Merge branch 'spi-5.3' into spi-next

17 files changed, 1603 insertions, 241 deletions

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 30a40280c157..3a1d8f1170de 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -120,7 +120,7 @@ config SPI_AXI_SPI_ENGINE
 config SPI_BCM2835
 	tristate "BCM2835 SPI controller"
 	depends on GPIOLIB
-	depends on ARCH_BCM2835 || COMPILE_TEST
+	depends on ARCH_BCM2835 || ARCH_BRCMSTB || COMPILE_TEST
 	help
 	  This selects a driver for the Broadcom BCM2835 SPI master.
 
@@ -131,7 +131,7 @@ config SPI_BCM2835
 
 config SPI_BCM2835AUX
 	tristate "BCM2835 SPI auxiliary controller"
-	depends on (ARCH_BCM2835 && GPIOLIB) || COMPILE_TEST
+	depends on ((ARCH_BCM2835 || ARCH_BRCMSTB) && GPIOLIB) || COMPILE_TEST
 	help
 	  This selects a driver for the Broadcom BCM2835 SPI aux master.
 
@@ -733,6 +733,16 @@ config SPI_SUN6I
 	help
 	  This enables using the SPI controller on the Allwinner A31 SoCs.
 
+config SPI_SYNQUACER
+	tristate "Socionext's SynQuacer HighSpeed SPI controller"
+	depends on ARCH_SYNQUACER || COMPILE_TEST
+	help
+	  SPI driver for Socionext's High speed SPI controller which provides
+	  various operating modes for interfacing to serial peripheral devices
+	  that use the de-facto standard SPI protocol.
+
+	  It also supports the new dual-bit and quad-bit SPI protocol.
+
 config SPI_MXIC
         tristate "Macronix MX25F0A SPI controller"
         depends on SPI_MASTER
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index f2f78d03dc28..63dcab552bcb 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -106,6 +106,7 @@ obj-$(CONFIG_SPI_STM32_QSPI) 		+= spi-stm32-qspi.o
 obj-$(CONFIG_SPI_ST_SSC4)		+= spi-st-ssc4.o
 obj-$(CONFIG_SPI_SUN4I)			+= spi-sun4i.o
 obj-$(CONFIG_SPI_SUN6I)			+= spi-sun6i.o
+obj-$(CONFIG_SPI_SYNQUACER)		+= spi-synquacer.o
 obj-$(CONFIG_SPI_TEGRA114)		+= spi-tegra114.o
 obj-$(CONFIG_SPI_TEGRA20_SFLASH)	+= spi-tegra20-sflash.o
 obj-$(CONFIG_SPI_TEGRA20_SLINK)		+= spi-tegra20-slink.o
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index 9f24d5f0b431..6a7d7b553d95 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -151,6 +151,7 @@ struct atmel_qspi {
 	const struct atmel_qspi_caps *caps;
 	u32			pending;
 	u32			mr;
+	u32			scr;
 	struct completion	cmd_completion;
 };
 
@@ -382,7 +383,7 @@ static int atmel_qspi_setup(struct spi_device *spi)
 	struct spi_controller *ctrl = spi->master;
 	struct atmel_qspi *aq = spi_controller_get_devdata(ctrl);
 	unsigned long src_rate;
-	u32 scr, scbr;
+	u32 scbr;
 
 	if (ctrl->busy)
 		return -EBUSY;
@@ -399,13 +400,13 @@ static int atmel_qspi_setup(struct spi_device *spi)
 	if (scbr > 0)
 		scbr--;
 
-	scr = QSPI_SCR_SCBR(scbr);
-	writel_relaxed(scr, aq->regs + QSPI_SCR);
+	aq->scr = QSPI_SCR_SCBR(scbr);
+	writel_relaxed(aq->scr, aq->regs + QSPI_SCR);
 
 	return 0;
 }
 
-static int atmel_qspi_init(struct atmel_qspi *aq)
+static void atmel_qspi_init(struct atmel_qspi *aq)
 {
 	/* Reset the QSPI controller */
 	writel_relaxed(QSPI_CR_SWRST, aq->regs + QSPI_CR);
@@ -416,8 +417,6 @@ static int atmel_qspi_init(struct atmel_qspi *aq)
 
 	/* Enable the QSPI controller */
 	writel_relaxed(QSPI_CR_QSPIEN, aq->regs + QSPI_CR);
-
-	return 0;
 }
 
 static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id)
@@ -536,9 +535,7 @@ static int atmel_qspi_probe(struct platform_device *pdev)
 	if (err)
 		goto disable_qspick;
 
-	err = atmel_qspi_init(aq);
-	if (err)
-		goto disable_qspick;
+	atmel_qspi_init(aq);
 
 	err = spi_register_controller(ctrl);
 	if (err)
@@ -587,7 +584,11 @@ static int __maybe_unused atmel_qspi_resume(struct device *dev)
 	clk_prepare_enable(aq->pclk);
 	clk_prepare_enable(aq->qspick);
 
-	return atmel_qspi_init(aq);
+	atmel_qspi_init(aq);
+
+	writel_relaxed(aq->scr, aq->regs + QSPI_SCR);
+
+	return 0;
 }
 
 static SIMPLE_DEV_PM_OPS(atmel_qspi_pm_ops, atmel_qspi_suspend,
diff --git a/drivers/spi/spi-at91-usart.c b/drivers/spi/spi-at91-usart.c
index f763e14bdf12..a40bb2ef89dc 100644
--- a/drivers/spi/spi-at91-usart.c
+++ b/drivers/spi/spi-at91-usart.c
@@ -8,9 +8,12 @@
 
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-direction.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/of_platform.h>
 #include <linux/of_gpio.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
@@ -59,6 +62,8 @@
 
 #define US_INIT \
 	(US_MR_SPI_MASTER | US_MR_CHRL | US_MR_CLKO | US_MR_WRDBT)
+#define US_DMA_MIN_BYTES       16
+#define US_DMA_TIMEOUT         (msecs_to_jiffies(1000))
 
 /* Register access macros */
 #define at91_usart_spi_readl(port, reg) \
@@ -72,14 +77,19 @@
 	writeb_relaxed((value), (port)->regs + US_##reg)
 
 struct at91_usart_spi {
+	struct platform_device  *mpdev;
 	struct spi_transfer	*current_transfer;
 	void __iomem		*regs;
 	struct device		*dev;
 	struct clk		*clk;
 
+	struct completion	xfer_completion;
+
 	/*used in interrupt to protect data reading*/
 	spinlock_t		lock;
 
+	phys_addr_t		phybase;
+
 	int			irq;
 	unsigned int		current_tx_remaining_bytes;
 	unsigned int		current_rx_remaining_bytes;
@@ -88,8 +98,182 @@ struct at91_usart_spi {
 	u32			status;
 
 	bool			xfer_failed;
+	bool			use_dma;
 };
 
+static void dma_callback(void *data)
+{
+	struct spi_controller   *ctlr = data;
+	struct at91_usart_spi   *aus = spi_master_get_devdata(ctlr);
+
+	at91_usart_spi_writel(aus, IER, US_IR_RXRDY);
+	aus->current_rx_remaining_bytes = 0;
+	complete(&aus->xfer_completion);
+}
+
+static bool at91_usart_spi_can_dma(struct spi_controller *ctrl,
+				   struct spi_device *spi,
+				   struct spi_transfer *xfer)
+{
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctrl);
+
+	return aus->use_dma && xfer->len >= US_DMA_MIN_BYTES;
+}
+
+static int at91_usart_spi_configure_dma(struct spi_controller *ctlr,
+					struct at91_usart_spi *aus)
+{
+	struct dma_slave_config slave_config;
+	struct device *dev = &aus->mpdev->dev;
+	phys_addr_t phybase = aus->phybase;
+	dma_cap_mask_t mask;
+	int err = 0;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	ctlr->dma_tx = dma_request_slave_channel_reason(dev, "tx");
+	if (IS_ERR_OR_NULL(ctlr->dma_tx)) {
+		if (IS_ERR(ctlr->dma_tx)) {
+			err = PTR_ERR(ctlr->dma_tx);
+			goto at91_usart_spi_error_clear;
+		}
+
+		dev_dbg(dev,
+			"DMA TX channel not available, SPI unable to use DMA\n");
+		err = -EBUSY;
+		goto at91_usart_spi_error_clear;
+	}
+
+	ctlr->dma_rx = dma_request_slave_channel_reason(dev, "rx");
+	if (IS_ERR_OR_NULL(ctlr->dma_rx)) {
+		if (IS_ERR(ctlr->dma_rx)) {
+			err = PTR_ERR(ctlr->dma_rx);
+			goto at91_usart_spi_error;
+		}
+
+		dev_dbg(dev,
+			"DMA RX channel not available, SPI unable to use DMA\n");
+		err = -EBUSY;
+		goto at91_usart_spi_error;
+	}
+
+	slave_config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	slave_config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	slave_config.dst_addr = (dma_addr_t)phybase + US_THR;
+	slave_config.src_addr = (dma_addr_t)phybase + US_RHR;
+	slave_config.src_maxburst = 1;
+	slave_config.dst_maxburst = 1;
+	slave_config.device_fc = false;
+
+	slave_config.direction = DMA_DEV_TO_MEM;
+	if (dmaengine_slave_config(ctlr->dma_rx, &slave_config)) {
+		dev_err(&ctlr->dev,
+			"failed to configure rx dma channel\n");
+		err = -EINVAL;
+		goto at91_usart_spi_error;
+	}
+
+	slave_config.direction = DMA_MEM_TO_DEV;
+	if (dmaengine_slave_config(ctlr->dma_tx, &slave_config)) {
+		dev_err(&ctlr->dev,
+			"failed to configure tx dma channel\n");
+		err = -EINVAL;
+		goto at91_usart_spi_error;
+	}
+
+	aus->use_dma = true;
+	return 0;
+
+at91_usart_spi_error:
+	if (!IS_ERR_OR_NULL(ctlr->dma_tx))
+		dma_release_channel(ctlr->dma_tx);
+	if (!IS_ERR_OR_NULL(ctlr->dma_rx))
+		dma_release_channel(ctlr->dma_rx);
+	ctlr->dma_tx = NULL;
+	ctlr->dma_rx = NULL;
+
+at91_usart_spi_error_clear:
+	return err;
+}
+
+static void at91_usart_spi_release_dma(struct spi_controller *ctlr)
+{
+	if (ctlr->dma_rx)
+		dma_release_channel(ctlr->dma_rx);
+	if (ctlr->dma_tx)
+		dma_release_channel(ctlr->dma_tx);
+}
+
+static void at91_usart_spi_stop_dma(struct spi_controller *ctlr)
+{
+	if (ctlr->dma_rx)
+		dmaengine_terminate_all(ctlr->dma_rx);
+	if (ctlr->dma_tx)
+		dmaengine_terminate_all(ctlr->dma_tx);
+}
+
+static int at91_usart_spi_dma_transfer(struct spi_controller *ctlr,
+				       struct spi_transfer *xfer)
+{
+	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
+	struct dma_chan	 *rxchan = ctlr->dma_rx;
+	struct dma_chan *txchan = ctlr->dma_tx;
+	struct dma_async_tx_descriptor *rxdesc;
+	struct dma_async_tx_descriptor *txdesc;
+	dma_cookie_t cookie;
+
+	/* Disable RX interrupt */
+	at91_usart_spi_writel(aus, IDR, US_IR_RXRDY);
+
+	rxdesc = dmaengine_prep_slave_sg(rxchan,
+					 xfer->rx_sg.sgl,
+					 xfer->rx_sg.nents,
+					 DMA_DEV_TO_MEM,
+					 DMA_PREP_INTERRUPT |
+					 DMA_CTRL_ACK);
+	if (!rxdesc)
+		goto at91_usart_spi_err_dma;
+
+	txdesc = dmaengine_prep_slave_sg(txchan,
+					 xfer->tx_sg.sgl,
+					 xfer->tx_sg.nents,
+					 DMA_MEM_TO_DEV,
+					 DMA_PREP_INTERRUPT |
+					 DMA_CTRL_ACK);
+	if (!txdesc)
+		goto at91_usart_spi_err_dma;
+
+	rxdesc->callback = dma_callback;
+	rxdesc->callback_param = ctlr;
+
+	cookie = rxdesc->tx_submit(rxdesc);
+	if (dma_submit_error(cookie))
+		goto at91_usart_spi_err_dma;
+
+	cookie = txdesc->tx_submit(txdesc);
+	if (dma_submit_error(cookie))
+		goto at91_usart_spi_err_dma;
+
+	rxchan->device->device_issue_pending(rxchan);
+	txchan->device->device_issue_pending(txchan);
+
+	return 0;
+
+at91_usart_spi_err_dma:
+	/* Enable RX interrupt if something fails and fallback to PIO */
+	at91_usart_spi_writel(aus, IER, US_IR_RXRDY);
+	at91_usart_spi_stop_dma(ctlr);
+
+	return -ENOMEM;
+}
+
+static unsigned long at91_usart_spi_dma_timeout(struct at91_usart_spi *aus)
+{
+	return wait_for_completion_timeout(&aus->xfer_completion,
+					   US_DMA_TIMEOUT);
+}
+
 static inline u32 at91_usart_spi_tx_ready(struct at91_usart_spi *aus)
 {
 	return aus->status & US_IR_TXRDY;
@@ -216,6 +400,8 @@ static int at91_usart_spi_transfer_one(struct spi_controller *ctlr,
 				       struct spi_transfer *xfer)
 {
 	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
+	unsigned long dma_timeout = 0;
+	int ret = 0;
 
 	at91_usart_spi_set_xfer_speed(aus, xfer);
 	aus->xfer_failed = false;
@@ -225,8 +411,25 @@ static int at91_usart_spi_transfer_one(struct spi_controller *ctlr,
 
 	while ((aus->current_tx_remaining_bytes ||
 		aus->current_rx_remaining_bytes) && !aus->xfer_failed) {
-		at91_usart_spi_read_status(aus);
-		at91_usart_spi_tx(aus);
+		reinit_completion(&aus->xfer_completion);
+		if (at91_usart_spi_can_dma(ctlr, spi, xfer) &&
+		    !ret) {
+			ret = at91_usart_spi_dma_transfer(ctlr, xfer);
+			if (ret)
+				continue;
+
+			dma_timeout = at91_usart_spi_dma_timeout(aus);
+
+			if (WARN_ON(dma_timeout == 0)) {
+				dev_err(&spi->dev, "DMA transfer timeout\n");
+				return -EIO;
+			}
+			aus->current_tx_remaining_bytes = 0;
+		} else {
+			at91_usart_spi_read_status(aus);
+			at91_usart_spi_tx(aus);
+		}
+
 		cpu_relax();
 	}
 
