Merge tag 'spi-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi

Pull spi updates from Mark Brown:
 "One small core feature this time around but mostly driver improvements
  and additions for SPI:

   - Add support for controlling the idle state of MOSI, some systems
     can support this and depending on the system integration may need
     it to avoid glitching in some situations

   - Support for polling mode in the S3C64xx driver and DMA on the
     Qualcomm QSPI driver

   - Support for several Allwinner SoCs, AMD Pensando Elba, Intel Mount
     Evans, Renesas RZ/V2M, and ST STM32H7"

* tag 'spi-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi: (66 commits)
  spi: dt-bindings: atmel,at91rm9200-spi: fix broken sam9x7 compatible
  spi: dt-bindings: atmel,at91rm9200-spi: add sam9x7 compatible
  spi: Add support for Renesas CSI
  spi: dt-bindings: Add bindings for RZ/V2M CSI
  spi: sun6i: Use the new helper to derive the xfer timeout value
  spi: atmel: Prevent false timeouts on long transfers
  spi: dt-bindings: stm32: do not disable spi-slave property for stm32f4-f7
  spi: Create a helper to derive adaptive timeouts
  spi: spi-geni-qcom: correctly handle -EPROBE_DEFER from dma_request_chan()
  spi: stm32: disable spi-slave property for stm32f4-f7
  spi: stm32: introduction of stm32h7 SPI device mode support
  spi: stm32: use dmaengine_terminate_{a}sync instead of _all
  spi: stm32: renaming of spi_master into spi_controller
  spi: dw: Remove misleading comment for Mount Evans SoC
  spi: dt-bindings: snps,dw-apb-ssi: Add compatible for Intel Mount Evans SoC
  spi: dw: Add compatible for Intel Mount Evans SoC
  spi: s3c64xx: Use dev_err_probe()
  spi: s3c64xx: Use the managed spi master allocation function
  spi: spl022: Probe defer is no error
  spi: spi-imx: fix mixing of native and gpio chipselects for imx51/imx53/imx6 variants
  ...

39 files changed, 1635 insertions, 413 deletions

diff --git a/Documentation/devicetree/bindings/spi/allwinner,sun4i-a10-spi.yaml b/Documentation/devicetree/bindings/spi/allwinner,sun4i-a10-spi.yaml
index 2155478bfc4d..a6f34bdd1d3c 100644
--- a/Documentation/devicetree/bindings/spi/allwinner,sun4i-a10-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/allwinner,sun4i-a10-spi.yaml
@@ -14,9 +14,6 @@ maintainers:
   - Maxime Ripard <mripard@kernel.org>
 
 properties:
-  "#address-cells": true
-  "#size-cells": true
-
   compatible:
     const: allwinner,sun4i-a10-spi
 
@@ -46,12 +43,9 @@ properties:
       - const: rx
       - const: tx
 
-  num-cs: true
-
 patternProperties:
   "^.*@[0-9a-f]+":
     type: object
-    additionalProperties: true
     properties:
       reg:
         items:
@@ -71,7 +65,7 @@ required:
   - clocks
   - clock-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
index de36c6a34a0f..28b8ace63044 100644
--- a/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/allwinner,sun6i-a31-spi.yaml
@@ -14,11 +14,9 @@ maintainers:
   - Maxime Ripard <mripard@kernel.org>
 
 properties:
-  "#address-cells": true
-  "#size-cells": true
-
   compatible:
     oneOf:
+      - const: allwinner,sun50i-r329-spi
       - const: allwinner,sun6i-a31-spi
       - const: allwinner,sun8i-h3-spi
       - items:
@@ -28,6 +26,15 @@ properties:
               - allwinner,sun50i-h616-spi
               - allwinner,suniv-f1c100s-spi
           - const: allwinner,sun8i-h3-spi
+      - items:
+          - enum:
+              - allwinner,sun20i-d1-spi
+              - allwinner,sun50i-r329-spi-dbi
+          - const: allwinner,sun50i-r329-spi
+      - items:
+          - const: allwinner,sun20i-d1-spi-dbi
+          - const: allwinner,sun50i-r329-spi-dbi
+          - const: allwinner,sun50i-r329-spi
 
   reg:
     maxItems: 1
@@ -58,12 +65,9 @@ properties:
       - const: rx
       - const: tx
 
-  num-cs: true
-
 patternProperties:
   "^.*@[0-9a-f]+":
     type: object
-    additionalProperties: true
     properties:
       reg:
         items:
@@ -83,7 +87,7 @@ required:
   - clocks
   - clock-names
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml
index 6c57dd6c3a36..58367587bfbc 100644
--- a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml
@@ -20,6 +20,10 @@ properties:
       - items:
           - const: microchip,sam9x60-spi
           - const: atmel,at91rm9200-spi
+      - items:
+          - const: microchip,sam9x7-spi
+          - const: microchip,sam9x60-spi
+          - const: atmel,at91rm9200-spi
 
   reg:
     maxItems: 1
diff --git a/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml b/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
index b310069762dd..4f15f9a0cc34 100644
--- a/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
+++ b/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
@@ -46,12 +46,28 @@ allOf:
           maxItems: 2
           items:
             enum: [ qspi, qspi-ocp ]
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: amd,pensando-elba-qspi
+    then:
+      properties:
+        cdns,fifo-depth:
+          enum: [ 128, 256, 1024 ]
+          default: 1024
+    else:
+      properties:
+        cdns,fifo-depth:
+          enum: [ 128, 256 ]
+          default: 128
 
 properties:
   compatible:
     oneOf:
       - items:
           - enum:
+              - amd,pensando-elba-qspi
               - ti,k2g-qspi
               - ti,am654-ospi
               - intel,lgm-qspi
@@ -76,8 +92,6 @@ properties:
     description:
       Size of the data FIFO in words.
     $ref: /schemas/types.yaml#/definitions/uint32
-    enum: [ 128, 256 ]
-    default: 128
 
   cdns,fifo-width:
     $ref: /schemas/types.yaml#/definitions/uint32
diff --git a/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml b/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml
index ee8f7ea907b0..1696ac46a660 100644
--- a/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml
+++ b/Documentation/devicetree/bindings/spi/qcom,spi-qcom-qspi.yaml
@@ -29,6 +29,9 @@ properties:
   reg:
     maxItems: 1
 
