Merge tag 'spi-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi

Pull spi updates from Mark Brown:
 "The main focus of this release from a framework point of view has been
  spi-mem where we've acquired support for a few new hardware features
  which enable better performance on suitable hardware.

  Otherwise mostly thanks to Arnd's cleanup efforts on old platforms
  we've removed several obsolete drivers which just about balance out
  the newer drivers we've added this cycle.

  Summary:

   - Allow drivers to flag if they are unidirectional.

   - Support for DTR mode and hardware acceleration of dummy cycles in
     spi-mem.

   - Support for Allwinder H616, Intel Lightning Mountain, nVidia Tegra
     QuadSPI, Realtek RTL838x and RTL839x.

   - Removal of obsolete EFM32, Txx9 and SIRF Prima and Atlas drivers"

* tag 'spi-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi: (76 commits)
  spi: Skip zero-length transfers in spi_transfer_one_message()
  spi: dw: Avoid stack content exposure
  spi: cadence-quadspi: Use spi_mem_dtr_supports_op()
  spi: spi-mem: add spi_mem_dtr_supports_op()
  spi: atmel-quadspi: Disable the QSPI IP at suspend()
  spi: pxa2xx: Add IDs for the controllers found on Intel Lynxpoint
  spi: pxa2xx: Fix the controller numbering for Wildcat Point
  spi: Change provied to provided in the file spi.h
  spi: mediatek: add set_cs_timing support
  spi: support CS timing for HW & SW mode
  spi: add power control when set_cs_timing
  spi: stm32: make spurious and overrun interrupts visible
  spi: stm32h7: replace private SPI_1HZ_NS with NSEC_PER_SEC
  spi: stm32: defer probe for reset
  spi: stm32: driver uses reset controller only at init
  spi: stm32h7: ensure message are smaller than max size
  spi: stm32: use bitfield macros
  spi: stm32: do not mandate cs_gpio
  spi: stm32: properly handle 0 byte transfer
  spi: clps711xx: remove redundant white-space
  ...

32 files changed, 2272 insertions, 2434 deletions

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 74ea73a05981..09a263cf4ae2 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -203,7 +203,7 @@ config SPI_CADENCE
 
 config SPI_CADENCE_QUADSPI
 	tristate "Cadence Quad SPI controller"
-	depends on OF && (ARM || ARM64 || COMPILE_TEST)
+	depends on OF && (ARM || ARM64 || X86 || COMPILE_TEST)
 	help
 	  Enable support for the Cadence Quad SPI Flash controller.
 
@@ -292,13 +292,6 @@ config SPI_DLN2
 	 This driver can also be built as a module.  If so, the module
 	 will be called spi-dln2.
 
-config SPI_EFM32
-	tristate "EFM32 SPI controller"
-	depends on OF && ARM && (ARCH_EFM32 || COMPILE_TEST)
-	select SPI_BITBANG
-	help
-	  Driver for the spi controller found on Energy Micro's EFM32 SoCs.
-
 config SPI_EP93XX
 	tristate "Cirrus Logic EP93xx SPI controller"
 	depends on ARCH_EP93XX || COMPILE_TEST
@@ -649,7 +642,7 @@ config SPI_RPCIF
 	tristate "Renesas RPC-IF SPI driver"
 	depends on RENESAS_RPCIF
 	help
-	  SPI driver for Renesas R-Car Gen3 RPC-IF.
+	  SPI driver for Renesas R-Car Gen3 or RZ/G2 RPC-IF.
 
 config SPI_RSPI
 	tristate "Renesas RSPI/QSPI controller"
@@ -750,13 +743,6 @@ config SPI_SIFIVE
 	help
 	  This exposes the SPI controller IP from SiFive.
 
-config SPI_SIRF
-	tristate "CSR SiRFprimaII SPI controller"
-	depends on SIRF_DMA
-	select SPI_BITBANG
-	help
-	  SPI driver for CSR SiRFprimaII SoCs
-
 config SPI_SLAVE_MT27XX
 	tristate "MediaTek SPI slave device"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
@@ -842,6 +828,15 @@ config SPI_MXS
 	help
 	  SPI driver for Freescale MXS devices.
 
+config SPI_TEGRA210_QUAD
+	tristate "NVIDIA Tegra QSPI Controller"
+	depends on ARCH_TEGRA || COMPILE_TEST
+	depends on RESET_CONTROLLER
+	help
+	  QSPI driver for NVIDIA Tegra QSPI Controller interface. This
+	  controller is different from the SPI controller and is available
+	  on Tegra SoCs starting from Tegra210.
+
 config SPI_TEGRA114
 	tristate "NVIDIA Tegra114 SPI Controller"
 	depends on (ARCH_TEGRA && TEGRA20_APB_DMA) || COMPILE_TEST
@@ -884,12 +879,6 @@ config SPI_TOPCLIFF_PCH
 	  This driver also supports the ML7213/ML7223/ML7831, a companion chip
 	  for the Atom E6xx series and compatible with the Intel EG20T PCH.
 
-config SPI_TXX9
-	tristate "Toshiba TXx9 SPI controller"
-	depends on GPIOLIB && (CPU_TX49XX || COMPILE_TEST)
-	help
-	  SPI driver for Toshiba TXx9 MIPS SoCs
-
 config SPI_UNIPHIER
 	tristate "Socionext UniPhier SPI Controller"
 	depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 6fea5821662e..0f06fc0813c6 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -42,7 +42,6 @@ spi-dw-$(CONFIG_SPI_DW_DMA)		+= spi-dw-dma.o
 obj-$(CONFIG_SPI_DW_BT1)		+= spi-dw-bt1.o
 obj-$(CONFIG_SPI_DW_MMIO)		+= spi-dw-mmio.o
 obj-$(CONFIG_SPI_DW_PCI)		+= spi-dw-pci.o
-obj-$(CONFIG_SPI_EFM32)			+= spi-efm32.o
 obj-$(CONFIG_SPI_EP93XX)		+= spi-ep93xx.o
 obj-$(CONFIG_SPI_FALCON)		+= spi-falcon.o
 obj-$(CONFIG_SPI_FSI)			+= spi-fsi.o
@@ -94,6 +93,7 @@ obj-$(CONFIG_SPI_QCOM_QSPI)		+= spi-qcom-qspi.o
 obj-$(CONFIG_SPI_QUP)			+= spi-qup.o
 obj-$(CONFIG_SPI_ROCKCHIP)		+= spi-rockchip.o
 obj-$(CONFIG_SPI_RB4XX)			+= spi-rb4xx.o
+obj-$(CONFIG_MACH_REALTEK_RTL)		+= spi-realtek-rtl.o
 obj-$(CONFIG_SPI_RPCIF)			+= spi-rpc-if.o
 obj-$(CONFIG_SPI_RSPI)			+= spi-rspi.o
 obj-$(CONFIG_SPI_S3C24XX)		+= spi-s3c24xx-hw.o
@@ -105,7 +105,6 @@ obj-$(CONFIG_SPI_SH_HSPI)		+= spi-sh-hspi.o
 obj-$(CONFIG_SPI_SH_MSIOF)		+= spi-sh-msiof.o
 obj-$(CONFIG_SPI_SH_SCI)		+= spi-sh-sci.o
 obj-$(CONFIG_SPI_SIFIVE)		+= spi-sifive.o
-obj-$(CONFIG_SPI_SIRF)		+= spi-sirf.o
 obj-$(CONFIG_SPI_SLAVE_MT27XX)          += spi-slave-mt27xx.o
 obj-$(CONFIG_SPI_SPRD)			+= spi-sprd.o
 obj-$(CONFIG_SPI_SPRD_ADI)		+= spi-sprd-adi.o
@@ -115,6 +114,7 @@ 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-$(CONFIG_SPI_TEGRA210_QUAD)		+= spi-tegra210-quad.o
 obj-$(CONFIG_SPI_TEGRA114)		+= spi-tegra114.o
 obj-$(CONFIG_SPI_TEGRA20_SFLASH)	+= spi-tegra20-sflash.o
 obj-$(CONFIG_SPI_TEGRA20_SLINK)		+= spi-tegra20-slink.o
@@ -122,7 +122,6 @@ obj-$(CONFIG_SPI_TLE62X0)		+= spi-tle62x0.o
 spi-thunderx-objs			:= spi-cavium.o spi-cavium-thunderx.o
 obj-$(CONFIG_SPI_THUNDERX)		+= spi-thunderx.o
 obj-$(CONFIG_SPI_TOPCLIFF_PCH)		+= spi-topcliff-pch.o
-obj-$(CONFIG_SPI_TXX9)			+= spi-txx9.o
 obj-$(CONFIG_SPI_UNIPHIER)		+= spi-uniphier.o
 obj-$(CONFIG_SPI_XCOMM)		+= spi-xcomm.o
 obj-$(CONFIG_SPI_XILINX)		+= spi-xilinx.o
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index 10bc5390ab91..95d4fa32c299 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -657,6 +657,7 @@ static int __maybe_unused atmel_qspi_suspend(struct device *dev)
 	struct spi_controller *ctrl = dev_get_drvdata(dev);
 	struct atmel_qspi *aq = spi_controller_get_devdata(ctrl);
 
+	atmel_qspi_write(QSPI_CR_QSPIDIS, aq, QSPI_CR);
 	clk_disable_unprepare(aq->qspick);
 	clk_disable_unprepare(aq->pclk);
 
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 948396b382d7..f429436082af 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1590,7 +1590,7 @@ static int atmel_spi_probe(struct platform_device *pdev)
 		if (ret == 0) {
 			as->use_dma = true;
 		} else if (ret == -EPROBE_DEFER) {
-			return ret;
+			goto out_unmap_regs;
 		}
 	} else if (as->caps.has_pdc_support) {
 		as->use_pdc = true;
diff --git a/drivers/spi/spi-au1550.c b/drivers/spi/spi-au1550.c
index dfb7196f4caf..4b59a1b1bf7e 100644
--- a/drivers/spi/spi-au1550.c
+++ b/drivers/spi/spi-au1550.c
@@ -26,7 +26,7 @@
 
 #include <asm/mach-au1x00/au1550_spi.h>
 
-static unsigned usedma = 1;
+static unsigned int usedma = 1;
 module_param(usedma, uint, 0644);
 
 /*
@@ -43,9 +43,9 @@ struct au1550_spi {
 	volatile psc_spi_t __iomem *regs;
 	int irq;
 
-	unsigned len;
-	unsigned tx_count;
-	unsigned rx_count;
+	unsigned int len;
+	unsigned int tx_count;
+	unsigned int rx_count;
 	const u8 *tx;
 	u8 *rx;
 
@@ -56,14 +56,14 @@ struct au1550_spi {
 
 	struct completion master_done;
 
-	unsigned usedma;
+	unsigned int usedma;
 	u32 dma_tx_id;
 	u32 dma_rx_id;
 	u32 dma_tx_ch;
 	u32 dma_rx_ch;
 
 	u8 *dma_rx_tmpbuf;
-	unsigned dma_rx_tmpbuf_size;
+	unsigned int dma_rx_tmpbuf_size;
 	u32 dma_rx_tmpbuf_addr;
 
 	struct spi_master *master;
@@ -74,8 +74,7 @@ struct au1550_spi {
 
 
 /* we use an 8-bit memory device for dma transfers to/from spi fifo */
-static dbdev_tab_t au1550_spi_mem_dbdev =
-{
+static dbdev_tab_t au1550_spi_mem_dbdev = {
 	.dev_id			= DBDMA_MEM_CHAN,
 	.dev_flags		= DEV_FLAGS_ANYUSE|DEV_FLAGS_SYNC,
 	.dev_tsize		= 0,
@@ -99,7 +98,7 @@ static void au1550_spi_bits_handlers_set(struct au1550_spi *hw, int bpw);
  *    BRG valid range is 4..63
  *    DIV valid range is 0..3
  */
-static u32 au1550_spi_baudcfg(struct au1550_spi *hw, unsigned speed_hz)
+static u32 au1550_spi_baudcfg(struct au1550_spi *hw, unsigned int speed_hz)
 {
 	u32 mainclk_hz = hw->pdata->mainclk_hz;
 	u32 div, brg;
@@ -161,7 +160,7 @@ static void au1550_spi_reset_fifos(struct au1550_spi *hw)
 static void au1550_spi_chipsel(struct spi_device *spi, int value)
 {
 	struct au1550_spi *hw = spi_master_get_devdata(spi->master);
-	unsigned cspol = spi->mode & SPI_CS_HIGH ? 1 : 0;
+	unsigned int cspol = spi->mode & SPI_CS_HIGH ? 1 : 0;
 	u32 cfg, stat;
 
 	switch (value) {
@@ -221,7 +220,7 @@ static void au1550_spi_chipsel(struct spi_device *spi, int value)
 static int au1550_spi_setupxfer(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct au1550_spi *hw = spi_master_get_devdata(spi->master);
-	unsigned bpw, hz;
+	unsigned int bpw, hz;
 	u32 cfg, stat;
 
 	if (t) {
@@ -276,7 +275,7 @@ static int au1550_spi_setupxfer(struct spi_device *spi, struct spi_transfer *t)
  * spi master done event irq is not generated unless rx fifo is empty (emptied)
  * so we need rx tmp buffer to use for rx dma if user does not provide one
  */
-static int au1550_spi_dma_rxtmp_alloc(struct au1550_spi *hw, unsigned size)
+static int au1550_spi_dma_rxtmp_alloc(struct au1550_spi *hw, unsigned int size)
 {
 	hw->dma_rx_tmpbuf = kmalloc(size, GFP_KERNEL);
 	if (!hw->dma_rx_tmpbuf)
@@ -399,10 +398,10 @@ static int au1550_spi_dma_txrxb(struct spi_device *spi, struct spi_transfer *t)
 			DMA_FROM_DEVICE);
 	}
 	/* unmap buffers if mapped above */
-	if (t->rx_buf && t->rx_dma == 0 )
+	if (t->rx_buf && t->rx_dma == 0)
 		dma_unmap_single(hw->dev, dma_rx_addr, t->len,
 			DMA_FROM_DEVICE);
-	if (t->tx_buf && t->tx_dma == 0 )
+	if (t->tx_buf && t->tx_dma == 0)
 		dma_unmap_single(hw->dev, dma_tx_addr, t->len,
 			DMA_TO_DEVICE);
 
@@ -447,8 +446,8 @@ static irqreturn_t au1550_spi_dma_irq_callback(struct au1550_spi *hw)
 				"dma transfer: receive FIFO overflow!\n");
 		else
 			dev_err(hw->dev,
-				"dma transfer: unexpected SPI error "
-				"(event=0x%x stat=0x%x)!\n", evnt, stat);
+				"dma transfer: unexpected SPI error (event=0x%x stat=0x%x)!\n",
+				evnt, stat);
 
 		complete(&hw->master_done);
 		return IRQ_HANDLED;
@@ -493,12 +492,12 @@ static void au1550_spi_tx_word_##size(struct au1550_spi *hw)		\
 	wmb(); /* drain writebuffer */					\
 }
 
-AU1550_SPI_RX_WORD(8,0xff)
-AU1550_SPI_RX_WORD(16,0xffff)
-AU1550_SPI_RX_WORD(32,0xffffff)
-AU1550_SPI_TX_WORD(8,0xff)
-AU1550_SPI_TX_WORD(16,0xffff)
-AU1550_SPI_TX_WORD(32,0xffffff)
+AU1550_SPI_RX_WORD(8, 0xff)
+AU1550_SPI_RX_WORD(16, 0xffff)
+AU1550_SPI_RX_WORD(32, 0xffffff)
+AU1550_SPI_TX_WORD(8, 0xff)
+AU1550_SPI_TX_WORD(16, 0xffff)
+AU1550_SPI_TX_WORD(32, 0xffffff)
 
 static int au1550_spi_pio_txrxb(struct spi_device *spi, struct spi_transfer *t)
 {
@@ -567,8 +566,8 @@ static irqreturn_t au1550_spi_pio_irq_callback(struct au1550_spi *hw)
 		au1550_spi_mask_ack_all(hw);
 		au1550_spi_reset_fifos(hw);
 		dev_err(hw->dev,
-			"pio transfer: unexpected SPI error "
-			"(event=0x%x stat=0x%x)!\n", evnt, stat);
+			"pio transfer: unexpected SPI error (event=0x%x stat=0x%x)!\n",
+			evnt, stat);
 		complete(&hw->master_done);
 		return IRQ_HANDLED;
 	}
@@ -636,12 +635,14 @@ static irqreturn_t au1550_spi_pio_irq_callback(struct au1550_spi *hw)
 static int au1550_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct au1550_spi *hw = spi_master_get_devdata(spi->master);
+
 	return hw->txrx_bufs(spi, t);
 }
 
 static irqreturn_t au1550_spi_irq(int irq, void *dev)
 {
 	struct au1550_spi *hw = dev;
+
 	return hw->irq_callback(hw);
 }
 
@@ -872,6 +873,7 @@ static int au1550_spi_probe(struct platform_device *pdev)
 	{
 		int min_div = (2 << 0) * (2 * (4 + 1));
 		int max_div = (2 << 3) * (2 * (63 + 1));
+
 		master->max_speed_hz = hw->pdata->mainclk_hz / min_div;
 		master->min_speed_hz =
 				hw->pdata->mainclk_hz / (max_div + 1) + 1;
@@ -972,8 +974,7 @@ static int __init au1550_spi_init(void)
 	if (usedma) {
 		ddma_memid = au1xxx_ddma_add_device(&au1550_spi_mem_dbdev);
 		if (!ddma_memid)
-			printk(KERN_ERR "au1550-spi: cannot add memory"
-					"dbdma device\n");
+			printk(KERN_ERR "au1550-spi: cannot add memory dbdma device\n");
 	}
 	return platform_driver_register(&au1550_spi_drv);
 }
diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c
index c028446c7460..707fe3a5d8ef 100644
--- a/drivers/spi/spi-bcm-qspi.c
+++ b/drivers/spi/spi-bcm-qspi.c
@@ -881,7 +881,7 @@ static int bcm_qspi_bspi_exec_mem_op(struct spi_device *spi,
 	 * when using flex mode we need to send
 	 * the upper address byte to bspi
 	 */
-	if (bcm_qspi_bspi_ver_three(qspi) == false) {
+	if (!bcm_qspi_bspi_ver_three(qspi)) {
 		addr = from & 0xff000000;
 		bcm_qspi_write(qspi, BSPI,
 			       BSPI_BSPI_FLASH_UPPER_ADDR_BYTE, addr);
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 197485f2c2b2..8965fe61c8b4 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -386,7 +386,7 @@ static irqreturn_t bcm2835_spi_interrupt(int irq, void *dev_id)
 		/* Transfer complete - reset SPI HW */
 		bcm2835_spi_reset_hw(bs);
 		/* wake up the framework */
-		complete(&bs->ctlr->xfer_completion);
+		spi_finalize_current_transfer(bs->ctlr);
 	}
 
 	return IRQ_HANDLED;
@@ -608,7 +608,7 @@ static void bcm2835_spi_dma_rx_done(void *data)
 	bcm2835_spi_reset_hw(bs);
 
 	/* and mark as completed */;
-	complete(&ctlr->xfer_completion);
+	spi_finalize_current_transfer(ctlr);
 }
 
 /**
@@ -640,7 +640,7 @@ static void bcm2835_spi_dma_tx_done(void *data)
 
 	bcm2835_spi_undo_prologue(bs);
 	bcm2835_spi_reset_hw(bs);
-	complete(&ctlr->xfer_completion);
+	spi_finalize_current_transfer(ctlr);
 }
 
 /**
@@ -1307,6 +1307,8 @@ static int bcm2835_spi_probe(struct platform_device *pdev)
 		return dev_err_probe(&pdev->dev, PTR_ERR(bs->clk),
 				     "could not get clk\n");
 
+	ctlr->max_speed_hz = clk_get_rate(bs->clk) / 2;
+
 	bs->irq = platform_get_irq(pdev, 0);
 	if (bs->irq <= 0)
 		return bs->irq ? bs->irq : -ENODEV;
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index 1a26865c42f8..75589ac6e95f 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -254,7 +254,7 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
 	/* and if rx_len is 0 then disable interrupts and wake up completion */
 	if (!bs->rx_len) {
 		bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1]);
-		complete(&master->xfer_completion);
+		spi_finalize_current_transfer(master);
 	}
 
 	return IRQ_HANDLED;
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index ba7d40c2922f..442cc7c53a47 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -52,6 +52,7 @@ struct cqspi_flash_pdata {
 	u8		inst_width;
 	u8		addr_width;
 	u8		data_width;
+	bool		dtr;
 	u8		cs;
 };
 
@@ -75,6 +76,7 @@ struct cqspi_st {
 	bool			is_decoded_cs;
 	u32			fifo_depth;
 	u32			fifo_width;
+	u32			num_chipselect;
 	bool			rclk_en;
 	u32			trigger_address;
 	u32			wr_delay;
@@ -111,6 +113,8 @@ struct cqspi_driver_platdata {
 #define CQSPI_REG_CONFIG_CHIPSELECT_LSB		10
 #define CQSPI_REG_CONFIG_DMA_MASK		BIT(15)
 #define CQSPI_REG_CONFIG_BAUD_LSB		19
+#define CQSPI_REG_CONFIG_DTR_PROTO		BIT(24)
+#define CQSPI_REG_CONFIG_DUAL_OPCODE		BIT(30)
 #define CQSPI_REG_CONFIG_IDLE_LSB		31
 #define CQSPI_REG_CONFIG_CHIPSELECT_MASK	0xF
 #define CQSPI_REG_CONFIG_BAUD_MASK		0xF
@@ -173,6 +177,9 @@ struct cqspi_driver_platdata {
 #define CQSPI_REG_SDRAMLEVEL_RD_MASK		0xFFFF
 #define CQSPI_REG_SDRAMLEVEL_WR_MASK		0xFFFF
 
+#define CQSPI_REG_WR_COMPLETION_CTRL		0x38
+#define CQSPI_REG_WR_DISABLE_AUTO_POLL		BIT(14)
+
 #define CQSPI_REG_IRQSTATUS			0x40
 #define CQSPI_REG_IRQMASK			0x44
 
@@ -188,6 +195,7 @@ struct cqspi_driver_platdata {
 #define CQSPI_REG_CMDCTRL			0x90
 #define CQSPI_REG_CMDCTRL_EXECUTE_MASK		BIT(0)
 #define CQSPI_REG_CMDCTRL_INPROGRESS_MASK	BIT(1)
+#define CQSPI_REG_CMDCTRL_DUMMY_LSB		7
 #define CQSPI_REG_CMDCTRL_WR_BYTES_LSB		12
 #define CQSPI_REG_CMDCTRL_WR_EN_LSB		15
 #define CQSPI_REG_CMDCTRL_ADD_BYTES_LSB		16
@@ -198,6 +206,7 @@ struct cqspi_driver_platdata {
 #define CQSPI_REG_CMDCTRL_WR_BYTES_MASK		0x7
 #define CQSPI_REG_CMDCTRL_ADD_BYTES_MASK	0x3
 #define CQSPI_REG_CMDCTRL_RD_BYTES_MASK		0x7
+#define CQSPI_REG_CMDCTRL_DUMMY_MASK		0x1F
 
 #define CQSPI_REG_INDIRECTWR			0x70
 #define CQSPI_REG_INDIRECTWR_START_MASK		BIT(0)
@@ -214,6 +223,14 @@ struct cqspi_driver_platdata {
 #define CQSPI_REG_CMDWRITEDATALOWER		0xA8
 #define CQSPI_REG_CMDWRITEDATAUPPER		0xAC
 
+#define CQSPI_REG_POLLING_STATUS		0xB0
+#define CQSPI_REG_POLLING_STATUS_DUMMY_LSB	16
+
+#define CQSPI_REG_OP_EXT_LOWER			0xE0
+#define CQSPI_REG_OP_EXT_READ_LSB		24
+#define CQSPI_REG_OP_EXT_WRITE_LSB		16
+#define CQSPI_REG_OP_EXT_STIG_LSB		0
+
 /* Interrupt status bits */
 #define CQSPI_REG_IRQ_MODE_ERR			BIT(0)
 #define CQSPI_REG_IRQ_UNDERFLOW			BIT(1)
@@ -288,6 +305,80 @@ static unsigned int cqspi_calc_rdreg(struct cqspi_flash_pdata *f_pdata)
 	return rdreg;
 }
 
+static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr)
+{
+	unsigned int dummy_clk;
+
+	dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth);
+	if (dtr)
+		dummy_clk /= 2;
+
+	return dummy_clk;
+}
+
+static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata,
+			      const struct spi_mem_op *op)
+{
+	f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE;
+	f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE;
+	f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
+	f_pdata->dtr = op->data.dtr && op->cmd.dtr && op->addr.dtr;
+
+	switch (op->data.buswidth) {
+	case 0:
+		break;
+	case 1:
+		f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
+		break;
+	case 2:
+		f_pdata->data_width = CQSPI_INST_TYPE_DUAL;
+		break;
+	case 4:
+		f_pdata->data_width = CQSPI_INST_TYPE_QUAD;
+		break;
+	case 8:
+		f_pdata->data_width = CQSPI_INST_TYPE_OCTAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Right now we only support 8-8-8 DTR mode. */
+	if (f_pdata->dtr) {
+		switch (op->cmd.buswidth) {
+		case 0:
+			break;
+		case 8:
+			f_pdata->inst_width = CQSPI_INST_TYPE_OCTAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		switch (op->addr.buswidth) {
+		case 0:
+			break;
+		case 8:
+			f_pdata->addr_width = CQSPI_INST_TYPE_OCTAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		switch (op->data.buswidth) {
+		case 0:
+			break;
+		case 8:
+			f_pdata->data_width = CQSPI_INST_TYPE_OCTAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int cqspi_wait_idle(struct cqspi_st *cqspi)
 {
 	const unsigned int poll_idle_retry = 3;
@@ -345,19 +436,85 @@ static int cqspi_exec_flash_cmd(struct cqspi_st *cqspi, unsigned int reg)
 	return cqspi_wait_idle(cqspi);
 }
 
+static int cqspi_setup_opcode_ext(struct cqspi_flash_pdata *f_pdata,
+				  const struct spi_mem_op *op,
+				  unsigned int shift)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int reg;
+	u8 ext;
+
+	if (op->cmd.nbytes != 2)
+		return -EINVAL;
+
+	/* Opcode extension is the LSB. */
+	ext = op->cmd.opcode & 0xff;
+
+	reg = readl(reg_base + CQSPI_REG_OP_EXT_LOWER);
+	reg &= ~(0xff << shift);
+	reg |= ext << shift;
+	writel(reg, reg_base + CQSPI_REG_OP_EXT_LOWER);
+
+	return 0;
+}
+
+static int cqspi_enable_dtr(struct cqspi_flash_pdata *f_pdata,
+			    const struct spi_mem_op *op, unsigned int shift,
+			    bool enable)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int reg;
+	int ret;
+
+	reg = readl(reg_base + CQSPI_REG_CONFIG);
+
+	/*
+	 * We enable dual byte opcode here. The callers have to set up the
+	 * extension opcode based on which type of operation it is.
+	 */
+	if (enable) {
+		reg |= CQSPI_REG_CONFIG_DTR_PROTO;
+		reg |= CQSPI_REG_CONFIG_DUAL_OPCODE;
+
+		/* Set up command opcode extension. */
+		ret = cqspi_setup_opcode_ext(f_pdata, op, shift);
+		if (ret)
+			return ret;
+	} else {
+		reg &= ~CQSPI_REG_CONFIG_DTR_PROTO;
+		reg &= ~CQSPI_REG_CONFIG_DUAL_OPCODE;
+	}
+
+	writel(reg, reg_base + CQSPI_REG_CONFIG);
+
+	return cqspi_wait_idle(cqspi);
+}
+
 static int cqspi_command_read(struct cqspi_flash_pdata *f_pdata,
 			      const struct spi_mem_op *op)
 {
 	struct cqspi_st *cqspi = f_pdata->cqspi;
 	void __iomem *reg_base = cqspi->iobase;
 	u8 *rxbuf = op->data.buf.in;
-	u8 opcode = op->cmd.opcode;
+	u8 opcode;
 	size_t n_rx = op->data.nbytes;
 	unsigned int rdreg;
 	unsigned int reg;
+	unsigned int dummy_clk;
 	size_t read_len;
 	int status;
 
+	status = cqspi_set_protocol(f_pdata, op);
+	if (status)
+		return status;
+
+	status = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_STIG_LSB,
+				  f_pdata->dtr);
+	if (status)
+		return status;
+
 	if (!n_rx || n_rx > CQSPI_STIG_DATA_LEN_MAX || !rxbuf) {
 		dev_err(&cqspi->pdev->dev,
 			"Invalid input argument, len %zu rxbuf 0x%p\n",
@@ -365,11 +522,24 @@ static int cqspi_command_read(struct cqspi_flash_pdata *f_pdata,
 		return -EINVAL;
 	}
 
+	if (f_pdata->dtr)
+		opcode = op->cmd.opcode >> 8;
+	else
+		opcode = op->cmd.opcode;
+
 	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
 
 	rdreg = cqspi_calc_rdreg(f_pdata);
 	writel(rdreg, reg_base + CQSPI_REG_RD_INSTR);
 
+	dummy_clk = cqspi_calc_dummy(op, f_pdata->dtr);
+	if (dummy_clk > CQSPI_DUMMY_CLKS_MAX)
+		return -EOPNOTSUPP;
+
+	if (dummy_clk)
+		reg |= (dummy_clk & CQSPI_REG_CMDCTRL_DUMMY_MASK)
+		     << CQSPI_REG_CMDCTRL_DUMMY_LSB;
+
 	reg |= (0x1 << CQSPI_REG_CMDCTRL_RD_EN_LSB);
 
 	/* 0 means 1 byte. */
@@ -401,12 +571,22 @@ static int cqspi_command_write(struct cqspi_flash_pdata *f_pdata,
 {
 	struct cqspi_st *cqspi = f_pdata->cqspi;
 	void __iomem *reg_base = cqspi->iobase;
-	const u8 opcode = op->cmd.opcode;
+	u8 opcode;
 	const u8 *txbuf = op->data.buf.out;
 	size_t n_tx = op->data.nbytes;
 	unsigned int reg;
 	unsigned int data;
 	size_t write_len;
+	int ret;
+
+	ret = cqspi_set_protocol(f_pdata, op);
+	if (ret)
+		return ret;
+
+	ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_STIG_LSB,
+			       f_pdata->dtr);
+	if (ret)
+		return ret;
 
 	if (n_tx > CQSPI_STIG_DATA_LEN_MAX || (n_tx && !txbuf)) {
 		dev_err(&cqspi->pdev->dev,
@@ -415,6 +595,14 @@ static int cqspi_command_write(struct cqspi_flash_pdata *f_pdata,
 		return -EINVAL;
 	}
 
