_pm = true;
 	master->num_chipselect = MAX_CHIP_SELECT;
 	master->bus_num = -1;
 
diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c
index 80490cc11ce5..c70353672a23 100644
--- a/drivers/spi/spi-tegra20-slink.c
+++ b/drivers/spi/spi-tegra20-slink.c
@@ -836,11 +836,6 @@ static int tegra_slink_transfer_one_message(struct spi_master *master,
 
 	msg->status = 0;
 	msg->actual_length = 0;
-	ret = pm_runtime_get_sync(tspi->dev);
-	if (ret < 0) {
-		dev_err(tspi->dev, "runtime get failed: %d\n", ret);
-		goto done;
-	}
 
 	single_xfer = list_is_singular(&msg->transfers);
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
@@ -878,8 +873,6 @@ static int tegra_slink_transfer_one_message(struct spi_master *master,
 exit:
 	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
 	tegra_slink_writel(tspi, tspi->def_command2_reg, SLINK_COMMAND2);
-	pm_runtime_put(tspi->dev);
-done:
 	msg->status = ret;
 	spi_finalize_current_message(master);
 	return ret;
@@ -1086,6 +1079,7 @@ static int tegra_slink_probe(struct platform_device *pdev)
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 	master->setup = tegra_slink_setup;
 	master->transfer_one_message = tegra_slink_transfer_one_message;
+	master->auto_runtime_pm = true;
 	master->num_chipselect = MAX_CHIP_SELECT;
 	master->bus_num = -1;
 
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
new file mode 100644
index 000000000000..e12d962a289f
--- /dev/null
+++ b/drivers/spi/spi-ti-qspi.c
@@ -0,0 +1,574 @@
+/*
+ * TI QSPI driver
+ *
+ * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ * Author: Sourav Poddar <sourav.poddar@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GPLv2.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR /PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/omap-dma.h>
+#include <linux/platform_device.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/consumer.h>
+
+#include <linux/spi/spi.h>
+
+struct ti_qspi_regs {
+	u32 clkctrl;
+};
+
+struct ti_qspi {
+	struct completion       transfer_complete;
+
+	/* IRQ synchronization */
+	spinlock_t              lock;
+
+	/* list synchronization */
+	struct mutex            list_lock;
+
+	struct spi_master	*master;
+	void __iomem            *base;
+	struct clk		*fclk;
+	struct device           *dev;
+
+	struct ti_qspi_regs     ctx_reg;
+
+	u32 spi_max_frequency;
+	u32 cmd;
+	u32 dc;
+	u32 stat;
+};
+
+#define QSPI_PID			(0x0)
+#define QSPI_SYSCONFIG			(0x10)
+#define QSPI_INTR_STATUS_RAW_SET	(0x20)
+#define QSPI_INTR_STATUS_ENABLED_CLEAR	(0x24)
+#define QSPI_INTR_ENABLE_SET_REG	(0x28)
+#define QSPI_INTR_ENABLE_CLEAR_REG	(0x2c)
+#define QSPI_SPI_CLOCK_CNTRL_REG	(0x40)
+#define QSPI_SPI_DC_REG			(0x44)
+#define QSPI_SPI_CMD_REG		(0x48)
+#define QSPI_SPI_STATUS_REG		(0x4c)
+#define QSPI_SPI_DATA_REG		(0x50)
+#define QSPI_SPI_SETUP0_REG		(0x54)
+#define QSPI_SPI_SWITCH_REG		(0x64)
+#define QSPI_SPI_SETUP1_REG		(0x58)