+  iommus:
+    maxItems: 1
+
   interrupts:
     maxItems: 1
 
diff --git a/Documentation/devicetree/bindings/spi/renesas,rzv2m-csi.yaml b/Documentation/devicetree/bindings/spi/renesas,rzv2m-csi.yaml
new file mode 100644
index 000000000000..e59183e53690
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/renesas,rzv2m-csi.yaml
@@ -0,0 +1,70 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/renesas,rzv2m-csi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas RZ/V2M Clocked Serial Interface (CSI)
+
+maintainers:
+  - Fabrizio Castro <fabrizio.castro.jz@renesas.com>
+  - Geert Uytterhoeven <geert+renesas@glider.be>
+
+allOf:
+  - $ref: spi-controller.yaml#
+
+properties:
+  compatible:
+    const: renesas,rzv2m-csi
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: The clock used to generate the output clock (CSICLK)
+      - description: Internal clock to access the registers (PCLK)
+
+  clock-names:
+    items:
+      - const: csiclk
+      - const: pclk
+
+  resets:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - resets
+  - power-domains
+  - '#address-cells'
+  - '#size-cells'
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/r9a09g011-cpg.h>
+    csi4: spi@a4020200 {
+        compatible = "renesas,rzv2m-csi";
+        reg = <0xa4020200 0x80>;
+        interrupts = <GIC_SPI 230 IRQ_TYPE_LEVEL_HIGH>;
+        clocks = <&cpg CPG_MOD R9A09G011_CSI4_CLK>,
+                 <&cpg CPG_MOD R9A09G011_CPERI_GRPH_PCLK>;
+        clock-names = "csiclk", "pclk";
+        resets = <&cpg R9A09G011_CSI_GPH_PRESETN>;
+        power-domains = <&cpg>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+    };
diff --git a/Documentation/devicetree/bindings/spi/samsung,spi.yaml b/Documentation/devicetree/bindings/spi/samsung,spi.yaml
index e0a465d70b0a..79da99ca0e53 100644
--- a/Documentation/devicetree/bindings/spi/samsung,spi.yaml
+++ b/Documentation/devicetree/bindings/spi/samsung,spi.yaml
@@ -35,8 +35,6 @@ properties:
     minItems: 2
     maxItems: 3
 
-  cs-gpios: true
-
   dmas:
     minItems: 2
     maxItems: 2
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
index 12ca108864c6..a47cb144b09f 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml
@@ -74,6 +74,8 @@ properties:
         const: intel,keembay-ssi
       - description: Intel Thunder Bay SPI Controller
         const: intel,thunderbay-ssi
+      - description: Intel Mount Evans Integrated Management Complex SPI Controller
+        const: intel,mountevans-imc-ssi
       - description: AMD Pensando Elba SoC SPI Controller
         const: amd,pensando-elba-spi
       - description: Baikal-T1 SPI Controller
diff --git a/Documentation/devicetree/bindings/spi/socionext,uniphier-spi.yaml b/Documentation/devicetree/bindings/spi/socionext,uniphier-spi.yaml
index 597fc4e6b01c..c96131ebbea1 100644
--- a/Documentation/devicetree/bindings/spi/socionext,uniphier-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/socionext,uniphier-spi.yaml
@@ -17,9 +17,6 @@ allOf:
   - $ref: spi-controller.yaml#
 
 properties:
-  "#address-cells": true
-  "#size-cells": true
-
   compatible:
     const: socionext,uniphier-scssi
 
diff --git a/Documentation/devicetree/bindings/spi/spi-controller.yaml b/Documentation/devicetree/bindings/spi/spi-controller.yaml
index 90945f59b7e8..524f6fe8c27b 100644
--- a/Documentation/devicetree/bindings/spi/spi-controller.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-controller.yaml
@@ -17,7 +17,7 @@ description: |
 
 properties:
   $nodename:
-    pattern: "^spi(@.*|-[0-9a-f])*$"
+    pattern: "^spi(@.*|-([0-9]|[1-9][0-9]+))?$"
 
   "#address-cells":
     enum: [0, 1]
diff --git a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.yaml b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.yaml
index 20f77246d365..226d8b493b57 100644
--- a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.yaml
@@ -32,6 +32,12 @@ properties:
   clocks:
     maxItems: 2
 
+  iommus:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
 required:
   - compatible
   - reg
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 3de2ebe8294a..abbd1fb5fbc0 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -825,6 +825,12 @@ config SPI_RSPI
 	help
 	  SPI driver for Renesas RSPI and QSPI blocks.
 
+config SPI_RZV2M_CSI
+	tristate "Renesas RZV2M CSI controller"
+	depends on ARCH_RENESAS || COMPILE_TEST
+	help
+	  SPI driver for Renesas RZ/V2M Clocked Serial Interface (CSI)
+
 config SPI_QCOM_QSPI
 	tristate "QTI QSPI controller"
 	depends on ARCH_QCOM || COMPILE_TEST
@@ -936,6 +942,7 @@ config SPI_SPRD_ADI
 config SPI_STM32
 	tristate "STMicroelectronics STM32 SPI controller"
 	depends on ARCH_STM32 || COMPILE_TEST
+	select SPI_SLAVE
 	help
 	  SPI driver for STMicroelectronics STM32 SoCs.
 