@@ -345,6 +548,7 @@ static int at91_usart_spi_probe(struct platform_device *pdev)
 	controller->transfer_one = at91_usart_spi_transfer_one;
 	controller->prepare_message = at91_usart_spi_prepare_message;
 	controller->unprepare_message = at91_usart_spi_unprepare_message;
+	controller->can_dma = at91_usart_spi_can_dma;
 	controller->cleanup = at91_usart_spi_cleanup;
 	controller->max_speed_hz = DIV_ROUND_UP(clk_get_rate(clk),
 						US_MIN_CLK_DIV);
@@ -376,7 +580,17 @@ static int at91_usart_spi_probe(struct platform_device *pdev)
 	aus->spi_clk = clk_get_rate(clk);
 	at91_usart_spi_init(aus);
 
+	aus->phybase = regs->start;
+
+	aus->mpdev = to_platform_device(pdev->dev.parent);
+
+	ret = at91_usart_spi_configure_dma(controller, aus);
+	if (ret)
+		goto at91_usart_fail_dma;
+
 	spin_lock_init(&aus->lock);
+	init_completion(&aus->xfer_completion);
+
 	ret = devm_spi_register_master(&pdev->dev, controller);
 	if (ret)
 		goto at91_usart_fail_register_master;
@@ -389,6 +603,8 @@ static int at91_usart_spi_probe(struct platform_device *pdev)
 	return 0;
 
 at91_usart_fail_register_master:
+	at91_usart_spi_release_dma(controller);
+at91_usart_fail_dma:
 	clk_disable_unprepare(clk);
 at91_usart_spi_probe_fail:
 	spi_master_put(controller);
@@ -453,6 +669,7 @@ static int at91_usart_spi_remove(struct platform_device *pdev)
 	struct spi_controller *ctlr = platform_get_drvdata(pdev);
 	struct at91_usart_spi *aus = spi_master_get_devdata(ctlr);
 
+	at91_usart_spi_release_dma(ctlr);
 	clk_disable_unprepare(aus->clk);
 
 	return 0;
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 402c1efcd762..6f243a90c844 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -13,6 +13,7 @@
 
 #include <linux/clk.h>
 #include <linux/completion.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
@@ -64,14 +65,18 @@
 
 #define BCM2835_SPI_FIFO_SIZE		64
 #define BCM2835_SPI_FIFO_SIZE_3_4	48
-#define BCM2835_SPI_POLLING_LIMIT_US	30
-#define BCM2835_SPI_POLLING_JIFFIES	2
 #define BCM2835_SPI_DMA_MIN_LENGTH	96
 #define BCM2835_SPI_MODE_BITS	(SPI_CPOL | SPI_CPHA | SPI_CS_HIGH \
 				| SPI_NO_CS | SPI_3WIRE)
 
 #define DRV_NAME	"spi-bcm2835"
 
+/* define polling limits */
+unsigned int polling_limit_us = 30;
+module_param(polling_limit_us, uint, 0664);
+MODULE_PARM_DESC(polling_limit_us,
+		 "time in us to run a transfer in polling mode\n");
+
 /**
  * struct bcm2835_spi - BCM2835 SPI controller
  * @regs: base address of register map
@@ -88,6 +93,15 @@
  *	length is not a multiple of 4 (to overcome hardware limitation)
  * @tx_spillover: whether @tx_prologue spills over to second TX sglist entry
  * @dma_pending: whether a DMA transfer is in progress
+ * @debugfs_dir: the debugfs directory - neede to remove debugfs when
+ *      unloading the module
+ * @count_transfer_polling: count of how often polling mode is used
+ * @count_transfer_irq: count of how often interrupt mode is used
+ * @count_transfer_irq_after_polling: count of how often we fall back to
+ *      interrupt mode after starting in polling mode.
+ *      These are counted as well in @count_transfer_polling and
+ *      @count_transfer_irq
+ * @count_transfer_dma: count how often dma mode is used
  */
 struct bcm2835_spi {
 	void __iomem *regs;
@@ -102,8 +116,55 @@ struct bcm2835_spi {
 	int rx_prologue;
 	unsigned int tx_spillover;
 	unsigned int dma_pending;
+
+	struct dentry *debugfs_dir;
+	u64 count_transfer_polling;
+	u64 count_transfer_irq;
+	u64 count_transfer_irq_after_polling;
+	u64 count_transfer_dma;
 };
 
+#if defined(CONFIG_DEBUG_FS)
+static void bcm2835_debugfs_create(struct bcm2835_spi *bs,
+				   const char *dname)
+{
+	char name[64];
+	struct dentry *dir;
+
+	/* get full name */
+	snprintf(name, sizeof(name), "spi-bcm2835-%s", dname);
+
+	/* the base directory */
+	dir = debugfs_create_dir(name, NULL);
+	bs->debugfs_dir = dir;
+
+	/* the counters */
+	debugfs_create_u64("count_transfer_polling", 0444, dir,
+			   &bs->count_transfer_polling);
+	debugfs_create_u64("count_transfer_irq", 0444, dir,
+			   &bs->count_transfer_irq);
+	debugfs_create_u64("count_transfer_irq_after_polling", 0444, dir,
+			   &bs->count_transfer_irq_after_polling);
+	debugfs_create_u64("count_transfer_dma", 0444, dir,
+			   &bs->count_transfer_dma);
+}
+
+static void bcm2835_debugfs_remove(struct bcm2835_spi *bs)
+{
+	debugfs_remove_recursive(bs->debugfs_dir);
+	bs->debugfs_dir = NULL;
+}
+#else
+static void bcm2835_debugfs_create(struct bcm2835_spi *bs,
+				   const char *dname)
+{
+}
+
+static void bcm2835_debugfs_remove(struct bcm2835_spi *bs)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
 static inline u32 bcm2835_rd(struct bcm2835_spi *bs, unsigned reg)
 {
 	return readl(bs->regs + reg);
@@ -248,9 +309,9 @@ static inline void bcm2835_wr_fifo_blind(struct bcm2835_spi *bs, int count)
 	}
 }
 
-static void bcm2835_spi_reset_hw(struct spi_master *master)
+static void bcm2835_spi_reset_hw(struct spi_controller *ctlr)
 {
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
 
 	/* Disable SPI interrupts and transfer */
@@ -269,8 +330,8 @@ static void bcm2835_spi_reset_hw(struct spi_master *master)
 
 static irqreturn_t bcm2835_spi_interrupt(int irq, void *dev_id)
 {
-	struct spi_master *master = dev_id;
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = dev_id;
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
 
 	/*
@@ -292,20 +353,23 @@ static irqreturn_t bcm2835_spi_interrupt(int irq, void *dev_id)
 
 	if (!bs->rx_len) {
 		/* Transfer complete - reset SPI HW */
-		bcm2835_spi_reset_hw(master);
+		bcm2835_spi_reset_hw(ctlr);
 		/* wake up the framework */
-		complete(&master->xfer_completion);
+		complete(&ctlr->xfer_completion);
 	}
 
 	return IRQ_HANDLED;
 }
 
-static int bcm2835_spi_transfer_one_irq(struct spi_master *master,
+static int bcm2835_spi_transfer_one_irq(struct spi_controller *ctlr,
 					struct spi_device *spi,
 					struct spi_transfer *tfr,
 					u32 cs, bool fifo_empty)
 {
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
+
+	/* update usage statistics */
+	bs->count_transfer_irq++;
 
 	/*
 	 * Enable HW block, but with interrupts still disabled.
@@ -328,7 +392,7 @@ static int bcm2835_spi_transfer_one_irq(struct spi_master *master,
 
 /**
  * bcm2835_spi_transfer_prologue() - transfer first few bytes without DMA
- * @master: SPI master
+ * @ctlr: SPI master controller
  * @tfr: SPI transfer
  * @bs: BCM2835 SPI controller
  * @cs: CS register
@@ -372,7 +436,7 @@ static int bcm2835_spi_transfer_one_irq(struct spi_master *master,
  * be transmitted in 32-bit width to ensure that the following DMA transfer can
  * pick up the residue in the RX FIFO in ungarbled form.
  */
-static void bcm2835_spi_transfer_prologue(struct spi_master *master,
+static void bcm2835_spi_transfer_prologue(struct spi_controller *ctlr,
 					  struct spi_transfer *tfr,
 					  struct bcm2835_spi *bs,
 					  u32 cs)
@@ -413,9 +477,9 @@ static void bcm2835_spi_transfer_prologue(struct spi_master *master,
 		bcm2835_wr_fifo_count(bs, bs->rx_prologue);
 		bcm2835_wait_tx_fifo_empty(bs);
 		bcm2835_rd_fifo_count(bs, bs->rx_prologue);
-		bcm2835_spi_reset_hw(master);
+		bcm2835_spi_reset_hw(ctlr);
 
-		dma_sync_single_for_device(master->dma_rx->device->dev,
+		dma_sync_single_for_device(ctlr->dma_rx->device->dev,
 					   sg_dma_address(&tfr->rx_sg.sgl[0]),
 					   bs->rx_prologue, DMA_FROM_DEVICE);
 
@@ -479,11 +543,11 @@ static void bcm2835_spi_undo_prologue(struct bcm2835_spi *bs)
 
 static void bcm2835_spi_dma_done(void *data)
 {
-	struct spi_master *master = data;
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = data;
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 
 	/* reset fifo and HW */
-	bcm2835_spi_reset_hw(master);
+	bcm2835_spi_reset_hw(ctlr);
 
 	/* and terminate tx-dma as we do not have an irq for it
 	 * because when the rx dma will terminate and this callback
@@ -491,15 +555,15 @@ static void bcm2835_spi_dma_done(void *data)
 	 * situation otherwise...
 	 */
 	if (cmpxchg(&bs->dma_pending, true, false)) {
-		dmaengine_terminate_async(master->dma_tx);
+		dmaengine_terminate_async(ctlr->dma_tx);
 		bcm2835_spi_undo_prologue(bs);
 	}
 
 	/* and mark as completed */;
-	complete(&master->xfer_completion);
+	complete(&ctlr->xfer_completion);
 }
 
-static int bcm2835_spi_prepare_sg(struct spi_master *master,
+static int bcm2835_spi_prepare_sg(struct spi_controller *ctlr,
 				  struct spi_transfer *tfr,
 				  bool is_tx)
 {
@@ -514,14 +578,14 @@ static int bcm2835_spi_prepare_sg(struct spi_master *master,
 
 	if (is_tx) {
 		dir   = DMA_MEM_TO_DEV;
-		chan  = master->dma_tx;
+		chan  = ctlr->dma_tx;
 		nents = tfr->tx_sg.nents;
 		sgl   = tfr->tx_sg.sgl;
 		flags = 0 /* no  tx interrupt */;
 
 	} else {
 		dir   = DMA_DEV_TO_MEM;
-		chan  = master->dma_rx;
+		chan  = ctlr->dma_rx;
 		nents = tfr->rx_sg.nents;
 		sgl   = tfr->rx_sg.sgl;
 		flags = DMA_PREP_INTERRUPT;
@@ -534,7 +598,7 @@ static int bcm2835_spi_prepare_sg(struct spi_master *master,
 	/* set callback for rx */
 	if (!is_tx) {
 		desc->callback = bcm2835_spi_dma_done;
-		desc->callback_param = master;
+		desc->callback_param = ctlr;
 	}
 
 	/* submit it to DMA-engine */
@@ -543,27 +607,30 @@ static int bcm2835_spi_prepare_sg(struct spi_master *master,
 	return dma_submit_error(cookie);
 }
 
-static int bcm2835_spi_transfer_one_dma(struct spi_master *master,
+static int bcm2835_spi_transfer_one_dma(struct spi_controller *ctlr,
 					struct spi_device *spi,
 					struct spi_transfer *tfr,
 					u32 cs)
 {
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	int ret;
 
+	/* update usage statistics */
+	bs->count_transfer_dma++;
+
 	/*
 	 * Transfer first few bytes without DMA if length of first TX or RX
 	 * sglist entry is not a multiple of 4 bytes (hardware limitation).
 	 */
-	bcm2835_spi_transfer_prologue(master, tfr, bs, cs);
+	bcm2835_spi_transfer_prologue(ctlr, tfr, bs, cs);
 
 	/* setup tx-DMA */
-	ret = bcm2835_spi_prepare_sg(master, tfr, true);
+	ret = bcm2835_spi_prepare_sg(ctlr, tfr, true);
 	if (ret)
 		goto err_reset_hw;
 
 	/* start TX early */
-	dma_async_issue_pending(master->dma_tx);
+	dma_async_issue_pending(ctlr->dma_tx);
 
 	/* mark as dma pending */
 	bs->dma_pending = 1;
@@ -579,27 +646,27 @@ static int bcm2835_spi_transfer_one_dma(struct spi_master *master,
 	 * mapping of the rx buffers still takes place
 	 * this saves 10us or more.
 	 */
-	ret = bcm2835_spi_prepare_sg(master, tfr, false);
+	ret = bcm2835_spi_prepare_sg(ctlr, tfr, false);
 	if (ret) {
 		/* need to reset on errors */
-		dmaengine_terminate_sync(master->dma_tx);
+		dmaengine_terminate_sync(ctlr->dma_tx);
 		bs->dma_pending = false;
 		goto err_reset_hw;
 	}
 
 	/* start rx dma late */
-	dma_async_issue_pending(master->dma_rx);
+	dma_async_issue_pending(ctlr->dma_rx);
 
 	/* wait for wakeup in framework */
 	return 1;
 
 err_reset_hw:
-	bcm2835_spi_reset_hw(master);
+	bcm2835_spi_reset_hw(ctlr);
 	bcm2835_spi_undo_prologue(bs);
 	return ret;
 }
 