+#define QSPI_SPI_SETUP2_REG		(0x5c)
+#define QSPI_SPI_SETUP3_REG		(0x60)
+#define QSPI_SPI_DATA_REG_1		(0x68)
+#define QSPI_SPI_DATA_REG_2		(0x6c)
+#define QSPI_SPI_DATA_REG_3		(0x70)
+
+#define QSPI_COMPLETION_TIMEOUT		msecs_to_jiffies(2000)
+
+#define QSPI_FCLK			192000000
+
+/* Clock Control */
+#define QSPI_CLK_EN			(1 << 31)
+#define QSPI_CLK_DIV_MAX		0xffff
+
+/* Command */
+#define QSPI_EN_CS(n)			(n << 28)
+#define QSPI_WLEN(n)			((n - 1) << 19)
+#define QSPI_3_PIN			(1 << 18)
+#define QSPI_RD_SNGL			(1 << 16)
+#define QSPI_WR_SNGL			(2 << 16)
+#define QSPI_RD_DUAL			(3 << 16)
+#define QSPI_RD_QUAD			(7 << 16)
+#define QSPI_INVAL			(4 << 16)
+#define QSPI_WC_CMD_INT_EN			(1 << 14)
+#define QSPI_FLEN(n)			((n - 1) << 0)
+
+/* STATUS REGISTER */
+#define WC				0x02
+
+/* INTERRUPT REGISTER */
+#define QSPI_WC_INT_EN				(1 << 1)
+#define QSPI_WC_INT_DISABLE			(1 << 1)
+
+/* Device Control */
+#define QSPI_DD(m, n)			(m << (3 + n * 8))
+#define QSPI_CKPHA(n)			(1 << (2 + n * 8))
+#define QSPI_CSPOL(n)			(1 << (1 + n * 8))
+#define QSPI_CKPOL(n)			(1 << (n * 8))
+
+#define	QSPI_FRAME			4096
+
+#define QSPI_AUTOSUSPEND_TIMEOUT         2000
+
+static inline unsigned long ti_qspi_read(struct ti_qspi *qspi,
+		unsigned long reg)
+{
+	return readl(qspi->base + reg);
+}
+
+static inline void ti_qspi_write(struct ti_qspi *qspi,
+		unsigned long val, unsigned long reg)
+{
+	writel(val, qspi->base + reg);
+}
+
+static int ti_qspi_setup(struct spi_device *spi)
+{
+	struct ti_qspi	*qspi = spi_master_get_devdata(spi->master);
+	struct ti_qspi_regs *ctx_reg = &qspi->ctx_reg;
+	int clk_div = 0, ret;
+	u32 clk_ctrl_reg, clk_rate, clk_mask;
+
+	if (spi->master->busy) {
+		dev_dbg(qspi->dev, "master busy doing other trasnfers\n");
+		return -EBUSY;
+	}
+
+	if (!qspi->spi_max_frequency) {
+		dev_err(qspi->dev, "spi max frequency not defined\n");
+		return -EINVAL;
+	}
+
+	clk_rate = clk_get_rate(qspi->fclk);
+
+	clk_div = DIV_ROUND_UP(clk_rate, qspi->spi_max_frequency) - 1;
+
+	if (clk_div < 0) {
+		dev_dbg(qspi->dev, "clock divider < 0, using /1 divider\n");
+		return -EINVAL;
+	}
+
+	if (clk_div > QSPI_CLK_DIV_MAX) {
+		dev_dbg(qspi->dev, "clock divider >%d , using /%d divider\n",
+				QSPI_CLK_DIV_MAX, QSPI_CLK_DIV_MAX + 1);
+		return -EINVAL;
+	}
+
+	dev_dbg(qspi->dev, "hz: %d, clock divider %d\n",
+			qspi->spi_max_frequency, clk_div);
+
+	ret = pm_runtime_get_sync(qspi->dev);
+	if (ret) {
+		dev_err(qspi->dev, "pm_runtime_get_sync() failed\n");
+		return ret;
+	}
+
+	clk_ctrl_reg = ti_qspi_read(qspi, QSPI_SPI_CLOCK_CNTRL_REG);
+
+	clk_ctrl_reg &= ~QSPI_CLK_EN;
+
+	/* disable SCLK */
+	ti_qspi_write(qspi, clk_ctrl_reg, QSPI_SPI_CLOCK_CNTRL_REG);
+
+	/* enable SCLK */
+	clk_mask = QSPI_CLK_EN | clk_div;
+	ti_qspi_write(qspi, clk_mask, QSPI_SPI_CLOCK_CNTRL_REG);
+	ctx_reg->clkctrl = clk_mask;
+
+	pm_runtime_mark_last_busy(qspi->dev);