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 28c4817a8a74..080c2c1b3ec1 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -113,6 +113,7 @@ 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-$(CONFIG_SPI_RZV2M_CSI)		+= spi-rzv2m-csi.o
 obj-$(CONFIG_SPI_S3C64XX)		+= spi-s3c64xx.o
 obj-$(CONFIG_SPI_SC18IS602)		+= spi-sc18is602.o
 obj-$(CONFIG_SPI_SH)			+= spi-sh.o
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 7f06305e16cb..152cd6773403 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -233,7 +233,8 @@
  */
 #define DMA_MIN_BYTES	16
 
-#define SPI_DMA_TIMEOUT		(msecs_to_jiffies(1000))
+#define SPI_DMA_MIN_TIMEOUT	(msecs_to_jiffies(1000))
+#define SPI_DMA_TIMEOUT_PER_10K	(msecs_to_jiffies(4))
 
 #define AUTOSUSPEND_TIMEOUT	2000
 
@@ -1279,7 +1280,8 @@ static int atmel_spi_one_transfer(struct spi_controller *host,
 	struct atmel_spi_device	*asd;
 	int			timeout;
 	int			ret;
-	unsigned long		dma_timeout;
+	unsigned int		dma_timeout;
+	long			ret_timeout;
 
 	as = spi_controller_get_devdata(host);
 
@@ -1333,11 +1335,13 @@ static int atmel_spi_one_transfer(struct spi_controller *host,
 			atmel_spi_unlock(as);
 		}
 
-		dma_timeout = wait_for_completion_timeout(&as->xfer_completion,
-							  SPI_DMA_TIMEOUT);
-		if (WARN_ON(dma_timeout == 0)) {
-			dev_err(&spi->dev, "spi transfer timeout\n");
-			as->done_status = -EIO;
+		dma_timeout = msecs_to_jiffies(spi_controller_xfer_timeout(host, xfer));
+		ret_timeout = wait_for_completion_interruptible_timeout(&as->xfer_completion,
+									dma_timeout);
+		if (ret_timeout <= 0) {
+			dev_err(&spi->dev, "spi transfer %s\n",
+				!ret_timeout ? "timeout" : "canceled");
+			as->done_status = ret_timeout < 0 ? ret_timeout : -EIO;
 		}
 
 		if (as->done_status)
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 32449bef4415..abf10f92415d 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -40,6 +40,7 @@
 #define CQSPI_SUPPORT_EXTERNAL_DMA	BIT(2)
 #define CQSPI_NO_SUPPORT_WR_COMPLETION	BIT(3)
 #define CQSPI_SLOW_SRAM		BIT(4)
+#define CQSPI_NEEDS_APB_AHB_HAZARD_WAR	BIT(5)
 
 /* Capabilities */
 #define CQSPI_SUPPORTS_OCTAL		BIT(0)
@@ -90,6 +91,7 @@ struct cqspi_st {
 	u32			pd_dev_id;
 	bool			wr_completion;
 	bool			slow_sram;
+	bool			apb_ahb_hazard;
 };
 
 struct cqspi_driver_platdata {
@@ -1027,6 +1029,13 @@ static int cqspi_indirect_write_execute(struct cqspi_flash_pdata *f_pdata,
 	if (cqspi->wr_delay)
 		ndelay(cqspi->wr_delay);
 
+	/*
+	 * If a hazard exists between the APB and AHB interfaces, perform a
+	 * dummy readback from the controller to ensure synchronization.
+	 */
+	if (cqspi->apb_ahb_hazard)
+		readl(reg_base + CQSPI_REG_INDIRECTWR);
+
 	while (remaining > 0) {
 		size_t write_words, mod_bytes;
 
@@ -1754,6 +1763,8 @@ static int cqspi_probe(struct platform_device *pdev)
 			cqspi->wr_completion = false;
 		if (ddata->quirks & CQSPI_SLOW_SRAM)
 			cqspi->slow_sram = true;
+		if (ddata->quirks & CQSPI_NEEDS_APB_AHB_HAZARD_WAR)
+			cqspi->apb_ahb_hazard = true;
 
 		if (of_device_is_compatible(pdev->dev.of_node,
 					    "xlnx,versal-ospi-1.0")) {
@@ -1888,6 +1899,10 @@ static const struct cqspi_driver_platdata jh7110_qspi = {
 	.quirks = CQSPI_DISABLE_DAC_MODE,
 };
 
+static const struct cqspi_driver_platdata pensando_cdns_qspi = {
+	.quirks = CQSPI_NEEDS_APB_AHB_HAZARD_WAR | CQSPI_DISABLE_DAC_MODE,
+};
+
 static const struct of_device_id cqspi_dt_ids[] = {
 	{
 		.compatible = "cdns,qspi-nor",
@@ -1917,6 +1932,10 @@ static const struct of_device_id cqspi_dt_ids[] = {
 		.compatible = "starfive,jh7110-qspi",
 		.data = &jh7110_qspi,
 	},
+	{
+		.compatible = "amd,pensando-elba-qspi",
+		.data = &pensando_cdns_qspi,
+	},
 	{ /* end of table */ }
 };
 
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 26e663369319..de8fe3c5becb 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -102,6 +102,7 @@
  * @regs:		Virtual address of the SPI controller registers
  * @ref_clk:		Pointer to the peripheral clock
  * @pclk:		Pointer to the APB clock
+ * @clk_rate:		Reference clock frequency, taken from @ref_clk
  * @speed_hz:		Current SPI bus clock speed in Hz
  * @txbuf:		Pointer	to the TX buffer
  * @rxbuf:		Pointer to the RX buffer
diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c
index ae3108c70f50..a8ba41ad4541 100644
--- a/drivers/spi/spi-dw-core.c
+++ b/drivers/spi/spi-dw-core.c
@@ -57,21 +57,17 @@ static const struct debugfs_reg32 dw_spi_dbgfs_regs[] = {
 	DW_SPI_DBGFS_REG("RX_SAMPLE_DLY", DW_SPI_RX_SAMPLE_DLY),
 };
 
-static int dw_spi_debugfs_init(struct dw_spi *dws)
+static void dw_spi_debugfs_init(struct dw_spi *dws)
 {
 	char name[32];
 
 	snprintf(name, 32, "dw_spi%d", dws->master->bus_num);
 	dws->debugfs = debugfs_create_dir(name, NULL);
-	if (!dws->debugfs)
-		return -ENOMEM;
 
 	dws->regset.regs = dw_spi_dbgfs_regs;
 	dws->regset.nregs = ARRAY_SIZE(dw_spi_dbgfs_regs);
 	dws->regset.base = dws->regs;
 	debugfs_create_regset32("registers", 0400, dws->debugfs, &dws->regset);
-
-	return 0;
 }
 
 static void dw_spi_debugfs_remove(struct dw_spi *dws)
@@ -80,9 +76,8 @@ static void dw_spi_debugfs_remove(struct dw_spi *dws)
 }
 