+	reg = cqspi_calc_rdreg(f_pdata);
+	writel(reg, reg_base + CQSPI_REG_RD_INSTR);
+
+	if (f_pdata->dtr)
+		opcode = op->cmd.opcode >> 8;
+	else
+		opcode = op->cmd.opcode;
+
 	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
 
 	if (op->addr.nbytes) {
@@ -454,14 +642,27 @@ static int cqspi_read_setup(struct cqspi_flash_pdata *f_pdata,
 	void __iomem *reg_base = cqspi->iobase;
 	unsigned int dummy_clk = 0;
 	unsigned int reg;
+	int ret;
+	u8 opcode;
+
+	ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_READ_LSB,
+			       f_pdata->dtr);
+	if (ret)
+		return ret;
 
-	reg = op->cmd.opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB;
+	if (f_pdata->dtr)
+		opcode = op->cmd.opcode >> 8;
+	else
+		opcode = op->cmd.opcode;
+
+	reg = opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB;
 	reg |= cqspi_calc_rdreg(f_pdata);
 
 	/* Setup dummy clock cycles */
-	dummy_clk = op->dummy.nbytes * 8;
+	dummy_clk = cqspi_calc_dummy(op, f_pdata->dtr);
+
 	if (dummy_clk > CQSPI_DUMMY_CLKS_MAX)
-		dummy_clk = CQSPI_DUMMY_CLKS_MAX;
+		return -EOPNOTSUPP;
 
 	if (dummy_clk)
 		reg |= (dummy_clk & CQSPI_REG_RD_INSTR_DUMMY_MASK)
@@ -573,15 +774,43 @@ static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata,
 			     const struct spi_mem_op *op)
 {
 	unsigned int reg;
+	int ret;
 	struct cqspi_st *cqspi = f_pdata->cqspi;
 	void __iomem *reg_base = cqspi->iobase;
+	u8 opcode;
+
+	ret = cqspi_enable_dtr(f_pdata, op, CQSPI_REG_OP_EXT_WRITE_LSB,
+			       f_pdata->dtr);
+	if (ret)
+		return ret;
+
+	if (f_pdata->dtr)
+		opcode = op->cmd.opcode >> 8;
+	else
+		opcode = op->cmd.opcode;
 
 	/* Set opcode. */
-	reg = op->cmd.opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB;
+	reg = opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB;
+	reg |= f_pdata->data_width << CQSPI_REG_WR_INSTR_TYPE_DATA_LSB;
+	reg |= f_pdata->addr_width << CQSPI_REG_WR_INSTR_TYPE_ADDR_LSB;
 	writel(reg, reg_base + CQSPI_REG_WR_INSTR);
 	reg = cqspi_calc_rdreg(f_pdata);
 	writel(reg, reg_base + CQSPI_REG_RD_INSTR);
 
+	if (f_pdata->dtr) {
+		/*
+		 * Some flashes like the cypress Semper flash expect a 4-byte
+		 * dummy address with the Read SR command in DTR mode, but this
+		 * controller does not support sending address with the Read SR
+		 * command. So, disable write completion polling on the
+		 * controller's side. spi-nor will take care of polling the
+		 * status register.
+		 */
+		reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+		reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+		writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+	}
+
 	reg = readl(reg_base + CQSPI_REG_SIZE);
 	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
 	reg |= (op->addr.nbytes - 1);
@@ -835,35 +1064,6 @@ static void cqspi_configure(struct cqspi_flash_pdata *f_pdata,
 		cqspi_controller_enable(cqspi, 1);
 }
 
-static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata,
-			      const struct spi_mem_op *op)
-{
-	f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE;
-	f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE;
-	f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
-
-	if (op->data.dir == SPI_MEM_DATA_IN) {
-		switch (op->data.buswidth) {
-		case 1:
-			f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
-			break;
-		case 2:
-			f_pdata->data_width = CQSPI_INST_TYPE_DUAL;
-			break;
-		case 4:
-			f_pdata->data_width = CQSPI_INST_TYPE_QUAD;
-			break;
-		case 8:
-			f_pdata->data_width = CQSPI_INST_TYPE_OCTAL;
-			break;
-		default:
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
 static ssize_t cqspi_write(struct cqspi_flash_pdata *f_pdata,
 			   const struct spi_mem_op *op)
 {
@@ -881,7 +1081,16 @@ static ssize_t cqspi_write(struct cqspi_flash_pdata *f_pdata,
 	if (ret)
 		return ret;
 
-	if (cqspi->use_direct_mode && ((to + len) <= cqspi->ahb_size)) {
+	/*
+	 * Some flashes like the Cypress Semper flash expect a dummy 4-byte
+	 * address (all 0s) with the read status register command in DTR mode.
+	 * But this controller does not support sending dummy address bytes to
+	 * the flash when it is polling the write completion register in DTR
+	 * mode. So, we can not use direct mode when in DTR mode for writing
+	 * data.
+	 */
+	if (!f_pdata->dtr && cqspi->use_direct_mode &&
+	    ((to + len) <= cqspi->ahb_size)) {
 		memcpy_toio(cqspi->ahb_base + to, buf, len);
 		return cqspi_wait_idle(cqspi);
 	}
@@ -942,7 +1151,7 @@ static int cqspi_direct_read_execute(struct cqspi_flash_pdata *f_pdata,
 
 	dma_async_issue_pending(cqspi->rx_chan);
 	if (!wait_for_completion_timeout(&cqspi->rx_dma_complete,
-					 msecs_to_jiffies(len))) {
+					 msecs_to_jiffies(max_t(size_t, len, 500)))) {
 		dmaengine_terminate_sync(cqspi->rx_chan);
 		dev_err(dev, "DMA wait_for_completion_timeout\n");
 		ret = -ETIMEDOUT;
@@ -1010,6 +1219,26 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	return ret;
 }
 
+static bool cqspi_supports_mem_op(struct spi_mem *mem,
+				  const struct spi_mem_op *op)
+{
+	bool all_true, all_false;
+
+	all_true = op->cmd.dtr && op->addr.dtr && op->dummy.dtr &&
+		   op->data.dtr;
+	all_false = !op->cmd.dtr && !op->addr.dtr && !op->dummy.dtr &&
+		    !op->data.dtr;
+
+	/* Mixed DTR modes not supported. */
+	if (!(all_true || all_false))
+		return false;
+
+	if (all_true)
+		return spi_mem_dtr_supports_op(mem, op);
+	else
+		return spi_mem_default_supports_op(mem, op);
+}
+
 static int cqspi_of_get_flash_pdata(struct platform_device *pdev,
 				    struct cqspi_flash_pdata *f_pdata,
 				    struct device_node *np)
@@ -1070,6 +1299,9 @@ static int cqspi_of_get_pdata(struct cqspi_st *cqspi)
 		return -ENXIO;
 	}
 
+	if (of_property_read_u32(np, "num-cs", &cqspi->num_chipselect))
+		cqspi->num_chipselect = CQSPI_MAX_CHIPSELECT;
+
 	cqspi->rclk_en = of_property_read_bool(np, "cdns,rclk-en");
 
 	return 0;
@@ -1101,10 +1333,12 @@ static void cqspi_controller_init(struct cqspi_st *cqspi)
 	writel(cqspi->fifo_depth * cqspi->fifo_width / 8,
 	       cqspi->iobase + CQSPI_REG_INDIRECTWRWATERMARK);
 
-	/* Enable Direct Access Controller */
-	reg = readl(cqspi->iobase + CQSPI_REG_CONFIG);
-	reg |= CQSPI_REG_CONFIG_ENB_DIR_ACC_CTRL;
-	writel(reg, cqspi->iobase + CQSPI_REG_CONFIG);
+	/* Disable direct access controller */
+	if (!cqspi->use_direct_mode) {
+		reg = readl(cqspi->iobase + CQSPI_REG_CONFIG);
+		reg &= ~CQSPI_REG_CONFIG_ENB_DIR_ACC_CTRL;
+		writel(reg, cqspi->iobase + CQSPI_REG_CONFIG);
+	}
 
 	cqspi_controller_enable(cqspi, 1);
 }
@@ -1138,6 +1372,7 @@ static const char *cqspi_get_name(struct spi_mem *mem)
 static const struct spi_controller_mem_ops cqspi_mem_ops = {
 	.exec_op = cqspi_exec_mem_op,
 	.get_name = cqspi_get_name,
+	.supports_op = cqspi_supports_mem_op,
 };
 
 static int cqspi_setup_flash(struct cqspi_st *cqspi)
@@ -1279,13 +1514,14 @@ static int cqspi_probe(struct platform_device *pdev)
 	reset_control_deassert(rstc_ocp);
 
 	cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk);
+	master->max_speed_hz = cqspi->master_ref_clk_hz;
 	ddata  = of_device_get_match_data(dev);
 	if (ddata) {
 		if (ddata->quirks & CQSPI_NEEDS_WR_DELAY)
-			cqspi->wr_delay = 5 * DIV_ROUND_UP(NSEC_PER_SEC,
+			cqspi->wr_delay = 50 * DIV_ROUND_UP(NSEC_PER_SEC,
 						cqspi->master_ref_clk_hz);
 		if (ddata->hwcaps_mask & CQSPI_SUPPORTS_OCTAL)
-			master->mode_bits |= SPI_RX_OCTAL;
+			master->mode_bits |= SPI_RX_OCTAL | SPI_TX_OCTAL;
 		if (!(ddata->quirks & CQSPI_DISABLE_DAC_MODE))
 			cqspi->use_direct_mode = true;
 	}
@@ -1302,6 +1538,8 @@ static int cqspi_probe(struct platform_device *pdev)
 	cqspi->current_cs = -1;
 	cqspi->sclk = 0;
 
+	master->num_chipselect = cqspi->num_chipselect;
+
 	ret = cqspi_setup_flash(cqspi);
 	if (ret) {
 		dev_err(dev, "failed to setup flash parameters %d\n", ret);
@@ -1390,6 +1628,10 @@ static const struct cqspi_driver_platdata am654_ospi = {
 	.quirks = CQSPI_NEEDS_WR_DELAY,
 };
 
+static const struct cqspi_driver_platdata intel_lgm_qspi = {
+	.quirks = CQSPI_DISABLE_DAC_MODE,
+};
+
 static const struct of_device_id cqspi_dt_ids[] = {
 	{
 		.compatible = "cdns,qspi-nor",
@@ -1403,6 +1645,10 @@ static const struct of_device_id cqspi_dt_ids[] = {
 		.compatible = "ti,am654-ospi",
 		.data = &am654_ospi,
 	},
+	{
+		.compatible = "intel,lgm-qspi",
+		.data = &intel_lgm_qspi,
+	},
 	{ /* end of table */ }
 };
 
@@ -1427,3 +1673,4 @@ MODULE_AUTHOR("Ley Foon Tan <lftan@altera.com>");
 MODULE_AUTHOR("Graham Moore <grmoore@opensource.altera.com>");
 MODULE_AUTHOR("Vadivel Murugan R <vadivel.muruganx.ramuthevar@intel.com>");
 MODULE_AUTHOR("Vignesh Raghavendra <vigneshr@ti.com>");
+MODULE_AUTHOR("Pratyush Yadav <p.yadav@ti.com>");
diff --git a/drivers/spi/spi-clps711x.c b/drivers/spi/spi-clps711x.c
index 5e900f228919..0bef5ce08094 100644
--- a/drivers/spi/spi-clps711x.c
+++ b/drivers/spi/spi-clps711x.c
@@ -104,7 +104,7 @@ static int spi_clps711x_probe(struct platform_device *pdev)
 	master->use_gpio_descriptors = true;
 	master->bus_num = -1;
 	master->mode_bits = SPI_CPHA | SPI_CS_HIGH;
-	master->bits_per_word_mask =  SPI_BPW_RANGE_MASK(1, 8);
+	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 8);
 	master->dev.of_node = pdev->dev.of_node;
 	master->prepare_message = spi_clps711x_prepare_message;
 	master->transfer_one = spi_clps711x_transfer_one;
diff --git a/drivers/spi/spi-dw-bt1.c b/drivers/spi/spi-dw-bt1.c
index 4aa8596fb1f2..5be6b7b80c21 100644
--- a/drivers/spi/spi-dw-bt1.c
+++ b/drivers/spi/spi-dw-bt1.c
@@ -84,7 +84,7 @@ static void dw_spi_bt1_dirmap_copy_from_map(void *to, void __iomem *from, size_t
 	if (shift) {
 		chunk = min_t(size_t, 4 - shift, len);
 		data = readl_relaxed(from - shift);
-		memcpy(to, &data + shift, chunk);
+		memcpy(to, (char *)&data + shift, chunk);
 		from += chunk;
 		to += chunk;
 		len -= chunk;
diff --git a/drivers/spi/spi-efm32.c b/drivers/spi/spi-efm32.c
deleted file mode 100644
index ea6e4a7b3feb..000000000000
--- a/drivers/spi/spi-efm32.c
+++ /dev/null
@@ -1,462 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) 2012-2013 Uwe Kleine-Koenig for Pengutronix
- */
-#include <linux/kernel.h>
-#include <linux/io.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/spi_bitbang.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/platform_data/efm32-spi.h>
-#include <linux/of.h>
-
-#define DRIVER_NAME "efm32-spi"
-
-#define MASK_VAL(mask, val)		((val << __ffs(mask)) & mask)
-
-#define REG_CTRL		0x00
-#define REG_CTRL_SYNC			0x0001
-#define REG_CTRL_CLKPOL			0x0100
-#define REG_CTRL_CLKPHA			0x0200
-#define REG_CTRL_MSBF			0x0400
-#define REG_CTRL_TXBIL			0x1000
-
-#define REG_FRAME		0x04
-#define REG_FRAME_DATABITS__MASK	0x000f
-#define REG_FRAME_DATABITS(n)		((n) - 3)
-
-#define REG_CMD			0x0c
-#define REG_CMD_RXEN			0x0001
-#define REG_CMD_RXDIS			0x0002
-#define REG_CMD_TXEN			0x0004
-#define REG_CMD_TXDIS			0x0008
-#define REG_CMD_MASTEREN		0x0010
-
-#define REG_STATUS		0x10
-#define REG_STATUS_TXENS		0x0002
-#define REG_STATUS_TXC			0x0020
-#define REG_STATUS_TXBL			0x0040
-#define REG_STATUS_RXDATAV		0x0080
-
-#define REG_CLKDIV		0x14
-
-#define REG_RXDATAX		0x18
-#define REG_RXDATAX_RXDATA__MASK	0x01ff
-#define REG_RXDATAX_PERR		0x4000
-#define REG_RXDATAX_FERR		0x8000
-
-#define REG_TXDATA		0x34
-
-#define REG_IF		0x40
-#define REG_IF_TXBL			0x0002
-#define REG_IF_RXDATAV			0x0004
-
-#define REG_IFS		0x44
-#define REG_IFC		0x48
-#define REG_IEN		0x4c
-
-#define REG_ROUTE		0x54
-#define REG_ROUTE_RXPEN			0x0001
-#define REG_ROUTE_TXPEN			0x0002
-#define REG_ROUTE_CLKPEN		0x0008
-#define REG_ROUTE_LOCATION__MASK	0x0700
-#define REG_ROUTE_LOCATION(n)		MASK_VAL(REG_ROUTE_LOCATION__MASK, (n))
-
-struct efm32_spi_ddata {
-	struct spi_bitbang bitbang;
-
-	spinlock_t lock;
-
-	struct clk *clk;
-	void __iomem *base;
-	unsigned int rxirq, txirq;
-	struct efm32_spi_pdata pdata;
-
-	/* irq data */
-	struct completion done;
-	const u8 *tx_buf;
-	u8 *rx_buf;
-	unsigned tx_len, rx_len;
-};
-
-#define ddata_to_dev(ddata)	(&(ddata->bitbang.master->dev))
-#define efm32_spi_vdbg(ddata, format, arg...)	\
-	dev_vdbg(ddata_to_dev(ddata), format, ##arg)
-
-static void efm32_spi_write32(struct efm32_spi_ddata *ddata,
-		u32 value, unsigned offset)
-{
-	writel_relaxed(value, ddata->base + offset);
-}
-
-static u32 efm32_spi_read32(struct efm32_spi_ddata *ddata, unsigned offset)
-{
-	return readl_relaxed(ddata->base + offset);
-}
-
-static int efm32_spi_setup_transfer(struct spi_device *spi,
-		struct spi_transfer *t)
-{
-	struct efm32_spi_ddata *ddata = spi_master_get_devdata(spi->master);
-
-	unsigned bpw = t->bits_per_word ?: spi->bits_per_word;
-	unsigned speed = t->speed_hz ?: spi->max_speed_hz;
-	unsigned long clkfreq = clk_get_rate(ddata->clk);
-	u32 clkdiv;
-
-	efm32_spi_write32(ddata, REG_CTRL_SYNC | REG_CTRL_MSBF |
-			(spi->mode & SPI_CPHA ? REG_CTRL_CLKPHA : 0) |
-			(spi->mode & SPI_CPOL ? REG_CTRL_CLKPOL : 0), REG_CTRL);
-
-	efm32_spi_write32(ddata,
-			REG_FRAME_DATABITS(bpw), REG_FRAME);
-
-	if (2 * speed >= clkfreq)
-		clkdiv = 0;
-	else
-		clkdiv = 64 * (DIV_ROUND_UP(2 * clkfreq, speed) - 4);
-
-	if (clkdiv > (1U << 21))
-		return -EINVAL;
-
-	efm32_spi_write32(ddata, clkdiv, REG_CLKDIV);
-	efm32_spi_write32(ddata, REG_CMD_MASTEREN, REG_CMD);
-	efm32_spi_write32(ddata, REG_CMD_RXEN | REG_CMD_TXEN, REG_CMD);
-
-	return 0;
-}
-
-static void efm32_spi_tx_u8(struct efm32_spi_ddata *ddata)
-{
-	u8 val = 0;
-
-	if (ddata->tx_buf) {
-		val = *ddata->tx_buf;
-		ddata->tx_buf++;
-	}
-
-	ddata->tx_len--;
-	efm32_spi_write32(ddata, val, REG_TXDATA);
-	efm32_spi_vdbg(ddata, "%s: tx 0x%x\n", __func__, val);
-}
-
-static void efm32_spi_rx_u8(struct efm32_spi_ddata *ddata)
-{
-	u32 rxdata = efm32_spi_read32(ddata, REG_RXDATAX);
-	efm32_spi_vdbg(ddata, "%s: rx 0x%x\n", __func__, rxdata);
-
-	if (ddata->rx_buf) {
-		*ddata->rx_buf = rxdata;
-		ddata->rx_buf++;
-	}
-
-	ddata->rx_len--;
-}
-
-static void efm32_spi_filltx(struct efm32_spi_ddata *ddata)
-{
-	while (ddata->tx_len &&
-			ddata->tx_len + 2 > ddata->rx_len &&
-			efm32_spi_read32(ddata, REG_STATUS) & REG_STATUS_TXBL) {
-		efm32_spi_tx_u8(ddata);
-	}
-}
-
-static int efm32_spi_txrx_bufs(struct spi_device *spi, struct spi_transfer *t)
-{
-	struct efm32_spi_ddata *ddata = spi_master_get_devdata(spi->master);
-	int ret = -EBUSY;
-
-	spin_lock_irq(&ddata->lock);
-
-	if (ddata->tx_buf || ddata->rx_buf)
-		goto out_unlock;
-
-	ddata->tx_buf = t->tx_buf;
-	ddata->rx_buf = t->rx_buf;
-	ddata->tx_len = ddata->rx_len =
-		t->len * DIV_ROUND_UP(t->bits_per_word, 8);
-
-	efm32_spi_filltx(ddata);
-
-	reinit_completion(&ddata->done);
-
-	efm32_spi_write32(ddata, REG_IF_TXBL | REG_IF_RXDATAV, REG_IEN);
-
-	spin_unlock_irq(&ddata->lock);
-
-	wait_for_completion(&ddata->done);
-
-	spin_lock_irq(&ddata->lock);
-
-	ret = t->len - max(ddata->tx_len, ddata->rx_len);
-
-	efm32_spi_write32(ddata, 0, REG_IEN);
-	ddata->tx_buf = ddata->rx_buf = NULL;
-
-out_unlock:
-	spin_unlock_irq(&ddata->lock);
-
-	return ret;
-}
-
-static irqreturn_t efm32_spi_rxirq(int irq, void *data)
-{
-	struct efm32_spi_ddata *ddata = data;
-	irqreturn_t ret = IRQ_NONE;
-
-	spin_lock(&ddata->lock);
-
-	while (ddata->rx_len > 0 &&
-			efm32_spi_read32(ddata, REG_STATUS) &
-			REG_STATUS_RXDATAV) {
-		efm32_spi_rx_u8(ddata);
-
-		ret = IRQ_HANDLED;
-	}
-
-	if (!ddata->rx_len) {
-		u32 ien = efm32_spi_read32(ddata, REG_IEN);
-
-		ien &= ~REG_IF_RXDATAV;
-
-		efm32_spi_write32(ddata, ien, REG_IEN);
-
-		complete(&ddata->done);
-	}
-
-	spin_unlock(&ddata->lock);
-
-	return ret;
-}
-
-static irqreturn_t efm32_spi_txirq(int irq, void *data)
-{
-	struct efm32_spi_ddata *ddata = data;
-
-	efm32_spi_vdbg(ddata,
-			"%s: txlen = %u, rxlen = %u, if=0x%08x, stat=0x%08x\n",
-			__func__, ddata->tx_len, ddata->rx_len,
-			efm32_spi_read32(ddata, REG_IF),
-			efm32_spi_read32(ddata, REG_STATUS));
-
-	spin_lock(&ddata->lock);
-
-	efm32_spi_filltx(ddata);
-
-	efm32_spi_vdbg(ddata, "%s: txlen = %u, rxlen = %u\n",
-			__func__, ddata->tx_len, ddata->rx_len);
-
-	if (!ddata->tx_len) {
-		u32 ien = efm32_spi_read32(ddata, REG_IEN);
-
-		ien &= ~REG_IF_TXBL;
-
-		efm32_spi_write32(ddata, ien, REG_IEN);
-		efm32_spi_vdbg(ddata, "disable TXBL\n");
-	}
-
-	spin_unlock(&ddata->lock);
-
-	return IRQ_HANDLED;
-}
-
-static u32 efm32_spi_get_configured_location(struct efm32_spi_ddata *ddata)
-{
-	u32 reg = efm32_spi_read32(ddata, REG_ROUTE);
-
-	return (reg & REG_ROUTE_LOCATION__MASK) >> __ffs(REG_ROUTE_LOCATION__MASK);
-}
-
-static void efm32_spi_probe_dt(struct platform_device *pdev,
-		struct spi_master *master, struct efm32_spi_ddata *ddata)
-{
-	struct device_node *np = pdev->dev.of_node;
-	u32 location;
-	int ret;
-
-	ret = of_property_read_u32(np, "energymicro,location", &location);
-
-	if (ret)
-		/* fall back to wrongly namespaced property */
-		ret = of_property_read_u32(np, "efm32,location", &location);
-
-	if (ret)
-		/* fall back to old and (wrongly) generic property "location" */
-		ret = of_property_read_u32(np, "location", &location);
-
-	if (!ret) {
-		dev_dbg(&pdev->dev, "using location %u\n", location);
-	} else {
-		/* default to location configured in hardware */
-		location = efm32_spi_get_configured_location(ddata);
-
-		dev_info(&pdev->dev, "fall back to location %u\n", location);
-	}
-
-	ddata->pdata.location = location;
-}
-
-static int efm32_spi_probe(struct platform_device *pdev)
-{
-	struct efm32_spi_ddata *ddata;
-	struct resource *res;
-	int ret;
-	struct spi_master *master;
-	struct device_node *np = pdev->dev.of_node;
-
-	if (!np)
-		return -EINVAL;
-
-	master = spi_alloc_master(&pdev->dev, sizeof(*ddata));
-	if (!master) {
-		dev_dbg(&pdev->dev,
-				"failed to allocate spi master controller\n");
-		return -ENOMEM;
-	}
-	platform_set_drvdata(pdev, master);
-
-	master->dev.of_node = pdev->dev.of_node;
-
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
-	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
-	master->use_gpio_descriptors = true;
-
-	ddata = spi_master_get_devdata(master);
-
-	ddata->bitbang.master = master;
-	ddata->bitbang.setup_transfer = efm32_spi_setup_transfer;
-	ddata->bitbang.txrx_bufs = efm32_spi_txrx_bufs;
-
-	spin_lock_init(&ddata->lock);
-	init_completion(&ddata->done);
-
-	ddata->clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(ddata->clk)) {
-		ret = PTR_ERR(ddata->clk);
-		dev_err(&pdev->dev, "failed to get clock: %d\n", ret);
-		goto err;
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		ret = -ENODEV;
-		dev_err(&pdev->dev, "failed to determine base address\n");
-		goto err;
-	}
-
-	if (resource_size(res) < 0x60) {
-		ret = -EINVAL;
-		dev_err(&pdev->dev, "memory resource too small\n");
-		goto err;
-	}
-
-	ddata->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(ddata->base)) {
-		ret = PTR_ERR(ddata->base);
-		goto err;
-	}
-
-	ret = platform_get_irq(pdev, 0);
-	if (ret <= 0)
-		goto err;
-
-	ddata->rxirq = ret;
-
-	ret = platform_get_irq(pdev, 1);
-	if (ret <= 0)
-		ret = ddata->rxirq + 1;
-
-	ddata->txirq = ret;
-
-	ret = clk_prepare_enable(ddata->clk);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "failed to enable clock (%d)\n", ret);
-		goto err;
-	}
-
-	efm32_spi_probe_dt(pdev, master, ddata);
-
-	efm32_spi_write32(ddata, 0, REG_IEN);
-	efm32_spi_write32(ddata, REG_ROUTE_TXPEN | REG_ROUTE_RXPEN |
-			REG_ROUTE_CLKPEN |
-			REG_ROUTE_LOCATION(ddata->pdata.location), REG_ROUTE);
-
-	ret = request_irq(ddata->rxirq, efm32_spi_rxirq,
-			0, DRIVER_NAME " rx", ddata);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register rxirq (%d)\n", ret);
-		goto err_disable_clk;
-	}
-
-	ret = request_irq(ddata->txirq, efm32_spi_txirq,
-			0, DRIVER_NAME " tx", ddata);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register txirq (%d)\n", ret);
-		goto err_free_rx_irq;
-	}
-
-	ret = spi_bitbang_start(&ddata->bitbang);
-	if (ret) {
-		dev_err(&pdev->dev, "spi_bitbang_start failed (%d)\n", ret);
-
-		free_irq(ddata->txirq, ddata);
-err_free_rx_irq:
-		free_irq(ddata->rxirq, ddata);
-err_disable_clk:
-		clk_disable_unprepare(ddata->clk);
-err:
-		spi_master_put(master);
-	}
-
-	return ret;
-}
-
-static int efm32_spi_remove(struct platform_device *pdev)
-{
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct efm32_spi_ddata *ddata = spi_master_get_devdata(master);
-
-	spi_bitbang_stop(&ddata->bitbang);
-
-	efm32_spi_write32(ddata, 0, REG_IEN);
-
-	free_irq(ddata->txirq, ddata);
-	free_irq(ddata->rxirq, ddata);
-	clk_disable_unprepare(ddata->clk);
-	spi_master_put(master);
-
-	return 0;
-}
-
-static const struct of_device_id efm32_spi_dt_ids[] = {
-	{
-		.compatible = "energymicro,efm32-spi",
-	}, {
-		/* doesn't follow the "vendor,device" scheme, don't use */
-		.compatible = "efm32,spi",
-	}, {
-		/* sentinel */
-	}
-};
-MODULE_DEVICE_TABLE(of, efm32_spi_dt_ids);
-
-static struct platform_driver efm32_spi_driver = {
-	.probe = efm32_spi_probe,
-	.remove = efm32_spi_remove,
-
-	.driver = {
-		.name = DRIVER_NAME,
-		.of_match_table = efm32_spi_dt_ids,
-	},
-};
-module_platform_driver(efm32_spi_driver);
-
-MODULE_AUTHOR("Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>");
-MODULE_DESCRIPTION("EFM32 SPI driver");
-MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 6d8e0a05a535..e4a8d203f940 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -695,7 +695,7 @@ static void fsl_spi_cs_control(struct spi_device *spi, bool on)
 
 		if (WARN_ON_ONCE(!pinfo->immr_spi_cs))
 			return;
-		iowrite32be(on ? SPI_BOOT_SEL_BIT : 0, pinfo->immr_spi_cs);
+		iowrite32be(on ? 0 : SPI_BOOT_SEL_BIT, pinfo->immr_spi_cs);
 	}
 }
 
diff --git a/drivers/spi/spi-hisi-sfc-v3xx.c b/drivers/spi/spi-hisi-sfc-v3xx.c
index 4650b483a33d..385eb7bba05a 100644
--- a/drivers/spi/spi-hisi-sfc-v3xx.c
+++ b/drivers/spi/spi-hisi-sfc-v3xx.c
@@ -19,6 +19,8 @@
 
 #define HISI_SFC_V3XX_VERSION (0x1f8)
 
+#define HISI_SFC_V3XX_GLB_CFG (0x100)
+#define HISI_SFC_V3XX_GLB_CFG_CS0_ADDR_MODE BIT(2)
 #define HISI_SFC_V3XX_RAW_INT_STAT (0x120)
 #define HISI_SFC_V3XX_INT_STAT (0x124)
 #define HISI_SFC_V3XX_INT_MASK (0x128)
@@ -75,6 +77,7 @@ struct hisi_sfc_v3xx_host {
 	void __iomem *regbase;
 	int max_cmd_dword;
 	struct completion *completion;
+	u8 address_mode;
 	int irq;
 };
 
@@ -168,10 +171,18 @@ static int hisi_sfc_v3xx_adjust_op_size(struct spi_mem *mem,
 static bool hisi_sfc_v3xx_supports_op(struct spi_mem *mem,
 				      const struct spi_mem_op *op)
 {
+	struct spi_device *spi = mem->spi;
+	struct hisi_sfc_v3xx_host *host;
+
+	host = spi_controller_get_devdata(spi->master);
+
 	if (op->data.buswidth > 4 || op->dummy.buswidth > 4 ||
 	    op->addr.buswidth > 4 || op->cmd.buswidth > 4)
 		return false;
 
+	if (op->addr.nbytes != host->address_mode && op->addr.nbytes)
+		return false;
+
 	return spi_mem_default_supports_op(mem, op);
 }
 
@@ -416,7 +427,7 @@ static int hisi_sfc_v3xx_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct hisi_sfc_v3xx_host *host;
 	struct spi_controller *ctlr;
-	u32 version;
+	u32 version, glb_config;
 	int ret;
 
 	ctlr = spi_alloc_master(&pdev->dev, sizeof(*host));
@@ -463,16 +474,24 @@ static int hisi_sfc_v3xx_probe(struct platform_device *pdev)
 	ctlr->num_chipselect = 1;
 	ctlr->mem_ops = &hisi_sfc_v3xx_mem_ops;
 