+	ret = pm_runtime_put_autosuspend(qspi->dev);
+	if (ret < 0) {
+		dev_err(qspi->dev, "pm_runtime_put_autosuspend() failed\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void ti_qspi_restore_ctx(struct ti_qspi *qspi)
+{
+	struct ti_qspi_regs *ctx_reg = &qspi->ctx_reg;
+
+	ti_qspi_write(qspi, ctx_reg->clkctrl, QSPI_SPI_CLOCK_CNTRL_REG);
+}
+
+static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+{
+	int wlen, count, ret;
+	unsigned int cmd;
+	const u8 *txbuf;
+
+	txbuf = t->tx_buf;
+	cmd = qspi->cmd | QSPI_WR_SNGL;
+	count = t->len;
+	wlen = t->bits_per_word;
+
+	while (count) {
+		switch (wlen) {
+		case 8:
+			dev_dbg(qspi->dev, "tx cmd %08x dc %08x data %02x\n",
+					cmd, qspi->dc, *txbuf);
+			writeb(*txbuf, qspi->base + QSPI_SPI_DATA_REG);
+			ti_qspi_write(qspi, cmd, QSPI_SPI_CMD_REG);
+			ret = wait_for_completion_timeout(&qspi->transfer_complete,
+					QSPI_COMPLETION_TIMEOUT);
+			if (ret == 0) {
+				dev_err(qspi->dev, "write timed out\n");
+				return -ETIMEDOUT;
+			}
+			txbuf += 1;
+			count -= 1;
+			break;
+		case 16:
+			dev_dbg(qspi->dev, "tx cmd %08x dc %08x data %04x\n",
+					cmd, qspi->dc, *txbuf);
+			writew(*((u16 *)txbuf), qspi->base + QSPI_SPI_DATA_REG);
+			ti_qspi_write(qspi, cmd, QSPI_SPI_CMD_REG);
+			ret = wait_for_completion_timeout(&qspi->transfer_complete,
+				QSPI_COMPLETION_TIMEOUT);
+			if (ret == 0) {
+				dev_err(qspi->dev, "write timed out\n");
+				return -ETIMEDOUT;
+			}
+			txbuf += 2;
+			count -= 2;
+			break;
+		case 32:
+			dev_dbg(qspi->dev, "tx cmd %08x dc %08x data %08x\n",
+					cmd, qspi->dc, *txbuf);
+			writel(*((u32 *)txbuf), qspi->base + QSPI_SPI_DATA_REG);
+			ti_qspi_write(qspi, cmd, QSPI_SPI_CMD_REG);
+			ret = wait_for_completion_timeout(&qspi->transfer_complete,
+				QSPI_COMPLETION_TIMEOUT);
+			if (ret == 0) {
+				dev_err(qspi->dev, "write timed out\n");
+				return -ETIMEDOUT;
+			}
+			txbuf += 4;
+			count -= 4;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+{
+	int wlen, count, ret;
+	unsigned int cmd;
+	u8 *rxbuf;
+
+	rxbuf = t->rx_buf;
+	cmd = qspi->cmd;
+	switch (t->rx_nbits) {
+	case SPI_NBITS_DUAL:
+		cmd |= QSPI_RD_DUAL;
+		break;
+	case SPI_NBITS_QUAD:
+		cmd |= QSPI_RD_QUAD;
+		break;
+	default:
+		cmd |= QSPI_RD_SNGL;
+		break;
+	}
+	count = t->len;
+	wlen = t->bits_per_word;
+
+	while (count) {
+		dev_dbg(qspi->dev, "rx cmd %08x dc %08x\n", cmd, qspi->dc);
+		ti_qspi_write(qspi, cmd, QSPI_SPI_CMD_REG);
+		ret = wait_for_completion_timeout(&qspi->transfer_complete,
+				QSPI_COMPLETION_TIMEOUT);
+		if (ret == 0) {
+			dev_err(qspi->dev, "read timed out\n");
+			return -ETIMEDOUT;
+		}
+		switch (wlen) {
+		case 8:
+			*rxbuf = readb(qspi->base + QSPI_SPI_DATA_REG);
+			rxbuf += 1;
+			count -= 1;
+			break;
+		case 16:
+			*((u16 *)rxbuf) = readw(qspi->base + QSPI_SPI_DATA_REG);
+			rxbuf += 2;
+			count -= 2;
+			break;