 #else
-static inline int dw_spi_debugfs_init(struct dw_spi *dws)
+static inline void dw_spi_debugfs_init(struct dw_spi *dws)
 {
-	return 0;
 }
 
 static inline void dw_spi_debugfs_remove(struct dw_spi *dws)
@@ -426,7 +421,10 @@ static int dw_spi_transfer_one(struct spi_controller *master,
 	int ret;
 
 	dws->dma_mapped = 0;
-	dws->n_bytes = DIV_ROUND_UP(transfer->bits_per_word, BITS_PER_BYTE);
+	dws->n_bytes =
+		roundup_pow_of_two(DIV_ROUND_UP(transfer->bits_per_word,
+						BITS_PER_BYTE));
+
 	dws->tx = (void *)transfer->tx_buf;
 	dws->tx_len = transfer->len / dws->n_bytes;
 	dws->rx = transfer->rx_buf;
diff --git a/drivers/spi/spi-dw-dma.c b/drivers/spi/spi-dw-dma.c
index ababb910b391..df819652901a 100644
--- a/drivers/spi/spi-dw-dma.c
+++ b/drivers/spi/spi-dw-dma.c
@@ -72,12 +72,22 @@ static void dw_spi_dma_maxburst_init(struct dw_spi *dws)
 	dw_writel(dws, DW_SPI_DMATDLR, dws->txburst);
 }
 
-static void dw_spi_dma_sg_burst_init(struct dw_spi *dws)
+static int dw_spi_dma_caps_init(struct dw_spi *dws)
 {
-	struct dma_slave_caps tx = {0}, rx = {0};
+	struct dma_slave_caps tx, rx;
+	int ret;
+
+	ret = dma_get_slave_caps(dws->txchan, &tx);
+	if (ret)
+		return ret;
 
-	dma_get_slave_caps(dws->txchan, &tx);
-	dma_get_slave_caps(dws->rxchan, &rx);
+	ret = dma_get_slave_caps(dws->rxchan, &rx);
+	if (ret)
+		return ret;
+
+	if (!(tx.directions & BIT(DMA_MEM_TO_DEV) &&
+	      rx.directions & BIT(DMA_DEV_TO_MEM)))
+		return -ENXIO;
 
 	if (tx.max_sg_burst > 0 && rx.max_sg_burst > 0)
 		dws->dma_sg_burst = min(tx.max_sg_burst, rx.max_sg_burst);
@@ -87,6 +97,15 @@ static void dw_spi_dma_sg_burst_init(struct dw_spi *dws)
 		dws->dma_sg_burst = rx.max_sg_burst;
 	else
 		dws->dma_sg_burst = 0;
+
+	/*
+	 * Assuming both channels belong to the same DMA controller hence the
+	 * peripheral side address width capabilities most likely would be
+	 * the same.
+	 */
+	dws->dma_addr_widths = tx.dst_addr_widths & rx.src_addr_widths;
+
+	return 0;
 }
 
 static int dw_spi_dma_init_mfld(struct device *dev, struct dw_spi *dws)
@@ -95,6 +114,7 @@ static int dw_spi_dma_init_mfld(struct device *dev, struct dw_spi *dws)
 	struct dw_dma_slave dma_rx = { .src_id = 0 }, *rx = &dma_rx;
 	struct pci_dev *dma_dev;
 	dma_cap_mask_t mask;
+	int ret = -EBUSY;
 
 	/*
 	 * Get pci device for DMA controller, currently it could only
@@ -124,20 +144,25 @@ static int dw_spi_dma_init_mfld(struct device *dev, struct dw_spi *dws)
 
 	init_completion(&dws->dma_completion);
 
-	dw_spi_dma_maxburst_init(dws);
+	ret = dw_spi_dma_caps_init(dws);
+	if (ret)
+		goto free_txchan;
 
-	dw_spi_dma_sg_burst_init(dws);
+	dw_spi_dma_maxburst_init(dws);
 
 	pci_dev_put(dma_dev);
 
 	return 0;
 
+free_txchan:
+	dma_release_channel(dws->txchan);
+	dws->txchan = NULL;
 free_rxchan:
 	dma_release_channel(dws->rxchan);
 	dws->rxchan = NULL;
 err_exit:
 	pci_dev_put(dma_dev);
-	return -EBUSY;
+	return ret;
 }
 
 static int dw_spi_dma_init_generic(struct device *dev, struct dw_spi *dws)
@@ -163,12 +188,17 @@ static int dw_spi_dma_init_generic(struct device *dev, struct dw_spi *dws)
 
 	init_completion(&dws->dma_completion);
 
-	dw_spi_dma_maxburst_init(dws);
+	ret = dw_spi_dma_caps_init(dws);
+	if (ret)
+		goto free_txchan;
 
-	dw_spi_dma_sg_burst_init(dws);
+	dw_spi_dma_maxburst_init(dws);
 
 	return 0;
 
+free_txchan:
+	dma_release_channel(dws->txchan);
+	dws->txchan = NULL;
 free_rxchan:
 	dma_release_channel(dws->rxchan);
 	dws->rxchan = NULL;
@@ -198,22 +228,32 @@ static irqreturn_t dw_spi_dma_transfer_handler(struct dw_spi *dws)
 	return IRQ_HANDLED;
 }
 
+static enum dma_slave_buswidth dw_spi_dma_convert_width(u8 n_bytes)
+{
+	switch (n_bytes) {
+	case 1:
+		return DMA_SLAVE_BUSWIDTH_1_BYTE;
+	case 2:
+		return DMA_SLAVE_BUSWIDTH_2_BYTES;
+	case 4:
+		return DMA_SLAVE_BUSWIDTH_4_BYTES;
+	default:
+		return DMA_SLAVE_BUSWIDTH_UNDEFINED;
+	}
+}
+
 static bool dw_spi_can_dma(struct spi_controller *master,
 			   struct spi_device *spi, struct spi_transfer *xfer)
 {
 	struct dw_spi *dws = spi_controller_get_devdata(master);
+	enum dma_slave_buswidth dma_bus_width;
 
-	return xfer->len > dws->fifo_len;
-}
+	if (xfer->len <= dws->fifo_len)
+		return false;
 
-static enum dma_slave_buswidth dw_spi_dma_convert_width(u8 n_bytes)
-{
-	if (n_bytes == 1)
-		return DMA_SLAVE_BUSWIDTH_1_BYTE;
-	else if (n_bytes == 2)
-		return DMA_SLAVE_BUSWIDTH_2_BYTES;
+	dma_bus_width = dw_spi_dma_convert_width(dws->n_bytes);
 