+	/*
+	 * The address mode of the controller is either 3 or 4,
+	 * which is indicated by the address mode bit in
+	 * the global config register. The register is read only
+	 * for the OS driver.
+	 */
+	glb_config = readl(host->regbase + HISI_SFC_V3XX_GLB_CFG);
+	if (glb_config & HISI_SFC_V3XX_GLB_CFG_CS0_ADDR_MODE)
+		host->address_mode = 4;
+	else
+		host->address_mode = 3;
+
 	version = readl(host->regbase + HISI_SFC_V3XX_VERSION);
 
-	switch (version) {
-	case 0x351:
+	if (version >= 0x351)
 		host->max_cmd_dword = 64;
-		break;
-	default:
+	else
 		host->max_cmd_dword = 16;
-		break;
-	}
 
 	ret = devm_spi_register_controller(dev, ctlr);
 	if (ret)
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 73ca821763d6..5dc4ea4b4450 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1685,7 +1685,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 	master->dev.of_node = pdev->dev.of_node;
 	ret = spi_bitbang_start(&spi_imx->bitbang);
 	if (ret) {
-		dev_err(&pdev->dev, "bitbang start failed with %d\n", ret);
+		dev_err_probe(&pdev->dev, ret, "bitbang start failed\n");
 		goto out_bitbang_start;
 	}
 
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index f3a3f196e628..dc713b0c3c4d 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -137,8 +137,8 @@ static int spi_check_buswidth_req(struct spi_mem *mem, u8 buswidth, bool tx)
 	return -ENOTSUPP;
 }
 
-bool spi_mem_default_supports_op(struct spi_mem *mem,
-				 const struct spi_mem_op *op)
+static bool spi_mem_check_buswidth(struct spi_mem *mem,
+				   const struct spi_mem_op *op)
 {
 	if (spi_check_buswidth_req(mem, op->cmd.buswidth, true))
 		return false;
@@ -156,13 +156,29 @@ bool spi_mem_default_supports_op(struct spi_mem *mem,
 				   op->data.dir == SPI_MEM_DATA_OUT))
 		return false;
 
+	return true;
+}
+
+bool spi_mem_dtr_supports_op(struct spi_mem *mem,
+			     const struct spi_mem_op *op)
+{
+	if (op->cmd.nbytes != 2)
+		return false;
+
+	return spi_mem_check_buswidth(mem, op);
+}
+EXPORT_SYMBOL_GPL(spi_mem_dtr_supports_op);
+
+bool spi_mem_default_supports_op(struct spi_mem *mem,
+				 const struct spi_mem_op *op)
+{
 	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
 		return false;
 
 	if (op->cmd.nbytes != 1)
 		return false;
 
-	return true;
+	return spi_mem_check_buswidth(mem, op);
 }
 EXPORT_SYMBOL_GPL(spi_mem_default_supports_op);
 
@@ -354,6 +370,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 		xfers[xferpos].tx_buf = tmpbuf + op->addr.nbytes + 1;
 		xfers[xferpos].len = op->dummy.nbytes;
 		xfers[xferpos].tx_nbits = op->dummy.buswidth;
+		xfers[xferpos].dummy_data = 1;
 		spi_message_add_tail(&xfers[xferpos], &msg);
 		xferpos++;
 		totalxferlen += op->dummy.nbytes;
diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c
index ef2f24420460..36f941500676 100644
--- a/drivers/spi/spi-mpc52xx.c
+++ b/drivers/spi/spi-mpc52xx.c
@@ -248,7 +248,9 @@ static int mpc52xx_spi_fsmstate_transfer(int irq, struct mpc52xx_spi *ms,
 	ms->len--;
 	if (ms->len == 0) {
 		ms->timestamp = get_tbl();
-		ms->timestamp += ms->transfer->delay_usecs * tb_ticks_per_usec;
+		if (ms->transfer->delay.unit == SPI_DELAY_UNIT_USECS)
+			ms->timestamp += ms->transfer->delay.value *
+					 tb_ticks_per_usec;
 		ms->state = mpc52xx_spi_fsmstate_wait;
 		return FSM_CONTINUE;
 	}
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 5d643051bf3d..976f73b9e299 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -287,7 +287,7 @@ static void mtk_spi_set_cs(struct spi_device *spi, bool enable)
 static void mtk_spi_prepare_transfer(struct spi_master *master,
 				     struct spi_transfer *xfer)
 {
-	u32 spi_clk_hz, div, sck_time, cs_time, reg_val;
+	u32 spi_clk_hz, div, sck_time, reg_val;
 	struct mtk_spi *mdata = spi_master_get_devdata(master);
 
 	spi_clk_hz = clk_get_rate(mdata->spi_clk);
@@ -297,32 +297,25 @@ static void mtk_spi_prepare_transfer(struct spi_master *master,
 		div = 1;
 
 	sck_time = (div + 1) / 2;
-	cs_time = sck_time * 2;
 
 	if (mdata->dev_comp->enhance_timing) {
-		reg_val = (((sck_time - 1) & 0xffff)
+		reg_val = readl(mdata->base + SPI_CFG2_REG);
+		reg_val &= ~(0xffff << SPI_CFG2_SCK_HIGH_OFFSET);
+		reg_val |= (((sck_time - 1) & 0xffff)
 			   << SPI_CFG2_SCK_HIGH_OFFSET);
+		reg_val &= ~(0xffff << SPI_CFG2_SCK_LOW_OFFSET);
 		reg_val |= (((sck_time - 1) & 0xffff)
 			   << SPI_CFG2_SCK_LOW_OFFSET);
 		writel(reg_val, mdata->base + SPI_CFG2_REG);
-		reg_val = (((cs_time - 1) & 0xffff)
-			   << SPI_ADJUST_CFG0_CS_HOLD_OFFSET);
-		reg_val |= (((cs_time - 1) & 0xffff)
-			   << SPI_ADJUST_CFG0_CS_SETUP_OFFSET);
-		writel(reg_val, mdata->base + SPI_CFG0_REG);
 	} else {
-		reg_val = (((sck_time - 1) & 0xff)
+		reg_val = readl(mdata->base + SPI_CFG0_REG);
+		reg_val &= ~(0xff << SPI_CFG0_SCK_HIGH_OFFSET);
+		reg_val |= (((sck_time - 1) & 0xff)
 			   << SPI_CFG0_SCK_HIGH_OFFSET);
+		reg_val &= ~(0xff << SPI_CFG0_SCK_LOW_OFFSET);
 		reg_val |= (((sck_time - 1) & 0xff) << SPI_CFG0_SCK_LOW_OFFSET);
-		reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG0_CS_HOLD_OFFSET);
-		reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG0_CS_SETUP_OFFSET);
 		writel(reg_val, mdata->base + SPI_CFG0_REG);
 	}
-
-	reg_val = readl(mdata->base + SPI_CFG1_REG);
-	reg_val &= ~SPI_CFG1_CS_IDLE_MASK;
-	reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG1_CS_IDLE_OFFSET);
-	writel(reg_val, mdata->base + SPI_CFG1_REG);
 }
 
 static void mtk_spi_setup_packet(struct spi_master *master)
@@ -513,6 +506,52 @@ static bool mtk_spi_can_dma(struct spi_master *master,
 		(unsigned long)xfer->rx_buf % 4 == 0);
 }
 
+static int mtk_spi_set_hw_cs_timing(struct spi_device *spi,
+				    struct spi_delay *setup,
+				    struct spi_delay *hold,
+				    struct spi_delay *inactive)
+{
+	struct mtk_spi *mdata = spi_master_get_devdata(spi->master);
+	u16 setup_dly, hold_dly, inactive_dly;
+	u32 reg_val;
+
+	if ((setup && setup->unit != SPI_DELAY_UNIT_SCK) ||
+	    (hold && hold->unit != SPI_DELAY_UNIT_SCK) ||
+	    (inactive && inactive->unit != SPI_DELAY_UNIT_SCK)) {
+		dev_err(&spi->dev,
+			"Invalid delay unit, should be SPI_DELAY_UNIT_SCK\n");
+		return -EINVAL;
+	}
+
+	setup_dly = setup ? setup->value : 1;
+	hold_dly = hold ? hold->value : 1;
+	inactive_dly = inactive ? inactive->value : 1;
+
+	reg_val = readl(mdata->base + SPI_CFG0_REG);
+	if (mdata->dev_comp->enhance_timing) {
+		reg_val &= ~(0xffff << SPI_ADJUST_CFG0_CS_HOLD_OFFSET);
+		reg_val |= (((hold_dly - 1) & 0xffff)
+			   << SPI_ADJUST_CFG0_CS_HOLD_OFFSET);
+		reg_val &= ~(0xffff << SPI_ADJUST_CFG0_CS_SETUP_OFFSET);
+		reg_val |= (((setup_dly - 1) & 0xffff)
+			   << SPI_ADJUST_CFG0_CS_SETUP_OFFSET);
+	} else {
+		reg_val &= ~(0xff << SPI_CFG0_CS_HOLD_OFFSET);
+		reg_val |= (((hold_dly - 1) & 0xff) << SPI_CFG0_CS_HOLD_OFFSET);
+		reg_val &= ~(0xff << SPI_CFG0_CS_SETUP_OFFSET);
+		reg_val |= (((setup_dly - 1) & 0xff)
+			    << SPI_CFG0_CS_SETUP_OFFSET);
+	}
+	writel(reg_val, mdata->base + SPI_CFG0_REG);
+
+	reg_val = readl(mdata->base + SPI_CFG1_REG);
+	reg_val &= ~SPI_CFG1_CS_IDLE_MASK;
+	reg_val |= (((inactive_dly - 1) & 0xff) << SPI_CFG1_CS_IDLE_OFFSET);
+	writel(reg_val, mdata->base + SPI_CFG1_REG);
+
+	return 0;
+}
+
 static int mtk_spi_setup(struct spi_device *spi)
 {
 	struct mtk_spi *mdata = spi_master_get_devdata(spi->master);
@@ -644,6 +683,7 @@ static int mtk_spi_probe(struct platform_device *pdev)
 	master->transfer_one = mtk_spi_transfer_one;
 	master->can_dma = mtk_spi_can_dma;
 	master->setup = mtk_spi_setup;
+	master->set_cs_timing = mtk_spi_set_hw_cs_timing;
 
 	of_id = of_match_node(mtk_spi_of_match, pdev->dev.of_node);
 	if (!of_id) {
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index b57b8b3cc26e..68ed7fd64256 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -96,10 +96,16 @@ struct orion_spi {
 	struct clk              *clk;
 	struct clk              *axi_clk;
 	const struct orion_spi_dev *devdata;
+	struct device		*dev;
 
 	struct orion_child_options	child[ORION_NUM_CHIPSELECTS];
 };
 
+#ifdef CONFIG_PM
+static int orion_spi_runtime_suspend(struct device *dev);
+static int orion_spi_runtime_resume(struct device *dev);
+#endif
+
 static inline void __iomem *spi_reg(struct orion_spi *orion_spi, u32 reg)
 {
 	return orion_spi->base + reg;
@@ -369,8 +375,15 @@ orion_spi_write_read_8bit(struct spi_device *spi,
 {
 	void __iomem *tx_reg, *rx_reg, *int_reg;
 	struct orion_spi *orion_spi;
+	bool cs_single_byte;
+
+	cs_single_byte = spi->mode & SPI_CS_WORD;
 
 	orion_spi = spi_master_get_devdata(spi->master);
+
+	if (cs_single_byte)
+		orion_spi_set_cs(spi, 0);
+
 	tx_reg = spi_reg(orion_spi, ORION_SPI_DATA_OUT_REG);
 	rx_reg = spi_reg(orion_spi, ORION_SPI_DATA_IN_REG);
 	int_reg = spi_reg(orion_spi, ORION_SPI_INT_CAUSE_REG);
@@ -384,6 +397,11 @@ orion_spi_write_read_8bit(struct spi_device *spi,
 		writel(0, tx_reg);
 
 	if (orion_spi_wait_till_ready(orion_spi) < 0) {
+		if (cs_single_byte) {
+			orion_spi_set_cs(spi, 1);
+			/* Satisfy some SLIC devices requirements */
+			udelay(4);
+		}
 		dev_err(&spi->dev, "TXS timed out\n");
 		return -1;
 	}
@@ -391,6 +409,12 @@ orion_spi_write_read_8bit(struct spi_device *spi,
 	if (rx_buf && *rx_buf)
 		*(*rx_buf)++ = readl(rx_reg);
 
+	if (cs_single_byte) {
+		orion_spi_set_cs(spi, 1);
+		/* Satisfy some SLIC devices requirements */
+		udelay(4);
+	}
+
 	return 1;
 }
 
@@ -401,6 +425,11 @@ orion_spi_write_read_16bit(struct spi_device *spi,
 	void __iomem *tx_reg, *rx_reg, *int_reg;
 	struct orion_spi *orion_spi;
 
+	if (spi->mode & SPI_CS_WORD) {
+		dev_err(&spi->dev, "SPI_CS_WORD is only supported for 8 bit words\n");
+		return -1;
+	}
+
 	orion_spi = spi_master_get_devdata(spi->master);
 	tx_reg = spi_reg(orion_spi, ORION_SPI_DATA_OUT_REG);
 	rx_reg = spi_reg(orion_spi, ORION_SPI_DATA_IN_REG);
@@ -440,12 +469,13 @@ orion_spi_write_read(struct spi_device *spi, struct spi_transfer *xfer)
 	orion_spi = spi_master_get_devdata(spi->master);
 
 	/*
-	 * Use SPI direct write mode if base address is available. Otherwise
-	 * fall back to PIO mode for this transfer.
+	 * Use SPI direct write mode if base address is available
+	 * and SPI_CS_WORD flag is not set.
+	 * Otherwise fall back to PIO mode for this transfer.
 	 */
 	vaddr = orion_spi->child[cs].direct_access.vaddr;
 
-	if (vaddr && xfer->tx_buf && word_len == 8) {
+	if (vaddr && xfer->tx_buf && word_len == 8 && (spi->mode & SPI_CS_WORD) == 0) {
 		unsigned int cnt = count / 4;
 		unsigned int rem = count % 4;
 
@@ -507,7 +537,21 @@ static int orion_spi_transfer_one(struct spi_master *master,
 
 static int orion_spi_setup(struct spi_device *spi)
 {
-	return orion_spi_setup_transfer(spi, NULL);
+	int ret;
+#ifdef CONFIG_PM
+	struct orion_spi *orion_spi = spi_master_get_devdata(spi->master);
+	struct device *dev = orion_spi->dev;
+
+	orion_spi_runtime_resume(dev);
+#endif
+
+	ret = orion_spi_setup_transfer(spi, NULL);
+
+#ifdef CONFIG_PM
+	orion_spi_runtime_suspend(dev);
+#endif
+
+	return ret;
 }
 
 static int orion_spi_reset(struct orion_spi *orion_spi)
@@ -616,7 +660,7 @@ static int orion_spi_probe(struct platform_device *pdev)
 	}
 
 	/* we support all 4 SPI modes and LSB first option */
-	master->mode_bits = SPI_CPHA | SPI_CPOL | SPI_LSB_FIRST;
+	master->mode_bits = SPI_CPHA | SPI_CPOL | SPI_LSB_FIRST | SPI_CS_WORD;
 	master->set_cs = orion_spi_set_cs;
 	master->transfer_one = orion_spi_transfer_one;
 	master->num_chipselect = ORION_NUM_CHIPSELECTS;
@@ -630,6 +674,7 @@ static int orion_spi_probe(struct platform_device *pdev)
 
 	spi = spi_master_get_devdata(master);
 	spi->master = master;
+	spi->dev = &pdev->dev;
 
 	of_id = of_match_device(orion_spi_of_match_table, &pdev->dev);
 	devdata = (of_id) ? of_id->data : &orion_spi_dev_data;
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index f236e3034cf8..14fc41ed2361 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -21,7 +21,8 @@ enum {
 	PORT_BSW1,
 	PORT_BSW2,
 	PORT_CE4100,
-	PORT_LPT,
+	PORT_LPT0,
+	PORT_LPT1,
 };
 
 struct pxa_spi_info {
@@ -57,8 +58,10 @@ static struct dw_dma_slave bsw1_rx_param = { .src_id = 7 };
 static struct dw_dma_slave bsw2_tx_param = { .dst_id = 8 };
 static struct dw_dma_slave bsw2_rx_param = { .src_id = 9 };
 
-static struct dw_dma_slave lpt_tx_param = { .dst_id = 0 };
-static struct dw_dma_slave lpt_rx_param = { .src_id = 1 };
+static struct dw_dma_slave lpt1_tx_param = { .dst_id = 0 };
+static struct dw_dma_slave lpt1_rx_param = { .src_id = 1 };
+static struct dw_dma_slave lpt0_tx_param = { .dst_id = 2 };
+static struct dw_dma_slave lpt0_rx_param = { .src_id = 3 };
 
 static bool lpss_dma_filter(struct dma_chan *chan, void *param)
 {
@@ -185,12 +188,19 @@ static struct pxa_spi_info spi_info_configs[] = {
 		.num_chipselect = 1,
 		.max_clk_rate = 50000000,
 	},
-	[PORT_LPT] = {
+	[PORT_LPT0] = {
 		.type = LPSS_LPT_SSP,
 		.port_id = 0,
 		.setup = lpss_spi_setup,
-		.tx_param = &lpt_tx_param,
-		.rx_param = &lpt_rx_param,
+		.tx_param = &lpt0_tx_param,
+		.rx_param = &lpt0_rx_param,
+	},
+	[PORT_LPT1] = {
+		.type = LPSS_LPT_SSP,
+		.port_id = 1,
+		.setup = lpss_spi_setup,
+		.tx_param = &lpt1_tx_param,
+		.rx_param = &lpt1_rx_param,
 	},
 };
 
@@ -285,8 +295,11 @@ static const struct pci_device_id pxa2xx_spi_pci_devices[] = {
 	{ PCI_VDEVICE(INTEL, 0x2290), PORT_BSW1 },
 	{ PCI_VDEVICE(INTEL, 0x22ac), PORT_BSW2 },
 	{ PCI_VDEVICE(INTEL, 0x2e6a), PORT_CE4100 },
-	{ PCI_VDEVICE(INTEL, 0x9ce6), PORT_LPT },
-	{ },
+	{ PCI_VDEVICE(INTEL, 0x9c65), PORT_LPT0 },
+	{ PCI_VDEVICE(INTEL, 0x9c66), PORT_LPT1 },
+	{ PCI_VDEVICE(INTEL, 0x9ce5), PORT_LPT0 },
+	{ PCI_VDEVICE(INTEL, 0x9ce6), PORT_LPT1 },
+	{ }
 };
 MODULE_DEVICE_TABLE(pci, pxa2xx_spi_pci_devices);
 
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index bd2354fd438d..0cc767283674 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1492,6 +1492,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0x43ab), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0x43fb), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0x43fd), LPSS_CNL_SSP },
+	/* ADL-P */
+	{ PCI_VDEVICE(INTEL, 0x51aa), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x51ab), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x51fb), LPSS_CNL_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
diff --git a/drivers/spi/spi-qcom-qspi.c b/drivers/spi/spi-qcom-qspi.c
index 8863be370884..1dbcc410cd35 100644
--- a/drivers/spi/spi-qcom-qspi.c
+++ b/drivers/spi/spi-qcom-qspi.c
@@ -511,8 +511,7 @@ static int qcom_qspi_probe(struct platform_device *pdev)
 	ret = platform_get_irq(pdev, 0);
 	if (ret < 0)
 		return ret;
-	ret = devm_request_irq(dev, ret, qcom_qspi_irq,
-			IRQF_TRIGGER_HIGH, dev_name(dev), ctrl);
+	ret = devm_request_irq(dev, ret, qcom_qspi_irq, 0, dev_name(dev), ctrl);
 	if (ret) {
 		dev_err(dev, "Failed to request irq %d\n", ret);
 		return ret;
diff --git a/drivers/spi/spi-realtek-rtl.c b/drivers/spi/spi-realtek-rtl.c
new file mode 100644
index 000000000000..866b0477dbd7
--- /dev/null
+++ b/drivers/spi/spi-realtek-rtl.c
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mod_devicetable.h>
+#include <linux/spi/spi.h>
+
+struct rtspi {
+	void __iomem *base;
+};
+
+/* SPI Flash Configuration Register */
+#define RTL_SPI_SFCR			0x00
+#define RTL_SPI_SFCR_RBO		BIT(28)
+#define RTL_SPI_SFCR_WBO		BIT(27)
+
+/* SPI Flash Control and Status Register */
+#define RTL_SPI_SFCSR			0x08
+#define RTL_SPI_SFCSR_CSB0		BIT(31)
+#define RTL_SPI_SFCSR_CSB1		BIT(30)
+#define RTL_SPI_SFCSR_RDY		BIT(27)
+#define RTL_SPI_SFCSR_CS		BIT(24)
+#define RTL_SPI_SFCSR_LEN_MASK		~(0x03 << 28)
+#define RTL_SPI_SFCSR_LEN1		(0x00 << 28)
+#define RTL_SPI_SFCSR_LEN4		(0x03 << 28)
+
+/* SPI Flash Data Register */
+#define RTL_SPI_SFDR			0x0c
+
+#define REG(x)		(rtspi->base + x)
+
+
+static void rt_set_cs(struct spi_device *spi, bool active)
+{
+	struct rtspi *rtspi = spi_controller_get_devdata(spi->controller);
+	u32 value;
+
+	/* CS0 bit is active low */
+	value = readl(REG(RTL_SPI_SFCSR));
+	if (active)
+		value |= RTL_SPI_SFCSR_CSB0;
+	else
+		value &= ~RTL_SPI_SFCSR_CSB0;
+	writel(value, REG(RTL_SPI_SFCSR));
+}
+
+static void set_size(struct rtspi *rtspi, int size)
+{
+	u32 value;
+
+	value = readl(REG(RTL_SPI_SFCSR));
+	value &= RTL_SPI_SFCSR_LEN_MASK;
+	if (size == 4)
+		value |= RTL_SPI_SFCSR_LEN4;
+	else if (size == 1)
+		value |= RTL_SPI_SFCSR_LEN1;
+	writel(value, REG(RTL_SPI_SFCSR));
+}
+
+static inline void wait_ready(struct rtspi *rtspi)
+{
+	while (!(readl(REG(RTL_SPI_SFCSR)) & RTL_SPI_SFCSR_RDY))
+		cpu_relax();
+}
+static void send4(struct rtspi *rtspi, const u32 *buf)
+{
+	wait_ready(rtspi);
+	set_size(rtspi, 4);
+	writel(*buf, REG(RTL_SPI_SFDR));
+}
+
+static void send1(struct rtspi *rtspi, const u8 *buf)
+{
+	wait_ready(rtspi);
+	set_size(rtspi, 1);
+	writel(buf[0] << 24, REG(RTL_SPI_SFDR));
+}
+
+static void rcv4(struct rtspi *rtspi, u32 *buf)
+{
+	wait_ready(rtspi);
+	set_size(rtspi, 4);
+	*buf = readl(REG(RTL_SPI_SFDR));
+}
+
+static void rcv1(struct rtspi *rtspi, u8 *buf)
+{
+	wait_ready(rtspi);
+	set_size(rtspi, 1);
+	*buf = readl(REG(RTL_SPI_SFDR)) >> 24;
+}
+
+static int transfer_one(struct spi_controller *ctrl, struct spi_device *spi,
+			struct spi_transfer *xfer)
+{
+	struct rtspi *rtspi = spi_controller_get_devdata(ctrl);
+	void *rx_buf;
+	const void *tx_buf;
+	int cnt;
+
+	tx_buf = xfer->tx_buf;
+	rx_buf = xfer->rx_buf;
+	cnt = xfer->len;
+	if (tx_buf) {
+		while (cnt >= 4) {
+			send4(rtspi, tx_buf);
+			tx_buf += 4;
+			cnt -= 4;
+		}
+		while (cnt) {
+			send1(rtspi, tx_buf);
+			tx_buf++;
+			cnt--;
+		}
+	} else if (rx_buf) {
+		while (cnt >= 4) {
+			rcv4(rtspi, rx_buf);
+			rx_buf += 4;
+			cnt -= 4;
+		}
+		while (cnt) {
+			rcv1(rtspi, rx_buf);
+			rx_buf++;
+			cnt--;
+		}
+	}
+
+	spi_finalize_current_transfer(ctrl);
+
+	return 0;
+}
+
+static void init_hw(struct rtspi *rtspi)
+{
+	u32 value;
+
+	/* Turn on big-endian byte ordering */
+	value = readl(REG(RTL_SPI_SFCR));
+	value |= RTL_SPI_SFCR_RBO | RTL_SPI_SFCR_WBO;
+	writel(value, REG(RTL_SPI_SFCR));
+
+	value = readl(REG(RTL_SPI_SFCSR));
+	/* Permanently disable CS1, since it's never used */
+	value |= RTL_SPI_SFCSR_CSB1;
+	/* Select CS0 for use */
+	value &= RTL_SPI_SFCSR_CS;
+	writel(value, REG(RTL_SPI_SFCSR));
+}
+
+static int realtek_rtl_spi_probe(struct platform_device *pdev)
+{
+	struct spi_controller *ctrl;
+	struct rtspi *rtspi;
+	int err;
+
+	ctrl = devm_spi_alloc_master(&pdev->dev, sizeof(*rtspi));
+	if (!ctrl) {
+		dev_err(&pdev->dev, "Error allocating SPI controller\n");
+		return -ENOMEM;
+	}
+	platform_set_drvdata(pdev, ctrl);
+	rtspi = spi_controller_get_devdata(ctrl);
+
+	rtspi->base = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	if (IS_ERR(rtspi->base)) {
+		dev_err(&pdev->dev, "Could not map SPI register address");
+		return -ENOMEM;
+	}
+
+	init_hw(rtspi);
+
+	ctrl->dev.of_node = pdev->dev.of_node;
+	ctrl->flags = SPI_CONTROLLER_HALF_DUPLEX;
+	ctrl->set_cs = rt_set_cs;
+	ctrl->transfer_one = transfer_one;
+
+	err = devm_spi_register_controller(&pdev->dev, ctrl);
+	if (err) {
+		dev_err(&pdev->dev, "Could not register SPI controller\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+
+static const struct of_device_id realtek_rtl_spi_of_ids[] = {
+	{ .compatible = "realtek,rtl8380-spi" },
+	{ .compatible = "realtek,rtl8382-spi" },
+	{ .compatible = "realtek,rtl8391-spi" },
+	{ .compatible = "realtek,rtl8392-spi" },
+	{ .compatible = "realtek,rtl8393-spi" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, realtek_rtl_spi_of_ids);
+
+static struct platform_driver realtek_rtl_spi_driver = {
+	.probe = realtek_rtl_spi_probe,
+	.driver = {
+		.name = "realtek-rtl-spi",
+		.of_match_table = realtek_rtl_spi_of_ids,
+	},
+};
+
+module_platform_driver(realtek_rtl_spi_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Bert Vermeulen <bert@biot.com>");
+MODULE_DESCRIPTION("Realtek RTL SPI driver");
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 09d8e92400eb..936ef54e0903 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -566,7 +566,7 @@ static int rockchip_spi_slave_abort(struct spi_controller *ctlr)
 	struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
 
 	rs->slave_abort = true;
-	complete(&ctlr->xfer_completion);
+	spi_finalize_current_transfer(ctlr);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c
index 3579675485a5..c53138ce0030 100644
--- a/drivers/spi/spi-rpc-if.c
+++ b/drivers/spi/spi-rpc-if.c
@@ -176,15 +176,14 @@ static int rpcif_spi_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
-static int rpcif_spi_suspend(struct device *dev)
+static int __maybe_unused rpcif_spi_suspend(struct device *dev)
 {
 	struct spi_controller *ctlr = dev_get_drvdata(dev);
 
 	return spi_controller_suspend(ctlr);
 }
 
-static int rpcif_spi_resume(struct device *dev)
+static int __maybe_unused rpcif_spi_resume(struct device *dev)
 {
 	struct spi_controller *ctlr = dev_get_drvdata(dev);
 
@@ -192,17 +191,15 @@ static int rpcif_spi_resume(struct device *dev)
 }
 
 static SIMPLE_DEV_PM_OPS(rpcif_spi_pm_ops, rpcif_spi_suspend, rpcif_spi_resume);
-#define DEV_PM_OPS	(&rpcif_spi_pm_ops)
-#else
-#define DEV_PM_OPS	NULL
-#endif
 
 static struct platform_driver rpcif_spi_driver = {
 	.probe	= rpcif_spi_probe,
 	.remove	= rpcif_spi_remove,
 	.driver = {
 		.name	= "rpc-if-spi",
-		.pm	= DEV_PM_OPS,
+#ifdef CONFIG_PM_SLEEP
+		.pm	= &rpcif_spi_pm_ops,
+#endif
 	},
 };
 module_platform_driver(rpcif_spi_driver);
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index b2579af0e3eb..41ed9ff8fad0 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -259,11 +259,13 @@ static const u32 sh_msiof_spi_div_array[] = {
 };
 
 static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p,
-				      unsigned long parent_rate, u32 spi_hz)
+				      struct spi_transfer *t)
 {
+	unsigned long parent_rate = clk_get_rate(p->clk);
+	unsigned int div_pow = p->min_div_pow;
+	u32 spi_hz = t->speed_hz;
 	unsigned long div;
 	u32 brps, scr;
-	unsigned int div_pow = p->min_div_pow;
 
 	if (!spi_hz || !parent_rate) {
 		WARN(1, "Invalid clock rate parameters %lu and %u\n",
@@ -292,6 +294,8 @@ static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p,
 		brps = 32;
 	}
 
+	t->effective_speed_hz = parent_rate / (brps << div_pow);
+
 	scr = sh_msiof_spi_div_array[div_pow] | SISCR_BRPS(brps);
 	sh_msiof_write(p, SITSCR, scr);
 	if (!(p->ctlr->flags & SPI_CONTROLLER_MUST_TX))
@@ -923,7 +927,7 @@ static int sh_msiof_transfer_one(struct spi_controller *ctlr,
 
 	/* setup clocks (clock already enabled in chipselect()) */
 	if (!spi_controller_is_slave(p->ctlr))
-		sh_msiof_spi_set_clk_regs(p, clk_get_rate(p->clk), t->speed_hz);
+		sh_msiof_spi_set_clk_regs(p, t);
 
 	while (ctlr->dma_tx && len > 15) {
 		/*
@@ -1258,6 +1262,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	const struct sh_msiof_chipdata *chipdata;
 	struct sh_msiof_spi_info *info;
 	struct sh_msiof_spi_priv *p;
+	unsigned long clksrc;
 	int i;
 	int ret;
 