-static bool bcm2835_spi_can_dma(struct spi_master *master,
+static bool bcm2835_spi_can_dma(struct spi_controller *ctlr,
 				struct spi_device *spi,
 				struct spi_transfer *tfr)
 {
@@ -611,21 +678,21 @@ static bool bcm2835_spi_can_dma(struct spi_master *master,
 	return true;
 }
 
-static void bcm2835_dma_release(struct spi_master *master)
+static void bcm2835_dma_release(struct spi_controller *ctlr)
 {
-	if (master->dma_tx) {
-		dmaengine_terminate_sync(master->dma_tx);
-		dma_release_channel(master->dma_tx);
-		master->dma_tx = NULL;
+	if (ctlr->dma_tx) {
+		dmaengine_terminate_sync(ctlr->dma_tx);
+		dma_release_channel(ctlr->dma_tx);
+		ctlr->dma_tx = NULL;
 	}
-	if (master->dma_rx) {
-		dmaengine_terminate_sync(master->dma_rx);
-		dma_release_channel(master->dma_rx);
-		master->dma_rx = NULL;
+	if (ctlr->dma_rx) {
+		dmaengine_terminate_sync(ctlr->dma_rx);
+		dma_release_channel(ctlr->dma_rx);
+		ctlr->dma_rx = NULL;
 	}
 }
 
-static void bcm2835_dma_init(struct spi_master *master, struct device *dev)
+static void bcm2835_dma_init(struct spi_controller *ctlr, struct device *dev)
 {
 	struct dma_slave_config slave_config;
 	const __be32 *addr;
@@ -633,7 +700,7 @@ static void bcm2835_dma_init(struct spi_master *master, struct device *dev)
 	int ret;
 
 	/* base address in dma-space */
-	addr = of_get_address(master->dev.of_node, 0, NULL, NULL);
+	addr = of_get_address(ctlr->dev.of_node, 0, NULL, NULL);
 	if (!addr) {
 		dev_err(dev, "could not get DMA-register address - not using dma mode\n");
 		goto err;
@@ -641,38 +708,36 @@ static void bcm2835_dma_init(struct spi_master *master, struct device *dev)
 	dma_reg_base = be32_to_cpup(addr);
 
 	/* get tx/rx dma */
-	master->dma_tx = dma_request_slave_channel(dev, "tx");
-	if (!master->dma_tx) {
+	ctlr->dma_tx = dma_request_slave_channel(dev, "tx");
+	if (!ctlr->dma_tx) {
 		dev_err(dev, "no tx-dma configuration found - not using dma mode\n");
 		goto err;
 	}
-	master->dma_rx = dma_request_slave_channel(dev, "rx");
-	if (!master->dma_rx) {
+	ctlr->dma_rx = dma_request_slave_channel(dev, "rx");
+	if (!ctlr->dma_rx) {
 		dev_err(dev, "no rx-dma configuration found - not using dma mode\n");
 		goto err_release;
 	}
 
 	/* configure DMAs */
-	slave_config.direction = DMA_MEM_TO_DEV;
 	slave_config.dst_addr = (u32)(dma_reg_base + BCM2835_SPI_FIFO);
 	slave_config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 
-	ret = dmaengine_slave_config(master->dma_tx, &slave_config);
+	ret = dmaengine_slave_config(ctlr->dma_tx, &slave_config);
 	if (ret)
 		goto err_config;
 
-	slave_config.direction = DMA_DEV_TO_MEM;
 	slave_config.src_addr = (u32)(dma_reg_base + BCM2835_SPI_FIFO);
 	slave_config.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 
-	ret = dmaengine_slave_config(master->dma_rx, &slave_config);
+	ret = dmaengine_slave_config(ctlr->dma_rx, &slave_config);
 	if (ret)
 		goto err_config;
 
 	/* all went well, so set can_dma */
-	master->can_dma = bcm2835_spi_can_dma;
+	ctlr->can_dma = bcm2835_spi_can_dma;
 	/* need to do TX AND RX DMA, so we need dummy buffers */
-	master->flags = SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX;
+	ctlr->flags = SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX;
 
 	return;
 
@@ -680,20 +745,22 @@ err_config:
 	dev_err(dev, "issue configuring dma: %d - not using DMA mode\n",
 		ret);
 err_release:
-	bcm2835_dma_release(master);
+	bcm2835_dma_release(ctlr);
 err:
 	return;
 }
 
-static int bcm2835_spi_transfer_one_poll(struct spi_master *master,
+static int bcm2835_spi_transfer_one_poll(struct spi_controller *ctlr,
 					 struct spi_device *spi,
 					 struct spi_transfer *tfr,
-					 u32 cs,
-					 unsigned long long xfer_time_us)
+					 u32 cs)
 {
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	unsigned long timeout;
 
+	/* update usage statistics */
+	bs->count_transfer_polling++;
+
 	/* enable HW block without interrupts */
 	bcm2835_wr(bs, BCM2835_SPI_CS, cs | BCM2835_SPI_CS_TA);
 
@@ -703,8 +770,8 @@ static int bcm2835_spi_transfer_one_poll(struct spi_master *master,
 	 */
 	bcm2835_wr_fifo_blind(bs, BCM2835_SPI_FIFO_SIZE);
 
-	/* set the timeout */
-	timeout = jiffies + BCM2835_SPI_POLLING_JIFFIES;
+	/* set the timeout to at least 2 jiffies */
+	timeout = jiffies + 2 + HZ * polling_limit_us / 1000000;
 
 	/* loop until finished the transfer */
 	while (bs->rx_len) {
@@ -723,25 +790,28 @@ static int bcm2835_spi_transfer_one_poll(struct spi_master *master,
 					    jiffies - timeout,
 					    bs->tx_len, bs->rx_len);
 			/* fall back to interrupt mode */
-			return bcm2835_spi_transfer_one_irq(master, spi,
+
+			/* update usage statistics */
+			bs->count_transfer_irq_after_polling++;
+
+			return bcm2835_spi_transfer_one_irq(ctlr, spi,
 							    tfr, cs, false);
 		}
 	}
 
 	/* Transfer complete - reset SPI HW */
-	bcm2835_spi_reset_hw(master);
+	bcm2835_spi_reset_hw(ctlr);
 	/* and return without waiting for completion */
 	return 0;
 }
 
-static int bcm2835_spi_transfer_one(struct spi_master *master,
+static int bcm2835_spi_transfer_one(struct spi_controller *ctlr,
 				    struct spi_device *spi,
 				    struct spi_transfer *tfr)
 {
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
-	unsigned long spi_hz, clk_hz, cdiv;
-	unsigned long spi_used_hz;
-	unsigned long long xfer_time_us;
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
+	unsigned long spi_hz, clk_hz, cdiv, spi_used_hz;
+	unsigned long hz_per_byte, byte_limit;
 	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
 
 	/* set clock */
@@ -782,42 +852,49 @@ static int bcm2835_spi_transfer_one(struct spi_master *master,
 	bs->tx_len = tfr->len;
 	bs->rx_len = tfr->len;
 
-	/* calculate the estimated time in us the transfer runs */
-	xfer_time_us = (unsigned long long)tfr->len
-		* 9 /* clocks/byte - SPI-HW waits 1 clock after each byte */
-		* 1000000;
-	do_div(xfer_time_us, spi_used_hz);
+	/* Calculate the estimated time in us the transfer runs.  Note that
+	 * there is 1 idle clocks cycles after each byte getting transferred
+	 * so we have 9 cycles/byte.  This is used to find the number of Hz
+	 * per byte per polling limit.  E.g., we can transfer 1 byte in 30 us
+	 * per 300,000 Hz of bus clock.
+	 */
+	hz_per_byte = polling_limit_us ? (9 * 1000000) / polling_limit_us : 0;
+	byte_limit = hz_per_byte ? spi_used_hz / hz_per_byte : 1;
 
-	/* for short requests run polling*/
-	if (xfer_time_us <= BCM2835_SPI_POLLING_LIMIT_US)
-		return bcm2835_spi_transfer_one_poll(master, spi, tfr,
-						     cs, xfer_time_us);
+	/* run in polling mode for short transfers */
+	if (tfr->len < byte_limit)
+		return bcm2835_spi_transfer_one_poll(ctlr, spi, tfr, cs);
 
-	/* run in dma mode if conditions are right */
-	if (master->can_dma && bcm2835_spi_can_dma(master, spi, tfr))
-		return bcm2835_spi_transfer_one_dma(master, spi, tfr, cs);
+	/* run in dma mode if conditions are right
+	 * Note that unlike poll or interrupt mode DMA mode does not have
+	 * this 1 idle clock cycle pattern but runs the spi clock without gaps
+	 */
+	if (ctlr->can_dma && bcm2835_spi_can_dma(ctlr, spi, tfr))
+		return bcm2835_spi_transfer_one_dma(ctlr, spi, tfr, cs);
 
 	/* run in interrupt-mode */
-	return bcm2835_spi_transfer_one_irq(master, spi, tfr, cs, true);
+	return bcm2835_spi_transfer_one_irq(ctlr, spi, tfr, cs, true);
 }
 
-static int bcm2835_spi_prepare_message(struct spi_master *master,
+static int bcm2835_spi_prepare_message(struct spi_controller *ctlr,
 				       struct spi_message *msg)
 {
 	struct spi_device *spi = msg->spi;
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
 	int ret;
 
-	/*
-	 * DMA transfers are limited to 16 bit (0 to 65535 bytes) by the SPI HW
-	 * due to DLEN. Split up transfers (32-bit FIFO aligned) if the limit is
-	 * exceeded.
-	 */
-	ret = spi_split_transfers_maxsize(master, msg, 65532,
-					  GFP_KERNEL | GFP_DMA);
-	if (ret)
-		return ret;
+	if (ctlr->can_dma) {
+		/*
+		 * DMA transfers are limited to 16 bit (0 to 65535 bytes) by
+		 * the SPI HW due to DLEN. Split up transfers (32-bit FIFO
+		 * aligned) if the limit is exceeded.
+		 */
+		ret = spi_split_transfers_maxsize(ctlr, msg, 65532,
+						  GFP_KERNEL | GFP_DMA);
+		if (ret)
+			return ret;
+	}
 
 	cs &= ~(BCM2835_SPI_CS_CPOL | BCM2835_SPI_CS_CPHA);
 
@@ -831,19 +908,19 @@ static int bcm2835_spi_prepare_message(struct spi_master *master,
 	return 0;
 }
 
-static void bcm2835_spi_handle_err(struct spi_master *master,
+static void bcm2835_spi_handle_err(struct spi_controller *ctlr,
 				   struct spi_message *msg)
 {
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 
 	/* if an error occurred and we have an active dma, then terminate */
 	if (cmpxchg(&bs->dma_pending, true, false)) {
-		dmaengine_terminate_sync(master->dma_tx);
-		dmaengine_terminate_sync(master->dma_rx);
+		dmaengine_terminate_sync(ctlr->dma_tx);
+		dmaengine_terminate_sync(ctlr->dma_rx);
 		bcm2835_spi_undo_prologue(bs);
 	}
 	/* and reset */
-	bcm2835_spi_reset_hw(master);
+	bcm2835_spi_reset_hw(ctlr);
 }
 
 static int chip_match_name(struct gpio_chip *chip, void *data)
@@ -900,85 +977,88 @@ static int bcm2835_spi_setup(struct spi_device *spi)
 
 static int bcm2835_spi_probe(struct platform_device *pdev)
 {
-	struct spi_master *master;
+	struct spi_controller *ctlr;
 	struct bcm2835_spi *bs;
 	struct resource *res;
 	int err;
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*bs));
-	if (!master) {
-		dev_err(&pdev->dev, "spi_alloc_master() failed\n");
+	ctlr = spi_alloc_master(&pdev->dev, sizeof(*bs));
+	if (!ctlr)
 		return -ENOMEM;
-	}
 
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, ctlr);
 
-	master->mode_bits = BCM2835_SPI_MODE_BITS;
-	master->bits_per_word_mask = SPI_BPW_MASK(8);
-	master->num_chipselect = 3;
-	master->setup = bcm2835_spi_setup;
-	master->transfer_one = bcm2835_spi_transfer_one;
-	master->handle_err = bcm2835_spi_handle_err;
-	master->prepare_message = bcm2835_spi_prepare_message;
-	master->dev.of_node = pdev->dev.of_node;
+	ctlr->mode_bits = BCM2835_SPI_MODE_BITS;
+	ctlr->bits_per_word_mask = SPI_BPW_MASK(8);
+	ctlr->num_chipselect = 3;
+	ctlr->setup = bcm2835_spi_setup;
+	ctlr->transfer_one = bcm2835_spi_transfer_one;
+	ctlr->handle_err = bcm2835_spi_handle_err;
+	ctlr->prepare_message = bcm2835_spi_prepare_message;
+	ctlr->dev.of_node = pdev->dev.of_node;
 
-	bs = spi_master_get_devdata(master);
+	bs = spi_controller_get_devdata(ctlr);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	bs->regs = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(bs->regs)) {
 		err = PTR_ERR(bs->regs);
-		goto out_master_put;
+		goto out_controller_put;
 	}
 
 	bs->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(bs->clk)) {
 		err = PTR_ERR(bs->clk);
 		dev_err(&pdev->dev, "could not get clk: %d\n", err);
-		goto out_master_put;
+		goto out_controller_put;
 	}
 
 	bs->irq = platform_get_irq(pdev, 0);
 	if (bs->irq <= 0) {
 		dev_err(&pdev->dev, "could not get IRQ: %d\n", bs->irq);
 		err = bs->irq ? bs->irq : -ENODEV;
-		goto out_master_put;
+		goto out_controller_put;
 	}
 
 	clk_prepare_enable(bs->clk);
 
-	bcm2835_dma_init(master, &pdev->dev);
+	bcm2835_dma_init(ctlr, &pdev->dev);
 