-	return DMA_SLAVE_BUSWIDTH_UNDEFINED;
+	return dws->dma_addr_widths & BIT(dma_bus_width);
 }
 
 static int dw_spi_dma_wait(struct dw_spi *dws, unsigned int len, u32 speed)
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index 15f5e9cb54ad..a963bc96c223 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -236,6 +236,24 @@ static int dw_spi_intel_init(struct platform_device *pdev,
 	return 0;
 }
 
+/*
+ * DMA-based mem ops are not configured for this device and are not tested.
+ */
+static int dw_spi_mountevans_imc_init(struct platform_device *pdev,
+				      struct dw_spi_mmio *dwsmmio)
+{
+	/*
+	 * The Intel Mount Evans SoC's Integrated Management Complex DW
+	 * apb_ssi_v4.02a controller has an errata where a full TX FIFO can
+	 * result in data corruption. The suggested workaround is to never
+	 * completely fill the FIFO. The TX FIFO has a size of 32 so the
+	 * fifo_len is set to 31.
+	 */
+	dwsmmio->dws.fifo_len = 31;
+
+	return 0;
+}
+
 static int dw_spi_canaan_k210_init(struct platform_device *pdev,
 				   struct dw_spi_mmio *dwsmmio)
 {
@@ -405,6 +423,10 @@ static const struct of_device_id dw_spi_mmio_of_match[] = {
 	{ .compatible = "snps,dwc-ssi-1.01a", .data = dw_spi_hssi_init},
 	{ .compatible = "intel,keembay-ssi", .data = dw_spi_intel_init},
 	{ .compatible = "intel,thunderbay-ssi", .data = dw_spi_intel_init},
+	{
+		.compatible = "intel,mountevans-imc-ssi",
+		.data = dw_spi_mountevans_imc_init,
+	},
 	{ .compatible = "microchip,sparx5-spi", dw_spi_mscc_sparx5_init},
 	{ .compatible = "canaan,k210-spi", dw_spi_canaan_k210_init},
 	{ .compatible = "amd,pensando-elba-spi", .data = dw_spi_elba_init},
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 9e8eb2b52d5c..3962e6dcf880 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -190,6 +190,7 @@ struct dw_spi {
 	struct dma_chan		*rxchan;
 	u32			rxburst;
 	u32			dma_sg_burst;
+	u32			dma_addr_widths;
 	unsigned long		dma_chan_busy;
 	dma_addr_t		dma_addr; /* phy address of the Data register */
 	const struct dw_spi_dma_ops *dma_ops;
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 4b70038ceb6b..fb68c72df171 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -303,6 +303,12 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
 
 	perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
 
+	if (!config.speed_hz) {
+		dev_err(fsl_lpspi->dev,
+			"error: the transmission speed provided is 0!\n");
+		return -EINVAL;
+	}
+
 	if (config.speed_hz > perclk_rate / 2) {
 		dev_err(fsl_lpspi->dev,
 		      "per-clk should be at least two times of transfer speed");
@@ -911,7 +917,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	if (ret == -EPROBE_DEFER)
 		goto out_pm_get;
 	if (ret < 0)
-		dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret);
+		dev_warn(&pdev->dev, "dma setup error %d, use pio\n", ret);
 	else
 		/*
 		 * disable LPSPI module IRQ when enable DMA mode successfully,
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 135cdf394b76..26ce959d98df 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -35,7 +35,7 @@
 #define CS_DEMUX_OUTPUT_SEL	GENMASK(3, 0)
 
 #define SE_SPI_TRANS_CFG	0x25c
-#define CS_TOGGLE		BIT(0)
+#define CS_TOGGLE		BIT(1)
 
 #define SE_SPI_WORD_LEN		0x268
 #define WORD_LEN_MSK		GENMASK(9, 0)
diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c
index 524eadbef87b..2b4b3d2a22b8 100644
--- a/drivers/spi/spi-hisi-kunpeng.c
+++ b/drivers/spi/spi-hisi-kunpeng.c
@@ -169,7 +169,7 @@ static int hisi_spi_debugfs_init(struct hisi_spi *hs)
 	master = container_of(hs->dev, struct spi_controller, dev);
 	snprintf(name, 32, "hisi_spi%d", master->bus_num);
 	hs->debugfs = debugfs_create_dir(name, NULL);
-	if (!hs->debugfs)
+	if (IS_ERR(hs->debugfs))
 		return -ENOMEM;
 
 	hs->regset.regs = hisi_spi_regs;
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 34e5f81ec431..528ae46c087f 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -281,6 +281,7 @@ static bool spi_imx_can_dma(struct spi_controller *controller, struct spi_device
 #define MX51_ECSPI_CONFIG_SCLKPOL(cs)	(1 << ((cs & 3) +  4))
 #define MX51_ECSPI_CONFIG_SBBCTRL(cs)	(1 << ((cs & 3) +  8))
 #define MX51_ECSPI_CONFIG_SSBPOL(cs)	(1 << ((cs & 3) + 12))
+#define MX51_ECSPI_CONFIG_DATACTL(cs)	(1 << ((cs & 3) + 16))
 #define MX51_ECSPI_CONFIG_SCLKCTL(cs)	(1 << ((cs & 3) + 20))
 
 #define MX51_ECSPI_INT		0x10
@@ -516,6 +517,13 @@ static void mx51_ecspi_disable(struct spi_imx_data *spi_imx)
 	writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
 }
 
+static int mx51_ecspi_channel(const struct spi_device *spi)
+{
+	if (!spi_get_csgpiod(spi, 0))
+		return spi_get_chipselect(spi, 0);
+	return spi->controller->unused_native_cs;
+}
+
 static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx,
 				      struct spi_message *msg)
 {
@@ -526,6 +534,7 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx,
 	u32 testreg, delay;
 	u32 cfg = readl(spi_imx->base + MX51_ECSPI_CONFIG);
 	u32 current_cfg = cfg;
+	int channel = mx51_ecspi_channel(spi);
 
 	/* set Master or Slave mode */
 	if (spi_imx->slave_mode)
@@ -540,7 +549,7 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx,
 		ctrl |= MX51_ECSPI_CTRL_DRCTL(spi_imx->spi_drctl);
 