@@ -1333,6 +1338,9 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	/* init controller code */
 	ctlr->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 	ctlr->mode_bits |= SPI_LSB_FIRST | SPI_3WIRE;
+	clksrc = clk_get_rate(p->clk);
+	ctlr->min_speed_hz = DIV_ROUND_UP(clksrc, 1024);
+	ctlr->max_speed_hz = DIV_ROUND_UP(clksrc, 1 << p->min_div_pow);
 	ctlr->flags = chipdata->ctlr_flags;
 	ctlr->bus_num = pdev->id;
 	ctlr->num_chipselect = p->info->num_chipselect;
diff --git a/drivers/spi/spi-sirf.c b/drivers/spi/spi-sirf.c
deleted file mode 100644
index 8419e6722e17..000000000000
--- a/drivers/spi/spi-sirf.c
+++ /dev/null
@@ -1,1236 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * SPI bus driver for CSR SiRFprimaII
- *
- * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/clk.h>
-#include <linux/completion.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/of.h>
-#include <linux/bitops.h>
-#include <linux/err.h>
-#include <linux/platform_device.h>
-#include <linux/of_gpio.h>
-#include <linux/spi/spi.h>
-#include <linux/spi/spi_bitbang.h>
-#include <linux/dmaengine.h>
-#include <linux/dma-direction.h>
-#include <linux/dma-mapping.h>
-#include <linux/reset.h>
-
-#define DRIVER_NAME "sirfsoc_spi"
-/* SPI CTRL register defines */
-#define SIRFSOC_SPI_SLV_MODE		BIT(16)
-#define SIRFSOC_SPI_CMD_MODE		BIT(17)
-#define SIRFSOC_SPI_CS_IO_OUT		BIT(18)
-#define SIRFSOC_SPI_CS_IO_MODE		BIT(19)
-#define SIRFSOC_SPI_CLK_IDLE_STAT	BIT(20)
-#define SIRFSOC_SPI_CS_IDLE_STAT	BIT(21)
-#define SIRFSOC_SPI_TRAN_MSB		BIT(22)
-#define SIRFSOC_SPI_DRV_POS_EDGE	BIT(23)
-#define SIRFSOC_SPI_CS_HOLD_TIME	BIT(24)
-#define SIRFSOC_SPI_CLK_SAMPLE_MODE	BIT(25)
-#define SIRFSOC_SPI_TRAN_DAT_FORMAT_8	(0 << 26)
-#define SIRFSOC_SPI_TRAN_DAT_FORMAT_12	(1 << 26)
-#define SIRFSOC_SPI_TRAN_DAT_FORMAT_16	(2 << 26)
-#define SIRFSOC_SPI_TRAN_DAT_FORMAT_32	(3 << 26)
-#define SIRFSOC_SPI_CMD_BYTE_NUM(x)	((x & 3) << 28)
-#define SIRFSOC_SPI_ENA_AUTO_CLR	BIT(30)
-#define SIRFSOC_SPI_MUL_DAT_MODE	BIT(31)
-
-/* Interrupt Enable */
-#define SIRFSOC_SPI_RX_DONE_INT_EN	BIT(0)
-#define SIRFSOC_SPI_TX_DONE_INT_EN	BIT(1)
-#define SIRFSOC_SPI_RX_OFLOW_INT_EN	BIT(2)
-#define SIRFSOC_SPI_TX_UFLOW_INT_EN	BIT(3)
-#define SIRFSOC_SPI_RX_IO_DMA_INT_EN	BIT(4)
-#define SIRFSOC_SPI_TX_IO_DMA_INT_EN	BIT(5)
-#define SIRFSOC_SPI_RXFIFO_FULL_INT_EN	BIT(6)
-#define SIRFSOC_SPI_TXFIFO_EMPTY_INT_EN	BIT(7)
-#define SIRFSOC_SPI_RXFIFO_THD_INT_EN	BIT(8)
-#define SIRFSOC_SPI_TXFIFO_THD_INT_EN	BIT(9)
-#define SIRFSOC_SPI_FRM_END_INT_EN	BIT(10)
-
-/* Interrupt status */
-#define SIRFSOC_SPI_RX_DONE		BIT(0)
-#define SIRFSOC_SPI_TX_DONE		BIT(1)
-#define SIRFSOC_SPI_RX_OFLOW		BIT(2)
-#define SIRFSOC_SPI_TX_UFLOW		BIT(3)
-#define SIRFSOC_SPI_RX_IO_DMA		BIT(4)
-#define SIRFSOC_SPI_RX_FIFO_FULL	BIT(6)
-#define SIRFSOC_SPI_TXFIFO_EMPTY	BIT(7)
-#define SIRFSOC_SPI_RXFIFO_THD_REACH	BIT(8)
-#define SIRFSOC_SPI_TXFIFO_THD_REACH	BIT(9)
-#define SIRFSOC_SPI_FRM_END		BIT(10)
-
-/* TX RX enable */
-#define SIRFSOC_SPI_RX_EN		BIT(0)
-#define SIRFSOC_SPI_TX_EN		BIT(1)
-#define SIRFSOC_SPI_CMD_TX_EN		BIT(2)
-
-#define SIRFSOC_SPI_IO_MODE_SEL		BIT(0)
-#define SIRFSOC_SPI_RX_DMA_FLUSH	BIT(2)
-
-/* FIFO OPs */
-#define SIRFSOC_SPI_FIFO_RESET		BIT(0)
-#define SIRFSOC_SPI_FIFO_START		BIT(1)
-
-/* FIFO CTRL */
-#define SIRFSOC_SPI_FIFO_WIDTH_BYTE	(0 << 0)
-#define SIRFSOC_SPI_FIFO_WIDTH_WORD	(1 << 0)
-#define SIRFSOC_SPI_FIFO_WIDTH_DWORD	(2 << 0)
-/* USP related */
-#define SIRFSOC_USP_SYNC_MODE		BIT(0)
-#define SIRFSOC_USP_SLV_MODE		BIT(1)
-#define SIRFSOC_USP_LSB			BIT(4)
-#define SIRFSOC_USP_EN			BIT(5)
-#define SIRFSOC_USP_RXD_FALLING_EDGE	BIT(6)
-#define SIRFSOC_USP_TXD_FALLING_EDGE	BIT(7)
-#define SIRFSOC_USP_CS_HIGH_VALID	BIT(9)
-#define SIRFSOC_USP_SCLK_IDLE_STAT	BIT(11)
-#define SIRFSOC_USP_TFS_IO_MODE		BIT(14)
-#define SIRFSOC_USP_TFS_IO_INPUT	BIT(19)
-
-#define SIRFSOC_USP_RXD_DELAY_LEN_MASK	0xFF
-#define SIRFSOC_USP_TXD_DELAY_LEN_MASK	0xFF
-#define SIRFSOC_USP_RXD_DELAY_OFFSET	0
-#define SIRFSOC_USP_TXD_DELAY_OFFSET	8
-#define SIRFSOC_USP_RXD_DELAY_LEN	1
-#define SIRFSOC_USP_TXD_DELAY_LEN	1
-#define SIRFSOC_USP_CLK_DIVISOR_OFFSET	21
-#define SIRFSOC_USP_CLK_DIVISOR_MASK	0x3FF
-#define SIRFSOC_USP_CLK_10_11_MASK	0x3
-#define SIRFSOC_USP_CLK_10_11_OFFSET	30
-#define SIRFSOC_USP_CLK_12_15_MASK	0xF
-#define SIRFSOC_USP_CLK_12_15_OFFSET	24
-
-#define SIRFSOC_USP_TX_DATA_OFFSET	0
-#define SIRFSOC_USP_TX_SYNC_OFFSET	8
-#define SIRFSOC_USP_TX_FRAME_OFFSET	16
-#define SIRFSOC_USP_TX_SHIFTER_OFFSET	24
-
-#define SIRFSOC_USP_TX_DATA_MASK	0xFF
-#define SIRFSOC_USP_TX_SYNC_MASK	0xFF
-#define SIRFSOC_USP_TX_FRAME_MASK	0xFF
-#define SIRFSOC_USP_TX_SHIFTER_MASK	0x1F
-
-#define SIRFSOC_USP_RX_DATA_OFFSET	0
-#define SIRFSOC_USP_RX_FRAME_OFFSET	8
-#define SIRFSOC_USP_RX_SHIFTER_OFFSET	16
-
-#define SIRFSOC_USP_RX_DATA_MASK	0xFF
-#define SIRFSOC_USP_RX_FRAME_MASK	0xFF
-#define SIRFSOC_USP_RX_SHIFTER_MASK	0x1F
-#define SIRFSOC_USP_CS_HIGH_VALUE	BIT(1)
-
-#define SIRFSOC_SPI_FIFO_SC_OFFSET	0
-#define SIRFSOC_SPI_FIFO_LC_OFFSET	10
-#define SIRFSOC_SPI_FIFO_HC_OFFSET	20
-
-#define SIRFSOC_SPI_FIFO_FULL_MASK(s)	(1 << ((s)->fifo_full_offset))
-#define SIRFSOC_SPI_FIFO_EMPTY_MASK(s)	(1 << ((s)->fifo_full_offset + 1))
-#define SIRFSOC_SPI_FIFO_THD_MASK(s)	((s)->fifo_size - 1)
-#define SIRFSOC_SPI_FIFO_THD_OFFSET	2
-#define SIRFSOC_SPI_FIFO_LEVEL_CHK_MASK(s, val)	\
-	((val) & (s)->fifo_level_chk_mask)
-
-enum sirf_spi_type {
-	SIRF_REAL_SPI,
-	SIRF_USP_SPI_P2,
-	SIRF_USP_SPI_A7,
-};
-
-/*
- * only if the rx/tx buffer and transfer size are 4-bytes aligned, we use dma
- * due to the limitation of dma controller
- */
-
-#define ALIGNED(x) (!((u32)x & 0x3))
-#define IS_DMA_VALID(x) (x && ALIGNED(x->tx_buf) && ALIGNED(x->rx_buf) && \
-	ALIGNED(x->len) && (x->len < 2 * PAGE_SIZE))
-
-#define SIRFSOC_MAX_CMD_BYTES	4
-#define SIRFSOC_SPI_DEFAULT_FRQ 1000000
-
-struct sirf_spi_register {
-	/*SPI and USP-SPI common*/
-	u32 tx_rx_en;
-	u32 int_en;
-	u32 int_st;
-	u32 tx_dma_io_ctrl;
-	u32 tx_dma_io_len;
-	u32 txfifo_ctrl;
-	u32 txfifo_level_chk;
-	u32 txfifo_op;
-	u32 txfifo_st;
-	u32 txfifo_data;
-	u32 rx_dma_io_ctrl;
-	u32 rx_dma_io_len;
-	u32 rxfifo_ctrl;
-	u32 rxfifo_level_chk;
-	u32 rxfifo_op;
-	u32 rxfifo_st;
-	u32 rxfifo_data;
-	/*SPI self*/
-	u32 spi_ctrl;
-	u32 spi_cmd;
-	u32 spi_dummy_delay_ctrl;
-	/*USP-SPI self*/
-	u32 usp_mode1;
-	u32 usp_mode2;
-	u32 usp_tx_frame_ctrl;
-	u32 usp_rx_frame_ctrl;
-	u32 usp_pin_io_data;
-	u32 usp_risc_dsp_mode;
-	u32 usp_async_param_reg;
-	u32 usp_irda_x_mode_div;
-	u32 usp_sm_cfg;
-	u32 usp_int_en_clr;
-};
-
-static const struct sirf_spi_register real_spi_register = {
-	.tx_rx_en		= 0x8,
-	.int_en		= 0xc,
-	.int_st		= 0x10,
-	.tx_dma_io_ctrl	= 0x100,
-	.tx_dma_io_len	= 0x104,
-	.txfifo_ctrl	= 0x108,
-	.txfifo_level_chk	= 0x10c,
-	.txfifo_op		= 0x110,
-	.txfifo_st		= 0x114,
-	.txfifo_data	= 0x118,
-	.rx_dma_io_ctrl	= 0x120,
-	.rx_dma_io_len	= 0x124,
-	.rxfifo_ctrl	= 0x128,
-	.rxfifo_level_chk	= 0x12c,
-	.rxfifo_op		= 0x130,
-	.rxfifo_st		= 0x134,
-	.rxfifo_data	= 0x138,
-	.spi_ctrl		= 0x0,
-	.spi_cmd		= 0x4,
-	.spi_dummy_delay_ctrl	= 0x144,
-};
-
-static const struct sirf_spi_register usp_spi_register = {
-	.tx_rx_en		= 0x10,
-	.int_en		= 0x14,
-	.int_st		= 0x18,
-	.tx_dma_io_ctrl	= 0x100,
-	.tx_dma_io_len	= 0x104,
-	.txfifo_ctrl	= 0x108,
-	.txfifo_level_chk	= 0x10c,
-	.txfifo_op		= 0x110,
-	.txfifo_st		= 0x114,
-	.txfifo_data	= 0x118,
-	.rx_dma_io_ctrl	= 0x120,
-	.rx_dma_io_len	= 0x124,
-	.rxfifo_ctrl	= 0x128,
-	.rxfifo_level_chk	= 0x12c,
-	.rxfifo_op		= 0x130,
-	.rxfifo_st		= 0x134,
-	.rxfifo_data	= 0x138,
-	.usp_mode1		= 0x0,
-	.usp_mode2		= 0x4,
-	.usp_tx_frame_ctrl	= 0x8,
-	.usp_rx_frame_ctrl	= 0xc,
-	.usp_pin_io_data	= 0x1c,
-	.usp_risc_dsp_mode	= 0x20,
-	.usp_async_param_reg	= 0x24,
-	.usp_irda_x_mode_div	= 0x28,
-	.usp_sm_cfg		= 0x2c,
-	.usp_int_en_clr		= 0x140,
-};
-
-struct sirfsoc_spi {
-	struct spi_bitbang bitbang;
-	struct completion rx_done;
-	struct completion tx_done;
-
-	void __iomem *base;
-	u32 ctrl_freq;  /* SPI controller clock speed */
-	struct clk *clk;
-
-	/* rx & tx bufs from the spi_transfer */
-	const void *tx;
-	void *rx;
-
-	/* place received word into rx buffer */
-	void (*rx_word) (struct sirfsoc_spi *);
-	/* get word from tx buffer for sending */
-	void (*tx_word) (struct sirfsoc_spi *);
-
-	/* number of words left to be tranmitted/received */
-	unsigned int left_tx_word;
-	unsigned int left_rx_word;
-
-	/* rx & tx DMA channels */
-	struct dma_chan *rx_chan;
-	struct dma_chan *tx_chan;
-	dma_addr_t src_start;
-	dma_addr_t dst_start;
-	int word_width; /* in bytes */
-
-	/*
-	 * if tx size is not more than 4 and rx size is NULL, use
-	 * command model
-	 */
-	bool	tx_by_cmd;
-	bool	hw_cs;
-	enum sirf_spi_type type;
-	const struct sirf_spi_register *regs;
-	unsigned int fifo_size;
-	/* fifo empty offset is (fifo full offset + 1)*/
-	unsigned int fifo_full_offset;
-	/* fifo_level_chk_mask is (fifo_size/4 - 1) */
-	unsigned int fifo_level_chk_mask;
-	unsigned int dat_max_frm_len;
-};
-
-struct sirf_spi_comp_data {
-	const struct sirf_spi_register *regs;
-	enum sirf_spi_type type;
-	unsigned int dat_max_frm_len;
-	unsigned int fifo_size;
-	void (*hwinit)(struct sirfsoc_spi *sspi);
-};
-
-static void sirfsoc_usp_hwinit(struct sirfsoc_spi *sspi)
-{
-	/* reset USP and let USP can operate */
-	writel(readl(sspi->base + sspi->regs->usp_mode1) &
-		~SIRFSOC_USP_EN, sspi->base + sspi->regs->usp_mode1);
-	writel(readl(sspi->base + sspi->regs->usp_mode1) |
-		SIRFSOC_USP_EN, sspi->base + sspi->regs->usp_mode1);
-}
-
-static void spi_sirfsoc_rx_word_u8(struct sirfsoc_spi *sspi)
-{
-	u32 data;
-	u8 *rx = sspi->rx;
-
-	data = readl(sspi->base + sspi->regs->rxfifo_data);
-
-	if (rx) {
-		*rx++ = (u8) data;
-		sspi->rx = rx;
-	}
-
-	sspi->left_rx_word--;
-}
-
-static void spi_sirfsoc_tx_word_u8(struct sirfsoc_spi *sspi)
-{
-	u32 data = 0;
-	const u8 *tx = sspi->tx;
-
-	if (tx) {
-		data = *tx++;
-		sspi->tx = tx;
-	}
-	writel(data, sspi->base + sspi->regs->txfifo_data);
-	sspi->left_tx_word--;
-}
-
-static void spi_sirfsoc_rx_word_u16(struct sirfsoc_spi *sspi)
-{
-	u32 data;
-	u16 *rx = sspi->rx;
-
-	data = readl(sspi->base + sspi->regs->rxfifo_data);
-
-	if (rx) {
-		*rx++ = (u16) data;
-		sspi->rx = rx;
-	}
-
-	sspi->left_rx_word--;
-}
-
-static void spi_sirfsoc_tx_word_u16(struct sirfsoc_spi *sspi)
-{
-	u32 data = 0;
-	const u16 *tx = sspi->tx;
-
-	if (tx) {
-		data = *tx++;
-		sspi->tx = tx;
-	}
-
-	writel(data, sspi->base + sspi->regs->txfifo_data);
-	sspi->left_tx_word--;
-}
-
-static void spi_sirfsoc_rx_word_u32(struct sirfsoc_spi *sspi)
-{
-	u32 data;
-	u32 *rx = sspi->rx;
-
-	data = readl(sspi->base + sspi->regs->rxfifo_data);
-
-	if (rx) {
-		*rx++ = (u32) data;
-		sspi->rx = rx;
-	}
-
-	sspi->left_rx_word--;
-
-}
-
-static void spi_sirfsoc_tx_word_u32(struct sirfsoc_spi *sspi)
-{
-	u32 data = 0;
-	const u32 *tx = sspi->tx;
-
-	if (tx) {
-		data = *tx++;
-		sspi->tx = tx;
-	}
-
-	writel(data, sspi->base + sspi->regs->txfifo_data);
-	sspi->left_tx_word--;
-}
-
-static irqreturn_t spi_sirfsoc_irq(int irq, void *dev_id)
-{
-	struct sirfsoc_spi *sspi = dev_id;
-	u32 spi_stat;
-
-	spi_stat = readl(sspi->base + sspi->regs->int_st);
-	if (sspi->tx_by_cmd && sspi->type == SIRF_REAL_SPI
-		&& (spi_stat & SIRFSOC_SPI_FRM_END)) {
-		complete(&sspi->tx_done);
-		writel(0x0, sspi->base + sspi->regs->int_en);
-		writel(readl(sspi->base + sspi->regs->int_st),
-				sspi->base + sspi->regs->int_st);
-		return IRQ_HANDLED;
-	}
-	/* Error Conditions */
-	if (spi_stat & SIRFSOC_SPI_RX_OFLOW ||
-			spi_stat & SIRFSOC_SPI_TX_UFLOW) {
-		complete(&sspi->tx_done);
-		complete(&sspi->rx_done);
-		switch (sspi->type) {
-		case SIRF_REAL_SPI:
-		case SIRF_USP_SPI_P2:
-			writel(0x0, sspi->base + sspi->regs->int_en);
-			break;
-		case SIRF_USP_SPI_A7:
-			writel(~0UL, sspi->base + sspi->regs->usp_int_en_clr);
-			break;
-		}
-		writel(readl(sspi->base + sspi->regs->int_st),
-				sspi->base + sspi->regs->int_st);
-		return IRQ_HANDLED;
-	}
-	if (spi_stat & SIRFSOC_SPI_TXFIFO_EMPTY)
-		complete(&sspi->tx_done);
-	while (!(readl(sspi->base + sspi->regs->int_st) &
-		SIRFSOC_SPI_RX_IO_DMA))
-		cpu_relax();
-	complete(&sspi->rx_done);
-	switch (sspi->type) {
-	case SIRF_REAL_SPI:
-	case SIRF_USP_SPI_P2:
-		writel(0x0, sspi->base + sspi->regs->int_en);
-		break;
-	case SIRF_USP_SPI_A7:
-		writel(~0UL, sspi->base + sspi->regs->usp_int_en_clr);
-		break;
-	}
-	writel(readl(sspi->base + sspi->regs->int_st),
-			sspi->base + sspi->regs->int_st);
-
-	return IRQ_HANDLED;
-}
-
-static void spi_sirfsoc_dma_fini_callback(void *data)
-{
-	struct completion *dma_complete = data;
-
-	complete(dma_complete);
-}
-
-static void spi_sirfsoc_cmd_transfer(struct spi_device *spi,
-	struct spi_transfer *t)
-{
-	struct sirfsoc_spi *sspi;
-	int timeout = t->len * 10;
-	u32 cmd;
-
-	sspi = spi_master_get_devdata(spi->master);
-	writel(SIRFSOC_SPI_FIFO_RESET, sspi->base + sspi->regs->txfifo_op);
-	writel(SIRFSOC_SPI_FIFO_START, sspi->base + sspi->regs->txfifo_op);
-	memcpy(&cmd, sspi->tx, t->len);
-	if (sspi->word_width == 1 && !(spi->mode & SPI_LSB_FIRST))
-		cmd = cpu_to_be32(cmd) >>
-			((SIRFSOC_MAX_CMD_BYTES - t->len) * 8);
-	if (sspi->word_width == 2 && t->len == 4 &&
-			(!(spi->mode & SPI_LSB_FIRST)))
-		cmd = ((cmd & 0xffff) << 16) | (cmd >> 16);
-	writel(cmd, sspi->base + sspi->regs->spi_cmd);
-	writel(SIRFSOC_SPI_FRM_END_INT_EN,
-		sspi->base + sspi->regs->int_en);
-	writel(SIRFSOC_SPI_CMD_TX_EN,
-		sspi->base + sspi->regs->tx_rx_en);
-	if (wait_for_completion_timeout(&sspi->tx_done, timeout) == 0) {
-		dev_err(&spi->dev, "cmd transfer timeout\n");
-		return;
-	}
-	sspi->left_rx_word -= t->len;
-}
-
-static void spi_sirfsoc_dma_transfer(struct spi_device *spi,
-	struct spi_transfer *t)
-{
-	struct sirfsoc_spi *sspi;
-	struct dma_async_tx_descriptor *rx_desc, *tx_desc;
-	int timeout = t->len * 10;
-
-	sspi = spi_master_get_devdata(spi->master);
-	writel(SIRFSOC_SPI_FIFO_RESET, sspi->base + sspi->regs->rxfifo_op);
-	writel(SIRFSOC_SPI_FIFO_RESET, sspi->base + sspi->regs->txfifo_op);
-	switch (sspi->type) {
-	case SIRF_REAL_SPI:
-		writel(SIRFSOC_SPI_FIFO_START,
-			sspi->base + sspi->regs->rxfifo_op);
-		writel(SIRFSOC_SPI_FIFO_START,
-			sspi->base + sspi->regs->txfifo_op);
-		writel(0, sspi->base + sspi->regs->int_en);
-		break;
-	case SIRF_USP_SPI_P2:
-		writel(0x0, sspi->base + sspi->regs->rxfifo_op);
-		writel(0x0, sspi->base + sspi->regs->txfifo_op);
-		writel(0, sspi->base + sspi->regs->int_en);
-		break;
-	case SIRF_USP_SPI_A7:
-		writel(0x0, sspi->base + sspi->regs->rxfifo_op);
-		writel(0x0, sspi->base + sspi->regs->txfifo_op);
-		writel(~0UL, sspi->base + sspi->regs->usp_int_en_clr);
-		break;
-	}
-	writel(readl(sspi->base + sspi->regs->int_st),
-		sspi->base + sspi->regs->int_st);
-	if (sspi->left_tx_word < sspi->dat_max_frm_len) {
-		switch (sspi->type) {
-		case SIRF_REAL_SPI:
-			writel(readl(sspi->base + sspi->regs->spi_ctrl) |
-				SIRFSOC_SPI_ENA_AUTO_CLR |
-				SIRFSOC_SPI_MUL_DAT_MODE,
-				sspi->base + sspi->regs->spi_ctrl);
-			writel(sspi->left_tx_word - 1,
-				sspi->base + sspi->regs->tx_dma_io_len);
-			writel(sspi->left_tx_word - 1,
-				sspi->base + sspi->regs->rx_dma_io_len);
-			break;
-		case SIRF_USP_SPI_P2:
-		case SIRF_USP_SPI_A7:
-			/*USP simulate SPI, tx/rx_dma_io_len indicates bytes*/
-			writel(sspi->left_tx_word * sspi->word_width,
-				sspi->base + sspi->regs->tx_dma_io_len);
-			writel(sspi->left_tx_word * sspi->word_width,
-				sspi->base + sspi->regs->rx_dma_io_len);
-			break;
-		}
-	} else {
-		if (sspi->type == SIRF_REAL_SPI)
-			writel(readl(sspi->base + sspi->regs->spi_ctrl),
-				sspi->base + sspi->regs->spi_ctrl);
-		writel(0, sspi->base + sspi->regs->tx_dma_io_len);
-		writel(0, sspi->base + sspi->regs->rx_dma_io_len);
-	}
-	sspi->dst_start = dma_map_single(&spi->dev, sspi->rx, t->len,
-					(t->tx_buf != t->rx_buf) ?
-					DMA_FROM_DEVICE : DMA_BIDIRECTIONAL);
-	rx_desc = dmaengine_prep_slave_single(sspi->rx_chan,
-		sspi->dst_start, t->len, DMA_DEV_TO_MEM,
-		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-	rx_desc->callback = spi_sirfsoc_dma_fini_callback;
-	rx_desc->callback_param = &sspi->rx_done;
-
-	sspi->src_start = dma_map_single(&spi->dev, (void *)sspi->tx, t->len,
-					(t->tx_buf != t->rx_buf) ?
-					DMA_TO_DEVICE : DMA_BIDIRECTIONAL);
-	tx_desc = dmaengine_prep_slave_single(sspi->tx_chan,
-		sspi->src_start, t->len, DMA_MEM_TO_DEV,
-		DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-	tx_desc->callback = spi_sirfsoc_dma_fini_callback;
-	tx_desc->callback_param = &sspi->tx_done;
-
-	dmaengine_submit(tx_desc);
-	dmaengine_submit(rx_desc);
-	dma_async_issue_pending(sspi->tx_chan);
-	dma_async_issue_pending(sspi->rx_chan);
-	writel(SIRFSOC_SPI_RX_EN | SIRFSOC_SPI_TX_EN,
-			sspi->base + sspi->regs->tx_rx_en);
-	if (sspi->type == SIRF_USP_SPI_P2 ||
-		sspi->type == SIRF_USP_SPI_A7) {
-		writel(SIRFSOC_SPI_FIFO_START,
-			sspi->base + sspi->regs->rxfifo_op);
-		writel(SIRFSOC_SPI_FIFO_START,
-			sspi->base + sspi->regs->txfifo_op);
-	}
-	if (wait_for_completion_timeout(&sspi->rx_done, timeout) == 0) {
-		dev_err(&spi->dev, "transfer timeout\n");
-		dmaengine_terminate_all(sspi->rx_chan);
-	} else
-		sspi->left_rx_word = 0;
-	/*
-	 * we only wait tx-done event if transferring by DMA. for PIO,
-	 * we get rx data by writing tx data, so if rx is done, tx has
-	 * done earlier
-	 */
-	if (wait_for_completion_timeout(&sspi->tx_done, timeout) == 0) {
-		dev_err(&spi->dev, "transfer timeout\n");
-		if (sspi->type == SIRF_USP_SPI_P2 ||
-			sspi->type == SIRF_USP_SPI_A7)
-			writel(0, sspi->base + sspi->regs->tx_rx_en);
-		dmaengine_terminate_all(sspi->tx_chan);
-	}
-	dma_unmap_single(&spi->dev, sspi->src_start, t->len, DMA_TO_DEVICE);
-	dma_unmap_single(&spi->dev, sspi->dst_start, t->len, DMA_FROM_DEVICE);
-	/* TX, RX FIFO stop */
-	writel(0, sspi->base + sspi->regs->rxfifo_op);
-	writel(0, sspi->base + sspi->regs->txfifo_op);
-	if (sspi->left_tx_word >= sspi->dat_max_frm_len)
-		writel(0, sspi->base + sspi->regs->tx_rx_en);
-	if (sspi->type == SIRF_USP_SPI_P2 ||
-		sspi->type == SIRF_USP_SPI_A7)
-		writel(0, sspi->base + sspi->regs->tx_rx_en);
-}
-
-static void spi_sirfsoc_pio_transfer(struct spi_device *spi,
-		struct spi_transfer *t)
-{
-	struct sirfsoc_spi *sspi;
-	int timeout = t->len * 10;
-	unsigned int data_units;
-
-	sspi = spi_master_get_devdata(spi->master);
-	do {
-		writel(SIRFSOC_SPI_FIFO_RESET,
-			sspi->base + sspi->regs->rxfifo_op);
-		writel(SIRFSOC_SPI_FIFO_RESET,
-			sspi->base + sspi->regs->txfifo_op);
-		switch (sspi->type) {
-		case SIRF_USP_SPI_P2:
-			writel(0x0, sspi->base + sspi->regs->rxfifo_op);
-			writel(0x0, sspi->base + sspi->regs->txfifo_op);
-			writel(0, sspi->base + sspi->regs->int_en);
-			writel(readl(sspi->base + sspi->regs->int_st),
-				sspi->base + sspi->regs->int_st);
-			writel(min((sspi->left_tx_word * sspi->word_width),
-				sspi->fifo_size),
-				sspi->base + sspi->regs->tx_dma_io_len);
-			writel(min((sspi->left_rx_word * sspi->word_width),
-				sspi->fifo_size),
-				sspi->base + sspi->regs->rx_dma_io_len);
-			break;
-		case SIRF_USP_SPI_A7:
-			writel(0x0, sspi->base + sspi->regs->rxfifo_op);
-			writel(0x0, sspi->base + sspi->regs->txfifo_op);
-			writel(~0UL, sspi->base + sspi->regs->usp_int_en_clr);
-			writel(readl(sspi->base + sspi->regs->int_st),
-				sspi->base + sspi->regs->int_st);
-			writel(min((sspi->left_tx_word * sspi->word_width),
-				sspi->fifo_size),
-				sspi->base + sspi->regs->tx_dma_io_len);
-			writel(min((sspi->left_rx_word * sspi->word_width),
-				sspi->fifo_size),
-				sspi->base + sspi->regs->rx_dma_io_len);
-			break;
-		case SIRF_REAL_SPI:
-			writel(SIRFSOC_SPI_FIFO_START,
-				sspi->base + sspi->regs->rxfifo_op);
-			writel(SIRFSOC_SPI_FIFO_START,
-				sspi->base + sspi->regs->txfifo_op);
-			writel(0, sspi->base + sspi->regs->int_en);
-			writel(readl(sspi->base + sspi->regs->int_st),
-				sspi->base + sspi->regs->int_st);
-			writel(readl(sspi->base + sspi->regs->spi_ctrl) |
-				SIRFSOC_SPI_MUL_DAT_MODE |
-				SIRFSOC_SPI_ENA_AUTO_CLR,
-				sspi->base + sspi->regs->spi_ctrl);
-			data_units = sspi->fifo_size / sspi->word_width;
-			writel(min(sspi->left_tx_word, data_units) - 1,
-				sspi->base + sspi->regs->tx_dma_io_len);
-			writel(min(sspi->left_rx_word, data_units) - 1,
-				sspi->base + sspi->regs->rx_dma_io_len);
-			break;
-		}
-		while (!((readl(sspi->base + sspi->regs->txfifo_st)
-			& SIRFSOC_SPI_FIFO_FULL_MASK(sspi))) &&
-			sspi->left_tx_word)
-			sspi->tx_word(sspi);
-		writel(SIRFSOC_SPI_TXFIFO_EMPTY_INT_EN |
-			SIRFSOC_SPI_TX_UFLOW_INT_EN |
-			SIRFSOC_SPI_RX_OFLOW_INT_EN |
-			SIRFSOC_SPI_RX_IO_DMA_INT_EN,
-			sspi->base + sspi->regs->int_en);
-		writel(SIRFSOC_SPI_RX_EN | SIRFSOC_SPI_TX_EN,
-			sspi->base + sspi->regs->tx_rx_en);
-		if (sspi->type == SIRF_USP_SPI_P2 ||
-			sspi->type == SIRF_USP_SPI_A7) {
-			writel(SIRFSOC_SPI_FIFO_START,
-				sspi->base + sspi->regs->rxfifo_op);
-			writel(SIRFSOC_SPI_FIFO_START,
-				sspi->base + sspi->regs->txfifo_op);
-		}
-		if (!wait_for_completion_timeout(&sspi->tx_done, timeout) ||
-			!wait_for_completion_timeout(&sspi->rx_done, timeout)) {
-			dev_err(&spi->dev, "transfer timeout\n");
-			if (sspi->type == SIRF_USP_SPI_P2 ||
-				sspi->type == SIRF_USP_SPI_A7)
-				writel(0, sspi->base + sspi->regs->tx_rx_en);
-			break;
-		}
-		while (!((readl(sspi->base + sspi->regs->rxfifo_st)
-			& SIRFSOC_SPI_FIFO_EMPTY_MASK(sspi))) &&
-			sspi->left_rx_word)
-			sspi->rx_word(sspi);
-		if (sspi->type == SIRF_USP_SPI_P2 ||
-			sspi->type == SIRF_USP_SPI_A7)
-			writel(0, sspi->base + sspi->regs->tx_rx_en);
-		writel(0, sspi->base + sspi->regs->rxfifo_op);
-		writel(0, sspi->base + sspi->regs->txfifo_op);
-	} while (sspi->left_tx_word != 0 || sspi->left_rx_word != 0);
-}
-
-static int spi_sirfsoc_transfer(struct spi_device *spi, struct spi_transfer *t)
-{
-	struct sirfsoc_spi *sspi;
-
-	sspi = spi_master_get_devdata(spi->master);
-	sspi->tx = t->tx_buf;
-	sspi->rx = t->rx_buf;
-	sspi->left_tx_word = sspi->left_rx_word = t->len / sspi->word_width;
-	reinit_completion(&sspi->rx_done);
-	reinit_completion(&sspi->tx_done);
-	/*
-	 * in the transfer, if transfer data using command register with rx_buf
-	 * null, just fill command data into command register and wait for its
-	 * completion.
-	 */
-	if (sspi->type == SIRF_REAL_SPI && sspi->tx_by_cmd)
-		spi_sirfsoc_cmd_transfer(spi, t);
-	else if (IS_DMA_VALID(t))
-		spi_sirfsoc_dma_transfer(spi, t);
-	else
-		spi_sirfsoc_pio_transfer(spi, t);
-
-	return t->len - sspi->left_rx_word * sspi->word_width;
-}
-
-static void spi_sirfsoc_chipselect(struct spi_device *spi, int value)
-{
-	struct sirfsoc_spi *sspi = spi_master_get_devdata(spi->master);
-
-	if (sspi->hw_cs) {
-		u32 regval;
-
-		switch (sspi->type) {
-		case SIRF_REAL_SPI:
-			regval = readl(sspi->base + sspi->regs->spi_ctrl);
-			switch (value) {
-			case BITBANG_CS_ACTIVE:
-				if (spi->mode & SPI_CS_HIGH)
-					regval |= SIRFSOC_SPI_CS_IO_OUT;
-				else
-					regval &= ~SIRFSOC_SPI_CS_IO_OUT;
-				break;
-			case BITBANG_CS_INACTIVE:
-				if (spi->mode & SPI_CS_HIGH)
-					regval &= ~SIRFSOC_SPI_CS_IO_OUT;
-				else
-					regval |= SIRFSOC_SPI_CS_IO_OUT;
-				break;
-			}
-			writel(regval, sspi->base + sspi->regs->spi_ctrl);
-			break;
-		case SIRF_USP_SPI_P2:
-		case SIRF_USP_SPI_A7:
-			regval = readl(sspi->base +
-					sspi->regs->usp_pin_io_data);
-			switch (value) {
-			case BITBANG_CS_ACTIVE:
-				if (spi->mode & SPI_CS_HIGH)
-					regval |= SIRFSOC_USP_CS_HIGH_VALUE;
-				else
-					regval &= ~(SIRFSOC_USP_CS_HIGH_VALUE);
-				break;
-			case BITBANG_CS_INACTIVE:
-				if (spi->mode & SPI_CS_HIGH)
-					regval &= ~(SIRFSOC_USP_CS_HIGH_VALUE);
-				else
-					regval |= SIRFSOC_USP_CS_HIGH_VALUE;
-				break;
-			}
-			writel(regval,
-				sspi->base + sspi->regs->usp_pin_io_data);
-			break;
-		}
-	} else {
-		switch (value) {
-		case BITBANG_CS_ACTIVE:
-			gpio_direction_output(spi->cs_gpio,
-					spi->mode & SPI_CS_HIGH ? 1 : 0);
-			break;
-		case BITBANG_CS_INACTIVE:
-			gpio_direction_output(spi->cs_gpio,
-					spi->mode & SPI_CS_HIGH ? 0 : 1);
-			break;
-		}
-	}
-}
-
-static int spi_sirfsoc_config_mode(struct spi_device *spi)
-{
-	struct sirfsoc_spi *sspi;
-	u32 regval, usp_mode1;
-
-	sspi = spi_master_get_devdata(spi->master);
-	regval = readl(sspi->base + sspi->regs->spi_ctrl);
-	usp_mode1 = readl(sspi->base + sspi->regs->usp_mode1);
-	if (!(spi->mode & SPI_CS_HIGH)) {
-		regval |= SIRFSOC_SPI_CS_IDLE_STAT;
-		usp_mode1 &= ~SIRFSOC_USP_CS_HIGH_VALID;
-	} else {
-		regval &= ~SIRFSOC_SPI_CS_IDLE_STAT;
-		usp_mode1 |= SIRFSOC_USP_CS_HIGH_VALID;
-	}
-	if (!(spi->mode & SPI_LSB_FIRST)) {
-		regval |= SIRFSOC_SPI_TRAN_MSB;
-		usp_mode1 &= ~SIRFSOC_USP_LSB;
-	} else {
-		regval &= ~SIRFSOC_SPI_TRAN_MSB;
-		usp_mode1 |= SIRFSOC_USP_LSB;
-	}
-	if (spi->mode & SPI_CPOL) {
-		regval |= SIRFSOC_SPI_CLK_IDLE_STAT;
-		usp_mode1 |= SIRFSOC_USP_SCLK_IDLE_STAT;
-	} else {
-		regval &= ~SIRFSOC_SPI_CLK_IDLE_STAT;
-		usp_mode1 &= ~SIRFSOC_USP_SCLK_IDLE_STAT;
-	}
-	/*
-	 * Data should be driven at least 1/2 cycle before the fetch edge
-	 * to make sure that data gets stable at the fetch edge.
-	 */
-	if (((spi->mode & SPI_CPOL) && (spi->mode & SPI_CPHA)) ||
-	    (!(spi->mode & SPI_CPOL) && !(spi->mode & SPI_CPHA))) {
-		regval &= ~SIRFSOC_SPI_DRV_POS_EDGE;
-		usp_mode1 |= (SIRFSOC_USP_TXD_FALLING_EDGE |
-				SIRFSOC_USP_RXD_FALLING_EDGE);
-	} else {
-		regval |= SIRFSOC_SPI_DRV_POS_EDGE;
-		usp_mode1 &= ~(SIRFSOC_USP_RXD_FALLING_EDGE |
-				SIRFSOC_USP_TXD_FALLING_EDGE);
-	}
-	writel((SIRFSOC_SPI_FIFO_LEVEL_CHK_MASK(sspi, sspi->fifo_size - 2) <<
-		SIRFSOC_SPI_FIFO_SC_OFFSET) |
-		(SIRFSOC_SPI_FIFO_LEVEL_CHK_MASK(sspi, sspi->fifo_size / 2) <<
-		SIRFSOC_SPI_FIFO_LC_OFFSET) |
-		(SIRFSOC_SPI_FIFO_LEVEL_CHK_MASK(sspi, 2) <<
-		SIRFSOC_SPI_FIFO_HC_OFFSET),
-		sspi->base + sspi->regs->txfifo_level_chk);
-	writel((SIRFSOC_SPI_FIFO_LEVEL_CHK_MASK(sspi, 2) <<
-		SIRFSOC_SPI_FIFO_SC_OFFSET) |
-		(SIRFSOC_SPI_FIFO_LEVEL_CHK_MASK(sspi, sspi->fifo_size / 2) <<
-		SIRFSOC_SPI_FIFO_LC_OFFSET) |
-		(SIRFSOC_SPI_FIFO_LEVEL_CHK_MASK(sspi, sspi->fifo_size - 2) <<
-		SIRFSOC_SPI_FIFO_HC_OFFSET),
-		sspi->base + sspi->regs->rxfifo_level_chk);
-	/*
-	 * it should never set to hardware cs mode because in hardware cs mode,
-	 * cs signal can't controlled by driver.
-	 */
-	switch (sspi->type) {
-	case SIRF_REAL_SPI:
-		regval |= SIRFSOC_SPI_CS_IO_MODE;
-		writel(regval, sspi->base + sspi->regs->spi_ctrl);
-		break;
-	case SIRF_USP_SPI_P2:
-	case SIRF_USP_SPI_A7:
-		usp_mode1 |= SIRFSOC_USP_SYNC_MODE;
-		usp_mode1 |= SIRFSOC_USP_TFS_IO_MODE;
-		usp_mode1 &= ~SIRFSOC_USP_TFS_IO_INPUT;
-		writel(usp_mode1, sspi->base + sspi->regs->usp_mode1);
-		break;
-	}
-
-	return 0;
-}
-
-static int
-spi_sirfsoc_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
-{
-	struct sirfsoc_spi *sspi;
-	u8 bits_per_word = 0;
-	int hz = 0;
-	u32 regval, txfifo_ctrl, rxfifo_ctrl, tx_frm_ctl, rx_frm_ctl, usp_mode2;
-
-	sspi = spi_master_get_devdata(spi->master);
-
-	bits_per_word = (t) ? t->bits_per_word : spi->bits_per_word;
-	hz = t && t->speed_hz ? t->speed_hz : spi->max_speed_hz;
-
-	usp_mode2 = regval = (sspi->ctrl_freq / (2 * hz)) - 1;
-	if (regval > 0xFFFF || regval < 0) {
-		dev_err(&spi->dev, "Speed %d not supported\n", hz);
-		return -EINVAL;
-	}
-	switch (bits_per_word) {
-	case 8:
-		regval |= SIRFSOC_SPI_TRAN_DAT_FORMAT_8;
-		sspi->rx_word = spi_sirfsoc_rx_word_u8;
-		sspi->tx_word = spi_sirfsoc_tx_word_u8;
-		break;
-	case 12:
-	case 16:
-		regval |= (bits_per_word ==  12) ?
-			SIRFSOC_SPI_TRAN_DAT_FORMAT_12 :
-			SIRFSOC_SPI_TRAN_DAT_FORMAT_16;
-		sspi->rx_word = spi_sirfsoc_rx_word_u16;
-		sspi->tx_word = spi_sirfsoc_tx_word_u16;
-		break;
-	case 32:
-		regval |= SIRFSOC_SPI_TRAN_DAT_FORMAT_32;
-		sspi->rx_word = spi_sirfsoc_rx_word_u32;
-		sspi->tx_word = spi_sirfsoc_tx_word_u32;
-		break;
-	default:
-		dev_err(&spi->dev, "bpw %d not supported\n", bits_per_word);
-		return -EINVAL;
-	}
-	sspi->word_width = DIV_ROUND_UP(bits_per_word, 8);
-	txfifo_ctrl = (((sspi->fifo_size / 2) &
-			SIRFSOC_SPI_FIFO_THD_MASK(sspi))
-			<< SIRFSOC_SPI_FIFO_THD_OFFSET) |
-			(sspi->word_width >> 1);
-	rxfifo_ctrl = (((sspi->fifo_size / 2) &
-			SIRFSOC_SPI_FIFO_THD_MASK(sspi))
-			<< SIRFSOC_SPI_FIFO_THD_OFFSET) |
-			(sspi->word_width >> 1);
-	writel(txfifo_ctrl, sspi->base + sspi->regs->txfifo_ctrl);
-	writel(rxfifo_ctrl, sspi->base + sspi->regs->rxfifo_ctrl);
-	if (sspi->type == SIRF_USP_SPI_P2 ||
-		sspi->type == SIRF_USP_SPI_A7) {
-		tx_frm_ctl = 0;
-		tx_frm_ctl |= ((bits_per_word - 1) & SIRFSOC_USP_TX_DATA_MASK)
-				<< SIRFSOC_USP_TX_DATA_OFFSET;
-		tx_frm_ctl |= ((bits_per_word + 1 + SIRFSOC_USP_TXD_DELAY_LEN
-				- 1) & SIRFSOC_USP_TX_SYNC_MASK) <<
-				SIRFSOC_USP_TX_SYNC_OFFSET;
-		tx_frm_ctl |= ((bits_per_word + 1 + SIRFSOC_USP_TXD_DELAY_LEN
-				+ 2 - 1) & SIRFSOC_USP_TX_FRAME_MASK) <<
-				SIRFSOC_USP_TX_FRAME_OFFSET;
-		tx_frm_ctl |= ((bits_per_word - 1) &
-				SIRFSOC_USP_TX_SHIFTER_MASK) <<
-				SIRFSOC_USP_TX_SHIFTER_OFFSET;
-		rx_frm_ctl = 0;
-		rx_frm_ctl |= ((bits_per_word - 1) & SIRFSOC_USP_RX_DATA_MASK)
-				<< SIRFSOC_USP_RX_DATA_OFFSET;
-		rx_frm_ctl |= ((bits_per_word + 1 + SIRFSOC_USP_RXD_DELAY_LEN
-				+ 2 - 1) & SIRFSOC_USP_RX_FRAME_MASK) <<
-				SIRFSOC_USP_RX_FRAME_OFFSET;
-		rx_frm_ctl |= ((bits_per_word - 1)
-				& SIRFSOC_USP_RX_SHIFTER_MASK) <<
-				SIRFSOC_USP_RX_SHIFTER_OFFSET;
-		writel(tx_frm_ctl | (((usp_mode2 >> 10) &
-			SIRFSOC_USP_CLK_10_11_MASK) <<
-			SIRFSOC_USP_CLK_10_11_OFFSET),
-			sspi->base + sspi->regs->usp_tx_frame_ctrl);
-		writel(rx_frm_ctl | (((usp_mode2 >> 12) &
-			SIRFSOC_USP_CLK_12_15_MASK) <<
-			SIRFSOC_USP_CLK_12_15_OFFSET),
-			sspi->base + sspi->regs->usp_rx_frame_ctrl);
-		writel(readl(sspi->base + sspi->regs->usp_mode2) |
-			((usp_mode2 & SIRFSOC_USP_CLK_DIVISOR_MASK) <<
-			SIRFSOC_USP_CLK_DIVISOR_OFFSET) |
-			(SIRFSOC_USP_RXD_DELAY_LEN <<
-			 SIRFSOC_USP_RXD_DELAY_OFFSET) |
-			(SIRFSOC_USP_TXD_DELAY_LEN <<
-			 SIRFSOC_USP_TXD_DELAY_OFFSET),
-			sspi->base + sspi->regs->usp_mode2);
-	}
-	if (sspi->type == SIRF_REAL_SPI)
-		writel(regval, sspi->base + sspi->regs->spi_ctrl);
-	spi_sirfsoc_config_mode(spi);
-	if (sspi->type == SIRF_REAL_SPI) {
-		if (t && t->tx_buf && !t->rx_buf &&
-			(t->len <= SIRFSOC_MAX_CMD_BYTES)) {
-			sspi->tx_by_cmd = true;
-			writel(readl(sspi->base + sspi->regs->spi_ctrl) |
-				(SIRFSOC_SPI_CMD_BYTE_NUM((t->len - 1)) |
-				SIRFSOC_SPI_CMD_MODE),
-				sspi->base + sspi->regs->spi_ctrl);
-		} else {
-			sspi->tx_by_cmd = false;
-			writel(readl(sspi->base + sspi->regs->spi_ctrl) &
-				~SIRFSOC_SPI_CMD_MODE,
-				sspi->base + sspi->regs->spi_ctrl);
-		}
-	}
-	if (IS_DMA_VALID(t)) {
-		/* Enable DMA mode for RX, TX */
-		writel(0, sspi->base + sspi->regs->tx_dma_io_ctrl);
-		writel(SIRFSOC_SPI_RX_DMA_FLUSH,
-			sspi->base + sspi->regs->rx_dma_io_ctrl);
-	} else {
-		/* Enable IO mode for RX, TX */
-		writel(SIRFSOC_SPI_IO_MODE_SEL,
-			sspi->base + sspi->regs->tx_dma_io_ctrl);
-		writel(SIRFSOC_SPI_IO_MODE_SEL,
-			sspi->base + sspi->regs->rx_dma_io_ctrl);
-	}
-	return 0;
-}
-
-static int spi_sirfsoc_setup(struct spi_device *spi)
-{
-	struct sirfsoc_spi *sspi;
-	int ret = 0;
-
-	sspi = spi_master_get_devdata(spi->master);
-	if (spi->cs_gpio == -ENOENT)
-		sspi->hw_cs = true;
-	else {
-		sspi->hw_cs = false;
-		if (!spi_get_ctldata(spi)) {
-			void *cs = kmalloc(sizeof(int), GFP_KERNEL);
-			if (!cs) {
-				ret = -ENOMEM;
-				goto exit;
-			}
-			ret = gpio_is_valid(spi->cs_gpio);
-			if (!ret) {
-				dev_err(&spi->dev, "no valid gpio\n");
-				ret = -ENOENT;
-				goto exit;
-			}
-			ret = gpio_request(spi->cs_gpio, DRIVER_NAME);
-			if (ret) {
-				dev_err(&spi->dev, "failed to request gpio\n");
-				goto exit;
-			}
-			spi_set_ctldata(spi, cs);
-		}
-	}
-	spi_sirfsoc_config_mode(spi);
-	spi_sirfsoc_chipselect(spi, BITBANG_CS_INACTIVE);
-exit:
-	return ret;
-}
-
-static void spi_sirfsoc_cleanup(struct spi_device *spi)
-{
-	if (spi_get_ctldata(spi)) {
-		gpio_free(spi->cs_gpio);
-		kfree(spi_get_ctldata(spi));
-	}
-}
-
-static const struct sirf_spi_comp_data sirf_real_spi = {
-	.regs = &real_spi_register,
-	.type = SIRF_REAL_SPI,
-	.dat_max_frm_len = 64 * 1024,
-	.fifo_size = 256,
-};
-
-static const struct sirf_spi_comp_data sirf_usp_spi_p2 = {
-	.regs = &usp_spi_register,
-	.type = SIRF_USP_SPI_P2,
-	.dat_max_frm_len = 1024 * 1024,
-	.fifo_size = 128,
-	.hwinit = sirfsoc_usp_hwinit,
-};
-
-static const struct sirf_spi_comp_data sirf_usp_spi_a7 = {
-	.regs = &usp_spi_register,
-	.type = SIRF_USP_SPI_A7,
-	.dat_max_frm_len = 1024 * 1024,
-	.fifo_size = 512,
-	.hwinit = sirfsoc_usp_hwinit,
-};
-
-static const struct of_device_id spi_sirfsoc_of_match[] = {
-	{ .compatible = "sirf,prima2-spi", .data = &sirf_real_spi},
-	{ .compatible = "sirf,prima2-usp-spi", .data = &sirf_usp_spi_p2},
-	{ .compatible = "sirf,atlas7-usp-spi", .data = &sirf_usp_spi_a7},
-	{}
-};
-MODULE_DEVICE_TABLE(of, spi_sirfsoc_of_match);
-
-static int spi_sirfsoc_probe(struct platform_device *pdev)
-{
-	struct sirfsoc_spi *sspi;
-	struct spi_master *master;
-	const struct sirf_spi_comp_data *spi_comp_data;
-	int irq;
-	int ret;
-	const struct of_device_id *match;
-
-	ret = device_reset(&pdev->dev);
-	if (ret) {
-		dev_err(&pdev->dev, "SPI reset failed!\n");
-		return ret;
-	}
-
-	master = spi_alloc_master(&pdev->dev, sizeof(*sspi));
-	if (!master) {
-		dev_err(&pdev->dev, "Unable to allocate SPI master\n");
-		return -ENOMEM;
-	}
-	match = of_match_node(spi_sirfsoc_of_match, pdev->dev.of_node);
-	platform_set_drvdata(pdev, master);
-	sspi = spi_master_get_devdata(master);
-	sspi->fifo_full_offset = ilog2(sspi->fifo_size);
-	spi_comp_data = match->data;
-	sspi->regs = spi_comp_data->regs;
-	sspi->type = spi_comp_data->type;
-	sspi->fifo_level_chk_mask = (sspi->fifo_size / 4) - 1;
-	sspi->dat_max_frm_len = spi_comp_data->dat_max_frm_len;
-	sspi->fifo_size = spi_comp_data->fifo_size;
-	sspi->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(sspi->base)) {
-		ret = PTR_ERR(sspi->base);
-		goto free_master;
-	}
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		ret = -ENXIO;
-		goto free_master;
-	}
-	ret = devm_request_irq(&pdev->dev, irq, spi_sirfsoc_irq, 0,
-				DRIVER_NAME, sspi);
-	if (ret)
-		goto free_master;
-
-	sspi->bitbang.master = master;
-	sspi->bitbang.chipselect = spi_sirfsoc_chipselect;
-	sspi->bitbang.setup_transfer = spi_sirfsoc_setup_transfer;
-	sspi->bitbang.txrx_bufs = spi_sirfsoc_transfer;
-	sspi->bitbang.master->setup = spi_sirfsoc_setup;
-	sspi->bitbang.master->cleanup = spi_sirfsoc_cleanup;
-	master->bus_num = pdev->id;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST | SPI_CS_HIGH;
-	master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(12) |
-					SPI_BPW_MASK(16) | SPI_BPW_MASK(32);
-	master->max_speed_hz = SIRFSOC_SPI_DEFAULT_FRQ;
-	master->flags = SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX;
-	sspi->bitbang.master->dev.of_node = pdev->dev.of_node;
-
-	/* request DMA channels */
-	sspi->rx_chan = dma_request_chan(&pdev->dev, "rx");
-	if (IS_ERR(sspi->rx_chan)) {
-		dev_err(&pdev->dev, "can not allocate rx dma channel\n");
-		ret = PTR_ERR(sspi->rx_chan);
-		goto free_master;
-	}
-	sspi->tx_chan = dma_request_chan(&pdev->dev, "tx");
-	if (IS_ERR(sspi->tx_chan)) {
-		dev_err(&pdev->dev, "can not allocate tx dma channel\n");
-		ret = PTR_ERR(sspi->tx_chan);
-		goto free_rx_dma;
-	}
-
-	sspi->clk = clk_get(&pdev->dev, NULL);
-	if (IS_ERR(sspi->clk)) {
-		ret = PTR_ERR(sspi->clk);
-		goto free_tx_dma;
-	}
-	clk_prepare_enable(sspi->clk);
-	if (spi_comp_data->hwinit)
-		spi_comp_data->hwinit(sspi);
-	sspi->ctrl_freq = clk_get_rate(sspi->clk);
-
-	init_completion(&sspi->rx_done);
-	init_completion(&sspi->tx_done);
-
-	ret = spi_bitbang_start(&sspi->bitbang);
-	if (ret)
-		goto free_clk;
-	dev_info(&pdev->dev, "registered, bus number = %d\n", master->bus_num);
-
-	return 0;
-free_clk:
-	clk_disable_unprepare(sspi->clk);
-	clk_put(sspi->clk);
-free_tx_dma:
-	dma_release_channel(sspi->tx_chan);
-free_rx_dma:
-	dma_release_channel(sspi->rx_chan);
-free_master:
-	spi_master_put(master);
-
-	return ret;
-}
-
-static int  spi_sirfsoc_remove(struct platform_device *pdev)
-{
-	struct spi_master *master;
-	struct sirfsoc_spi *sspi;
-
-	master = platform_get_drvdata(pdev);
-	sspi = spi_master_get_devdata(master);
-	spi_bitbang_stop(&sspi->bitbang);
-	clk_disable_unprepare(sspi->clk);
-	clk_put(sspi->clk);
-	dma_release_channel(sspi->rx_chan);
-	dma_release_channel(sspi->tx_chan);
-	spi_master_put(master);
-	return 0;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static int spi_sirfsoc_suspend(struct device *dev)
-{
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct sirfsoc_spi *sspi = spi_master_get_devdata(master);
-	int ret;
-
-	ret = spi_master_suspend(master);
-	if (ret)
-		return ret;
-
-	clk_disable(sspi->clk);
-	return 0;
-}
-
-static int spi_sirfsoc_resume(struct device *dev)
-{
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct sirfsoc_spi *sspi = spi_master_get_devdata(master);
-
-	clk_enable(sspi->clk);
-	writel(SIRFSOC_SPI_FIFO_RESET, sspi->base + sspi->regs->txfifo_op);
-	writel(SIRFSOC_SPI_FIFO_RESET, sspi->base + sspi->regs->rxfifo_op);
-	writel(SIRFSOC_SPI_FIFO_START, sspi->base + sspi->regs->txfifo_op);
-	writel(SIRFSOC_SPI_FIFO_START, sspi->base + sspi->regs->rxfifo_op);
-	return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(spi_sirfsoc_pm_ops, spi_sirfsoc_suspend,
-			 spi_sirfsoc_resume);
-
-static struct platform_driver spi_sirfsoc_driver = {
-	.driver = {
-		.name = DRIVER_NAME,
-		.pm     = &spi_sirfsoc_pm_ops,
-		.of_match_table = spi_sirfsoc_of_match,
-	},
-	.probe = spi_sirfsoc_probe,
-	.remove = spi_sirfsoc_remove,
-};
-module_platform_driver(spi_sirfsoc_driver);
-MODULE_DESCRIPTION("SiRF SoC SPI master driver");
-MODULE_AUTHOR("Zhiwu Song <Zhiwu.Song@csr.com>");
-MODULE_AUTHOR("Barry Song <Baohua.Song@csr.com>");
-MODULE_AUTHOR("Qipan Li <Qipan.Li@csr.com>");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 6017209c6d2f..25c076461011 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2017, STMicroelectronics - All Rights Reserved
 // Author(s): Amelie Delaunay <amelie.delaunay@st.com> for STMicroelectronics.
 