+		case 32:
+			*((u32 *)rxbuf) = readl(qspi->base + QSPI_SPI_DATA_REG);
+			rxbuf += 4;
+			count -= 4;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+{
+	int ret;
+
+	if (t->tx_buf) {
+		ret = qspi_write_msg(qspi, t);
+		if (ret) {
+			dev_dbg(qspi->dev, "Error while writing\n");
+			return ret;
+		}
+	}
+
+	if (t->rx_buf) {
+		ret = qspi_read_msg(qspi, t);
+		if (ret) {
+			dev_dbg(qspi->dev, "Error while reading\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int ti_qspi_start_transfer_one(struct spi_master *master,
+		struct spi_message *m)
+{
+	struct ti_qspi *qspi = spi_master_get_devdata(master);
+	struct spi_device *spi = m->spi;
+	struct spi_transfer *t;
+	int status = 0, ret;
+	int frame_length;
+
+	/* setup device control reg */
+	qspi->dc = 0;
+
+	if (spi->mode & SPI_CPHA)
+		qspi->dc |= QSPI_CKPHA(spi->chip_select);
+	if (spi->mode & SPI_CPOL)
+		qspi->dc |= QSPI_CKPOL(spi->chip_select);
+	if (spi->mode & SPI_CS_HIGH)
+		qspi->dc |= QSPI_CSPOL(spi->chip_select);
+
+	frame_length = (m->frame_length << 3) / spi->bits_per_word;
+
+	frame_length = clamp(frame_length, 0, QSPI_FRAME);
+
+	/* setup command reg */
+	qspi->cmd = 0;
+	qspi->cmd |= QSPI_EN_CS(spi->chip_select);
+	qspi->cmd |= QSPI_FLEN(frame_length);
+	qspi->cmd |= QSPI_WC_CMD_INT_EN;
+
+	ti_qspi_write(qspi, QSPI_WC_INT_EN, QSPI_INTR_ENABLE_SET_REG);
+	ti_qspi_write(qspi, qspi->dc, QSPI_SPI_DC_REG);
+
+	mutex_lock(&qspi->list_lock);
+
+	list_for_each_entry(t, &m->transfers, transfer_list) {
+		qspi->cmd |= QSPI_WLEN(t->bits_per_word);
+
+		ret = qspi_transfer_msg(qspi, t);
+		if (ret) {
+			dev_dbg(qspi->dev, "transfer message failed\n");
+			mutex_unlock(&qspi->list_lock);
+			return -EINVAL;
+		}
+
+		m->actual_length += t->len;
+	}
+
+	mutex_unlock(&qspi->list_lock);
+
+	m->status = status;
+	spi_finalize_current_message(master);
+
+	ti_qspi_write(qspi, qspi->cmd | QSPI_INVAL, QSPI_SPI_CMD_REG);
+
+	return status;
+}
+
+static irqreturn_t ti_qspi_isr(int irq, void *dev_id)
+{
+	struct ti_qspi *qspi = dev_id;
+	u16 int_stat;
+
+	irqreturn_t ret = IRQ_HANDLED;
+
+	spin_lock(&qspi->lock);
+
+	int_stat = ti_qspi_read(qspi, QSPI_INTR_STATUS_ENABLED_CLEAR);
+	qspi->stat = ti_qspi_read(qspi, QSPI_SPI_STATUS_REG);
+
+	if (!int_stat) {
+		dev_dbg(qspi->dev, "No IRQ triggered\n");
+		ret = IRQ_NONE;
+		goto out;
+	}
+
+	ret = IRQ_WAKE_THREAD;
+
+	ti_qspi_write(qspi, QSPI_WC_INT_DISABLE, QSPI_INTR_ENABLE_CLEAR_REG);
+	ti_qspi_write(qspi, QSPI_WC_INT_DISABLE,
+				QSPI_INTR_STATUS_ENABLED_CLEAR);
+
+out:
+	spin_unlock(&qspi->lock);
+
+	return ret;
+}
+
+static irqreturn_t ti_qspi_threaded_isr(int this_irq, void *dev_id)
+{
+	struct ti_qspi *qspi = dev_id;
+	unsigned long flags;
+
+	spin_lock_irqsave(&qspi->lock, flags);
+
+	if (qspi->stat & WC)
+		complete(&qspi->transfer_complete);
+
+	spin_unlock_irqrestore(&qspi->lock, flags);
+