 	/* set chip select to use */
-	ctrl |= MX51_ECSPI_CTRL_CS(spi_get_chipselect(spi, 0));
+	ctrl |= MX51_ECSPI_CTRL_CS(channel);
 
 	/*
 	 * The ctrl register must be written first, with the EN bit set other
@@ -561,22 +570,27 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx,
 	 * BURST_LENGTH + 1 bits are received
 	 */
 	if (spi_imx->slave_mode && is_imx53_ecspi(spi_imx))
-		cfg &= ~MX51_ECSPI_CONFIG_SBBCTRL(spi_get_chipselect(spi, 0));
+		cfg &= ~MX51_ECSPI_CONFIG_SBBCTRL(channel);
 	else
-		cfg |= MX51_ECSPI_CONFIG_SBBCTRL(spi_get_chipselect(spi, 0));
+		cfg |= MX51_ECSPI_CONFIG_SBBCTRL(channel);
 
 	if (spi->mode & SPI_CPOL) {
-		cfg |= MX51_ECSPI_CONFIG_SCLKPOL(spi_get_chipselect(spi, 0));
-		cfg |= MX51_ECSPI_CONFIG_SCLKCTL(spi_get_chipselect(spi, 0));
+		cfg |= MX51_ECSPI_CONFIG_SCLKPOL(channel);
+		cfg |= MX51_ECSPI_CONFIG_SCLKCTL(channel);
 	} else {
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKPOL(spi_get_chipselect(spi, 0));
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKCTL(spi_get_chipselect(spi, 0));
+		cfg &= ~MX51_ECSPI_CONFIG_SCLKPOL(channel);
+		cfg &= ~MX51_ECSPI_CONFIG_SCLKCTL(channel);
 	}
 
+	if (spi->mode & SPI_MOSI_IDLE_LOW)
+		cfg |= MX51_ECSPI_CONFIG_DATACTL(channel);
+	else
+		cfg &= ~MX51_ECSPI_CONFIG_DATACTL(channel);
+
 	if (spi->mode & SPI_CS_HIGH)
-		cfg |= MX51_ECSPI_CONFIG_SSBPOL(spi_get_chipselect(spi, 0));
+		cfg |= MX51_ECSPI_CONFIG_SSBPOL(channel);
 	else
-		cfg &= ~MX51_ECSPI_CONFIG_SSBPOL(spi_get_chipselect(spi, 0));
+		cfg &= ~MX51_ECSPI_CONFIG_SSBPOL(channel);
 
 	if (cfg == current_cfg)
 		return 0;
@@ -621,14 +635,15 @@ static void mx51_configure_cpha(struct spi_imx_data *spi_imx,
 	bool cpha = (spi->mode & SPI_CPHA);
 	bool flip_cpha = (spi->mode & SPI_RX_CPHA_FLIP) && spi_imx->rx_only;
 	u32 cfg = readl(spi_imx->base + MX51_ECSPI_CONFIG);
+	int channel = mx51_ecspi_channel(spi);
 
 	/* Flip cpha logical value iff flip_cpha */
 	cpha ^= flip_cpha;
 
 	if (cpha)
-		cfg |= MX51_ECSPI_CONFIG_SCLKPHA(spi_get_chipselect(spi, 0));
+		cfg |= MX51_ECSPI_CONFIG_SCLKPHA(channel);
 	else
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKPHA(spi_get_chipselect(spi, 0));
+		cfg &= ~MX51_ECSPI_CONFIG_SCLKPHA(channel);
 
 	writel(cfg, spi_imx->base + MX51_ECSPI_CONFIG);
 }
@@ -1737,20 +1752,21 @@ static int spi_imx_probe(struct platform_device *pdev)
 	else
 		controller->num_chipselect = 3;
 
-	spi_imx->controller->transfer_one = spi_imx_transfer_one;
-	spi_imx->controller->setup = spi_imx_setup;
-	spi_imx->controller->cleanup = spi_imx_cleanup;
-	spi_imx->controller->prepare_message = spi_imx_prepare_message;
-	spi_imx->controller->unprepare_message = spi_imx_unprepare_message;
-	spi_imx->controller->slave_abort = spi_imx_slave_abort;
-	spi_imx->controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_NO_CS;
+	controller->transfer_one = spi_imx_transfer_one;
+	controller->setup = spi_imx_setup;
+	controller->cleanup = spi_imx_cleanup;
+	controller->prepare_message = spi_imx_prepare_message;
+	controller->unprepare_message = spi_imx_unprepare_message;
+	controller->slave_abort = spi_imx_slave_abort;
+	controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_NO_CS |
+				SPI_MOSI_IDLE_LOW;
 
 	if (is_imx35_cspi(spi_imx) || is_imx51_ecspi(spi_imx) ||
 	    is_imx53_ecspi(spi_imx))
-		spi_imx->controller->mode_bits |= SPI_LOOP | SPI_READY;
+		controller->mode_bits |= SPI_LOOP | SPI_READY;
 
 	if (is_imx51_ecspi(spi_imx) || is_imx53_ecspi(spi_imx))
-		spi_imx->controller->mode_bits |= SPI_RX_CPHA_FLIP;
+		controller->mode_bits |= SPI_RX_CPHA_FLIP;
 
 	if (is_imx51_ecspi(spi_imx) &&
 	    device_property_read_u32(&pdev->dev, "cs-gpios", NULL))
@@ -1759,7 +1775,12 @@ static int spi_imx_probe(struct platform_device *pdev)
 		 * setting the burst length to the word size. This is
 		 * considerably faster than manually controlling the CS.
 		 */
-		spi_imx->controller->mode_bits |= SPI_CS_WORD;
+		controller->mode_bits |= SPI_CS_WORD;
+
+	if (is_imx51_ecspi(spi_imx) || is_imx53_ecspi(spi_imx)) {
+		controller->max_native_cs = 4;
+		controller->flags |= SPI_MASTER_GPIO_SS;
+	}
 
 	spi_imx->spi_drctl = spi_drctl;
 