+#include <linux/bitfield.h>
 #include <linux/debugfs.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -94,27 +95,22 @@
 #define STM32H7_SPI_CR1_SSI		BIT(12)
 
 /* STM32H7_SPI_CR2 bit fields */
-#define STM32H7_SPI_CR2_TSIZE_SHIFT	0
 #define STM32H7_SPI_CR2_TSIZE		GENMASK(15, 0)
+#define STM32H7_SPI_TSIZE_MAX		GENMASK(15, 0)
 
 /* STM32H7_SPI_CFG1 bit fields */
-#define STM32H7_SPI_CFG1_DSIZE_SHIFT	0
 #define STM32H7_SPI_CFG1_DSIZE		GENMASK(4, 0)
-#define STM32H7_SPI_CFG1_FTHLV_SHIFT	5
 #define STM32H7_SPI_CFG1_FTHLV		GENMASK(8, 5)
 #define STM32H7_SPI_CFG1_RXDMAEN	BIT(14)
 #define STM32H7_SPI_CFG1_TXDMAEN	BIT(15)
-#define STM32H7_SPI_CFG1_MBR_SHIFT	28
 #define STM32H7_SPI_CFG1_MBR		GENMASK(30, 28)
+#define STM32H7_SPI_CFG1_MBR_SHIFT	28
 #define STM32H7_SPI_CFG1_MBR_MIN	0
 #define STM32H7_SPI_CFG1_MBR_MAX	(GENMASK(30, 28) >> 28)
 
 /* STM32H7_SPI_CFG2 bit fields */
-#define STM32H7_SPI_CFG2_MIDI_SHIFT	4
 #define STM32H7_SPI_CFG2_MIDI		GENMASK(7, 4)
-#define STM32H7_SPI_CFG2_COMM_SHIFT	17
 #define STM32H7_SPI_CFG2_COMM		GENMASK(18, 17)
-#define STM32H7_SPI_CFG2_SP_SHIFT	19
 #define STM32H7_SPI_CFG2_SP		GENMASK(21, 19)
 #define STM32H7_SPI_CFG2_MASTER		BIT(22)
 #define STM32H7_SPI_CFG2_LSBFRST	BIT(23)
@@ -140,7 +136,6 @@
 #define STM32H7_SPI_SR_OVR		BIT(6)
 #define STM32H7_SPI_SR_MODF		BIT(9)
 #define STM32H7_SPI_SR_SUSP		BIT(11)
-#define STM32H7_SPI_SR_RXPLVL_SHIFT	13
 #define STM32H7_SPI_SR_RXPLVL		GENMASK(14, 13)
 #define STM32H7_SPI_SR_RXWNE		BIT(15)
 