 	/* initialise the hardware with the default polarities */
 	bcm2835_wr(bs, BCM2835_SPI_CS,
 		   BCM2835_SPI_CS_CLEAR_RX | BCM2835_SPI_CS_CLEAR_TX);
 
 	err = devm_request_irq(&pdev->dev, bs->irq, bcm2835_spi_interrupt, 0,
-			       dev_name(&pdev->dev), master);
+			       dev_name(&pdev->dev), ctlr);
 	if (err) {
 		dev_err(&pdev->dev, "could not request IRQ: %d\n", err);
 		goto out_clk_disable;
 	}
 
-	err = devm_spi_register_master(&pdev->dev, master);
+	err = devm_spi_register_controller(&pdev->dev, ctlr);
 	if (err) {
-		dev_err(&pdev->dev, "could not register SPI master: %d\n", err);
+		dev_err(&pdev->dev, "could not register SPI controller: %d\n",
+			err);
 		goto out_clk_disable;
 	}
 
+	bcm2835_debugfs_create(bs, dev_name(&pdev->dev));
+
 	return 0;
 
 out_clk_disable:
 	clk_disable_unprepare(bs->clk);
-out_master_put:
-	spi_master_put(master);
+out_controller_put:
+	spi_controller_put(ctlr);
 	return err;
 }
 
 static int bcm2835_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	struct spi_controller *ctlr = platform_get_drvdata(pdev);
+	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
+
+	bcm2835_debugfs_remove(bs);
 
 	/* Clear FIFOs, and disable the HW block */
 	bcm2835_wr(bs, BCM2835_SPI_CS,
@@ -986,7 +1066,7 @@ static int bcm2835_spi_remove(struct platform_device *pdev)
 
 	clk_disable_unprepare(bs->clk);
 
-	bcm2835_dma_release(master);
+	bcm2835_dma_release(ctlr);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 40dfb7f58efe..bb57035c5770 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -496,10 +496,8 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
 	int err;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(*bs));
-	if (!master) {
-		dev_err(&pdev->dev, "spi_alloc_master() failed\n");
+	if (!master)
 		return -ENOMEM;
-	}
 
 	platform_set_drvdata(pdev, master);
 	master->mode_bits = (SPI_CPOL | SPI_CS_HIGH | SPI_NO_CS);
diff --git a/drivers/spi/spi-meson-spifc.c b/drivers/spi/spi-meson-spifc.c
index ea4b1bf0fa16..f7fe9b13d122 100644
--- a/drivers/spi/spi-meson-spifc.c
+++ b/drivers/spi/spi-meson-spifc.c
@@ -1,9 +1,9 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Driver for Amlogic Meson SPI flash controller (SPIFC)
- *
- * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Driver for Amlogic Meson SPI flash controller (SPIFC)
+//
+// Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com>
+//
 
 #include <linux/clk.h>
 #include <linux/delay.h>
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 10041eab36a2..45d8a7048b6c 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -123,8 +123,6 @@ static const struct mtk_spi_compatible mt8183_compat = {
  * supplies it.
  */
 static const struct mtk_chip_config mtk_default_chip_info = {
-	.rx_mlsb = 1,
-	.tx_mlsb = 1,
 	.cs_pol = 0,
 	.sample_sel = 0,
 };
@@ -195,14 +193,13 @@ static int mtk_spi_prepare_message(struct spi_master *master,
 		reg_val &= ~SPI_CMD_CPOL;
 
 	/* set the mlsbx and mlsbtx */
-	if (chip_config->tx_mlsb)
-		reg_val |= SPI_CMD_TXMSBF;
-	else
+	if (spi->mode & SPI_LSB_FIRST) {
 		reg_val &= ~SPI_CMD_TXMSBF;
-	if (chip_config->rx_mlsb)
-		reg_val |= SPI_CMD_RXMSBF;
-	else
 		reg_val &= ~SPI_CMD_RXMSBF;
+	} else {
+		reg_val |= SPI_CMD_TXMSBF;
+		reg_val |= SPI_CMD_RXMSBF;
+	}
 
 	/* set the tx/rx endian */
 #ifdef __LITTLE_ENDIAN
@@ -599,7 +596,7 @@ static int mtk_spi_probe(struct platform_device *pdev)
 
 	master->auto_runtime_pm = true;
 	master->dev.of_node = pdev->dev.of_node;
-	master->mode_bits = SPI_CPOL | SPI_CPHA;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
 
 	master->set_cs = mtk_spi_set_cs;
 	master->prepare_message = mtk_spi_prepare_message;
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index af3f37ba82c8..fc7ab4b26880 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1437,6 +1437,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0x34aa), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0x34ab), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0x34fb), LPSS_CNL_SSP },
+	/* EHL */
+	{ PCI_VDEVICE(INTEL, 0x4b2a), LPSS_BXT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x4b2b), LPSS_BXT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x4b37), LPSS_BXT_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
@@ -1704,6 +1708,16 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 		goto out_error_dma_irq_alloc;
 
 	controller->max_speed_hz = clk_get_rate(ssp->clk);
+	/*
+	 * Set minimum speed for all other platforms than Intel Quark which is
+	 * able do under 1 Hz transfers.
+	 */
+	if (!pxa25x_ssp_comp(drv_data))
+		controller->min_speed_hz =
+			DIV_ROUND_UP(controller->max_speed_hz, 4096);
+	else if (!is_quark_x1000_ssp(drv_data))
+		controller->min_speed_hz =
+			DIV_ROUND_UP(controller->max_speed_hz, 512);
 
 	/* Load default SSP configuration */
 	pxa2xx_spi_write(drv_data, SSCR0, 0);
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index eb8a6a2e91c9..2f559e531100 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -873,10 +873,6 @@ static int spi_qup_transfer_one(struct spi_master *master,
 	else
 		ret = spi_qup_do_pio(spi, xfer, timeout);
 
-	if (ret)
-		goto exit;
-
-exit:
 	spi_qup_set_state(controller, QUP_STATE_RESET);
 	spin_lock_irqsave(&controller->lock, flags);
 	if (!ret)
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 9b91188a85f9..2cc6d9951b52 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -417,7 +417,7 @@ static int rockchip_spi_prepare_dma(struct rockchip_spi *rs,
 			.direction = DMA_MEM_TO_DEV,
 			.dst_addr = rs->dma_addr_tx,
 			.dst_addr_width = rs->n_bytes,
-			.dst_maxburst = rs->fifo_len / 2,
+			.dst_maxburst = rs->fifo_len / 4,
 		};
 
 		dmaengine_slave_config(master->dma_tx, &txconf);
@@ -518,7 +518,7 @@ static void rockchip_spi_config(struct rockchip_spi *rs,
 	else
 		writel_relaxed(rs->fifo_len / 2 - 1, rs->regs + ROCKCHIP_SPI_RXFTLR);
 
-	writel_relaxed(rs->fifo_len / 2 - 1, rs->regs + ROCKCHIP_SPI_DMATDLR);
+	writel_relaxed(rs->fifo_len / 2, rs->regs + ROCKCHIP_SPI_DMATDLR);
 	writel_relaxed(0, rs->regs + ROCKCHIP_SPI_DMARDLR);
 	writel_relaxed(dmacr, rs->regs + ROCKCHIP_SPI_DMACR);
 
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 6aab7b2136db..b50bdbc27e58 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -229,7 +229,7 @@ static int sh_msiof_modify_ctr_wait(struct sh_msiof_spi_priv *p,
 	sh_msiof_write(p, CTR, data);
 
 	return readl_poll_timeout_atomic(p->mapbase + CTR, data,
-					 (data & mask) == set, 10, 1000);
+					 (data & mask) == set, 1, 100);
 }
 
 static irqreturn_t sh_msiof_spi_irq(int irq, void *data)
diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c
index 5dbb6a8e893c..655e4afbfb2a 100644
--- a/drivers/spi/spi-stm32-qspi.c
+++ b/drivers/spi/spi-stm32-qspi.c
@@ -245,12 +245,8 @@ static int stm32_qspi_tx_dma(struct stm32_qspi *qspi,
 	writel_relaxed(cr | CR_DMAEN, qspi->io_base + QSPI_CR);
 
 	t_out = sgt.nents * STM32_COMP_TIMEOUT_MS;
-	if (!wait_for_completion_interruptible_timeout(&qspi->dma_completion,
-						       msecs_to_jiffies(t_out)))
-		err = -ETIMEDOUT;
-
-	if (dma_async_is_tx_complete(dma_ch, cookie,
-				     NULL, NULL) != DMA_COMPLETE)
+	if (!wait_for_completion_timeout(&qspi->dma_completion,
+					 msecs_to_jiffies(t_out)))
 		err = -ETIMEDOUT;
 
 	if (err)
@@ -304,7 +300,7 @@ static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi,
 	cr = readl_relaxed(qspi->io_base + QSPI_CR);
 	writel_relaxed(cr | CR_TCIE | CR_TEIE, qspi->io_base + QSPI_CR);
 