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index d7432e2219d8..39272ad6641b 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -1144,7 +1144,8 @@ static int mtk_spi_probe(struct platform_device *pdev)
 	if (mdata->dev_comp->must_tx)
 		master->flags = SPI_MASTER_MUST_TX;
 	if (mdata->dev_comp->ipm_design)
-		master->mode_bits |= SPI_LOOP;
+		master->mode_bits |= SPI_LOOP | SPI_RX_DUAL | SPI_TX_DUAL |
+				     SPI_RX_QUAD | SPI_TX_QUAD;
 
 	if (mdata->dev_comp->ipm_design) {
 		mdata->dev = dev;
@@ -1269,7 +1270,7 @@ static int mtk_spi_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int mtk_spi_remove(struct platform_device *pdev)
+static void mtk_spi_remove(struct platform_device *pdev)
 {
 	struct spi_master *master = platform_get_drvdata(pdev);
 	struct mtk_spi *mdata = spi_master_get_devdata(master);
@@ -1278,21 +1279,25 @@ static int mtk_spi_remove(struct platform_device *pdev)
 	if (mdata->use_spimem && !completion_done(&mdata->spimem_done))
 		complete(&mdata->spimem_done);
 
-	ret = pm_runtime_resume_and_get(&pdev->dev);
-	if (ret < 0)
-		return ret;
-
-	mtk_spi_reset(mdata);
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_warn(&pdev->dev, "Failed to resume hardware (%pe)\n", ERR_PTR(ret));
+	} else {
+		/*
+		 * If pm runtime resume failed, clks are disabled and
+		 * unprepared. So don't access the hardware and skip clk
+		 * unpreparing.
+		 */
+		mtk_spi_reset(mdata);
 
-	if (mdata->dev_comp->no_need_unprepare) {
-		clk_unprepare(mdata->spi_clk);
-		clk_unprepare(mdata->spi_hclk);
+		if (mdata->dev_comp->no_need_unprepare) {
+			clk_unprepare(mdata->spi_clk);
+			clk_unprepare(mdata->spi_hclk);
+		}
 	}
 
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -1311,7 +1316,7 @@ static int mtk_spi_suspend(struct device *dev)
 		clk_disable_unprepare(mdata->spi_hclk);
 	}
 
-	return ret;
+	return 0;
 }
 
 static int mtk_spi_resume(struct device *dev)
@@ -1412,7 +1417,7 @@ static struct platform_driver mtk_spi_driver = {
 		.of_match_table = mtk_spi_of_match,
 	},
 	.probe = mtk_spi_probe,
-	.remove = mtk_spi_remove,
+	.remove_new = mtk_spi_remove,
 };
 
 module_platform_driver(mtk_spi_driver);
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 982407bc5d9f..1af75eff26b6 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -2217,8 +2217,8 @@ static int pl022_probe(struct amba_device *adev, const struct amba_id *id)
 	amba_set_drvdata(adev, pl022);
 	status = devm_spi_register_master(&adev->dev, master);
 	if (status != 0) {
-		dev_err(&adev->dev,
-			"probe - problem registering spi master\n");
+		dev_err_probe(&adev->dev, status,
+			      "problem registering spi master\n");
 		goto err_spi_register;
 	}
 	dev_dbg(dev, "probe succeeded\n");
diff --git a/drivers/spi/spi-qcom-qspi.c b/drivers/spi/spi-qcom-qspi.c
index fab155389999..a8a683d6145c 100644
--- a/drivers/spi/spi-qcom-qspi.c
+++ b/drivers/spi/spi-qcom-qspi.c
@@ -2,6 +2,8 @@
 // Copyright (c) 2017-2018, The Linux foundation. All rights reserved.
 
 #include <linux/clk.h>
+#include <linux/dmapool.h>
+#include <linux/dma-mapping.h>
 #include <linux/interconnect.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -62,6 +64,7 @@
 #define WR_FIFO_FULL		BIT(10)
 #define WR_FIFO_OVERRUN		BIT(11)
 #define TRANSACTION_DONE	BIT(16)
+#define DMA_CHAIN_DONE		BIT(31)
 #define QSPI_ERR_IRQS		(RESP_FIFO_UNDERRUN | HRESP_FROM_NOC_ERR | \
 				 WR_FIFO_OVERRUN)
 #define QSPI_ALL_IRQS		(QSPI_ERR_IRQS | RESP_FIFO_RDY | \
@@ -108,18 +111,34 @@
 #define RD_FIFO_RESET		0x0030
 #define RESET_FIFO		BIT(0)
 
+#define NEXT_DMA_DESC_ADDR	0x0040
+#define CURRENT_DMA_DESC_ADDR	0x0044
+#define CURRENT_MEM_ADDR	0x0048
+
 #define CUR_MEM_ADDR		0x0048
 #define HW_VERSION		0x004c
 #define RD_FIFO			0x0050
 #define SAMPLING_CLK_CFG	0x0090
 #define SAMPLING_CLK_STATUS	0x0094
 
+#define QSPI_ALIGN_REQ	32
 
 enum qspi_dir {
 	QSPI_READ,
 	QSPI_WRITE,
 };
 
+struct qspi_cmd_desc {
+	u32 data_address;
+	u32 next_descriptor;
+	u32 direction:1;
+	u32 multi_io_mode:3;
+	u32 reserved1:4;
+	u32 fragment:1;
+	u32 reserved2:7;
+	u32 length:16;
+};
+
 struct qspi_xfer {
 	union {
 		const void *tx_buf;
@@ -137,11 +156,23 @@ enum qspi_clocks {
 	QSPI_NUM_CLKS
 };
 