@@ -167,8 +162,6 @@
 #define SPI_3WIRE_TX		3
 #define SPI_3WIRE_RX		4
 
-#define SPI_1HZ_NS		1000000000
-
 /*
  * use PIO for small transfers, avoiding DMA setup/teardown overhead for drivers
  * without fifo buffers.
@@ -268,7 +261,6 @@ struct stm32_spi_cfg {
  * @base: virtual memory area
  * @clk: hw kernel clock feeding the SPI clock generator
  * @clk_rate: rate of the hw kernel clock feeding the SPI clock generator
- * @rst: SPI controller reset line
  * @lock: prevent I/O concurrent access
  * @irq: SPI controller interrupt line
  * @fifo_size: size of the embedded fifo in bytes
@@ -294,7 +286,6 @@ struct stm32_spi {
 	void __iomem *base;
 	struct clk *clk;
 	u32 clk_rate;
-	struct reset_control *rst;
 	spinlock_t lock; /* prevent I/O concurrent access */
 	int irq;
 	unsigned int fifo_size;
@@ -417,9 +408,7 @@ static int stm32h7_spi_get_bpw_mask(struct stm32_spi *spi)
 	stm32_spi_set_bits(spi, STM32H7_SPI_CFG1, STM32H7_SPI_CFG1_DSIZE);
 
 	cfg1 = readl_relaxed(spi->base + STM32H7_SPI_CFG1);
-	max_bpw = (cfg1 & STM32H7_SPI_CFG1_DSIZE) >>
-		  STM32H7_SPI_CFG1_DSIZE_SHIFT;
-	max_bpw += 1;
+	max_bpw = FIELD_GET(STM32H7_SPI_CFG1_DSIZE, cfg1) + 1;
 
 	spin_unlock_irqrestore(&spi->lock, flags);
 
@@ -473,34 +462,14 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz,
  */
 static u32 stm32h7_spi_prepare_fthlv(struct stm32_spi *spi, u32 xfer_len)
 {
-	u32 fthlv, half_fifo, packet;
+	u32 packet, bpw;
 
 	/* data packet should not exceed 1/2 of fifo space */
-	half_fifo = (spi->fifo_size / 2);
-
-	/* data_packet should not exceed transfer length */
-	if (half_fifo > xfer_len)
-		packet = xfer_len;
-	else
-		packet = half_fifo;
-
-	if (spi->cur_bpw <= 8)
-		fthlv = packet;
-	else if (spi->cur_bpw <= 16)
-		fthlv = packet / 2;
-	else
-		fthlv = packet / 4;
+	packet = clamp(xfer_len, 1U, spi->fifo_size / 2);
 
 	/* align packet size with data registers access */
-	if (spi->cur_bpw > 8)
-		fthlv += (fthlv % 2) ? 1 : 0;
-	else
-		fthlv += (fthlv % 4) ? (4 - (fthlv % 4)) : 0;
-
-	if (!fthlv)
-		fthlv = 1;
-
-	return fthlv;
+	bpw = DIV_ROUND_UP(spi->cur_bpw, 8);
+	return DIV_ROUND_UP(packet, bpw);
 }
 
 /**
@@ -607,8 +576,7 @@ static void stm32f4_spi_read_rx(struct stm32_spi *spi)
 static void stm32h7_spi_read_rxfifo(struct stm32_spi *spi, bool flush)
 {
 	u32 sr = readl_relaxed(spi->base + STM32H7_SPI_SR);
-	u32 rxplvl = (sr & STM32H7_SPI_SR_RXPLVL) >>
-		     STM32H7_SPI_SR_RXPLVL_SHIFT;
+	u32 rxplvl = FIELD_GET(STM32H7_SPI_SR_RXPLVL, sr);
 
 	while ((spi->rx_len > 0) &&
 	       ((sr & STM32H7_SPI_SR_RXP) ||
@@ -635,8 +603,7 @@ static void stm32h7_spi_read_rxfifo(struct stm32_spi *spi, bool flush)
 		}
 
 		sr = readl_relaxed(spi->base + STM32H7_SPI_SR);
-		rxplvl = (sr & STM32H7_SPI_SR_RXPLVL) >>
-			 STM32H7_SPI_SR_RXPLVL_SHIFT;
+		rxplvl = FIELD_GET(STM32H7_SPI_SR_RXPLVL, sr);
 	}
 
 	dev_dbg(spi->dev, "%s%s: %d bytes left\n", __func__,
@@ -928,8 +895,8 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 		mask |= STM32H7_SPI_SR_RXP;
 
 	if (!(sr & mask)) {
-		dev_dbg(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n",
-			sr, ier);
+		dev_warn(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n",
+			 sr, ier);
 		spin_unlock_irqrestore(&spi->lock, flags);
 		return IRQ_NONE;
 	}
@@ -956,15 +923,8 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 	}
 
 	if (sr & STM32H7_SPI_SR_OVR) {
-		dev_warn(spi->dev, "Overrun: received value discarded\n");
-		if (!spi->cur_usedma && (spi->rx_buf && (spi->rx_len > 0)))
-			stm32h7_spi_read_rxfifo(spi, false);
-		/*
-		 * If overrun is detected while using DMA, it means that
-		 * something went wrong, so stop the current transfer
-		 */
-		if (spi->cur_usedma)
-			end = true;
+		dev_err(spi->dev, "Overrun: RX data lost\n");
+		end = true;
 	}
 
 	if (sr & STM32H7_SPI_SR_EOT) {
@@ -1028,10 +988,24 @@ static int stm32_spi_prepare_msg(struct spi_master *master,
 		clrb |= spi->cfg->regs->lsb_first.mask;
 
 	dev_dbg(spi->dev, "cpol=%d cpha=%d lsb_first=%d cs_high=%d\n",
-		spi_dev->mode & SPI_CPOL,
-		spi_dev->mode & SPI_CPHA,
-		spi_dev->mode & SPI_LSB_FIRST,
-		spi_dev->mode & SPI_CS_HIGH);
+		!!(spi_dev->mode & SPI_CPOL),
+		!!(spi_dev->mode & SPI_CPHA),
+		!!(spi_dev->mode & SPI_LSB_FIRST),
+		!!(spi_dev->mode & SPI_CS_HIGH));
+
+	/* On STM32H7, messages should not exceed a maximum size setted
+	 * afterward via the set_number_of_data function. In order to
+	 * ensure that, split large messages into several messages
+	 */
+	if (spi->cfg->set_number_of_data) {
+		int ret;
+
+		ret = spi_split_transfers_maxsize(master, msg,
+						  STM32H7_SPI_TSIZE_MAX,
+						  GFP_KERNEL | GFP_DMA);
+		if (ret)
+			return ret;
+	}
 
 	spin_lock_irqsave(&spi->lock, flags);
 
@@ -1405,15 +1379,13 @@ static void stm32h7_spi_set_bpw(struct stm32_spi *spi)
 	bpw = spi->cur_bpw - 1;
 
 	cfg1_clrb |= STM32H7_SPI_CFG1_DSIZE;
-	cfg1_setb |= (bpw << STM32H7_SPI_CFG1_DSIZE_SHIFT) &
-		     STM32H7_SPI_CFG1_DSIZE;
+	cfg1_setb |= FIELD_PREP(STM32H7_SPI_CFG1_DSIZE, bpw);
 
 	spi->cur_fthlv = stm32h7_spi_prepare_fthlv(spi, spi->cur_xferlen);
 	fthlv = spi->cur_fthlv - 1;
 
 	cfg1_clrb |= STM32H7_SPI_CFG1_FTHLV;
-	cfg1_setb |= (fthlv << STM32H7_SPI_CFG1_FTHLV_SHIFT) &
-		     STM32H7_SPI_CFG1_FTHLV;
+	cfg1_setb |= FIELD_PREP(STM32H7_SPI_CFG1_FTHLV, fthlv);
 
 	writel_relaxed(
 		(readl_relaxed(spi->base + STM32H7_SPI_CFG1) &
@@ -1431,8 +1403,7 @@ static void stm32_spi_set_mbr(struct stm32_spi *spi, u32 mbrdiv)
 	u32 clrb = 0, setb = 0;
 
 	clrb |= spi->cfg->regs->br.mask;
-	setb |= ((u32)mbrdiv << spi->cfg->regs->br.shift) &
-		spi->cfg->regs->br.mask;
+	setb |= (mbrdiv << spi->cfg->regs->br.shift) & spi->cfg->regs->br.mask;
 
 	writel_relaxed((readl_relaxed(spi->base + spi->cfg->regs->br.reg) &
 			~clrb) | setb,
@@ -1523,8 +1494,7 @@ static int stm32h7_spi_set_mode(struct stm32_spi *spi, unsigned int comm_type)
 	}
 
 	cfg2_clrb |= STM32H7_SPI_CFG2_COMM;
-	cfg2_setb |= (mode << STM32H7_SPI_CFG2_COMM_SHIFT) &
-		     STM32H7_SPI_CFG2_COMM;
+	cfg2_setb |= FIELD_PREP(STM32H7_SPI_CFG2_COMM, mode);
 
 	writel_relaxed(
 		(readl_relaxed(spi->base + STM32H7_SPI_CFG2) &
@@ -1546,15 +1516,16 @@ static void stm32h7_spi_data_idleness(struct stm32_spi *spi, u32 len)
 
 	cfg2_clrb |= STM32H7_SPI_CFG2_MIDI;
 	if ((len > 1) && (spi->cur_midi > 0)) {
-		u32 sck_period_ns = DIV_ROUND_UP(SPI_1HZ_NS, spi->cur_speed);
-		u32 midi = min((u32)DIV_ROUND_UP(spi->cur_midi, sck_period_ns),
-			       (u32)STM32H7_SPI_CFG2_MIDI >>
-			       STM32H7_SPI_CFG2_MIDI_SHIFT);
+		u32 sck_period_ns = DIV_ROUND_UP(NSEC_PER_SEC, spi->cur_speed);
+		u32 midi = min_t(u32,
+				 DIV_ROUND_UP(spi->cur_midi, sck_period_ns),
+				 FIELD_GET(STM32H7_SPI_CFG2_MIDI,
+				 STM32H7_SPI_CFG2_MIDI));
+
 
 		dev_dbg(spi->dev, "period=%dns, midi=%d(=%dns)\n",
 			sck_period_ns, midi, midi * sck_period_ns);
-		cfg2_setb |= (midi << STM32H7_SPI_CFG2_MIDI_SHIFT) &
-			     STM32H7_SPI_CFG2_MIDI;
+		cfg2_setb |= FIELD_PREP(STM32H7_SPI_CFG2_MIDI, midi);
 	}
 
 	writel_relaxed((readl_relaxed(spi->base + STM32H7_SPI_CFG2) &
@@ -1569,14 +1540,8 @@ static void stm32h7_spi_data_idleness(struct stm32_spi *spi, u32 len)
  */
 static int stm32h7_spi_number_of_data(struct stm32_spi *spi, u32 nb_words)
 {
-	u32 cr2_clrb = 0, cr2_setb = 0;
-
-	if (nb_words <= (STM32H7_SPI_CR2_TSIZE >>
-			 STM32H7_SPI_CR2_TSIZE_SHIFT)) {
-		cr2_clrb |= STM32H7_SPI_CR2_TSIZE;
-		cr2_setb = nb_words << STM32H7_SPI_CR2_TSIZE_SHIFT;
-		writel_relaxed((readl_relaxed(spi->base + STM32H7_SPI_CR2) &
-				~cr2_clrb) | cr2_setb,
+	if (nb_words <= STM32H7_SPI_TSIZE_MAX) {
+		writel_relaxed(FIELD_PREP(STM32H7_SPI_CR2_TSIZE, nb_words),
 			       spi->base + STM32H7_SPI_CR2);
 	} else {
 		return -EMSGSIZE;
@@ -1677,6 +1642,10 @@ static int stm32_spi_transfer_one(struct spi_master *master,
 	struct stm32_spi *spi = spi_master_get_devdata(master);
 	int ret;
 
+	/* Don't do anything on 0 bytes transfers */
+	if (transfer->len == 0)
+		return 0;
+
 	spi->tx_buf = transfer->tx_buf;
 	spi->rx_buf = transfer->rx_buf;
 	spi->tx_len = spi->tx_buf ? transfer->len : 0;
@@ -1831,6 +1800,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	struct spi_master *master;
 	struct stm32_spi *spi;
 	struct resource *res;
+	struct reset_control *rst;
 	int ret;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(struct stm32_spi));
@@ -1892,11 +1862,17 @@ static int stm32_spi_probe(struct platform_device *pdev)
 		goto err_clk_disable;
 	}
 
-	spi->rst = devm_reset_control_get_exclusive(&pdev->dev, NULL);
-	if (!IS_ERR(spi->rst)) {
-		reset_control_assert(spi->rst);
+	rst = devm_reset_control_get_optional_exclusive(&pdev->dev, NULL);
+	if (rst) {
+		if (IS_ERR(rst)) {
+			ret = dev_err_probe(&pdev->dev, PTR_ERR(rst),
+					    "failed to get reset\n");
+			goto err_clk_disable;
+		}
+
+		reset_control_assert(rst);
 		udelay(2);
-		reset_control_deassert(spi->rst);
+		reset_control_deassert(rst);
 	}
 
 	if (spi->cfg->has_fifo)
@@ -1960,12 +1936,6 @@ static int stm32_spi_probe(struct platform_device *pdev)
 		goto err_pm_disable;
 	}
 
-	if (!master->cs_gpiods) {
-		dev_err(&pdev->dev, "no CS gpios available\n");
-		ret = -EINVAL;
-		goto err_pm_disable;
-	}
-
 	dev_info(&pdev->dev, "driver initialized\n");
 
 	return 0;
diff --git a/drivers/spi/spi-synquacer.c b/drivers/spi/spi-synquacer.c
index 8cdca6ab8098..ea706d9629cb 100644
--- a/drivers/spi/spi-synquacer.c
+++ b/drivers/spi/spi-synquacer.c
@@ -490,6 +490,10 @@ static void synquacer_spi_set_cs(struct spi_device *spi, bool enable)
 	val &= ~(SYNQUACER_HSSPI_DMPSEL_CS_MASK <<
 		 SYNQUACER_HSSPI_DMPSEL_CS_SHIFT);
 	val |= spi->chip_select << SYNQUACER_HSSPI_DMPSEL_CS_SHIFT;
+
+	if (!enable)
+		val |= SYNQUACER_HSSPI_DMSTOP_STOP;
+
 	writel(val, sspi->regs + SYNQUACER_HSSPI_REG_DMSTART);
 }
 
diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
new file mode 100644
index 000000000000..2f806f4b2c34
--- /dev/null
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -0,0 +1,1410 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// Copyright (C) 2020 NVIDIA CORPORATION.
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/reset.h>
+#include <linux/spi/spi.h>
+
+#define QSPI_COMMAND1				0x000
+#define QSPI_BIT_LENGTH(x)			(((x) & 0x1f) << 0)
+#define QSPI_PACKED				BIT(5)
+#define QSPI_INTERFACE_WIDTH_MASK		(0x03 << 7)
+#define QSPI_INTERFACE_WIDTH(x)			(((x) & 0x03) << 7)
+#define QSPI_INTERFACE_WIDTH_SINGLE		QSPI_INTERFACE_WIDTH(0)
+#define QSPI_INTERFACE_WIDTH_DUAL		QSPI_INTERFACE_WIDTH(1)
+#define QSPI_INTERFACE_WIDTH_QUAD		QSPI_INTERFACE_WIDTH(2)
+#define QSPI_SDR_DDR_SEL			BIT(9)
+#define QSPI_TX_EN				BIT(11)
+#define QSPI_RX_EN				BIT(12)
+#define QSPI_CS_SW_VAL				BIT(20)
+#define QSPI_CS_SW_HW				BIT(21)
+#define QSPI_CONTROL_MODE_0			(0 << 28)
+#define QSPI_CONTROL_MODE_3			(3 << 28)
+#define QSPI_CONTROL_MODE_MASK			(3 << 28)
+#define QSPI_M_S				BIT(30)
+#define QSPI_PIO				BIT(31)
+
+#define QSPI_COMMAND2				0x004
+#define QSPI_TX_TAP_DELAY(x)			(((x) & 0x3f) << 10)
+#define QSPI_RX_TAP_DELAY(x)			(((x) & 0xff) << 0)
+
+#define QSPI_CS_TIMING1				0x008
+#define QSPI_SETUP_HOLD(setup, hold)		(((setup) << 4) | (hold))
+
+#define QSPI_CS_TIMING2				0x00c
+#define CYCLES_BETWEEN_PACKETS_0(x)		(((x) & 0x1f) << 0)
+#define CS_ACTIVE_BETWEEN_PACKETS_0		BIT(5)
+
+#define QSPI_TRANS_STATUS			0x010
+#define QSPI_BLK_CNT(val)			(((val) >> 0) & 0xffff)
+#define QSPI_RDY				BIT(30)
+
+#define QSPI_FIFO_STATUS			0x014
+#define QSPI_RX_FIFO_EMPTY			BIT(0)
+#define QSPI_RX_FIFO_FULL			BIT(1)
+#define QSPI_TX_FIFO_EMPTY			BIT(2)
+#define QSPI_TX_FIFO_FULL			BIT(3)
+#define QSPI_RX_FIFO_UNF			BIT(4)
+#define QSPI_RX_FIFO_OVF			BIT(5)
+#define QSPI_TX_FIFO_UNF			BIT(6)
+#define QSPI_TX_FIFO_OVF			BIT(7)
+#define QSPI_ERR				BIT(8)
+#define QSPI_TX_FIFO_FLUSH			BIT(14)
+#define QSPI_RX_FIFO_FLUSH			BIT(15)
+#define QSPI_TX_FIFO_EMPTY_COUNT(val)		(((val) >> 16) & 0x7f)
+#define QSPI_RX_FIFO_FULL_COUNT(val)		(((val) >> 23) & 0x7f)
+
+#define QSPI_FIFO_ERROR				(QSPI_RX_FIFO_UNF | \
+						 QSPI_RX_FIFO_OVF | \
+						 QSPI_TX_FIFO_UNF | \
+						 QSPI_TX_FIFO_OVF)
+#define QSPI_FIFO_EMPTY				(QSPI_RX_FIFO_EMPTY | \
+						 QSPI_TX_FIFO_EMPTY)
+
+#define QSPI_TX_DATA				0x018
+#define QSPI_RX_DATA				0x01c
+
+#define QSPI_DMA_CTL				0x020
+#define QSPI_TX_TRIG(n)				(((n) & 0x3) << 15)
+#define QSPI_TX_TRIG_1				QSPI_TX_TRIG(0)
+#define QSPI_TX_TRIG_4				QSPI_TX_TRIG(1)
+#define QSPI_TX_TRIG_8				QSPI_TX_TRIG(2)
+#define QSPI_TX_TRIG_16				QSPI_TX_TRIG(3)
+
+#define QSPI_RX_TRIG(n)				(((n) & 0x3) << 19)
+#define QSPI_RX_TRIG_1				QSPI_RX_TRIG(0)
+#define QSPI_RX_TRIG_4				QSPI_RX_TRIG(1)
+#define QSPI_RX_TRIG_8				QSPI_RX_TRIG(2)
+#define QSPI_RX_TRIG_16				QSPI_RX_TRIG(3)
+
+#define QSPI_DMA_EN				BIT(31)
+
+#define QSPI_DMA_BLK				0x024
+#define QSPI_DMA_BLK_SET(x)			(((x) & 0xffff) << 0)
+
+#define QSPI_TX_FIFO				0x108
+#define QSPI_RX_FIFO				0x188
+
+#define QSPI_FIFO_DEPTH				64
+
+#define QSPI_INTR_MASK				0x18c
+#define QSPI_INTR_RX_FIFO_UNF_MASK		BIT(25)
+#define QSPI_INTR_RX_FIFO_OVF_MASK		BIT(26)
+#define QSPI_INTR_TX_FIFO_UNF_MASK		BIT(27)
+#define QSPI_INTR_TX_FIFO_OVF_MASK		BIT(28)
+#define QSPI_INTR_RDY_MASK			BIT(29)
+#define QSPI_INTR_RX_TX_FIFO_ERR		(QSPI_INTR_RX_FIFO_UNF_MASK | \
+						 QSPI_INTR_RX_FIFO_OVF_MASK | \
+						 QSPI_INTR_TX_FIFO_UNF_MASK | \
+						 QSPI_INTR_TX_FIFO_OVF_MASK)
+
+#define QSPI_MISC_REG                           0x194
+#define QSPI_NUM_DUMMY_CYCLE(x)			(((x) & 0xff) << 0)
+#define QSPI_DUMMY_CYCLES_MAX			0xff
+
+#define DATA_DIR_TX				BIT(0)
+#define DATA_DIR_RX				BIT(1)
+
+#define QSPI_DMA_TIMEOUT			(msecs_to_jiffies(1000))
+#define DEFAULT_QSPI_DMA_BUF_LEN		(64 * 1024)
+
+struct tegra_qspi_client_data {
+	int tx_clk_tap_delay;
+	int rx_clk_tap_delay;
+};
+
+struct tegra_qspi {
+	struct device				*dev;
+	struct spi_master			*master;
+	/* lock to protect data accessed by irq */
+	spinlock_t				lock;
+
+	struct clk				*clk;
+	struct reset_control			*rst;
+	void __iomem				*base;
+	phys_addr_t				phys;
+	unsigned int				irq;
+
+	u32					cur_speed;
+	unsigned int				cur_pos;
+	unsigned int				words_per_32bit;
+	unsigned int				bytes_per_word;
+	unsigned int				curr_dma_words;
+	unsigned int				cur_direction;
+
+	unsigned int				cur_rx_pos;
+	unsigned int				cur_tx_pos;
+
+	unsigned int				dma_buf_size;
+	unsigned int				max_buf_size;
+	bool					is_curr_dma_xfer;
+
+	struct completion			rx_dma_complete;
+	struct completion			tx_dma_complete;
+
+	u32					tx_status;
+	u32					rx_status;
+	u32					status_reg;
+	bool					is_packed;
+	bool					use_dma;
+
+	u32					command1_reg;
+	u32					dma_control_reg;
+	u32					def_command1_reg;
+	u32					def_command2_reg;
+	u32					spi_cs_timing1;
+	u32					spi_cs_timing2;
+	u8					dummy_cycles;
+
+	struct completion			xfer_completion;
+	struct spi_transfer			*curr_xfer;
+
+	struct dma_chan				*rx_dma_chan;
+	u32					*rx_dma_buf;
+	dma_addr_t				rx_dma_phys;
+	struct dma_async_tx_descriptor		*rx_dma_desc;
+
+	struct dma_chan				*tx_dma_chan;
+	u32					*tx_dma_buf;
+	dma_addr_t				tx_dma_phys;
+	struct dma_async_tx_descriptor		*tx_dma_desc;
+};
+
+static inline u32 tegra_qspi_readl(struct tegra_qspi *tqspi, unsigned long offset)
+{
+	return readl(tqspi->base + offset);
+}
+
+static inline void tegra_qspi_writel(struct tegra_qspi *tqspi, u32 value, unsigned long offset)
+{
+	writel(value, tqspi->base + offset);
+
+	/* read back register to make sure that register writes completed */
+	if (offset != QSPI_TX_FIFO)
+		readl(tqspi->base + QSPI_COMMAND1);
+}
+
+static void tegra_qspi_mask_clear_irq(struct tegra_qspi *tqspi)
+{
+	u32 value;
+
+	/* write 1 to clear status register */
+	value = tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS);
+	tegra_qspi_writel(tqspi, value, QSPI_TRANS_STATUS);
+
+	value = tegra_qspi_readl(tqspi, QSPI_INTR_MASK);
+	if (!(value & QSPI_INTR_RDY_MASK)) {
+		value |= (QSPI_INTR_RDY_MASK | QSPI_INTR_RX_TX_FIFO_ERR);
+		tegra_qspi_writel(tqspi, value, QSPI_INTR_MASK);
+	}
+
+	/* clear fifo status error if any */
+	value = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
+	if (value & QSPI_ERR)
+		tegra_qspi_writel(tqspi, QSPI_ERR | QSPI_FIFO_ERROR, QSPI_FIFO_STATUS);
+}
+
+static unsigned int
+tegra_qspi_calculate_curr_xfer_param(struct tegra_qspi *tqspi, struct spi_transfer *t)
+{
+	unsigned int max_word, max_len, total_fifo_words;
+	unsigned int remain_len = t->len - tqspi->cur_pos;
+	unsigned int bits_per_word = t->bits_per_word;
+
+	tqspi->bytes_per_word = DIV_ROUND_UP(bits_per_word, 8);
+
+	/*
+	 * Tegra QSPI controller supports packed or unpacked mode transfers.
+	 * Packed mode is used for data transfers using 8, 16, or 32 bits per
+	 * word with a minimum transfer of 1 word and for all other transfers
+	 * unpacked mode will be used.
+	 */
+
+	if ((bits_per_word == 8 || bits_per_word == 16 ||
+	     bits_per_word == 32) && t->len > 3) {
+		tqspi->is_packed = true;
+		tqspi->words_per_32bit = 32 / bits_per_word;
+	} else {
+		tqspi->is_packed = false;
+		tqspi->words_per_32bit = 1;
+	}
+
+	if (tqspi->is_packed) {
+		max_len = min(remain_len, tqspi->max_buf_size);
+		tqspi->curr_dma_words = max_len / tqspi->bytes_per_word;
+		total_fifo_words = (max_len + 3) / 4;
+	} else {
+		max_word = (remain_len - 1) / tqspi->bytes_per_word + 1;
+		max_word = min(max_word, tqspi->max_buf_size / 4);
+		tqspi->curr_dma_words = max_word;
+		total_fifo_words = max_word;
+	}
+
+	return total_fifo_words;
+}
+
+static unsigned int
+tegra_qspi_fill_tx_fifo_from_client_txbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
+{
+	unsigned int written_words, fifo_words_left, count;
+	unsigned int len, tx_empty_count, max_n_32bit, i;
+	u8 *tx_buf = (u8 *)t->tx_buf + tqspi->cur_tx_pos;
+	u32 fifo_status;
+
+	fifo_status = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
+	tx_empty_count = QSPI_TX_FIFO_EMPTY_COUNT(fifo_status);
+
+	if (tqspi->is_packed) {
+		fifo_words_left = tx_empty_count * tqspi->words_per_32bit;
+		written_words = min(fifo_words_left, tqspi->curr_dma_words);
+		len = written_words * tqspi->bytes_per_word;
+		max_n_32bit = DIV_ROUND_UP(len, 4);
+		for (count = 0; count < max_n_32bit; count++) {
+			u32 x = 0;
+
+			for (i = 0; (i < 4) && len; i++, len--)
+				x |= (u32)(*tx_buf++) << (i * 8);
+			tegra_qspi_writel(tqspi, x, QSPI_TX_FIFO);
+		}
+
+		tqspi->cur_tx_pos += written_words * tqspi->bytes_per_word;
+	} else {
+		unsigned int write_bytes;
+		u8 bytes_per_word = tqspi->bytes_per_word;
+
+		max_n_32bit = min(tqspi->curr_dma_words, tx_empty_count);
+		written_words = max_n_32bit;
+		len = written_words * tqspi->bytes_per_word;
+		if (len > t->len - tqspi->cur_pos)
+			len = t->len - tqspi->cur_pos;
+		write_bytes = len;
+		for (count = 0; count < max_n_32bit; count++) {
+			u32 x = 0;
+
+			for (i = 0; len && (i < bytes_per_word); i++, len--)
+				x |= (u32)(*tx_buf++) << (i * 8);
+			tegra_qspi_writel(tqspi, x, QSPI_TX_FIFO);
+		}
+
+		tqspi->cur_tx_pos += write_bytes;
+	}
+
+	return written_words;
+}
+
+static unsigned int
+tegra_qspi_read_rx_fifo_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
+{
+	u8 *rx_buf = (u8 *)t->rx_buf + tqspi->cur_rx_pos;
+	unsigned int len, rx_full_count, count, i;
+	unsigned int read_words = 0;
+	u32 fifo_status, x;
+
+	fifo_status = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
+	rx_full_count = QSPI_RX_FIFO_FULL_COUNT(fifo_status);
+	if (tqspi->is_packed) {
+		len = tqspi->curr_dma_words * tqspi->bytes_per_word;
+		for (count = 0; count < rx_full_count; count++) {
+			x = tegra_qspi_readl(tqspi, QSPI_RX_FIFO);
+
+			for (i = 0; len && (i < 4); i++, len--)
+				*rx_buf++ = (x >> i * 8) & 0xff;
+		}
+
+		read_words += tqspi->curr_dma_words;
+		tqspi->cur_rx_pos += tqspi->curr_dma_words * tqspi->bytes_per_word;
+	} else {
+		u32 rx_mask = ((u32)1 << t->bits_per_word) - 1;
+		u8 bytes_per_word = tqspi->bytes_per_word;
+		unsigned int read_bytes;
+
+		len = rx_full_count * bytes_per_word;
+		if (len > t->len - tqspi->cur_pos)
+			len = t->len - tqspi->cur_pos;
+		read_bytes = len;
+		for (count = 0; count < rx_full_count; count++) {
+			x = tegra_qspi_readl(tqspi, QSPI_RX_FIFO) & rx_mask;
+
+			for (i = 0; len && (i < bytes_per_word); i++, len--)
+				*rx_buf++ = (x >> (i * 8)) & 0xff;
+		}
+
+		read_words += rx_full_count;
+		tqspi->cur_rx_pos += read_bytes;
+	}
+
+	return read_words;
+}
+
+static void
+tegra_qspi_copy_client_txbuf_to_qspi_txbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
+{
+	dma_sync_single_for_cpu(tqspi->dev, tqspi->tx_dma_phys,
+				tqspi->dma_buf_size, DMA_TO_DEVICE);
+
+	/*
+	 * In packed mode, each word in FIFO may contain multiple packets
+	 * based on bits per word. So all bytes in each FIFO word are valid.
+	 *
+	 * In unpacked mode, each word in FIFO contains single packet and
+	 * based on bits per word any remaining bits in FIFO word will be
+	 * ignored by the hardware and are invalid bits.
+	 */
+	if (tqspi->is_packed) {
+		tqspi->cur_tx_pos += tqspi->curr_dma_words * tqspi->bytes_per_word;
+	} else {
+		u8 *tx_buf = (u8 *)t->tx_buf + tqspi->cur_tx_pos;
+		unsigned int i, count, consume, write_bytes;
+
+		/*
+		 * Fill tx_dma_buf to contain single packet in each word based
+		 * on bits per word from SPI core tx_buf.
+		 */
+		consume = tqspi->curr_dma_words * tqspi->bytes_per_word;
+		if (consume > t->len - tqspi->cur_pos)
+			consume = t->len - tqspi->cur_pos;
+		write_bytes = consume;
+		for (count = 0; count < tqspi->curr_dma_words; count++) {
+			u32 x = 0;
+
+			for (i = 0; consume && (i < tqspi->bytes_per_word); i++, consume--)
+				x |= (u32)(*tx_buf++) << (i * 8);
+			tqspi->tx_dma_buf[count] = x;
+		}
+
+		tqspi->cur_tx_pos += write_bytes;
+	}
+
+	dma_sync_single_for_device(tqspi->dev, tqspi->tx_dma_phys,
+				   tqspi->dma_buf_size, DMA_TO_DEVICE);
+}
+
+static void
+tegra_qspi_copy_qspi_rxbuf_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
+{
+	dma_sync_single_for_cpu(tqspi->dev, tqspi->rx_dma_phys,
+				tqspi->dma_buf_size, DMA_FROM_DEVICE);
+
+	if (tqspi->is_packed) {
+		tqspi->cur_rx_pos += tqspi->curr_dma_words * tqspi->bytes_per_word;
+	} else {
+		unsigned char *rx_buf = t->rx_buf + tqspi->cur_rx_pos;
+		u32 rx_mask = ((u32)1 << t->bits_per_word) - 1;
+		unsigned int i, count, consume, read_bytes;
+
+		/*
+		 * Each FIFO word contains single data packet.
+		 * Skip invalid bits in each FIFO word based on bits per word
+		 * and align bytes while filling in SPI core rx_buf.
+		 */
+		consume = tqspi->curr_dma_words * tqspi->bytes_per_word;
+		if (consume > t->len - tqspi->cur_pos)
+			consume = t->len - tqspi->cur_pos;
+		read_bytes = consume;
+		for (count = 0; count < tqspi->curr_dma_words; count++) {
+			u32 x = tqspi->rx_dma_buf[count] & rx_mask;
+
+			for (i = 0; consume && (i < tqspi->bytes_per_word); i++, consume--)
+				*rx_buf++ = (x >> (i * 8)) & 0xff;
+		}
+
+		tqspi->cur_rx_pos += read_bytes;
+	}
+
+	dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
+				   tqspi->dma_buf_size, DMA_FROM_DEVICE);
+}
+
+static void tegra_qspi_dma_complete(void *args)
+{
+	struct completion *dma_complete = args;
+
+	complete(dma_complete);
+}
+
+static int tegra_qspi_start_tx_dma(struct tegra_qspi *tqspi, struct spi_transfer *t, int len)
+{
+	dma_addr_t tx_dma_phys;
+
+	reinit_completion(&tqspi->tx_dma_complete);
+
+	if (tqspi->is_packed)
+		tx_dma_phys = t->tx_dma;
+	else
+		tx_dma_phys = tqspi->tx_dma_phys;
+
+	tqspi->tx_dma_desc = dmaengine_prep_slave_single(tqspi->tx_dma_chan, tx_dma_phys,
+							 len, DMA_MEM_TO_DEV,
+							 DMA_PREP_INTERRUPT |  DMA_CTRL_ACK);
+
+	if (!tqspi->tx_dma_desc) {
+		dev_err(tqspi->dev, "Unable to get TX descriptor\n");
+		return -EIO;
+	}
+
+	tqspi->tx_dma_desc->callback = tegra_qspi_dma_complete;
+	tqspi->tx_dma_desc->callback_param = &tqspi->tx_dma_complete;
+	dmaengine_submit(tqspi->tx_dma_desc);
+	dma_async_issue_pending(tqspi->tx_dma_chan);
+
+	return 0;
+}
+
+static int tegra_qspi_start_rx_dma(struct tegra_qspi *tqspi, struct spi_transfer *t, int len)
+{
+	dma_addr_t rx_dma_phys;
+
+	reinit_completion(&tqspi->rx_dma_complete);
+
+	if (tqspi->is_packed)
+		rx_dma_phys = t->rx_dma;
+	else
+		rx_dma_phys = tqspi->rx_dma_phys;
+
+	tqspi->rx_dma_desc = dmaengine_prep_slave_single(tqspi->rx_dma_chan, rx_dma_phys,
+							 len, DMA_DEV_TO_MEM,
+							 DMA_PREP_INTERRUPT |  DMA_CTRL_ACK);
+
+	if (!tqspi->rx_dma_desc) {
+		dev_err(tqspi->dev, "Unable to get RX descriptor\n");
+		return -EIO;
+	}
+
+	tqspi->rx_dma_desc->callback = tegra_qspi_dma_complete;
+	tqspi->rx_dma_desc->callback_param = &tqspi->rx_dma_complete;
+	dmaengine_submit(tqspi->rx_dma_desc);
+	dma_async_issue_pending(tqspi->rx_dma_chan);
+
+	return 0;
+}
+
+static int tegra_qspi_flush_fifos(struct tegra_qspi *tqspi, bool atomic)
+{
+	void __iomem *addr = tqspi->base + QSPI_FIFO_STATUS;
+	u32 val;
+
+	val = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
+	if ((val & QSPI_FIFO_EMPTY) == QSPI_FIFO_EMPTY)
+		return 0;
+
+	val |= QSPI_RX_FIFO_FLUSH | QSPI_TX_FIFO_FLUSH;
+	tegra_qspi_writel(tqspi, val, QSPI_FIFO_STATUS);
+
+	if (!atomic)
+		return readl_relaxed_poll_timeout(addr, val,
+						  (val & QSPI_FIFO_EMPTY) == QSPI_FIFO_EMPTY,
+						  1000, 1000000);
+
+	return readl_relaxed_poll_timeout_atomic(addr, val,
+						 (val & QSPI_FIFO_EMPTY) == QSPI_FIFO_EMPTY,
+						 1000, 1000000);
+}
+
+static void tegra_qspi_unmask_irq(struct tegra_qspi *tqspi)
+{
+	u32 intr_mask;
+
+	intr_mask = tegra_qspi_readl(tqspi, QSPI_INTR_MASK);
+	intr_mask &= ~(QSPI_INTR_RDY_MASK | QSPI_INTR_RX_TX_FIFO_ERR);
+	tegra_qspi_writel(tqspi, intr_mask, QSPI_INTR_MASK);
+}
+
+static int tegra_qspi_dma_map_xfer(struct tegra_qspi *tqspi, struct spi_transfer *t)
+{
+	u8 *tx_buf = (u8 *)t->tx_buf + tqspi->cur_tx_pos;
+	u8 *rx_buf = (u8 *)t->rx_buf + tqspi->cur_rx_pos;
+	unsigned int len;
+
+	len = DIV_ROUND_UP(tqspi->curr_dma_words * tqspi->bytes_per_word, 4) * 4;
+
+	if (t->tx_buf) {
+		t->tx_dma = dma_map_single(tqspi->dev, (void *)tx_buf, len, DMA_TO_DEVICE);
+		if (dma_mapping_error(tqspi->dev, t->tx_dma))
+			return -ENOMEM;
+	}
+
+	if (t->rx_buf) {
+		t->rx_dma = dma_map_single(tqspi->dev, (void *)rx_buf, len, DMA_FROM_DEVICE);
+		if (dma_mapping_error(tqspi->dev, t->rx_dma)) {
+			dma_unmap_single(tqspi->dev, t->tx_dma, len, DMA_TO_DEVICE);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static void tegra_qspi_dma_unmap_xfer(struct tegra_qspi *tqspi, struct spi_transfer *t)
+{
+	unsigned int len;
+
+	len = DIV_ROUND_UP(tqspi->curr_dma_words * tqspi->bytes_per_word, 4) * 4;
+
+	dma_unmap_single(tqspi->dev, t->tx_dma, len, DMA_TO_DEVICE);
+	dma_unmap_single(tqspi->dev, t->rx_dma, len, DMA_FROM_DEVICE);
+}
+
+static int tegra_qspi_start_dma_based_transfer(struct tegra_qspi *tqspi, struct spi_transfer *t)
+{
+	struct dma_slave_config dma_sconfig = { 0 };
+	unsigned int len;
+	u8 dma_burst;
+	int ret = 0;
+	u32 val;
+
+	if (tqspi->is_packed) {
+		ret = tegra_qspi_dma_map_xfer(tqspi, t);
+		if (ret < 0)
+			return ret;
+	}
+
+	val = QSPI_DMA_BLK_SET(tqspi->curr_dma_words - 1);
+	tegra_qspi_writel(tqspi, val, QSPI_DMA_BLK);
+
+	tegra_qspi_unmask_irq(tqspi);
+
+	if (tqspi->is_packed)
+		len = DIV_ROUND_UP(tqspi->curr_dma_words * tqspi->bytes_per_word, 4) * 4;
+	else
+		len = tqspi->curr_dma_words * 4;
+
+	/* set attention level based on length of transfer */
+	val = 0;
+	if (len & 0xf) {
+		val |= QSPI_TX_TRIG_1 | QSPI_RX_TRIG_1;
+		dma_burst = 1;
+	} else if (((len) >> 4) & 0x1) {
+		val |= QSPI_TX_TRIG_4 | QSPI_RX_TRIG_4;
+		dma_burst = 4;
+	} else {
+		val |= QSPI_TX_TRIG_8 | QSPI_RX_TRIG_8;
+		dma_burst = 8;
+	}
+
+	tegra_qspi_writel(tqspi, val, QSPI_DMA_CTL);
+	tqspi->dma_control_reg = val;
+
+	dma_sconfig.device_fc = true;
+	if (tqspi->cur_direction & DATA_DIR_TX) {
+		dma_sconfig.dst_addr = tqspi->phys + QSPI_TX_FIFO;
+		dma_sconfig.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_sconfig.dst_maxburst = dma_burst;
+		ret = dmaengine_slave_config(tqspi->tx_dma_chan, &dma_sconfig);
+		if (ret < 0) {
+			dev_err(tqspi->dev, "failed DMA slave config: %d\n", ret);
+			return ret;
+		}
+
+		tegra_qspi_copy_client_txbuf_to_qspi_txbuf(tqspi, t);
+		ret = tegra_qspi_start_tx_dma(tqspi, t, len);
+		if (ret < 0) {
+			dev_err(tqspi->dev, "failed to starting TX DMA: %d\n", ret);
+			return ret;
+		}
+	}
+
+	if (tqspi->cur_direction & DATA_DIR_RX) {
+		dma_sconfig.src_addr = tqspi->phys + QSPI_RX_FIFO;
+		dma_sconfig.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_sconfig.src_maxburst = dma_burst;
+		ret = dmaengine_slave_config(tqspi->rx_dma_chan, &dma_sconfig);
+		if (ret < 0) {
+			dev_err(tqspi->dev, "failed DMA slave config: %d\n", ret);
+			return ret;
+		}
+
+		dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
+					   tqspi->dma_buf_size,
+					   DMA_FROM_DEVICE);
+
+		ret = tegra_qspi_start_rx_dma(tqspi, t, len);
+		if (ret < 0) {
+			dev_err(tqspi->dev, "failed to start RX DMA: %d\n", ret);
+			if (tqspi->cur_direction & DATA_DIR_TX)
+				dmaengine_terminate_all(tqspi->tx_dma_chan);
+			return ret;
+		}
+	}
+
+	tegra_qspi_writel(tqspi, tqspi->command1_reg, QSPI_COMMAND1);
+
+	tqspi->is_curr_dma_xfer = true;
+	tqspi->dma_control_reg = val;
+	val |= QSPI_DMA_EN;
+	tegra_qspi_writel(tqspi, val, QSPI_DMA_CTL);
+
+	return ret;
+}
+
+static int tegra_qspi_start_cpu_based_transfer(struct tegra_qspi *qspi, struct spi_transfer *t)
+{
+	u32 val;
+	unsigned int cur_words;
+
+	if (qspi->cur_direction & DATA_DIR_TX)
+		cur_words = tegra_qspi_fill_tx_fifo_from_client_txbuf(qspi, t);
+	else
+		cur_words = qspi->curr_dma_words;
+
+	val = QSPI_DMA_BLK_SET(cur_words - 1);
+	tegra_qspi_writel(qspi, val, QSPI_DMA_BLK);
+
+	tegra_qspi_unmask_irq(qspi);
+
+	qspi->is_curr_dma_xfer = false;
+	val = qspi->command1_reg;
+	val |= QSPI_PIO;
+	tegra_qspi_writel(qspi, val, QSPI_COMMAND1);
+
+	return 0;
+}
+
+static void tegra_qspi_deinit_dma(struct tegra_qspi *tqspi)
+{
+	if (tqspi->tx_dma_buf) {
+		dma_free_coherent(tqspi->dev, tqspi->dma_buf_size,
+				  tqspi->tx_dma_buf, tqspi->tx_dma_phys);
+		tqspi->tx_dma_buf = NULL;
+	}
+
+	if (tqspi->tx_dma_chan) {
+		dma_release_channel(tqspi->tx_dma_chan);
+		tqspi->tx_dma_chan = NULL;
+	}
+
+	if (tqspi->rx_dma_buf) {
+		dma_free_coherent(tqspi->dev, tqspi->dma_buf_size,
+				  tqspi->rx_dma_buf, tqspi->rx_dma_phys);
+		tqspi->rx_dma_buf = NULL;
+	}
+
+	if (tqspi->rx_dma_chan) {
+		dma_release_channel(tqspi->rx_dma_chan);
+		tqspi->rx_dma_chan = NULL;
+	}
+}
+
+static int tegra_qspi_init_dma(struct tegra_qspi *tqspi)
+{
+	struct dma_chan *dma_chan;
+	dma_addr_t dma_phys;
+	u32 *dma_buf;
+	int err;
+
+	dma_chan = dma_request_chan(tqspi->dev, "rx");
+	if (IS_ERR(dma_chan)) {
+		err = PTR_ERR(dma_chan);
+		goto err_out;
+	}
+
+	tqspi->rx_dma_chan = dma_chan;
+
+	dma_buf = dma_alloc_coherent(tqspi->dev, tqspi->dma_buf_size, &dma_phys, GFP_KERNEL);
+	if (!dma_buf) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	tqspi->rx_dma_buf = dma_buf;
+	tqspi->rx_dma_phys = dma_phys;
+
+	dma_chan = dma_request_chan(tqspi->dev, "tx");
+	if (IS_ERR(dma_chan)) {
+		err = PTR_ERR(dma_chan);
+		goto err_out;
+	}
+
+	tqspi->tx_dma_chan = dma_chan;
+
+	dma_buf = dma_alloc_coherent(tqspi->dev, tqspi->dma_buf_size, &dma_phys, GFP_KERNEL);
+	if (!dma_buf) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	tqspi->tx_dma_buf = dma_buf;
+	tqspi->tx_dma_phys = dma_phys;
+	tqspi->use_dma = true;
+
+	return 0;
+
+err_out:
+	tegra_qspi_deinit_dma(tqspi);
+
+	if (err != -EPROBE_DEFER) {
+		dev_err(tqspi->dev, "cannot use DMA: %d\n", err);
+		dev_err(tqspi->dev, "falling back to PIO\n");
+		return 0;
+	}
+
+	return err;
+}
+
+static u32 tegra_qspi_setup_transfer_one(struct spi_device *spi, struct spi_transfer *t,
+					 bool is_first_of_msg)
+{
+	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	struct tegra_qspi_client_data *cdata = spi->controller_data;
+	u32 command1, command2, speed = t->speed_hz;
+	u8 bits_per_word = t->bits_per_word;
+	u32 tx_tap = 0, rx_tap = 0;
+	int req_mode;
+
+	if (speed != tqspi->cur_speed) {
+		clk_set_rate(tqspi->clk, speed);
+		tqspi->cur_speed = speed;
+	}
+
+	tqspi->cur_pos = 0;
+	tqspi->cur_rx_pos = 0;
+	tqspi->cur_tx_pos = 0;
+	tqspi->curr_xfer = t;
+
+	if (is_first_of_msg) {
+		tegra_qspi_mask_clear_irq(tqspi);
+
+		command1 = tqspi->def_command1_reg;
+		command1 |= QSPI_BIT_LENGTH(bits_per_word - 1);
+
+		command1 &= ~QSPI_CONTROL_MODE_MASK;
+		req_mode = spi->mode & 0x3;
+		if (req_mode == SPI_MODE_3)
+			command1 |= QSPI_CONTROL_MODE_3;
+		else
+			command1 |= QSPI_CONTROL_MODE_0;
+
+		if (spi->mode & SPI_CS_HIGH)
+			command1 |= QSPI_CS_SW_VAL;
+		else
+			command1 &= ~QSPI_CS_SW_VAL;
+		tegra_qspi_writel(tqspi, command1, QSPI_COMMAND1);
+
+		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 = QSPI_TX_TAP_DELAY(tx_tap) | QSPI_RX_TAP_DELAY(rx_tap);
+		if (command2 != tqspi->def_command2_reg)
+			tegra_qspi_writel(tqspi, command2, QSPI_COMMAND2);
+
+	} else {
+		command1 = tqspi->command1_reg;
+		command1 &= ~QSPI_BIT_LENGTH(~0);
+		command1 |= QSPI_BIT_LENGTH(bits_per_word - 1);
+	}
+
+	command1 &= ~QSPI_SDR_DDR_SEL;
+
+	return command1;
+}
+
+static int tegra_qspi_start_transfer_one(struct spi_device *spi,
+					 struct spi_transfer *t, u32 command1)
+{
+	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	unsigned int total_fifo_words;
+	u8 bus_width = 0;
+	int ret;
+
+	total_fifo_words = tegra_qspi_calculate_curr_xfer_param(tqspi, t);
+
+	command1 &= ~QSPI_PACKED;
+	if (tqspi->is_packed)
+		command1 |= QSPI_PACKED;
+	tegra_qspi_writel(tqspi, command1, QSPI_COMMAND1);
+
+	tqspi->cur_direction = 0;
+
+	command1 &= ~(QSPI_TX_EN | QSPI_RX_EN);
+	if (t->rx_buf) {
+		command1 |= QSPI_RX_EN;
+		tqspi->cur_direction |= DATA_DIR_RX;
+		bus_width = t->rx_nbits;
+	}
+
+	if (t->tx_buf) {
+		command1 |= QSPI_TX_EN;
+		tqspi->cur_direction |= DATA_DIR_TX;
+		bus_width = t->tx_nbits;
+	}
+
+	command1 &= ~QSPI_INTERFACE_WIDTH_MASK;
+
+	if (bus_width == SPI_NBITS_QUAD)
+		command1 |= QSPI_INTERFACE_WIDTH_QUAD;
+	else if (bus_width == SPI_NBITS_DUAL)
+		command1 |= QSPI_INTERFACE_WIDTH_DUAL;
+	else
+		command1 |= QSPI_INTERFACE_WIDTH_SINGLE;
+
+	tqspi->command1_reg = command1;
+
+	tegra_qspi_writel(tqspi, QSPI_NUM_DUMMY_CYCLE(tqspi->dummy_cycles), QSPI_MISC_REG);
+
+	ret = tegra_qspi_flush_fifos(tqspi, false);
+	if (ret < 0)
+		return ret;
+
+	if (tqspi->use_dma && total_fifo_words > QSPI_FIFO_DEPTH)
+		ret = tegra_qspi_start_dma_based_transfer(tqspi, t);
+	else
+		ret = tegra_qspi_start_cpu_based_transfer(tqspi, t);
+
+	return ret;
+}
+
+static struct tegra_qspi_client_data *tegra_qspi_parse_cdata_dt(struct spi_device *spi)
+{
+	struct tegra_qspi_client_data *cdata;
+	struct device_node *slave_np = spi->dev.of_node;
+
+	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_qspi_cleanup(struct spi_device *spi)
+{
+	struct tegra_qspi_client_data *cdata = spi->controller_data;
+
+	spi->controller_data = NULL;
+	kfree(cdata);
+}
+
+static int tegra_qspi_setup(struct spi_device *spi)
+{
+	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	struct tegra_qspi_client_data *cdata = spi->controller_data;
+	unsigned long flags;
+	u32 val;
+	int ret;
+
+	ret = pm_runtime_resume_and_get(tqspi->dev);
+	if (ret < 0) {
+		dev_err(tqspi->dev, "failed to get runtime PM: %d\n", ret);
+		return ret;
+	}
+
+	if (!cdata) {
+		cdata = tegra_qspi_parse_cdata_dt(spi);
+		spi->controller_data = cdata;
+	}
+
+	spin_lock_irqsave(&tqspi->lock, flags);
+
+	/* keep default cs state to inactive */
+	val = tqspi->def_command1_reg;
+	if (spi->mode & SPI_CS_HIGH)
+		val &= ~QSPI_CS_SW_VAL;
+	else
+		val |= QSPI_CS_SW_VAL;
+
+	tqspi->def_command1_reg = val;
+	tegra_qspi_writel(tqspi, tqspi->def_command1_reg, QSPI_COMMAND1);
+
+	spin_unlock_irqrestore(&tqspi->lock, flags);
+
+	pm_runtime_put(tqspi->dev);
+
+	return 0;
+}
+
+static void tegra_qspi_dump_regs(struct tegra_qspi *tqspi)
+{
+	dev_dbg(tqspi->dev, "============ QSPI REGISTER DUMP ============\n");
+	dev_dbg(tqspi->dev, "Command1:    0x%08x | Command2:    0x%08x\n",
+		tegra_qspi_readl(tqspi, QSPI_COMMAND1),
+		tegra_qspi_readl(tqspi, QSPI_COMMAND2));
+	dev_dbg(tqspi->dev, "DMA_CTL:     0x%08x | DMA_BLK:     0x%08x\n",
+		tegra_qspi_readl(tqspi, QSPI_DMA_CTL),
+		tegra_qspi_readl(tqspi, QSPI_DMA_BLK));
+	dev_dbg(tqspi->dev, "INTR_MASK:  0x%08x | MISC: 0x%08x\n",
+		tegra_qspi_readl(tqspi, QSPI_INTR_MASK),
+		tegra_qspi_readl(tqspi, QSPI_MISC_REG));
+	dev_dbg(tqspi->dev, "TRANS_STAT:  0x%08x | FIFO_STATUS: 0x%08x\n",
+		tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS),
+		tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS));
+}
+
+static void tegra_qspi_handle_error(struct tegra_qspi *tqspi)
+{
+	dev_err(tqspi->dev, "error in transfer, fifo status 0x%08x\n", tqspi->status_reg);
+	tegra_qspi_dump_regs(tqspi);
+	tegra_qspi_flush_fifos(tqspi, true);
+	reset_control_assert(tqspi->rst);
+	udelay(2);
+	reset_control_deassert(tqspi->rst);
+}
+
+static void tegra_qspi_transfer_end(struct spi_device *spi)
+{
+	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
+	int cs_val = (spi->mode & SPI_CS_HIGH) ? 0 : 1;
+
+	if (cs_val)
+		tqspi->command1_reg |= QSPI_CS_SW_VAL;
+	else
+		tqspi->command1_reg &= ~QSPI_CS_SW_VAL;
+	tegra_qspi_writel(tqspi, tqspi->command1_reg, QSPI_COMMAND1);
+	tegra_qspi_writel(tqspi, tqspi->def_command1_reg, QSPI_COMMAND1);
+}
+
+static int tegra_qspi_transfer_one_message(struct spi_master *master, struct spi_message *msg)
+{
+	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+	struct spi_device *spi = msg->spi;
+	struct spi_transfer *transfer;
+	bool is_first_msg = true;
+	int ret;
+
+	msg->status = 0;
+	msg->actual_length = 0;
+	tqspi->tx_status = 0;
+	tqspi->rx_status = 0;
+
+	list_for_each_entry(transfer, &msg->transfers, transfer_list) {
+		struct spi_transfer *xfer = transfer;
+		u8 dummy_bytes = 0;
+		u32 cmd1;
+
+		tqspi->dummy_cycles = 0;
+		/*
+		 * Tegra QSPI hardware supports dummy bytes transfer after actual transfer
+		 * bytes based on programmed dummy clock cycles in the QSPI_MISC register.
+		 * So, check if the next transfer is dummy data transfer and program dummy
+		 * clock cycles along with the current transfer and skip next transfer.
+		 */
+		if (!list_is_last(&xfer->transfer_list, &msg->transfers)) {
+			struct spi_transfer *next_xfer;
+
+			next_xfer = list_next_entry(xfer, transfer_list);
+			if (next_xfer->dummy_data) {
+				u32 dummy_cycles = next_xfer->len * 8 / next_xfer->tx_nbits;
+
+				if (dummy_cycles <= QSPI_DUMMY_CYCLES_MAX) {
+					tqspi->dummy_cycles = dummy_cycles;
+					dummy_bytes = next_xfer->len;
+					transfer = next_xfer;
+				}
+			}
+		}
+
+		reinit_completion(&tqspi->xfer_completion);
+
+		cmd1 = tegra_qspi_setup_transfer_one(spi, xfer, is_first_msg);
+
+		ret = tegra_qspi_start_transfer_one(spi, xfer, cmd1);
+		if (ret < 0) {
+			dev_err(tqspi->dev, "failed to start transfer: %d\n", ret);
+			goto complete_xfer;
+		}
+
+		is_first_msg = false;
+		ret = wait_for_completion_timeout(&tqspi->xfer_completion,
+						  QSPI_DMA_TIMEOUT);
+		if (WARN_ON(ret == 0)) {
+			dev_err(tqspi->dev, "transfer timeout: %d\n", ret);
+			if (tqspi->is_curr_dma_xfer && (tqspi->cur_direction & DATA_DIR_TX))
+				dmaengine_terminate_all(tqspi->tx_dma_chan);
+			if (tqspi->is_curr_dma_xfer && (tqspi->cur_direction & DATA_DIR_RX))
+				dmaengine_terminate_all(tqspi->rx_dma_chan);
+			tegra_qspi_handle_error(tqspi);
+			ret = -EIO;
+			goto complete_xfer;
+		}
+
+		if (tqspi->tx_status ||  tqspi->rx_status) {
+			tegra_qspi_handle_error(tqspi);
+			ret = -EIO;
+			goto complete_xfer;
+		}
+
+		msg->actual_length += xfer->len + dummy_bytes;
+
+complete_xfer:
+		if (ret < 0) {
+			tegra_qspi_transfer_end(spi);
+			spi_transfer_delay_exec(xfer);
+			goto exit;
+		}
+
+		if (list_is_last(&xfer->transfer_list, &msg->transfers)) {
+			/* de-activate CS after last transfer only when cs_change is not set */
+			if (!xfer->cs_change) {
+				tegra_qspi_transfer_end(spi);
+				spi_transfer_delay_exec(xfer);
+			}
+		} else if (xfer->cs_change) {
+			 /* de-activated CS between the transfers only when cs_change is set */
+			tegra_qspi_transfer_end(spi);
+			spi_transfer_delay_exec(xfer);
+		}
+	}
+
+	ret = 0;
+exit:
+	msg->status = ret;
+	spi_finalize_current_message(master);
+	return ret;
+}
+
+static irqreturn_t handle_cpu_based_xfer(struct tegra_qspi *tqspi)
+{
+	struct spi_transfer *t = tqspi->curr_xfer;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tqspi->lock, flags);
+
+	if (tqspi->tx_status ||  tqspi->rx_status) {
+		tegra_qspi_handle_error(tqspi);
+		complete(&tqspi->xfer_completion);
+		goto exit;
+	}
+
+	if (tqspi->cur_direction & DATA_DIR_RX)
+		tegra_qspi_read_rx_fifo_to_client_rxbuf(tqspi, t);
+
+	if (tqspi->cur_direction & DATA_DIR_TX)
+		tqspi->cur_pos = tqspi->cur_tx_pos;
+	else
+		tqspi->cur_pos = tqspi->cur_rx_pos;
+
+	if (tqspi->cur_pos == t->len) {
+		complete(&tqspi->xfer_completion);
+		goto exit;
+	}
+
+	tegra_qspi_calculate_curr_xfer_param(tqspi, t);
+	tegra_qspi_start_cpu_based_transfer(tqspi, t);
+exit:
+	spin_unlock_irqrestore(&tqspi->lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t handle_dma_based_xfer(struct tegra_qspi *tqspi)
+{
+	struct spi_transfer *t = tqspi->curr_xfer;
+	unsigned int total_fifo_words;
+	unsigned long flags;
+	long wait_status;
+	int err = 0;
+
+	if (tqspi->cur_direction & DATA_DIR_TX) {
+		if (tqspi->tx_status) {
+			dmaengine_terminate_all(tqspi->tx_dma_chan);
+			err += 1;
+		} else {
+			wait_status = wait_for_completion_interruptible_timeout(
+				&tqspi->tx_dma_complete, QSPI_DMA_TIMEOUT);
+			if (wait_status <= 0) {
+				dmaengine_terminate_all(tqspi->tx_dma_chan);
+				dev_err(tqspi->dev, "failed TX DMA transfer\n");
+				err += 1;
+			}
+		}
+	}
+
+	if (tqspi->cur_direction & DATA_DIR_RX) {
+		if (tqspi->rx_status) {
+			dmaengine_terminate_all(tqspi->rx_dma_chan);
+			err += 2;
+		} else {
+			wait_status = wait_for_completion_interruptible_timeout(
+				&tqspi->rx_dma_complete, QSPI_DMA_TIMEOUT);
+			if (wait_status <= 0) {
+				dmaengine_terminate_all(tqspi->rx_dma_chan);
+				dev_err(tqspi->dev, "failed RX DMA transfer\n");
+				err += 2;
+			}
+		}
+	}
+
+	spin_lock_irqsave(&tqspi->lock, flags);
+
+	if (err) {
+		tegra_qspi_dma_unmap_xfer(tqspi, t);
+		tegra_qspi_handle_error(tqspi);
+		complete(&tqspi->xfer_completion);
+		goto exit;
+	}
+
+	if (tqspi->cur_direction & DATA_DIR_RX)
+		tegra_qspi_copy_qspi_rxbuf_to_client_rxbuf(tqspi, t);
+
+	if (tqspi->cur_direction & DATA_DIR_TX)
+		tqspi->cur_pos = tqspi->cur_tx_pos;
+	else
+		tqspi->cur_pos = tqspi->cur_rx_pos;
+
+	if (tqspi->cur_pos == t->len) {
+		tegra_qspi_dma_unmap_xfer(tqspi, t);
+		complete(&tqspi->xfer_completion);
+		goto exit;
+	}
+
+	tegra_qspi_dma_unmap_xfer(tqspi, t);
+
+	/* continue transfer in current message */
+	total_fifo_words = tegra_qspi_calculate_curr_xfer_param(tqspi, t);
+	if (total_fifo_words > QSPI_FIFO_DEPTH)
+		err = tegra_qspi_start_dma_based_transfer(tqspi, t);
+	else
+		err = tegra_qspi_start_cpu_based_transfer(tqspi, t);
+
+exit:
+	spin_unlock_irqrestore(&tqspi->lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t tegra_qspi_isr_thread(int irq, void *context_data)
+{
+	struct tegra_qspi *tqspi = context_data;
+
+	tqspi->status_reg = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
+
+	if (tqspi->cur_direction & DATA_DIR_TX)
+		tqspi->tx_status = tqspi->status_reg & (QSPI_TX_FIFO_UNF | QSPI_TX_FIFO_OVF);
+
+	if (tqspi->cur_direction & DATA_DIR_RX)
+		tqspi->rx_status = tqspi->status_reg & (QSPI_RX_FIFO_OVF | QSPI_RX_FIFO_UNF);
+
+	tegra_qspi_mask_clear_irq(tqspi);
+
+	if (!tqspi->is_curr_dma_xfer)
+		return handle_cpu_based_xfer(tqspi);
+
+	return handle_dma_based_xfer(tqspi);
+}
+
+static const struct of_device_id tegra_qspi_of_match[] = {
+	{ .compatible = "nvidia,tegra210-qspi", },
+	{ .compatible = "nvidia,tegra186-qspi", },
+	{ .compatible = "nvidia,tegra194-qspi", },
+	{}
+};
+
+MODULE_DEVICE_TABLE(of, tegra_qspi_of_match);
+
+static int tegra_qspi_probe(struct platform_device *pdev)
+{
+	struct spi_master	*master;
+	struct tegra_qspi	*tqspi;
+	struct resource		*r;
+	int ret, qspi_irq;
+	int bus_num;
+
+	master = devm_spi_alloc_master(&pdev->dev, sizeof(*tqspi));
+	if (!master)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, master);
+	tqspi = spi_master_get_devdata(master);
+
+	master->mode_bits = SPI_MODE_0 | SPI_MODE_3 | SPI_CS_HIGH |
+			    SPI_TX_DUAL | SPI_RX_DUAL | SPI_TX_QUAD | SPI_RX_QUAD;
+	master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
+	master->setup = tegra_qspi_setup;
+	master->cleanup = tegra_qspi_cleanup;
+	master->transfer_one_message = tegra_qspi_transfer_one_message;
+	master->num_chipselect = 1;
+	master->auto_runtime_pm = true;
+
+	bus_num = of_alias_get_id(pdev->dev.of_node, "spi");
+	if (bus_num >= 0)
+		master->bus_num = bus_num;
+
+	tqspi->master = master;
+	tqspi->dev = &pdev->dev;
+	spin_lock_init(&tqspi->lock);
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	tqspi->base = devm_ioremap_resource(&pdev->dev, r);
+	if (IS_ERR(tqspi->base))
+		return PTR_ERR(tqspi->base);
+
+	tqspi->phys = r->start;
+	qspi_irq = platform_get_irq(pdev, 0);
+	tqspi->irq = qspi_irq;
+
+	tqspi->clk = devm_clk_get(&pdev->dev, "qspi");
+	if (IS_ERR(tqspi->clk)) {
+		ret = PTR_ERR(tqspi->clk);
+		dev_err(&pdev->dev, "failed to get clock: %d\n", ret);
+		return ret;
+	}
+
+	tqspi->rst = devm_reset_control_get_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(tqspi->rst)) {
+		ret = PTR_ERR(tqspi->rst);
+		dev_err(&pdev->dev, "failed to get reset control: %d\n", ret);
+		return ret;
+	}
+
+	tqspi->max_buf_size = QSPI_FIFO_DEPTH << 2;
+	tqspi->dma_buf_size = DEFAULT_QSPI_DMA_BUF_LEN;
+
+	ret = tegra_qspi_init_dma(tqspi);
+	if (ret < 0)
+		return ret;
+
+	if (tqspi->use_dma)
+		tqspi->max_buf_size = tqspi->dma_buf_size;
+
+	init_completion(&tqspi->tx_dma_complete);
+	init_completion(&tqspi->rx_dma_complete);
+	init_completion(&tqspi->xfer_completion);
+
+	pm_runtime_enable(&pdev->dev);
+	ret = pm_runtime_resume_and_get(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to get runtime PM: %d\n", ret);
+		goto exit_pm_disable;
+	}
+
+	reset_control_assert(tqspi->rst);
+	udelay(2);
+	reset_control_deassert(tqspi->rst);
+
+	tqspi->def_command1_reg = QSPI_M_S | QSPI_CS_SW_HW |  QSPI_CS_SW_VAL;
+	tegra_qspi_writel(tqspi, tqspi->def_command1_reg, QSPI_COMMAND1);
+	tqspi->spi_cs_timing1 = tegra_qspi_readl(tqspi, QSPI_CS_TIMING1);
+	tqspi->spi_cs_timing2 = tegra_qspi_readl(tqspi, QSPI_CS_TIMING2);
+	tqspi->def_command2_reg = tegra_qspi_readl(tqspi, QSPI_COMMAND2);
+
+	pm_runtime_put(&pdev->dev);
+
+	ret = request_threaded_irq(tqspi->irq, NULL,
+				   tegra_qspi_isr_thread, IRQF_ONESHOT,
+				   dev_name(&pdev->dev), tqspi);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n", tqspi->irq, ret);
+		goto exit_pm_disable;
+	}
+
+	master->dev.of_node = pdev->dev.of_node;
+	ret = spi_register_master(master);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to register master: %d\n", ret);
+		goto exit_free_irq;
+	}
+
+	return 0;
+
+exit_free_irq:
+	free_irq(qspi_irq, tqspi);
+exit_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+	tegra_qspi_deinit_dma(tqspi);
+	return ret;
+}
+
+static int tegra_qspi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+
+	spi_unregister_master(master);
+	free_irq(tqspi->irq, tqspi);
+	pm_runtime_disable(&pdev->dev);
+	tegra_qspi_deinit_dma(tqspi);
+
+	return 0;
+}
+
+static int __maybe_unused tegra_qspi_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+
+	return spi_master_suspend(master);
+}
+
+static int __maybe_unused tegra_qspi_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = pm_runtime_resume_and_get(dev);
+	if (ret < 0) {
+		dev_err(dev, "failed to get runtime PM: %d\n", ret);
+		return ret;
+	}
+
+	tegra_qspi_writel(tqspi, tqspi->command1_reg, QSPI_COMMAND1);
+	tegra_qspi_writel(tqspi, tqspi->def_command2_reg, QSPI_COMMAND2);
+	pm_runtime_put(dev);
+
+	return spi_master_resume(master);
+}
+
+static int __maybe_unused tegra_qspi_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+
+	/* flush all write which are in PPSB queue by reading back */
+	tegra_qspi_readl(tqspi, QSPI_COMMAND1);
+
+	clk_disable_unprepare(tqspi->clk);
+
+	return 0;
+}
+
+static int __maybe_unused tegra_qspi_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = clk_prepare_enable(tqspi->clk);
+	if (ret < 0)
+		dev_err(tqspi->dev, "failed to enable clock: %d\n", ret);
+
+	return ret;
+}
+
+static const struct dev_pm_ops tegra_qspi_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_qspi_runtime_suspend, tegra_qspi_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(tegra_qspi_suspend, tegra_qspi_resume)
+};
+
+static struct platform_driver tegra_qspi_driver = {
+	.driver = {
+		.name		= "tegra-qspi",
+		.pm		= &tegra_qspi_pm_ops,
+		.of_match_table	= tegra_qspi_of_match,
+	},
+	.probe =	tegra_qspi_probe,
+	.remove =	tegra_qspi_remove,
+};
+module_platform_driver(tegra_qspi_driver);
+
+MODULE_ALIAS("platform:qspi-tegra");
+MODULE_DESCRIPTION("NVIDIA Tegra QSPI Controller Driver");
+MODULE_AUTHOR("Sowjanya Komatineni <skomatineni@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-txx9.c b/drivers/spi/spi-txx9.c
deleted file mode 100644
index 3606232f190f..000000000000
--- a/drivers/spi/spi-txx9.c
+++ /dev/null
@@ -1,477 +0,0 @@
-/*
- * TXx9 SPI controller driver.
- *
- * Based on linux/arch/mips/tx4938/toshiba_rbtx4938/spi_txx9.c
- * Copyright (C) 2000-2001 Toshiba Corporation
- *
- * 2003-2005 (c) MontaVista Software, Inc. This file is licensed under the
- * terms of the GNU General Public License version 2. This program is
- * licensed "as is" without any warranty of any kind, whether express
- * or implied.
- *
- * Support for TX4938 in 2.6 - Manish Lachwani (mlachwani@mvista.com)
- *
- * Convert to generic SPI framework - Atsushi Nemoto (anemo@mba.ocn.ne.jp)
- */
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <linux/errno.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/sched.h>
-#include <linux/spinlock.h>
-#include <linux/workqueue.h>
-#include <linux/spi/spi.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/module.h>
-#include <linux/gpio/machine.h>
-#include <linux/gpio/consumer.h>
-
-
-#define SPI_FIFO_SIZE 4
-#define SPI_MAX_DIVIDER 0xff	/* Max. value for SPCR1.SER */
-#define SPI_MIN_DIVIDER 1	/* Min. value for SPCR1.SER */
-
-#define TXx9_SPMCR		0x00
-#define TXx9_SPCR0		0x04
-#define TXx9_SPCR1		0x08
-#define TXx9_SPFS		0x0c
-#define TXx9_SPSR		0x14
-#define TXx9_SPDR		0x18
-
-/* SPMCR : SPI Master Control */
-#define TXx9_SPMCR_OPMODE	0xc0
-#define TXx9_SPMCR_CONFIG	0x40
-#define TXx9_SPMCR_ACTIVE	0x80
-#define TXx9_SPMCR_SPSTP	0x02
-#define TXx9_SPMCR_BCLR		0x01
-
-/* SPCR0 : SPI Control 0 */
-#define TXx9_SPCR0_TXIFL_MASK	0xc000
-#define TXx9_SPCR0_RXIFL_MASK	0x3000
-#define TXx9_SPCR0_SIDIE	0x0800
-#define TXx9_SPCR0_SOEIE	0x0400
-#define TXx9_SPCR0_RBSIE	0x0200
-#define TXx9_SPCR0_TBSIE	0x0100
-#define TXx9_SPCR0_IFSPSE	0x0010
-#define TXx9_SPCR0_SBOS		0x0004
-#define TXx9_SPCR0_SPHA		0x0002
-#define TXx9_SPCR0_SPOL		0x0001
-
-/* SPSR : SPI Status */
-#define TXx9_SPSR_TBSI		0x8000
-#define TXx9_SPSR_RBSI		0x4000
-#define TXx9_SPSR_TBS_MASK	0x3800
-#define TXx9_SPSR_RBS_MASK	0x0700
-#define TXx9_SPSR_SPOE		0x0080
-#define TXx9_SPSR_IFSD		0x0008
-#define TXx9_SPSR_SIDLE		0x0004
-#define TXx9_SPSR_STRDY		0x0002
-#define TXx9_SPSR_SRRDY		0x0001
-
-
-struct txx9spi {
-	struct work_struct work;
-	spinlock_t lock;	/* protect 'queue' */
-	struct list_head queue;
-	wait_queue_head_t waitq;
-	void __iomem *membase;
-	int baseclk;
-	struct clk *clk;
-	struct gpio_desc *last_chipselect;
-	int last_chipselect_val;
-};
-
-static u32 txx9spi_rd(struct txx9spi *c, int reg)
-{
-	return __raw_readl(c->membase + reg);
-}
-static void txx9spi_wr(struct txx9spi *c, u32 val, int reg)
-{
-	__raw_writel(val, c->membase + reg);
-}
-
-static void txx9spi_cs_func(struct spi_device *spi, struct txx9spi *c,
-		int on, unsigned int cs_delay)
-{
-	/*
-	 * The GPIO descriptor will track polarity inversion inside
-	 * gpiolib.
-	 */
-	if (on) {
-		/* deselect the chip with cs_change hint in last transfer */
-		if (c->last_chipselect)
-			gpiod_set_value(c->last_chipselect,
-					!c->last_chipselect_val);
-		c->last_chipselect = spi->cs_gpiod;
-		c->last_chipselect_val = on;
-	} else {
-		c->last_chipselect = NULL;
-		ndelay(cs_delay);	/* CS Hold Time */
-	}
-	gpiod_set_value(spi->cs_gpiod, on);
-	ndelay(cs_delay);	/* CS Setup Time / CS Recovery Time */
-}
-
-static int txx9spi_setup(struct spi_device *spi)
-{
-	struct txx9spi *c = spi_master_get_devdata(spi->master);
-
-	if (!spi->max_speed_hz)
-		return -EINVAL;
-
-	/* deselect chip */
-	spin_lock(&c->lock);
-	txx9spi_cs_func(spi, c, 0, (NSEC_PER_SEC / 2) / spi->max_speed_hz);
-	spin_unlock(&c->lock);
-
-	return 0;
-}
-
-static irqreturn_t txx9spi_interrupt(int irq, void *dev_id)
-{
-	struct txx9spi *c = dev_id;
-
-	/* disable rx intr */
-	txx9spi_wr(c, txx9spi_rd(c, TXx9_SPCR0) & ~TXx9_SPCR0_RBSIE,
-			TXx9_SPCR0);
-	wake_up(&c->waitq);
-	return IRQ_HANDLED;
-}
-
-static void txx9spi_work_one(struct txx9spi *c, struct spi_message *m)
-{
-	struct spi_device *spi = m->spi;
-	struct spi_transfer *t;
-	unsigned int cs_delay;
-	unsigned int cs_change = 1;
-	int status = 0;
-	u32 mcr;
-	u32 prev_speed_hz = 0;
-	u8 prev_bits_per_word = 0;
-
-	/* CS setup/hold/recovery time in nsec */
-	cs_delay = 100 + (NSEC_PER_SEC / 2) / spi->max_speed_hz;
-
-	mcr = txx9spi_rd(c, TXx9_SPMCR);
-	if (unlikely((mcr & TXx9_SPMCR_OPMODE) == TXx9_SPMCR_ACTIVE)) {
-		dev_err(&spi->dev, "Bad mode.\n");
-		status = -EIO;
-		goto exit;
-	}
-	mcr &= ~(TXx9_SPMCR_OPMODE | TXx9_SPMCR_SPSTP | TXx9_SPMCR_BCLR);
-
-	/* enter config mode */
-	txx9spi_wr(c, mcr | TXx9_SPMCR_CONFIG | TXx9_SPMCR_BCLR, TXx9_SPMCR);
-	txx9spi_wr(c, TXx9_SPCR0_SBOS
-			| ((spi->mode & SPI_CPOL) ? TXx9_SPCR0_SPOL : 0)
-			| ((spi->mode & SPI_CPHA) ? TXx9_SPCR0_SPHA : 0)
-			| 0x08,
-			TXx9_SPCR0);
-
-	list_for_each_entry(t, &m->transfers, transfer_list) {
-		const void *txbuf = t->tx_buf;
-		void *rxbuf = t->rx_buf;
-		u32 data;
-		unsigned int len = t->len;
-		unsigned int wsize;
-		u32 speed_hz = t->speed_hz;
-		u8 bits_per_word = t->bits_per_word;
-
-		wsize = bits_per_word >> 3; /* in bytes */
-
-		if (prev_speed_hz != speed_hz
-				|| prev_bits_per_word != bits_per_word) {
-			int n = DIV_ROUND_UP(c->baseclk, speed_hz) - 1;
-
-			n = clamp(n, SPI_MIN_DIVIDER, SPI_MAX_DIVIDER);
-			/* enter config mode */
-			txx9spi_wr(c, mcr | TXx9_SPMCR_CONFIG | TXx9_SPMCR_BCLR,
-					TXx9_SPMCR);
-			txx9spi_wr(c, (n << 8) | bits_per_word, TXx9_SPCR1);
-			/* enter active mode */
-			txx9spi_wr(c, mcr | TXx9_SPMCR_ACTIVE, TXx9_SPMCR);
-
-			prev_speed_hz = speed_hz;
-			prev_bits_per_word = bits_per_word;
-		}
-
-		if (cs_change)
-			txx9spi_cs_func(spi, c, 1, cs_delay);
-		cs_change = t->cs_change;
-		while (len) {
-			unsigned int count = SPI_FIFO_SIZE;
-			int i;
-			u32 cr0;
-
-			if (len < count * wsize)
-				count = len / wsize;
-			/* now tx must be idle... */
-			while (!(txx9spi_rd(c, TXx9_SPSR) & TXx9_SPSR_SIDLE))
-				cpu_relax();
-			cr0 = txx9spi_rd(c, TXx9_SPCR0);
-			cr0 &= ~TXx9_SPCR0_RXIFL_MASK;
-			cr0 |= (count - 1) << 12;
-			/* enable rx intr */
-			cr0 |= TXx9_SPCR0_RBSIE;
-			txx9spi_wr(c, cr0, TXx9_SPCR0);
-			/* send */
-			for (i = 0; i < count; i++) {
-				if (txbuf) {
-					data = (wsize == 1)
-						? *(const u8 *)txbuf
-						: *(const u16 *)txbuf;
-					txx9spi_wr(c, data, TXx9_SPDR);
-					txbuf += wsize;
-				} else
-					txx9spi_wr(c, 0, TXx9_SPDR);
-			}
-			/* wait all rx data */
-			wait_event(c->waitq,
-				txx9spi_rd(c, TXx9_SPSR) & TXx9_SPSR_RBSI);
-			/* receive */
-			for (i = 0; i < count; i++) {
-				data = txx9spi_rd(c, TXx9_SPDR);
-				if (rxbuf) {
-					if (wsize == 1)
-						*(u8 *)rxbuf = data;
-					else
-						*(u16 *)rxbuf = data;
-					rxbuf += wsize;
-				}
-			}
-			len -= count * wsize;
-		}
-		m->actual_length += t->len;
-		spi_transfer_delay_exec(t);
-
-		if (!cs_change)
-			continue;
-		if (t->transfer_list.next == &m->transfers)
-			break;
-		/* sometimes a short mid-message deselect of the chip
-		 * may be needed to terminate a mode or command
-		 */
-		txx9spi_cs_func(spi, c, 0, cs_delay);
-	}
-
-exit:
-	m->status = status;
-	if (m->complete)
-		m->complete(m->context);
-
-	/* normally deactivate chipselect ... unless no error and
-	 * cs_change has hinted that the next message will probably
-	 * be for this chip too.
-	 */
-	if (!(status == 0 && cs_change))
-		txx9spi_cs_func(spi, c, 0, cs_delay);
-
-	/* enter config mode */
-	txx9spi_wr(c, mcr | TXx9_SPMCR_CONFIG | TXx9_SPMCR_BCLR, TXx9_SPMCR);
-}
-
-static void txx9spi_work(struct work_struct *work)
-{
-	struct txx9spi *c = container_of(work, struct txx9spi, work);
-	unsigned long flags;
-
-	spin_lock_irqsave(&c->lock, flags);
-	while (!list_empty(&c->queue)) {
-		struct spi_message *m;
-
-		m = container_of(c->queue.next, struct spi_message, queue);
-		list_del_init(&m->queue);
-		spin_unlock_irqrestore(&c->lock, flags);
-
-		txx9spi_work_one(c, m);
-
-		spin_lock_irqsave(&c->lock, flags);
-	}
-	spin_unlock_irqrestore(&c->lock, flags);
-}
-
-static int txx9spi_transfer(struct spi_device *spi, struct spi_message *m)
-{
-	struct spi_master *master = spi->master;
-	struct txx9spi *c = spi_master_get_devdata(master);
-	struct spi_transfer *t;
-	unsigned long flags;
-
-	m->actual_length = 0;
-
-	/* check each transfer's parameters */
-	list_for_each_entry(t, &m->transfers, transfer_list) {
-		if (!t->tx_buf && !t->rx_buf && t->len)
-			return -EINVAL;
-	}
-
-	spin_lock_irqsave(&c->lock, flags);
-	list_add_tail(&m->queue, &c->queue);
-	schedule_work(&c->work);
-	spin_unlock_irqrestore(&c->lock, flags);
-
-	return 0;
-}
-
-/*
- * Chip select uses GPIO only, further the driver is using the chip select
- * numer (from the device tree "reg" property, and this can only come from
- * device tree since this i MIPS and there is no way to pass platform data) as
- * the GPIO number. As the platform has only one GPIO controller (the txx9 GPIO
- * chip) it is thus using the chip select number as an offset into that chip.
- * This chip has a maximum of 16 GPIOs 0..15 and this is what all platforms
- * register.
- *
- * We modernized this behaviour by explicitly converting that offset to an
- * offset on the GPIO chip using a GPIO descriptor machine table of the same
- * size as the txx9 GPIO chip with a 1-to-1 mapping of chip select to GPIO
- * offset.
- *
- * This is admittedly a hack, but it is countering the hack of using "reg" to
- * contain a GPIO offset when it should be using "cs-gpios" as the SPI bindings
- * state.
- */
-static struct gpiod_lookup_table txx9spi_cs_gpio_table = {
-	.dev_id = "spi0",
-	.table = {
-		GPIO_LOOKUP_IDX("TXx9", 0, "cs", 0, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 1, "cs", 1, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 2, "cs", 2, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 3, "cs", 3, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 4, "cs", 4, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 5, "cs", 5, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 6, "cs", 6, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 7, "cs", 7, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 8, "cs", 8, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 9, "cs", 9, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 10, "cs", 10, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 11, "cs", 11, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 12, "cs", 12, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 13, "cs", 13, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 14, "cs", 14, GPIO_ACTIVE_LOW),
-		GPIO_LOOKUP_IDX("TXx9", 15, "cs", 15, GPIO_ACTIVE_LOW),
-		{ },
-	},
-};
-
-static int txx9spi_probe(struct platform_device *dev)
-{
-	struct spi_master *master;
-	struct txx9spi *c;
-	struct resource *res;
-	int ret = -ENODEV;
-	u32 mcr;
-	int irq;
-
-	master = spi_alloc_master(&dev->dev, sizeof(*c));
-	if (!master)
-		return ret;
-	c = spi_master_get_devdata(master);
-	platform_set_drvdata(dev, master);
-
-	INIT_WORK(&c->work, txx9spi_work);
-	spin_lock_init(&c->lock);
-	INIT_LIST_HEAD(&c->queue);
-	init_waitqueue_head(&c->waitq);
-
-	c->clk = devm_clk_get(&dev->dev, "spi-baseclk");
-	if (IS_ERR(c->clk)) {
-		ret = PTR_ERR(c->clk);
-		c->clk = NULL;
-		goto exit;
-	}
-	ret = clk_prepare_enable(c->clk);
-	if (ret) {
-		c->clk = NULL;
-		goto exit;
-	}
-	c->baseclk = clk_get_rate(c->clk);
-	master->min_speed_hz = DIV_ROUND_UP(c->baseclk, SPI_MAX_DIVIDER + 1);
-	master->max_speed_hz = c->baseclk / (SPI_MIN_DIVIDER + 1);
-
-	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	c->membase = devm_ioremap_resource(&dev->dev, res);
-	if (IS_ERR(c->membase))
-		goto exit_busy;
-
-	/* enter config mode */
-	mcr = txx9spi_rd(c, TXx9_SPMCR);
-	mcr &= ~(TXx9_SPMCR_OPMODE | TXx9_SPMCR_SPSTP | TXx9_SPMCR_BCLR);
-	txx9spi_wr(c, mcr | TXx9_SPMCR_CONFIG | TXx9_SPMCR_BCLR, TXx9_SPMCR);
-
-	irq = platform_get_irq(dev, 0);
-	if (irq < 0)
-		goto exit_busy;
-	ret = devm_request_irq(&dev->dev, irq, txx9spi_interrupt, 0,
-			       "spi_txx9", c);
-	if (ret)
-		goto exit;
-
-	c->last_chipselect = NULL;
-
-	dev_info(&dev->dev, "at %#llx, irq %d, %dMHz\n",
-		 (unsigned long long)res->start, irq,
-		 (c->baseclk + 500000) / 1000000);
-
-	gpiod_add_lookup_table(&txx9spi_cs_gpio_table);
-
-	/* the spi->mode bits understood by this driver: */
-	master->mode_bits = SPI_CS_HIGH | SPI_CPOL | SPI_CPHA;
-
-	master->bus_num = dev->id;
-	master->setup = txx9spi_setup;
-	master->transfer = txx9spi_transfer;
-	master->num_chipselect = (u16)UINT_MAX; /* any GPIO numbers */
-	master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
-	master->use_gpio_descriptors = true;
-
-	ret = devm_spi_register_master(&dev->dev, master);
-	if (ret)
-		goto exit;
-	return 0;
-exit_busy:
-	ret = -EBUSY;
-exit:
-	clk_disable_unprepare(c->clk);
-	spi_master_put(master);
-	return ret;
-}
-
-static int txx9spi_remove(struct platform_device *dev)
-{
-	struct spi_master *master = platform_get_drvdata(dev);
-	struct txx9spi *c = spi_master_get_devdata(master);
-
-	flush_work(&c->work);
-	clk_disable_unprepare(c->clk);
-	return 0;
-}
-
-/* work with hotplug and coldplug */
-MODULE_ALIAS("platform:spi_txx9");
-
-static struct platform_driver txx9spi_driver = {
-	.probe = txx9spi_probe,
-	.remove = txx9spi_remove,
-	.driver = {
-		.name = "spi_txx9",
-	},
-};
-
-static int __init txx9spi_init(void)
-{
-	return platform_driver_register(&txx9spi_driver);
-}
-subsys_initcall(txx9spi_init);
-
-static void __exit txx9spi_exit(void)
-{
-	platform_driver_unregister(&txx9spi_driver);
-}
-module_exit(txx9spi_exit);
-
-MODULE_DESCRIPTION("TXx9 SPI Driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 801d8b499788..b08efe88ccd6 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -810,7 +810,8 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
 	spi->controller->last_cs_enable = enable;
 	spi->controller->last_cs_mode_high = spi->mode & SPI_CS_HIGH;
 