-	if (!wait_for_completion_interruptible_timeout(&qspi->data_completion,
+	if (!wait_for_completion_timeout(&qspi->data_completion,
 				msecs_to_jiffies(STM32_COMP_TIMEOUT_MS))) {
 		err = -ETIMEDOUT;
 	} else {
diff --git a/drivers/spi/spi-synquacer.c b/drivers/spi/spi-synquacer.c
new file mode 100644
index 000000000000..f99abd85c50a
--- /dev/null
+++ b/drivers/spi/spi-synquacer.c
@@ -0,0 +1,828 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Synquacer HSSPI controller driver
+//
+// Copyright (c) 2015-2018 Socionext Inc.
+// Copyright (c) 2018-2019 Linaro Ltd.
+//
+
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/spinlock.h>
+#include <linux/clk.h>
+
+/* HSSPI register address definitions */
+#define SYNQUACER_HSSPI_REG_MCTRL	0x00
+#define SYNQUACER_HSSPI_REG_PCC0	0x04
+#define SYNQUACER_HSSPI_REG_PCC(n)	(SYNQUACER_HSSPI_REG_PCC0 + (n) * 4)
+#define SYNQUACER_HSSPI_REG_TXF		0x14
+#define SYNQUACER_HSSPI_REG_TXE		0x18
+#define SYNQUACER_HSSPI_REG_TXC		0x1C
+#define SYNQUACER_HSSPI_REG_RXF		0x20
+#define SYNQUACER_HSSPI_REG_RXE		0x24
+#define SYNQUACER_HSSPI_REG_RXC		0x28
+#define SYNQUACER_HSSPI_REG_FAULTF	0x2C
+#define SYNQUACER_HSSPI_REG_FAULTC	0x30
+#define SYNQUACER_HSSPI_REG_DMCFG	0x34
+#define SYNQUACER_HSSPI_REG_DMSTART	0x38
+#define SYNQUACER_HSSPI_REG_DMBCC	0x3C
+#define SYNQUACER_HSSPI_REG_DMSTATUS	0x40
+#define SYNQUACER_HSSPI_REG_FIFOCFG	0x4C
+#define SYNQUACER_HSSPI_REG_TX_FIFO	0x50
+#define SYNQUACER_HSSPI_REG_RX_FIFO	0x90
+#define SYNQUACER_HSSPI_REG_MID		0xFC
+
+/* HSSPI register bit definitions */
+#define SYNQUACER_HSSPI_MCTRL_MEN			BIT(0)
+#define SYNQUACER_HSSPI_MCTRL_COMMAND_SEQUENCE_EN	BIT(1)
+#define SYNQUACER_HSSPI_MCTRL_CDSS			BIT(3)
+#define SYNQUACER_HSSPI_MCTRL_MES			BIT(4)
+#define SYNQUACER_HSSPI_MCTRL_SYNCON			BIT(5)
+
+#define SYNQUACER_HSSPI_PCC_CPHA		BIT(0)
+#define SYNQUACER_HSSPI_PCC_CPOL		BIT(1)
+#define SYNQUACER_HSSPI_PCC_ACES		BIT(2)
+#define SYNQUACER_HSSPI_PCC_RTM			BIT(3)
+#define SYNQUACER_HSSPI_PCC_SSPOL		BIT(4)
+#define SYNQUACER_HSSPI_PCC_SDIR		BIT(7)
+#define SYNQUACER_HSSPI_PCC_SENDIAN		BIT(8)
+#define SYNQUACER_HSSPI_PCC_SAFESYNC		BIT(16)
+#define SYNQUACER_HSSPI_PCC_SS2CD_SHIFT		5U
+#define SYNQUACER_HSSPI_PCC_CDRS_MASK		0x7f
+#define SYNQUACER_HSSPI_PCC_CDRS_SHIFT		9U
+
+#define SYNQUACER_HSSPI_TXF_FIFO_FULL		BIT(0)
+#define SYNQUACER_HSSPI_TXF_FIFO_EMPTY		BIT(1)
+#define SYNQUACER_HSSPI_TXF_SLAVE_RELEASED	BIT(6)
+
+#define SYNQUACER_HSSPI_TXE_FIFO_FULL		BIT(0)
+#define SYNQUACER_HSSPI_TXE_FIFO_EMPTY		BIT(1)
+#define SYNQUACER_HSSPI_TXE_SLAVE_RELEASED	BIT(6)
+
+#define SYNQUACER_HSSPI_RXF_FIFO_MORE_THAN_THRESHOLD		BIT(5)
+#define SYNQUACER_HSSPI_RXF_SLAVE_RELEASED			BIT(6)
+
+#define SYNQUACER_HSSPI_RXE_FIFO_MORE_THAN_THRESHOLD		BIT(5)
+#define SYNQUACER_HSSPI_RXE_SLAVE_RELEASED			BIT(6)
+
+#define SYNQUACER_HSSPI_DMCFG_SSDC		BIT(1)
+#define SYNQUACER_HSSPI_DMCFG_MSTARTEN		BIT(2)
+
+#define SYNQUACER_HSSPI_DMSTART_START		BIT(0)
+#define SYNQUACER_HSSPI_DMSTOP_STOP		BIT(8)
+#define SYNQUACER_HSSPI_DMPSEL_CS_MASK		0x3
+#define SYNQUACER_HSSPI_DMPSEL_CS_SHIFT		16U
+#define SYNQUACER_HSSPI_DMTRP_BUS_WIDTH_SHIFT	24U
+#define SYNQUACER_HSSPI_DMTRP_DATA_MASK		0x3
+#define SYNQUACER_HSSPI_DMTRP_DATA_SHIFT	26U
+#define SYNQUACER_HSSPI_DMTRP_DATA_TXRX		0
+#define SYNQUACER_HSSPI_DMTRP_DATA_RX		1
+#define SYNQUACER_HSSPI_DMTRP_DATA_TX		2
+
+#define SYNQUACER_HSSPI_DMSTATUS_RX_DATA_MASK	0x1f
+#define SYNQUACER_HSSPI_DMSTATUS_RX_DATA_SHIFT	8U
+#define SYNQUACER_HSSPI_DMSTATUS_TX_DATA_MASK	0x1f
+#define SYNQUACER_HSSPI_DMSTATUS_TX_DATA_SHIFT	16U
+
+#define SYNQUACER_HSSPI_FIFOCFG_RX_THRESHOLD_MASK	0xf
+#define SYNQUACER_HSSPI_FIFOCFG_RX_THRESHOLD_SHIFT	0U
+#define SYNQUACER_HSSPI_FIFOCFG_TX_THRESHOLD_MASK	0xf
+#define SYNQUACER_HSSPI_FIFOCFG_TX_THRESHOLD_SHIFT	4U
+#define SYNQUACER_HSSPI_FIFOCFG_FIFO_WIDTH_MASK		0x3
+#define SYNQUACER_HSSPI_FIFOCFG_FIFO_WIDTH_SHIFT	8U
+#define SYNQUACER_HSSPI_FIFOCFG_RX_FLUSH		BIT(11)
+#define SYNQUACER_HSSPI_FIFOCFG_TX_FLUSH		BIT(12)
+
+#define SYNQUACER_HSSPI_FIFO_DEPTH		16U
+#define SYNQUACER_HSSPI_FIFO_TX_THRESHOLD	4U
+#define SYNQUACER_HSSPI_FIFO_RX_THRESHOLD \
+	(SYNQUACER_HSSPI_FIFO_DEPTH - SYNQUACER_HSSPI_FIFO_TX_THRESHOLD)
+
+#define SYNQUACER_HSSPI_TRANSFER_MODE_TX	BIT(1)
+#define SYNQUACER_HSSPI_TRANSFER_MODE_RX	BIT(2)
+#define SYNQUACER_HSSPI_TRANSFER_TMOUT_MSEC	2000U
+#define SYNQUACER_HSSPI_ENABLE_TMOUT_MSEC	1000U
+
+#define SYNQUACER_HSSPI_CLOCK_SRC_IHCLK		0
+#define SYNQUACER_HSSPI_CLOCK_SRC_IPCLK		1
+
+#define SYNQUACER_HSSPI_NUM_CHIP_SELECT		4U
+#define SYNQUACER_HSSPI_IRQ_NAME_MAX		32U
+
+struct synquacer_spi {
+	struct device *dev;
+	struct completion transfer_done;
+	unsigned int cs;
+	unsigned int bpw;
+	unsigned int mode;
+	unsigned int speed;
+	bool aces, rtm;
+	void *rx_buf;
+	const void *tx_buf;
+	struct clk *clk;
+	int clk_src_type;
+	void __iomem *regs;
+	u32 tx_words, rx_words;
+	unsigned int bus_width;
+	unsigned int transfer_mode;
+	char rx_irq_name[SYNQUACER_HSSPI_IRQ_NAME_MAX];
+	char tx_irq_name[SYNQUACER_HSSPI_IRQ_NAME_MAX];
+};
+
+static int read_fifo(struct synquacer_spi *sspi)
+{
+	u32 len = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMSTATUS);
+
+	len = (len >> SYNQUACER_HSSPI_DMSTATUS_RX_DATA_SHIFT) &
+	       SYNQUACER_HSSPI_DMSTATUS_RX_DATA_MASK;
+	len = min(len, sspi->rx_words);
+
+	switch (sspi->bpw) {
+	case 8: {
+		u8 *buf = sspi->rx_buf;
+
+		ioread8_rep(sspi->regs + SYNQUACER_HSSPI_REG_RX_FIFO,
+			    buf, len);
+		sspi->rx_buf = buf + len;
+		break;
+	}
+	case 16: {
+		u16 *buf = sspi->rx_buf;
+
+		ioread16_rep(sspi->regs + SYNQUACER_HSSPI_REG_RX_FIFO,
+			     buf, len);
+		sspi->rx_buf = buf + len;
+		break;
+	}
+	case 24:
+		/* fallthrough, should use 32-bits access */
+	case 32: {
+		u32 *buf = sspi->rx_buf;
+
+		ioread32_rep(sspi->regs + SYNQUACER_HSSPI_REG_RX_FIFO,
+			     buf, len);
+		sspi->rx_buf = buf + len;
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+
+	sspi->rx_words -= len;
+	return 0;
+}
+
+static int write_fifo(struct synquacer_spi *sspi)
+{
+	u32 len = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMSTATUS);
+
+	len = (len >> SYNQUACER_HSSPI_DMSTATUS_TX_DATA_SHIFT) &
+	       SYNQUACER_HSSPI_DMSTATUS_TX_DATA_MASK;
+	len = min(SYNQUACER_HSSPI_FIFO_DEPTH - len,
+		    sspi->tx_words);
+
+	switch (sspi->bpw) {
+	case 8: {
+		const u8 *buf = sspi->tx_buf;
+
+		iowrite8_rep(sspi->regs + SYNQUACER_HSSPI_REG_TX_FIFO,
+			     buf, len);
+		sspi->tx_buf = buf + len;
+		break;
+	}
+	case 16: {
+		const u16 *buf = sspi->tx_buf;
+
+		iowrite16_rep(sspi->regs + SYNQUACER_HSSPI_REG_TX_FIFO,
+			      buf, len);
+		sspi->tx_buf = buf + len;
+		break;
+	}
+	case 24:
+		/* fallthrough, should use 32-bits access */
+	case 32: {
+		const u32 *buf = sspi->tx_buf;
+
+		iowrite32_rep(sspi->regs + SYNQUACER_HSSPI_REG_TX_FIFO,
+			      buf, len);
+		sspi->tx_buf = buf + len;
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+
+	sspi->tx_words -= len;
+	return 0;
+}
+
+static int synquacer_spi_config(struct spi_master *master,
+				struct spi_device *spi,
+				struct spi_transfer *xfer)
+{
+	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	unsigned int speed, mode, bpw, cs, bus_width, transfer_mode;
+	u32 rate, val, div;
+
+	/* Full Duplex only on 1-bit wide bus */
+	if (xfer->rx_buf && xfer->tx_buf &&
+	    (xfer->rx_nbits != 1 || xfer->tx_nbits != 1)) {
+		dev_err(sspi->dev,
+			"RX and TX bus widths must be 1-bit for Full-Duplex!\n");
+		return -EINVAL;
+	}
+
+	if (xfer->tx_buf) {
+		bus_width = xfer->tx_nbits;
+		transfer_mode = SYNQUACER_HSSPI_TRANSFER_MODE_TX;
+	} else {
+		bus_width = xfer->rx_nbits;
+		transfer_mode = SYNQUACER_HSSPI_TRANSFER_MODE_RX;
+	}
+
+	mode = spi->mode;
+	cs = spi->chip_select;
+	speed = xfer->speed_hz;
+	bpw = xfer->bits_per_word;
+
+	/* return if nothing to change */
+	if (speed == sspi->speed &&
+		bus_width == sspi->bus_width && bpw == sspi->bpw &&
+		mode == sspi->mode && cs == sspi->cs &&
+		transfer_mode == sspi->transfer_mode) {
+		return 0;
+	}
+
+	sspi->transfer_mode = transfer_mode;
+	rate = master->max_speed_hz;
+
+	div = DIV_ROUND_UP(rate, speed);
+	if (div > 254) {
+		dev_err(sspi->dev, "Requested rate too low (%u)\n",
+			sspi->speed);
+		return -EINVAL;
+	}
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_PCC(cs));
+	val &= ~SYNQUACER_HSSPI_PCC_SAFESYNC;
+	if (bpw == 8 &&	(mode & (SPI_TX_DUAL | SPI_RX_DUAL)) && div < 3)
+		val |= SYNQUACER_HSSPI_PCC_SAFESYNC;
+	if (bpw == 8 &&	(mode & (SPI_TX_QUAD | SPI_RX_QUAD)) && div < 6)
+		val |= SYNQUACER_HSSPI_PCC_SAFESYNC;
+	if (bpw == 16 && (mode & (SPI_TX_QUAD | SPI_RX_QUAD)) && div < 3)
+		val |= SYNQUACER_HSSPI_PCC_SAFESYNC;
+
+	if (mode & SPI_CPHA)
+		val |= SYNQUACER_HSSPI_PCC_CPHA;
+	else
+		val &= ~SYNQUACER_HSSPI_PCC_CPHA;
+
+	if (mode & SPI_CPOL)
+		val |= SYNQUACER_HSSPI_PCC_CPOL;
+	else
+		val &= ~SYNQUACER_HSSPI_PCC_CPOL;
+
+	if (mode & SPI_CS_HIGH)
+		val |= SYNQUACER_HSSPI_PCC_SSPOL;
+	else
+		val &= ~SYNQUACER_HSSPI_PCC_SSPOL;
+
+	if (mode & SPI_LSB_FIRST)
+		val |= SYNQUACER_HSSPI_PCC_SDIR;
+	else
+		val &= ~SYNQUACER_HSSPI_PCC_SDIR;
+
+	if (sspi->aces)
+		val |= SYNQUACER_HSSPI_PCC_ACES;
+	else
+		val &= ~SYNQUACER_HSSPI_PCC_ACES;
+
+	if (sspi->rtm)
+		val |= SYNQUACER_HSSPI_PCC_RTM;
+	else
+		val &= ~SYNQUACER_HSSPI_PCC_RTM;
+
+	val |= (3 << SYNQUACER_HSSPI_PCC_SS2CD_SHIFT);
+	val |= SYNQUACER_HSSPI_PCC_SENDIAN;
+
+	val &= ~(SYNQUACER_HSSPI_PCC_CDRS_MASK <<
+		 SYNQUACER_HSSPI_PCC_CDRS_SHIFT);
+	val |= ((div >> 1) << SYNQUACER_HSSPI_PCC_CDRS_SHIFT);
+
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_PCC(cs));
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_FIFOCFG);
+	val &= ~(SYNQUACER_HSSPI_FIFOCFG_FIFO_WIDTH_MASK <<
+		 SYNQUACER_HSSPI_FIFOCFG_FIFO_WIDTH_SHIFT);
+	val |= ((bpw / 8 - 1) << SYNQUACER_HSSPI_FIFOCFG_FIFO_WIDTH_SHIFT);
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_FIFOCFG);
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+	val &= ~(SYNQUACER_HSSPI_DMTRP_DATA_MASK <<
+		 SYNQUACER_HSSPI_DMTRP_DATA_SHIFT);
+
+	if (xfer->rx_buf)
+		val |= (SYNQUACER_HSSPI_DMTRP_DATA_RX <<
+			SYNQUACER_HSSPI_DMTRP_DATA_SHIFT);
+	else
+		val |= (SYNQUACER_HSSPI_DMTRP_DATA_TX <<
+			SYNQUACER_HSSPI_DMTRP_DATA_SHIFT);
+
+	val &= ~(3 << SYNQUACER_HSSPI_DMTRP_BUS_WIDTH_SHIFT);
+	val |= ((bus_width >> 1) << SYNQUACER_HSSPI_DMTRP_BUS_WIDTH_SHIFT);
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+
+	sspi->bpw = bpw;
+	sspi->mode = mode;
+	sspi->speed = speed;
+	sspi->cs = spi->chip_select;
+	sspi->bus_width = bus_width;
+
+	return 0;
+}
+
+static int synquacer_spi_transfer_one(struct spi_master *master,
+				      struct spi_device *spi,
+				      struct spi_transfer *xfer)
+{
+	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	int ret;
+	int status = 0;
+	u32 words;
+	u8 bpw;
+	u32 val;
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+	val &= ~SYNQUACER_HSSPI_DMSTOP_STOP;
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_FIFOCFG);
+	val |= SYNQUACER_HSSPI_FIFOCFG_RX_FLUSH;
+	val |= SYNQUACER_HSSPI_FIFOCFG_TX_FLUSH;
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_FIFOCFG);
+
+	/*
+	 * See if we can transfer 4-bytes as 1 word
+	 * to maximize the FIFO buffer efficiency.
+	 */
+	bpw = xfer->bits_per_word;
+	if (bpw == 8 && !(xfer->len % 4) && !(spi->mode & SPI_LSB_FIRST))
+		xfer->bits_per_word = 32;
+
+	ret = synquacer_spi_config(master, spi, xfer);
+
+	/* restore */
+	xfer->bits_per_word = bpw;
+
+	if (ret)
+		return ret;
+
+	reinit_completion(&sspi->transfer_done);
+
+	sspi->tx_buf = xfer->tx_buf;
+	sspi->rx_buf = xfer->rx_buf;
+
+	switch (sspi->bpw) {
+	case 8:
+		words = xfer->len;
+		break;
+	case 16:
+		words = xfer->len / 2;
+		break;
+	case 24:
+		/* fallthrough, should use 32-bits access */
+	case 32:
+		words = xfer->len / 4;
+		break;
+	default:
+		dev_err(sspi->dev, "unsupported bpw: %d\n", sspi->bpw);