+	ti_qspi_write(qspi, QSPI_WC_INT_EN, QSPI_INTR_ENABLE_SET_REG);
+
+	return IRQ_HANDLED;
+}
+
+static int ti_qspi_runtime_resume(struct device *dev)
+{
+	struct ti_qspi      *qspi;
+	struct spi_master       *master;
+
+	master = dev_get_drvdata(dev);
+	qspi = spi_master_get_devdata(master);
+	ti_qspi_restore_ctx(qspi);
+
+	return 0;
+}
+
+static const struct of_device_id ti_qspi_match[] = {
+	{.compatible = "ti,dra7xxx-qspi" },
+	{.compatible = "ti,am4372-qspi" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ti_qspi_match);
+
+static int ti_qspi_probe(struct platform_device *pdev)
+{
+	struct  ti_qspi *qspi;
+	struct spi_master *master;
+	struct resource         *r;
+	struct device_node *np = pdev->dev.of_node;
+	u32 max_freq;
+	int ret = 0, num_cs, irq;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*qspi));
+	if (!master)
+		return -ENOMEM;
+
+	master->mode_bits = SPI_CPOL | SPI_CPHA;
+
+	master->bus_num = -1;
+	master->flags = SPI_MASTER_HALF_DUPLEX;
+	master->setup = ti_qspi_setup;
+	master->auto_runtime_pm = true;
+	master->transfer_one_message = ti_qspi_start_transfer_one;
+	master->dev.of_node = pdev->dev.of_node;
+	master->bits_per_word_mask = BIT(32 - 1) | BIT(16 - 1) | BIT(8 - 1);
+
+	if (!of_property_read_u32(np, "num-cs", &num_cs))
+		master->num_chipselect = num_cs;
+
+	platform_set_drvdata(pdev, master);
+
+	qspi = spi_master_get_devdata(master);
+	qspi->master = master;
+	qspi->dev = &pdev->dev;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "no irq resource?\n");
+		return irq;
+	}
+
+	spin_lock_init(&qspi->lock);
+	mutex_init(&qspi->list_lock);
+
+	qspi->base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(qspi->base)) {
+		ret = PTR_ERR(qspi->base);
+		goto free_master;
+	}
+
+	ret = devm_request_threaded_irq(&pdev->dev, irq, ti_qspi_isr,
+			ti_qspi_threaded_isr, 0,
+			dev_name(&pdev->dev), qspi);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to register ISR for IRQ %d\n",
+				irq);
+		goto free_master;
+	}
+
+	qspi->fclk = devm_clk_get(&pdev->dev, "fck");
+	if (IS_ERR(qspi->fclk)) {
+		ret = PTR_ERR(qspi->fclk);
+		dev_err(&pdev->dev, "could not get clk: %d\n", ret);
+	}
+
+	init_completion(&qspi->transfer_complete);
+
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, QSPI_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_enable(&pdev->dev);
+
+	if (!of_property_read_u32(np, "spi-max-frequency", &max_freq))
+		qspi->spi_max_frequency = max_freq;
+
+	ret = spi_register_master(master);
+	if (ret)
+		goto free_master;
+
+	return 0;
+
+free_master:
+	spi_master_put(master);
+	return ret;
+}
+
+static int ti_qspi_remove(struct platform_device *pdev)
+{
+	struct	ti_qspi *qspi = platform_get_drvdata(pdev);
+
+	spi_unregister_master(qspi->master);
+
+	return 0;
+}
+
+static const struct dev_pm_ops ti_qspi_pm_ops = {
+	.runtime_resume = ti_qspi_runtime_resume,
+};
+
+static struct platform_driver ti_qspi_driver = {