-	if (!spi->controller->set_cs_timing) {
+	if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio) ||
+	    !spi->controller->set_cs_timing) {
 		if (enable1)
 			spi_delay_exec(&spi->controller->cs_setup, NULL);
 		else
@@ -841,7 +842,8 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
 		spi->controller->set_cs(spi, !enable);
 	}
 
-	if (!spi->controller->set_cs_timing) {
+	if (spi->cs_gpiod || gpio_is_valid(spi->cs_gpio) ||
+	    !spi->controller->set_cs_timing) {
 		if (!enable1)
 			spi_delay_exec(&spi->controller->cs_inactive, NULL);
 	}
@@ -1267,7 +1269,7 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 			ptp_read_system_prets(xfer->ptp_sts);
 		}
 
-		if (xfer->tx_buf || xfer->rx_buf) {
+		if ((xfer->tx_buf || xfer->rx_buf) && xfer->len) {
 			reinit_completion(&ctlr->xfer_completion);
 
 fallback_pio:
@@ -1945,6 +1947,9 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
 	/* Device DUAL/QUAD mode */
 	if (!of_property_read_u32(nc, "spi-tx-bus-width", &value)) {
 		switch (value) {
+		case 0:
+			spi->mode |= SPI_NO_TX;
+			break;
 		case 1:
 			break;
 		case 2:
@@ -1966,6 +1971,9 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
 
 	if (!of_property_read_u32(nc, "spi-rx-bus-width", &value)) {
 		switch (value) {
+		case 0:
+			spi->mode |= SPI_NO_RX;
+			break;
 		case 1:
 			break;
 		case 2:
@@ -3333,12 +3341,16 @@ int spi_setup(struct spi_device *spi)
 	unsigned	bad_bits, ugly_bits;
 	int		status;
 
-	/* check mode to prevent that DUAL and QUAD set at the same time
+	/*
+	 * check mode to prevent that any two of DUAL, QUAD and NO_MOSI/MISO
+	 * are 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))) {
+	if ((hweight_long(spi->mode &
+		(SPI_TX_DUAL | SPI_TX_QUAD | SPI_NO_TX)) > 1) ||
+	    (hweight_long(spi->mode &
+		(SPI_RX_DUAL | SPI_RX_QUAD | SPI_NO_RX)) > 1)) {
 		dev_err(&spi->dev,
-		"setup: can not select dual and quad at the same time\n");
+		"setup: can not select any two of dual, quad and no-rx/tx at the same time\n");
 		return -EINVAL;
 	}
 	/* if it is SPI_3WIRE mode, DUAL and QUAD should be forbidden
@@ -3352,7 +3364,8 @@ int spi_setup(struct spi_device *spi)
 	 * SPI_CS_WORD has a fallback software implementation,
 	 * so it is ignored here.
 	 */
-	bad_bits = spi->mode & ~(spi->controller->mode_bits | SPI_CS_WORD);
+	bad_bits = spi->mode & ~(spi->controller->mode_bits | SPI_CS_WORD |
+				 SPI_NO_TX | SPI_NO_RX);
 	/* nothing prevents from working with active-high CS in case if it
 	 * is driven by GPIO.
 	 */
@@ -3449,11 +3462,31 @@ EXPORT_SYMBOL_GPL(spi_setup);
 int spi_set_cs_timing(struct spi_device *spi, struct spi_delay *setup,
 		      struct spi_delay *hold, struct spi_delay *inactive)
 {
+	struct device *parent = spi->controller->dev.parent;
 	size_t len;
+	int status;
+
+	if (spi->controller->set_cs_timing &&
+	    !(spi->cs_gpiod || gpio_is_valid(spi->cs_gpio))) {
+		if (spi->controller->auto_runtime_pm) {
+			status = pm_runtime_get_sync(parent);
+			if (status < 0) {
+				pm_runtime_put_noidle(parent);
+				dev_err(&spi->controller->dev, "Failed to power device: %d\n",
+					status);
+				return status;
+			}
 
-	if (spi->controller->set_cs_timing)
-		return spi->controller->set_cs_timing(spi, setup, hold,
-						      inactive);
+			status = spi->controller->set_cs_timing(spi, setup,
+								hold, inactive);
+			pm_runtime_mark_last_busy(parent);
+			pm_runtime_put_autosuspend(parent);
+			return status;
+		} else {
+			return spi->controller->set_cs_timing(spi, setup, hold,
+							      inactive);
+		}
+	}
 
 	if ((setup && setup->unit == SPI_DELAY_UNIT_SCK) ||
 	    (hold && hold->unit == SPI_DELAY_UNIT_SCK) ||
@@ -3615,6 +3648,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 		 * 2. check tx/rx_nbits match the mode in spi_device
 		 */
 		if (xfer->tx_buf) {
+			if (spi->mode & SPI_NO_TX)
+				return -EINVAL;
 			if (xfer->tx_nbits != SPI_NBITS_SINGLE &&
 				xfer->tx_nbits != SPI_NBITS_DUAL &&
 				xfer->tx_nbits != SPI_NBITS_QUAD)
@@ -3628,6 +3663,8 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 		}
 		/* check transfer rx_nbits */
 		if (xfer->rx_buf) {
+			if (spi->mode & SPI_NO_RX)
+				return -EINVAL;
 			if (xfer->rx_nbits != SPI_NBITS_SINGLE &&
 				xfer->rx_nbits != SPI_NBITS_DUAL &&
 				xfer->rx_nbits != SPI_NBITS_QUAD)