+		return -EINVAL;
+	}
+
+	if (xfer->tx_buf)
+		sspi->tx_words = words;
+	else
+		sspi->tx_words = 0;
+
+	if (xfer->rx_buf)
+		sspi->rx_words = words;
+	else
+		sspi->rx_words = 0;
+
+	if (xfer->tx_buf) {
+		status = write_fifo(sspi);
+		if (status < 0) {
+			dev_err(sspi->dev, "failed write_fifo. status: 0x%x\n",
+				status);
+			return status;
+		}
+	}
+
+	if (xfer->rx_buf) {
+		val = readl(sspi->regs + SYNQUACER_HSSPI_REG_FIFOCFG);
+		val &= ~(SYNQUACER_HSSPI_FIFOCFG_RX_THRESHOLD_MASK <<
+			 SYNQUACER_HSSPI_FIFOCFG_RX_THRESHOLD_SHIFT);
+		val |= ((sspi->rx_words > SYNQUACER_HSSPI_FIFO_DEPTH ?
+			SYNQUACER_HSSPI_FIFO_RX_THRESHOLD : sspi->rx_words) <<
+			SYNQUACER_HSSPI_FIFOCFG_RX_THRESHOLD_SHIFT);
+		writel(val, sspi->regs + SYNQUACER_HSSPI_REG_FIFOCFG);
+	}
+
+	writel(~0, sspi->regs + SYNQUACER_HSSPI_REG_TXC);
+	writel(~0, sspi->regs + SYNQUACER_HSSPI_REG_RXC);
+
+	/* Trigger */
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+	val |= SYNQUACER_HSSPI_DMSTART_START;
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+
+	if (xfer->tx_buf) {
+		val = SYNQUACER_HSSPI_TXE_FIFO_EMPTY;
+		writel(val, sspi->regs + SYNQUACER_HSSPI_REG_TXE);
+		status = wait_for_completion_timeout(&sspi->transfer_done,
+			msecs_to_jiffies(SYNQUACER_HSSPI_TRANSFER_TMOUT_MSEC));
+		writel(0, sspi->regs + SYNQUACER_HSSPI_REG_TXE);
+	}
+
+	if (xfer->rx_buf) {
+		u32 buf[SYNQUACER_HSSPI_FIFO_DEPTH];
+
+		val = SYNQUACER_HSSPI_RXE_FIFO_MORE_THAN_THRESHOLD |
+		      SYNQUACER_HSSPI_RXE_SLAVE_RELEASED;
+		writel(val, sspi->regs + SYNQUACER_HSSPI_REG_RXE);
+		status = wait_for_completion_timeout(&sspi->transfer_done,
+			msecs_to_jiffies(SYNQUACER_HSSPI_TRANSFER_TMOUT_MSEC));
+		writel(0, sspi->regs + SYNQUACER_HSSPI_REG_RXE);
+
+		/* stop RX and clean RXFIFO */
+		val = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+		val |= SYNQUACER_HSSPI_DMSTOP_STOP;
+		writel(val, sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+		sspi->rx_buf = buf;
+		sspi->rx_words = SYNQUACER_HSSPI_FIFO_DEPTH;
+		read_fifo(sspi);
+	}
+
+	if (status < 0) {
+		dev_err(sspi->dev, "failed to transfer. status: 0x%x\n",
+			status);
+		return status;
+	}
+
+	return 0;
+}
+
+static void synquacer_spi_set_cs(struct spi_device *spi, bool enable)
+{
+	struct synquacer_spi *sspi = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+	val &= ~(SYNQUACER_HSSPI_DMPSEL_CS_MASK <<
+		 SYNQUACER_HSSPI_DMPSEL_CS_SHIFT);
+	val |= spi->chip_select << SYNQUACER_HSSPI_DMPSEL_CS_SHIFT;
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
+}
+
+static int synquacer_spi_wait_status_update(struct synquacer_spi *sspi,
+					    bool enable)
+{
+	u32 val;
+	unsigned long timeout = jiffies +
+		msecs_to_jiffies(SYNQUACER_HSSPI_ENABLE_TMOUT_MSEC);
+
+	/* wait MES(Module Enable Status) is updated */
+	do {
+		val = readl(sspi->regs + SYNQUACER_HSSPI_REG_MCTRL) &
+		      SYNQUACER_HSSPI_MCTRL_MES;
+		if (enable && val)
+			return 0;
+		if (!enable && !val)
+			return 0;
+	} while (time_before(jiffies, timeout));
+
+	dev_err(sspi->dev, "timeout occurs in updating Module Enable Status\n");
+	return -EBUSY;
+}
+
+static int synquacer_spi_enable(struct spi_master *master)
+{
+	u32 val;
+	int status;
+	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+
+	/* Disable module */
+	writel(0, sspi->regs + SYNQUACER_HSSPI_REG_MCTRL);
+	status = synquacer_spi_wait_status_update(sspi, false);
+	if (status < 0)
+		return status;
+
+	writel(0, sspi->regs + SYNQUACER_HSSPI_REG_TXE);
+	writel(0, sspi->regs + SYNQUACER_HSSPI_REG_RXE);
+	writel(~0, sspi->regs + SYNQUACER_HSSPI_REG_TXC);
+	writel(~0, sspi->regs + SYNQUACER_HSSPI_REG_RXC);
+	writel(~0, sspi->regs + SYNQUACER_HSSPI_REG_FAULTC);
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_DMCFG);
+	val &= ~SYNQUACER_HSSPI_DMCFG_SSDC;
+	val &= ~SYNQUACER_HSSPI_DMCFG_MSTARTEN;
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_DMCFG);
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_MCTRL);
+	if (sspi->clk_src_type == SYNQUACER_HSSPI_CLOCK_SRC_IPCLK)
+		val |= SYNQUACER_HSSPI_MCTRL_CDSS;
+	else
+		val &= ~SYNQUACER_HSSPI_MCTRL_CDSS;
+
+	val &= ~SYNQUACER_HSSPI_MCTRL_COMMAND_SEQUENCE_EN;
+	val |= SYNQUACER_HSSPI_MCTRL_MEN;
+	val |= SYNQUACER_HSSPI_MCTRL_SYNCON;
+
+	/* Enable module */
+	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_MCTRL);
+	status = synquacer_spi_wait_status_update(sspi, true);
+	if (status < 0)
+		return status;
+
+	return 0;
+}
+
+static irqreturn_t sq_spi_rx_handler(int irq, void *priv)
+{
+	uint32_t val;
+	struct synquacer_spi *sspi = priv;
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_RXF);
+	if ((val & SYNQUACER_HSSPI_RXF_SLAVE_RELEASED) ||
+	    (val & SYNQUACER_HSSPI_RXF_FIFO_MORE_THAN_THRESHOLD)) {
+		read_fifo(sspi);
+
+		if (sspi->rx_words == 0) {
+			writel(0, sspi->regs + SYNQUACER_HSSPI_REG_RXE);
+			complete(&sspi->transfer_done);
+		}
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static irqreturn_t sq_spi_tx_handler(int irq, void *priv)
+{
+	uint32_t val;
+	struct synquacer_spi *sspi = priv;
+
+	val = readl(sspi->regs + SYNQUACER_HSSPI_REG_TXF);
+	if (val & SYNQUACER_HSSPI_TXF_FIFO_EMPTY) {
+		if (sspi->tx_words == 0) {
+			writel(0, sspi->regs + SYNQUACER_HSSPI_REG_TXE);
+			complete(&sspi->transfer_done);
+		} else {
+			write_fifo(sspi);
+		}
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static int synquacer_spi_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct spi_master *master;
+	struct synquacer_spi *sspi;
+	int ret;
+	int rx_irq, tx_irq;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*sspi));
+	if (!master)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, master);
+
+	sspi = spi_master_get_devdata(master);
+	sspi->dev = &pdev->dev;
+
+	init_completion(&sspi->transfer_done);
+
+	sspi->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(sspi->regs)) {
+		ret = PTR_ERR(sspi->regs);
+		goto put_spi;
+	}
+
+	sspi->clk_src_type = SYNQUACER_HSSPI_CLOCK_SRC_IHCLK; /* Default */
+	device_property_read_u32(&pdev->dev, "socionext,ihclk-rate",
+				 &master->max_speed_hz); /* for ACPI */
+
+	if (dev_of_node(&pdev->dev)) {
+		if (device_property_match_string(&pdev->dev,
+					 "clock-names", "iHCLK") >= 0) {
+			sspi->clk_src_type = SYNQUACER_HSSPI_CLOCK_SRC_IHCLK;
+			sspi->clk = devm_clk_get(sspi->dev, "iHCLK");
+		} else if (device_property_match_string(&pdev->dev,
+						"clock-names", "iPCLK") >= 0) {
+			sspi->clk_src_type = SYNQUACER_HSSPI_CLOCK_SRC_IPCLK;
+			sspi->clk = devm_clk_get(sspi->dev, "iPCLK");
+		} else {
+			dev_err(&pdev->dev, "specified wrong clock source\n");
+			ret = -EINVAL;
+			goto put_spi;
+		}
+
+		if (IS_ERR(sspi->clk)) {
+			if (!(PTR_ERR(sspi->clk) == -EPROBE_DEFER))
+				dev_err(&pdev->dev, "clock not found\n");
+			ret = PTR_ERR(sspi->clk);
+			goto put_spi;
+		}
+
+		ret = clk_prepare_enable(sspi->clk);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to enable clock (%d)\n",
+				ret);
+			goto put_spi;
+		}
+
+		master->max_speed_hz = clk_get_rate(sspi->clk);
+	}
+
+	if (!master->max_speed_hz) {
+		dev_err(&pdev->dev, "missing clock source\n");
+		return -EINVAL;
+	}
+	master->min_speed_hz = master->max_speed_hz / 254;
+
+	sspi->aces = device_property_read_bool(&pdev->dev,
+					       "socionext,set-aces");
+	sspi->rtm = device_property_read_bool(&pdev->dev, "socionext,use-rtm");
+
+	master->num_chipselect = SYNQUACER_HSSPI_NUM_CHIP_SELECT;
+
+	rx_irq = platform_get_irq(pdev, 0);
+	if (rx_irq <= 0) {
+		dev_err(&pdev->dev, "get rx_irq failed (%d)\n", rx_irq);
+		ret = rx_irq;
+		goto put_spi;
+	}
+	snprintf(sspi->rx_irq_name, SYNQUACER_HSSPI_IRQ_NAME_MAX, "%s-rx",
+		 dev_name(&pdev->dev));
+	ret = devm_request_irq(&pdev->dev, rx_irq, sq_spi_rx_handler,
+				0, sspi->rx_irq_name, sspi);
+	if (ret) {
+		dev_err(&pdev->dev, "request rx_irq failed (%d)\n", ret);
+		goto put_spi;
+	}
+
+	tx_irq = platform_get_irq(pdev, 1);
+	if (tx_irq <= 0) {
+		dev_err(&pdev->dev, "get tx_irq failed (%d)\n", tx_irq);
+		ret = tx_irq;
+		goto put_spi;
+	}
+	snprintf(sspi->tx_irq_name, SYNQUACER_HSSPI_IRQ_NAME_MAX, "%s-tx",
+		 dev_name(&pdev->dev));
+	ret = devm_request_irq(&pdev->dev, tx_irq, sq_spi_tx_handler,
+				0, sspi->tx_irq_name, sspi);
+	if (ret) {
+		dev_err(&pdev->dev, "request tx_irq failed (%d)\n", ret);
+		goto put_spi;
+	}
+
+	master->dev.of_node = np;
+	master->dev.fwnode = pdev->dev.fwnode;
+	master->auto_runtime_pm = true;
+	master->bus_num = pdev->id;
+
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_TX_DUAL | SPI_RX_DUAL |
+			    SPI_TX_QUAD | SPI_RX_QUAD;
+	master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(24) |
+				     SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
+
+	master->set_cs = synquacer_spi_set_cs;
+	master->transfer_one = synquacer_spi_transfer_one;
+
+	ret = synquacer_spi_enable(master);
+	if (ret)
+		goto fail_enable;
+
+	pm_runtime_set_active(sspi->dev);
+	pm_runtime_enable(sspi->dev);
+
+	ret = devm_spi_register_master(sspi->dev, master);
+	if (ret)
+		goto disable_pm;
+
+	return 0;
+
+disable_pm:
+	pm_runtime_disable(sspi->dev);
+fail_enable:
+	clk_disable_unprepare(sspi->clk);
+put_spi:
+	spi_master_put(master);
+
+	return ret;
+}
+
+static int synquacer_spi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+
+	pm_runtime_disable(sspi->dev);
+
+	clk_disable_unprepare(sspi->clk);
+
+	return 0;
+}
+
+static int __maybe_unused synquacer_spi_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = spi_master_suspend(master);
+	if (ret)
+		return ret;
+
+	if (!pm_runtime_suspended(dev))
+		clk_disable_unprepare(sspi->clk);
+
+	return ret;
+}
+
+static int __maybe_unused synquacer_spi_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct synquacer_spi *sspi = spi_master_get_devdata(master);
+	int ret;
+
+	if (!pm_runtime_suspended(dev)) {
+		/* Ensure reconfigure during next xfer */
+		sspi->speed = 0;
+
+		ret = clk_prepare_enable(sspi->clk);
+		if (ret < 0) {
+			dev_err(dev, "failed to enable clk (%d)\n",
+				ret);
+			return ret;
+		}
+
+		ret = synquacer_spi_enable(master);
+		if (ret) {
+			dev_err(dev, "failed to enable spi (%d)\n", ret);
+			return ret;
+		}
+	}
+
+	ret = spi_master_resume(master);
+	if (ret < 0)
+		clk_disable_unprepare(sspi->clk);
+
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(synquacer_spi_pm_ops, synquacer_spi_suspend,
+			 synquacer_spi_resume);
+
+static const struct of_device_id synquacer_spi_of_match[] = {
+	{.compatible = "socionext,synquacer-spi"},
+	{}
+};
+MODULE_DEVICE_TABLE(of, synquacer_spi_of_match);
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id synquacer_hsspi_acpi_ids[] = {
+	{ "SCX0004" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(acpi, synquacer_hsspi_acpi_ids);
+#endif
+
+static struct platform_driver synquacer_spi_driver = {
+	.driver = {
+		.name = "synquacer-spi",
+		.pm = &synquacer_spi_pm_ops,
+		.of_match_table = synquacer_spi_of_match,
+		.acpi_match_table = ACPI_PTR(synquacer_hsspi_acpi_ids),
+	},
+	.probe = synquacer_spi_probe,
+	.remove = synquacer_spi_remove,
+};
+module_platform_driver(synquacer_spi_driver);
+
+MODULE_DESCRIPTION("Socionext Synquacer HS-SPI controller driver");
+MODULE_AUTHOR("Masahisa Kojima <masahisa.kojima@linaro.org>");
+MODULE_AUTHOR("Jassi Brar <jaswinder.singh@linaro.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c
index d22f4d10413f..39374c2edcf3 100644
--- a/drivers/spi/spi-tegra114.c
+++ b/drivers/spi/spi-tegra114.c
@@ -84,8 +84,10 @@
 		(reg = (((val) & 0x1) << ((cs) * 8 + 5)) |	\
 			((reg) & ~(1 << ((cs) * 8 + 5))))
 #define SPI_SET_CYCLES_BETWEEN_PACKETS(reg, cs, val)		\
-		(reg = (((val) & 0xF) << ((cs) * 8)) |		\
-			((reg) & ~(0xF << ((cs) * 8))))
+		(reg = (((val) & 0x1F) << ((cs) * 8)) |		\
+			((reg) & ~(0x1F << ((cs) * 8))))
+#define MAX_SETUP_HOLD_CYCLES			16
+#define MAX_INACTIVE_CYCLES			32
 