+	.probe	= ti_qspi_probe,
+	.remove	= ti_qspi_remove,
+	.driver = {
+		.name	= "ti,dra7xxx-qspi",
+		.owner	= THIS_MODULE,
+		.pm =   &ti_qspi_pm_ops,
+		.of_match_table = ti_qspi_match,
+	}
+};
+
+module_platform_driver(ti_qspi_driver);
+
+MODULE_AUTHOR("Sourav Poddar <sourav.poddar@ti.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("TI QSPI controller driver");
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 7ed5c147c073..6ef349f82b5f 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -553,6 +553,10 @@ static void spi_pump_messages(struct kthread_work *work)
 		    master->unprepare_transfer_hardware(master))
 			dev_err(&master->dev,
 				"failed to unprepare transfer hardware\n");
+		if (master->auto_runtime_pm) {
+			pm_runtime_mark_last_busy(master->dev.parent);
+			pm_runtime_put_autosuspend(master->dev.parent);
+		}
 		return;
 	}
 
@@ -572,11 +576,23 @@ static void spi_pump_messages(struct kthread_work *work)
 		master->busy = true;
 	spin_unlock_irqrestore(&master->queue_lock, flags);
 
+	if (!was_busy && master->auto_runtime_pm) {
+		ret = pm_runtime_get_sync(master->dev.parent);
+		if (ret < 0) {
+			dev_err(&master->dev, "Failed to power device: %d\n",
+				ret);
+			return;
+		}
+	}
+
 	if (!was_busy && master->prepare_transfer_hardware) {
 		ret = master->prepare_transfer_hardware(master);
 		if (ret) {
 			dev_err(&master->dev,
 				"failed to prepare transfer hardware\n");
+
+			if (master->auto_runtime_pm)
+				pm_runtime_put(master->dev.parent);
 			return;
 		}
 	}
@@ -869,6 +885,51 @@ static void of_register_spi_devices(struct spi_master *master)
 		if (of_find_property(nc, "spi-3wire", NULL))
 			spi->mode |= SPI_3WIRE;
 
+		/* Device DUAL/QUAD mode */
+		prop = of_get_property(nc, "spi-tx-nbits", &len);
+		if (!prop || len < sizeof(*prop)) {
+			dev_err(&master->dev, "%s has no 'spi-tx-nbits' property\n",
+				nc->full_name);
+			spi_dev_put(spi);
+			continue;
+		}
+		switch (be32_to_cpup(prop)) {
+		case SPI_NBITS_SINGLE:
+			break;
+		case SPI_NBITS_DUAL:
+			spi->mode |= SPI_TX_DUAL;
+			break;
+		case SPI_NBITS_QUAD:
+			spi->mode |= SPI_TX_QUAD;
+			break;
+		default:
+			dev_err(&master->dev, "spi-tx-nbits value is not supported\n");
+			spi_dev_put(spi);
+			continue;
+		}
+
+		prop = of_get_property(nc, "spi-rx-nbits", &len);
+		if (!prop || len < sizeof(*prop)) {
+			dev_err(&master->dev, "%s has no 'spi-rx-nbits' property\n",
+				nc->full_name);
+			spi_dev_put(spi);
+			continue;
+		}
+		switch (be32_to_cpup(prop)) {
+		case SPI_NBITS_SINGLE:
+			break;
+		case SPI_NBITS_DUAL:
+			spi->mode |= SPI_RX_DUAL;
+			break;
+		case SPI_NBITS_QUAD:
+			spi->mode |= SPI_RX_QUAD;
+			break;
+		default:
+			dev_err(&master->dev, "spi-rx-nbits value is not supported\n");
+			spi_dev_put(spi);
+			continue;
+		}
+
 		/* Device speed */
 		prop = of_get_property(nc, "spi-max-frequency", &len);