 #define SPI_TRANS_STATUS			0x010
 #define SPI_BLK_CNT(val)			(((val) >> 0) & 0xFFFF)
@@ -156,6 +158,11 @@ struct tegra_spi_soc_data {
 	bool has_intr_mask_reg;
 };
 
+struct tegra_spi_client_data {
+	int tx_clk_tap_delay;
+	int rx_clk_tap_delay;
+};
+
 struct tegra_spi_data {
 	struct device				*dev;
 	struct spi_master			*master;
@@ -182,6 +189,7 @@ struct tegra_spi_data {
 	unsigned				dma_buf_size;
 	unsigned				max_buf_size;
 	bool					is_curr_dma_xfer;
+	bool					use_hw_based_cs;
 
 	struct completion			rx_dma_complete;
 	struct completion			tx_dma_complete;
@@ -194,6 +202,10 @@ struct tegra_spi_data {
 	u32					command1_reg;
 	u32					dma_control_reg;
 	u32					def_command1_reg;
+	u32					def_command2_reg;
+	u32					spi_cs_timing1;
+	u32					spi_cs_timing2;
+	u8					last_used_cs;
 
 	struct completion			xfer_completion;
 	struct spi_transfer			*curr_xfer;
@@ -711,14 +723,55 @@ static void tegra_spi_deinit_dma_param(struct tegra_spi_data *tspi,
 	dma_release_channel(dma_chan);
 }
 
+static void tegra_spi_set_hw_cs_timing(struct spi_device *spi, u8 setup_dly,
+				       u8 hold_dly, u8 inactive_dly)
+{
+	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	u32 setup_hold;
+	u32 spi_cs_timing;
+	u32 inactive_cycles;
+	u8 cs_state;
+
+	setup_dly = min_t(u8, setup_dly, MAX_SETUP_HOLD_CYCLES);
+	hold_dly = min_t(u8, hold_dly, MAX_SETUP_HOLD_CYCLES);
+	if (setup_dly && hold_dly) {
+		setup_hold = SPI_SETUP_HOLD(setup_dly - 1, hold_dly - 1);
+		spi_cs_timing = SPI_CS_SETUP_HOLD(tspi->spi_cs_timing1,
+						  spi->chip_select,
+						  setup_hold);
+		if (tspi->spi_cs_timing1 != spi_cs_timing) {
+			tspi->spi_cs_timing1 = spi_cs_timing;
+			tegra_spi_writel(tspi, spi_cs_timing, SPI_CS_TIMING1);
+		}
+	}
+
+	inactive_cycles = min_t(u8, inactive_dly, MAX_INACTIVE_CYCLES);
+	if (inactive_cycles)
+		inactive_cycles--;
+	cs_state = inactive_cycles ? 0 : 1;
+	spi_cs_timing = tspi->spi_cs_timing2;
+	SPI_SET_CS_ACTIVE_BETWEEN_PACKETS(spi_cs_timing, spi->chip_select,
+					  cs_state);
+	SPI_SET_CYCLES_BETWEEN_PACKETS(spi_cs_timing, spi->chip_select,
+				       inactive_cycles);
+	if (tspi->spi_cs_timing2 != spi_cs_timing) {
+		tspi->spi_cs_timing2 = spi_cs_timing;
+		tegra_spi_writel(tspi, spi_cs_timing, SPI_CS_TIMING2);
+	}
+}
+
 static u32 tegra_spi_setup_transfer_one(struct spi_device *spi,
-		struct spi_transfer *t, bool is_first_of_msg)
+					struct spi_transfer *t,
+					bool is_first_of_msg,
+					bool is_single_xfer)
 {
 	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_spi_client_data *cdata = spi->controller_data;
 	u32 speed = t->speed_hz;
 	u8 bits_per_word = t->bits_per_word;
-	u32 command1;
+	u32 command1, command2;
 	int req_mode;
+	u32 tx_tap = 0, rx_tap = 0;
 
 	if (speed != tspi->cur_speed) {
 		clk_set_rate(tspi->clk, speed);
@@ -765,13 +818,34 @@ static u32 tegra_spi_setup_transfer_one(struct spi_device *spi,
 		} else
 			tegra_spi_writel(tspi, command1, SPI_COMMAND1);
 
-		command1 |= SPI_CS_SW_HW;
-		if (spi->mode & SPI_CS_HIGH)
-			command1 |= SPI_CS_SW_VAL;
-		else
-			command1 &= ~SPI_CS_SW_VAL;
+		/* GPIO based chip select control */
+		if (spi->cs_gpiod)
+			gpiod_set_value(spi->cs_gpiod, 1);
+
+		if (is_single_xfer && !(t->cs_change)) {
+			tspi->use_hw_based_cs = true;
+			command1 &= ~(SPI_CS_SW_HW | SPI_CS_SW_VAL);
+		} else {
+			tspi->use_hw_based_cs = false;
+			command1 |= SPI_CS_SW_HW;
+			if (spi->mode & SPI_CS_HIGH)
+				command1 |= SPI_CS_SW_VAL;
+			else
+				command1 &= ~SPI_CS_SW_VAL;
+		}
+
+		if (tspi->last_used_cs != spi->chip_select) {
+			if (cdata && cdata->tx_clk_tap_delay)
+				tx_tap = cdata->tx_clk_tap_delay;
+			if (cdata && cdata->rx_clk_tap_delay)
+				rx_tap = cdata->rx_clk_tap_delay;
+			command2 = SPI_TX_TAP_DELAY(tx_tap) |
+				   SPI_RX_TAP_DELAY(rx_tap);
+			if (command2 != tspi->def_command2_reg)
+				tegra_spi_writel(tspi, command2, SPI_COMMAND2);
+			tspi->last_used_cs = spi->chip_select;
+		}
 
-		tegra_spi_writel(tspi, 0, SPI_COMMAND2);
 	} else {
 		command1 = tspi->command1_reg;
 		command1 &= ~SPI_BIT_LENGTH(~0);
@@ -827,9 +901,42 @@ static int tegra_spi_start_transfer_one(struct spi_device *spi,
 	return ret;
 }
 
+static struct tegra_spi_client_data
+	*tegra_spi_parse_cdata_dt(struct spi_device *spi)
+{
+	struct tegra_spi_client_data *cdata;
+	struct device_node *slave_np;
+
+	slave_np = spi->dev.of_node;
+	if (!slave_np) {
+		dev_dbg(&spi->dev, "device node not found\n");
+		return NULL;
+	}
+
+	cdata = kzalloc(sizeof(*cdata), GFP_KERNEL);
+	if (!cdata)
+		return NULL;
+
+	of_property_read_u32(slave_np, "nvidia,tx-clk-tap-delay",
+			     &cdata->tx_clk_tap_delay);
+	of_property_read_u32(slave_np, "nvidia,rx-clk-tap-delay",
+			     &cdata->rx_clk_tap_delay);
+	return cdata;
+}
+
+static void tegra_spi_cleanup(struct spi_device *spi)
+{
+	struct tegra_spi_client_data *cdata = spi->controller_data;
+
+	spi->controller_data = NULL;
+	if (spi->dev.of_node)
+		kfree(cdata);
+}
+
 static int tegra_spi_setup(struct spi_device *spi)
 {
 	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	struct tegra_spi_client_data *cdata = spi->controller_data;
 	u32 val;
 	unsigned long flags;
 	int ret;
@@ -840,9 +947,16 @@ static int tegra_spi_setup(struct spi_device *spi)
 		spi->mode & SPI_CPHA ? "" : "~",
 		spi->max_speed_hz);
 
+	if (!cdata) {
+		cdata = tegra_spi_parse_cdata_dt(spi);
+		spi->controller_data = cdata;
+	}
+
 	ret = pm_runtime_get_sync(tspi->dev);
 	if (ret < 0) {
 		dev_err(tspi->dev, "pm runtime failed, e = %d\n", ret);
+		if (cdata)
+			tegra_spi_cleanup(spi);
 		return ret;
 	}
 
@@ -853,6 +967,10 @@ static int tegra_spi_setup(struct spi_device *spi)
 	}
 
 	spin_lock_irqsave(&tspi->lock, flags);
+	/* GPIO based chip select control */
+	if (spi->cs_gpiod)
+		gpiod_set_value(spi->cs_gpiod, 0);
+
 	val = tspi->def_command1_reg;
 	if (spi->mode & SPI_CS_HIGH)
 		val &= ~SPI_CS_POL_INACTIVE(spi->chip_select);
@@ -882,11 +1000,18 @@ static void tegra_spi_transfer_end(struct spi_device *spi)
 	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
 	int cs_val = (spi->mode & SPI_CS_HIGH) ? 0 : 1;
 
-	if (cs_val)
-		tspi->command1_reg |= SPI_CS_SW_VAL;
-	else
-		tspi->command1_reg &= ~SPI_CS_SW_VAL;
-	tegra_spi_writel(tspi, tspi->command1_reg, SPI_COMMAND1);
+	/* GPIO based chip select control */
+	if (spi->cs_gpiod)
+		gpiod_set_value(spi->cs_gpiod, 0);
+
+	if (!tspi->use_hw_based_cs) {
+		if (cs_val)
+			tspi->command1_reg |= SPI_CS_SW_VAL;
+		else
+			tspi->command1_reg &= ~SPI_CS_SW_VAL;
+		tegra_spi_writel(tspi, tspi->command1_reg, SPI_COMMAND1);
+	}
+
 	tegra_spi_writel(tspi, tspi->def_command1_reg, SPI_COMMAND1);
 }
 
@@ -913,16 +1038,19 @@ static int tegra_spi_transfer_one_message(struct spi_master *master,
 	struct spi_device *spi = msg->spi;
 	int ret;
 	bool skip = false;
+	int single_xfer;
 
 	msg->status = 0;
 	msg->actual_length = 0;
 
+	single_xfer = list_is_singular(&msg->transfers);
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		u32 cmd1;
 
 		reinit_completion(&tspi->xfer_completion);
 
-		cmd1 = tegra_spi_setup_transfer_one(spi, xfer, is_first_msg);
+		cmd1 = tegra_spi_setup_transfer_one(spi, xfer, is_first_msg,
+						    single_xfer);
 
 		if (!xfer->len) {
 			ret = 0;
@@ -955,6 +1083,7 @@ static int tegra_spi_transfer_one_message(struct spi_master *master,
 			reset_control_assert(tspi->rst);
 			udelay(2);
 			reset_control_deassert(tspi->rst);
+			tspi->last_used_cs = master->num_chipselect + 1;
 			goto complete_xfer;
 		}
 
@@ -1188,11 +1317,14 @@ static int tegra_spi_probe(struct platform_device *pdev)
 		master->max_speed_hz = 25000000; /* 25MHz */
 
 	/* the spi->mode bits understood by this driver: */
+	master->use_gpio_descriptors = true;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST |
 			    SPI_TX_DUAL | SPI_RX_DUAL | SPI_3WIRE;
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	master->setup = tegra_spi_setup;
+	master->cleanup = tegra_spi_cleanup;
 	master->transfer_one_message = tegra_spi_transfer_one_message;
+	master->set_cs_timing = tegra_spi_set_hw_cs_timing;
 	master->num_chipselect = MAX_CHIP_SELECT;
 	master->auto_runtime_pm = true;
 	bus_num = of_alias_get_id(pdev->dev.of_node, "spi");
@@ -1268,6 +1400,10 @@ static int tegra_spi_probe(struct platform_device *pdev)
 	reset_control_deassert(tspi->rst);
 	tspi->def_command1_reg  = SPI_M_S;
 	tegra_spi_writel(tspi, tspi->def_command1_reg, SPI_COMMAND1);
+	tspi->spi_cs_timing1 = tegra_spi_readl(tspi, SPI_CS_TIMING1);
+	tspi->spi_cs_timing2 = tegra_spi_readl(tspi, SPI_CS_TIMING2);
+	tspi->def_command2_reg = tegra_spi_readl(tspi, SPI_COMMAND2);
+	tspi->last_used_cs = master->num_chipselect + 1;
 	pm_runtime_put(&pdev->dev);
 	ret = request_threaded_irq(tspi->irq, tegra_spi_isr,
 				   tegra_spi_isr_thread, IRQF_ONESHOT,
@@ -1340,6 +1476,8 @@ static int tegra_spi_resume(struct device *dev)
 		return ret;
 	}
 	tegra_spi_writel(tspi, tspi->command1_reg, SPI_COMMAND1);
+	tegra_spi_writel(tspi, tspi->def_command2_reg, SPI_COMMAND2);
+	tspi->last_used_cs = master->num_chipselect + 1;
 	pm_runtime_put(dev);
 
 	return spi_master_resume(master);
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 5e4654032bfa..81e4d9f7c0f4 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1090,6 +1090,60 @@ static int spi_transfer_wait(struct spi_controller *ctlr,
 	return 0;
 }
 
+static void _spi_transfer_delay_ns(u32 ns)
+{
+	if (!ns)
+		return;
+	if (ns <= 1000) {
+		ndelay(ns);
+	} else {
+		u32 us = DIV_ROUND_UP(ns, 1000);
+
+		if (us <= 10)
+			udelay(us);
+		else
+			usleep_range(us, us + DIV_ROUND_UP(us, 10));
+	}
+}
+
+static void _spi_transfer_cs_change_delay(struct spi_message *msg,
+					  struct spi_transfer *xfer)
+{
+	u32 delay = xfer->cs_change_delay;
+	u32 unit = xfer->cs_change_delay_unit;
+	u32 hz;
+
+	/* return early on "fast" mode - for everything but USECS */
+	if (!delay && unit != SPI_DELAY_UNIT_USECS)
+		return;
+
+	switch (unit) {
+	case SPI_DELAY_UNIT_USECS:
+		/* for compatibility use default of 10us */
+		if (!delay)
+			delay = 10000;
+		else
+			delay *= 1000;
+		break;
+	case SPI_DELAY_UNIT_NSECS: /* nothing to do here */
+		break;
+	case SPI_DELAY_UNIT_SCK:
+		/* if there is no effective speed know, then approximate
+		 * by underestimating with half the requested hz
+		 */
+		hz = xfer->effective_speed_hz ?: xfer->speed_hz / 2;
+		delay *= DIV_ROUND_UP(1000000000, hz);
+		break;
+	default:
+		dev_err_once(&msg->spi->dev,
+			     "Use of unsupported delay unit %i, using default of 10us\n",
+			     xfer->cs_change_delay_unit);
+		delay = 10000;
+	}
+	/* now sleep for the requested amount of time */
+	_spi_transfer_delay_ns(delay);
+}
+
 /*
  * spi_transfer_one_message - Default implementation of transfer_one_message()
  *
@@ -1148,14 +1202,8 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 		if (msg->status != -EINPROGRESS)
 			goto out;
 
-		if (xfer->delay_usecs) {
-			u16 us = xfer->delay_usecs;
-
-			if (us <= 10)
-				udelay(us);
-			else
-				usleep_range(us, us + DIV_ROUND_UP(us, 10));
-		}
+		if (xfer->delay_usecs)
+			_spi_transfer_delay_ns(xfer->delay_usecs * 1000);
 
 		if (xfer->cs_change) {
 			if (list_is_last(&xfer->transfer_list,
@@ -1163,7 +1211,7 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 				keep_cs = true;
 			} else {
 				spi_set_cs(msg->spi, false);
-				udelay(10);
+				_spi_transfer_cs_change_delay(msg, xfer);
 				spi_set_cs(msg->spi, true);
 			}
 		}
@@ -1804,9 +1852,18 @@ static void of_register_spi_devices(struct spi_controller *ctlr) { }
 #endif
 
 #ifdef CONFIG_ACPI
-static void acpi_spi_parse_apple_properties(struct spi_device *spi)
+struct acpi_spi_lookup {
+	struct spi_controller 	*ctlr;
+	u32			max_speed_hz;
+	u32			mode;
+	int			irq;
+	u8			bits_per_word;
+	u8			chip_select;
+};
+
+static void acpi_spi_parse_apple_properties(struct acpi_device *dev,
+					    struct acpi_spi_lookup *lookup)
 {
-	struct acpi_device *dev = ACPI_COMPANION(&spi->dev);
 	const union acpi_object *obj;
 
 	if (!x86_apple_machine)
@@ -1814,35 +1871,46 @@ static void acpi_spi_parse_apple_properties(struct spi_device *spi)
 
 	if (!acpi_dev_get_property(dev, "spiSclkPeriod", ACPI_TYPE_BUFFER, &obj)
 	    && obj->buffer.length >= 4)
-		spi->max_speed_hz  = NSEC_PER_SEC / *(u32 *)obj->buffer.pointer;
+		lookup->max_speed_hz  = NSEC_PER_SEC / *(u32 *)obj->buffer.pointer;
 
 	if (!acpi_dev_get_property(dev, "spiWordSize", ACPI_TYPE_BUFFER, &obj)
 	    && obj->buffer.length == 8)
-		spi->bits_per_word = *(u64 *)obj->buffer.pointer;
+		lookup->bits_per_word = *(u64 *)obj->buffer.pointer;
 
 	if (!acpi_dev_get_property(dev, "spiBitOrder", ACPI_TYPE_BUFFER, &obj)
 	    && obj->buffer.length == 8 && !*(u64 *)obj->buffer.pointer)
-		spi->mode |= SPI_LSB_FIRST;
+		lookup->mode |= SPI_LSB_FIRST;
 
 	if (!acpi_dev_get_property(dev, "spiSPO", ACPI_TYPE_BUFFER, &obj)
 	    && obj->buffer.length == 8 &&  *(u64 *)obj->buffer.pointer)
-		spi->mode |= SPI_CPOL;
+		lookup->mode |= SPI_CPOL;
 
 	if (!acpi_dev_get_property(dev, "spiSPH", ACPI_TYPE_BUFFER, &obj)
 	    && obj->buffer.length == 8 &&  *(u64 *)obj->buffer.pointer)
-		spi->mode |= SPI_CPHA;
+		lookup->mode |= SPI_CPHA;
 }
 
 static int acpi_spi_add_resource(struct acpi_resource *ares, void *data)
 {
-	struct spi_device *spi = data;
-	struct spi_controller *ctlr = spi->controller;
+	struct acpi_spi_lookup *lookup = data;
+	struct spi_controller *ctlr = lookup->ctlr;
 
 	if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) {
 		struct acpi_resource_spi_serialbus *sb;
+		acpi_handle parent_handle;
+		acpi_status status;
 
 		sb = &ares->data.spi_serial_bus;
 		if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_SPI) {
+
+			status = acpi_get_handle(NULL,
+						 sb->resource_source.string_ptr,
+						 &parent_handle);
+
+			if (ACPI_FAILURE(status) ||
+			    ACPI_HANDLE(ctlr->dev.parent) != parent_handle)
+				return -ENODEV;
+
 			/*
 			 * ACPI DeviceSelection numbering is handled by the
 			 * host controller driver in Windows and can vary
@@ -1855,25 +1923,25 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data)
 						sb->device_selection);
 				if (cs < 0)
 					return cs;
-				spi->chip_select = cs;
+				lookup->chip_select = cs;
 			} else {
-				spi->chip_select = sb->device_selection;
+				lookup->chip_select = sb->device_selection;
 			}
 
-			spi->max_speed_hz = sb->connection_speed;
+			lookup->max_speed_hz = sb->connection_speed;
 
 			if (sb->clock_phase == ACPI_SPI_SECOND_PHASE)
-				spi->mode |= SPI_CPHA;
+				lookup->mode |= SPI_CPHA;
 			if (sb->clock_polarity == ACPI_SPI_START_HIGH)
-				spi->mode |= SPI_CPOL;
+				lookup->mode |= SPI_CPOL;
 			if (sb->device_polarity == ACPI_SPI_ACTIVE_HIGH)
-				spi->mode |= SPI_CS_HIGH;
+				lookup->mode |= SPI_CS_HIGH;
 		}
-	} else if (spi->irq < 0) {
+	} else if (lookup->irq < 0) {
 		struct resource r;
 
 		if (acpi_dev_resource_interrupt(ares, 0, &r))
-			spi->irq = r.start;
+			lookup->irq = r.start;
 	}
 
 	/* Always tell the ACPI core to skip this resource */
@@ -1883,7 +1951,9 @@ static int acpi_spi_add_resource(struct acpi_resource *ares, void *data)
 static acpi_status acpi_register_spi_device(struct spi_controller *ctlr,
 					    struct acpi_device *adev)
 {
+	acpi_handle parent_handle = NULL;
 	struct list_head resource_list;
+	struct acpi_spi_lookup lookup = {};
 	struct spi_device *spi;
 	int ret;
 
@@ -1891,28 +1961,42 @@ static acpi_status acpi_register_spi_device(struct spi_controller *ctlr,
 	    acpi_device_enumerated(adev))
 		return AE_OK;
 
-	spi = spi_alloc_device(ctlr);
-	if (!spi) {
-		dev_err(&ctlr->dev, "failed to allocate SPI device for %s\n",
-			dev_name(&adev->dev));
-		return AE_NO_MEMORY;
-	}
-
-	ACPI_COMPANION_SET(&spi->dev, adev);
-	spi->irq = -1;
+	lookup.ctlr		= ctlr;
+	lookup.irq		= -1;
 
 	INIT_LIST_HEAD(&resource_list);
 	ret = acpi_dev_get_resources(adev, &resource_list,
-				     acpi_spi_add_resource, spi);
+				     acpi_spi_add_resource, &lookup);
 	acpi_dev_free_resource_list(&resource_list);
 
-	acpi_spi_parse_apple_properties(spi);
+	if (ret < 0)
+		/* found SPI in _CRS but it points to another controller */
+		return AE_OK;
 
-	if (ret < 0 || !spi->max_speed_hz) {
-		spi_dev_put(spi);
+	if (!lookup.max_speed_hz &&
+	    !ACPI_FAILURE(acpi_get_parent(adev->handle, &parent_handle)) &&
+	    ACPI_HANDLE(ctlr->dev.parent) == parent_handle) {
+		/* Apple does not use _CRS but nested devices for SPI slaves */
+		acpi_spi_parse_apple_properties(adev, &lookup);
+	}
+
+	if (!lookup.max_speed_hz)
 		return AE_OK;
+
+	spi = spi_alloc_device(ctlr);
+	if (!spi) {
+		dev_err(&ctlr->dev, "failed to allocate SPI device for %s\n",
+			dev_name(&adev->dev));
+		return AE_NO_MEMORY;
 	}
 
+	ACPI_COMPANION_SET(&spi->dev, adev);
+	spi->max_speed_hz	= lookup.max_speed_hz;
+	spi->mode		= lookup.mode;
+	spi->irq		= lookup.irq;
+	spi->bits_per_word	= lookup.bits_per_word;
+	spi->chip_select	= lookup.chip_select;
+
 	acpi_set_modalias(adev, acpi_device_hid(adev), spi->modalias,
 			  sizeof(spi->modalias));
 
@@ -1944,6 +2028,8 @@ static acpi_status acpi_spi_add_device(acpi_handle handle, u32 level,
 	return acpi_register_spi_device(ctlr, adev);
 }
 
+#define SPI_ACPI_ENUMERATE_MAX_DEPTH		32
+
 static void acpi_register_spi_devices(struct spi_controller *ctlr)
 {
 	acpi_status status;
@@ -1953,7 +2039,8 @@ static void acpi_register_spi_devices(struct spi_controller *ctlr)
 	if (!handle)
 		return;
 
-	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle, 1,
+	status = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
+				     SPI_ACPI_ENUMERATE_MAX_DEPTH,
 				     acpi_spi_add_device, NULL, ctlr, NULL);
 	if (ACPI_FAILURE(status))
 		dev_warn(&ctlr->dev, "failed to enumerate SPI slaves\n");
@@ -2286,11 +2373,6 @@ int spi_register_controller(struct spi_controller *ctlr)
 	if (status)
 		return status;
 
-	/* even if it's just one always-selected device, there must
-	 * be at least one chipselect
-	 */
-	if (ctlr->num_chipselect == 0)
-		return -EINVAL;
 	if (ctlr->bus_num >= 0) {
 		/* devices with a fixed bus num must check-in with the num */
 		mutex_lock(&board_lock);
@@ -2361,6 +2443,13 @@ int spi_register_controller(struct spi_controller *ctlr)
 		}
 	}
 
+	/*
+	 * Even if it's just one always-selected device, there must
+	 * be at least one chipselect.
+	 */
+	if (!ctlr->num_chipselect)
+		return -EINVAL;
+
 	status = device_add(&ctlr->dev);
 	if (status < 0) {
 		/* free bus id */
@@ -2470,7 +2559,6 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 {
 	struct spi_controller *found;
 	int id = ctlr->bus_num;
-	int dummy;
 
 	/* First make sure that this controller was ever added */
 	mutex_lock(&board_lock);
@@ -2484,7 +2572,7 @@ void spi_unregister_controller(struct spi_controller *ctlr)
 	list_del(&ctlr->list);
 	mutex_unlock(&board_lock);
 
-	dummy = device_for_each_child(&ctlr->dev, NULL, __unregister);
+	device_for_each_child(&ctlr->dev, NULL, __unregister);
 	device_unregister(&ctlr->dev);
 	/* free bus id */
 	mutex_lock(&board_lock);
@@ -2633,12 +2721,9 @@ EXPORT_SYMBOL_GPL(spi_res_add);
  */
 void spi_res_release(struct spi_controller *ctlr, struct spi_message *message)
 {
-	struct spi_res *res;
-
-	while (!list_empty(&message->resources)) {
-		res = list_last_entry(&message->resources,
-				      struct spi_res, entry);
+	struct spi_res *res, *tmp;
 
+	list_for_each_entry_safe_reverse(res, tmp, &message->resources, entry) {
 		if (res->release)
 			res->release(ctlr, message, res->data);
 
@@ -2702,8 +2787,7 @@ struct spi_replaced_transfers *spi_replace_transfers(
 
 	/* allocate the structure using spi_res */
 	rxfer = spi_res_alloc(msg->spi, __spi_replace_transfers_release,
-			      insert * sizeof(struct spi_transfer)
-			      + sizeof(struct spi_replaced_transfers)
+			      struct_size(rxfer, inserted_transfers, insert)
 			      + extradatasize,
 			      gfp);
 	if (!rxfer)
@@ -3083,6 +3167,7 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 	 */
 	message->frame_length = 0;
 	list_for_each_entry(xfer, &message->transfers, transfer_list) {
+		xfer->effective_speed_hz = 0;
 		message->frame_length += xfer->len;
 		if (!xfer->bits_per_word)
 			xfer->bits_per_word = spi->bits_per_word;
@@ -3762,4 +3847,3 @@ err0:
  * include needing to have boardinfo data structures be much more public.
  */
 postcore_initcall(spi_init);
-
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 422bac8cc3e0..255786f2e844 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -663,6 +663,8 @@ static const struct of_device_id spidev_dt_ids[] = {
 	{ .compatible = "ge,achc" },
 	{ .compatible = "semtech,sx1301" },
 	{ .compatible = "lwn,bk4" },
+	{ .compatible = "dh,dhcom-board" },
+	{ .compatible = "menlo,m53cpld" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, spidev_dt_ids);