 		if (!prop || len < sizeof(*prop)) {
@@ -1316,6 +1377,19 @@ int spi_setup(struct spi_device *spi)
 	unsigned	bad_bits;
 	int		status = 0;
 
+	/* check mode to prevent that DUAL and QUAD set at the same time
+	 */
+	if (((spi->mode & SPI_TX_DUAL) && (spi->mode & SPI_TX_QUAD)) ||
+		((spi->mode & SPI_RX_DUAL) && (spi->mode & SPI_RX_QUAD))) {
+		dev_err(&spi->dev,
+		"setup: can not select dual and quad at the same time\n");
+		return -EINVAL;
+	}
+	/* if it is SPI_3WIRE mode, DUAL and QUAD should be forbidden
+	 */
+	if ((spi->mode & SPI_3WIRE) && (spi->mode &
+		(SPI_TX_DUAL | SPI_TX_QUAD | SPI_RX_DUAL | SPI_RX_QUAD)))
+		return -EINVAL;
 	/* help drivers fail *cleanly* when they need options
 	 * that aren't supported with their current master
 	 */
@@ -1378,6 +1452,8 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message)
 	/**
 	 * Set transfer bits_per_word and max speed as spi device default if
 	 * it is not set for this transfer.
+	 * Set transfer tx_nbits and rx_nbits as single transfer default
+	 * (SPI_NBITS_SINGLE) if it is not set for this transfer.
 	 */
 	list_for_each_entry(xfer, &message->transfers, transfer_list) {
 		message->frame_length += xfer->len;
@@ -1404,7 +1480,47 @@ static int __spi_async(struct spi_device *spi, struct spi_message *message)
 			return -EINVAL;
 		if (xfer->speed_hz && master->max_speed_hz &&
 		    xfer->speed_hz > master->max_speed_hz)
-			return -EINVAL;
+
+		if (xfer->tx_buf && !xfer->tx_nbits)
+			xfer->tx_nbits = SPI_NBITS_SINGLE;
+		if (xfer->rx_buf && !xfer->rx_nbits)
+			xfer->rx_nbits = SPI_NBITS_SINGLE;
+		/* check transfer tx/rx_nbits:
+		 * 1. keep the value is not out of single, dual and quad
+		 * 2. keep tx/rx_nbits is contained by mode in spi_device
+		 * 3. if SPI_3WIRE, tx/rx_nbits should be in single
+		 */
+		if (xfer->tx_buf) {
+			if (xfer->tx_nbits != SPI_NBITS_SINGLE &&
+				xfer->tx_nbits != SPI_NBITS_DUAL &&
+				xfer->tx_nbits != SPI_NBITS_QUAD)
+				return -EINVAL;
+			if ((xfer->tx_nbits == SPI_NBITS_DUAL) &&
+				!(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD)))
+				return -EINVAL;
+			if ((xfer->tx_nbits == SPI_NBITS_QUAD) &&
+				!(spi->mode & SPI_TX_QUAD))
+				return -EINVAL;
+			if ((spi->mode & SPI_3WIRE) &&
+				(xfer->tx_nbits != SPI_NBITS_SINGLE))
+				return -EINVAL;
+		}
+		/* check transfer rx_nbits */
+		if (xfer->rx_buf) {
+			if (xfer->rx_nbits != SPI_NBITS_SINGLE &&
+				xfer->rx_nbits != SPI_NBITS_DUAL &&
+				xfer->rx_nbits != SPI_NBITS_QUAD)
+				return -EINVAL;
+			if ((xfer->rx_nbits == SPI_NBITS_DUAL) &&
+				!(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD)))
+				return -EINVAL;
+			if ((xfer->rx_nbits == SPI_NBITS_QUAD) &&
+				!(spi->mode & SPI_RX_QUAD))
+				return -EINVAL;
+			if ((spi->mode & SPI_3WIRE) &&
+				(xfer->rx_nbits != SPI_NBITS_SINGLE))
+				return -EINVAL;
+		}
 	}
 
 	message->spi = spi;