+/*
+ * Number of entries in sgt returned from spi framework that-
+ * will be supported. Can be modified as required.
+ * In practice, given max_dma_len is 64KB, the number of
+ * entries is not expected to exceed 1.
+ */
+#define QSPI_MAX_SG 5
+
 struct qcom_qspi {
 	void __iomem *base;
 	struct device *dev;
 	struct clk_bulk_data *clks;
 	struct qspi_xfer xfer;
+	struct dma_pool *dma_cmd_pool;
+	dma_addr_t dma_cmd_desc[QSPI_MAX_SG];
+	void *virt_cmd_desc[QSPI_MAX_SG];
+	unsigned int n_cmd_desc;
 	struct icc_path *icc_path_cpu_to_qspi;
 	unsigned long last_speed;
 	/* Lock to protect data accessed by IRQs */
@@ -153,21 +184,22 @@ static u32 qspi_buswidth_to_iomode(struct qcom_qspi *ctrl,
 {
 	switch (buswidth) {
 	case 1:
-		return SDR_1BIT << MULTI_IO_MODE_SHFT;
+		return SDR_1BIT;
 	case 2:
-		return SDR_2BIT << MULTI_IO_MODE_SHFT;
+		return SDR_2BIT;
 	case 4:
-		return SDR_4BIT << MULTI_IO_MODE_SHFT;
+		return SDR_4BIT;
 	default:
 		dev_warn_once(ctrl->dev,
 				"Unexpected bus width: %u\n", buswidth);
-		return SDR_1BIT << MULTI_IO_MODE_SHFT;
+		return SDR_1BIT;
 	}
 }
 
 static void qcom_qspi_pio_xfer_cfg(struct qcom_qspi *ctrl)
 {
 	u32 pio_xfer_cfg;
+	u32 iomode;
 	const struct qspi_xfer *xfer;
 
 	xfer = &ctrl->xfer;
@@ -179,7 +211,8 @@ static void qcom_qspi_pio_xfer_cfg(struct qcom_qspi *ctrl)
 	else
 		pio_xfer_cfg |= TRANSFER_FRAGMENT;
 	pio_xfer_cfg &= ~MULTI_IO_MODE_MSK;
-	pio_xfer_cfg |= qspi_buswidth_to_iomode(ctrl, xfer->buswidth);
+	iomode = qspi_buswidth_to_iomode(ctrl, xfer->buswidth);
+	pio_xfer_cfg |= iomode << MULTI_IO_MODE_SHFT;
 
 	writel(pio_xfer_cfg, ctrl->base + PIO_XFER_CFG);
 }
@@ -217,12 +250,22 @@ static void qcom_qspi_pio_xfer(struct qcom_qspi *ctrl)
 static void qcom_qspi_handle_err(struct spi_master *master,
 				 struct spi_message *msg)
 {
+	u32 int_status;
 	struct qcom_qspi *ctrl = spi_master_get_devdata(master);
 	unsigned long flags;
+	int i;
 
 	spin_lock_irqsave(&ctrl->lock, flags);
 	writel(0, ctrl->base + MSTR_INT_EN);
+	int_status = readl(ctrl->base + MSTR_INT_STATUS);
+	writel(int_status, ctrl->base + MSTR_INT_STATUS);
 	ctrl->xfer.rem_bytes = 0;
+
+	/* free cmd descriptors if they are around (DMA mode) */
+	for (i = 0; i < ctrl->n_cmd_desc; i++)
+		dma_pool_free(ctrl->dma_cmd_pool, ctrl->virt_cmd_desc[i],
+				  ctrl->dma_cmd_desc[i]);
+	ctrl->n_cmd_desc = 0;
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 }
 
@@ -242,7 +285,7 @@ static int qcom_qspi_set_speed(struct qcom_qspi *ctrl, unsigned long speed_hz)
 	}
 
 	/*
-	 * Set BW quota for CPU as driver supports FIFO mode only.
+	 * Set BW quota for CPU.
 	 * We don't have explicit peak requirement so keep it equal to avg_bw.
 	 */
 	avg_bw_cpu = Bps_to_icc(speed_hz);
@@ -258,6 +301,102 @@ static int qcom_qspi_set_speed(struct qcom_qspi *ctrl, unsigned long speed_hz)
 	return 0;
 }
 
+static int qcom_qspi_alloc_desc(struct qcom_qspi *ctrl, dma_addr_t dma_ptr,
+			uint32_t n_bytes)
+{
+	struct qspi_cmd_desc *virt_cmd_desc, *prev;
+	dma_addr_t dma_cmd_desc;
+
+	/* allocate for dma cmd descriptor */
+	virt_cmd_desc = dma_pool_alloc(ctrl->dma_cmd_pool, GFP_KERNEL | __GFP_ZERO, &dma_cmd_desc);
+	if (!virt_cmd_desc)
+		return -ENOMEM;
+
+	ctrl->virt_cmd_desc[ctrl->n_cmd_desc] = virt_cmd_desc;
+	ctrl->dma_cmd_desc[ctrl->n_cmd_desc] = dma_cmd_desc;
+	ctrl->n_cmd_desc++;
+
+	/* setup cmd descriptor */
+	virt_cmd_desc->data_address = dma_ptr;
+	virt_cmd_desc->direction = ctrl->xfer.dir;
+	virt_cmd_desc->multi_io_mode = qspi_buswidth_to_iomode(ctrl, ctrl->xfer.buswidth);
+	virt_cmd_desc->fragment = !ctrl->xfer.is_last;
+	virt_cmd_desc->length = n_bytes;
+
+	/* update previous descriptor */
+	if (ctrl->n_cmd_desc >= 2) {
+		prev = (ctrl->virt_cmd_desc)[ctrl->n_cmd_desc - 2];
+		prev->next_descriptor = dma_cmd_desc;
+		prev->fragment = 1;
+	}
+
+	return 0;
+}
+
+static int qcom_qspi_setup_dma_desc(struct qcom_qspi *ctrl,
+				struct spi_transfer *xfer)
+{
+	int ret;
+	struct sg_table *sgt;
+	dma_addr_t dma_ptr_sg;
+	unsigned int dma_len_sg;
+	int i;
+
+	if (ctrl->n_cmd_desc) {
+		dev_err(ctrl->dev, "Remnant dma buffers n_cmd_desc-%d\n", ctrl->n_cmd_desc);
+		return -EIO;
+	}
+
+	sgt = (ctrl->xfer.dir == QSPI_READ) ? &xfer->rx_sg : &xfer->tx_sg;
+	if (!sgt->nents || sgt->nents > QSPI_MAX_SG) {
+		dev_warn_once(ctrl->dev, "Cannot handle %d entries in scatter list\n", sgt->nents);
+		return -EAGAIN;
+	}
+
+	for (i = 0; i < sgt->nents; i++) {
+		dma_ptr_sg = sg_dma_address(sgt->sgl + i);
+		if (!IS_ALIGNED(dma_ptr_sg, QSPI_ALIGN_REQ)) {
+			dev_warn_once(ctrl->dev, "dma_address not aligned to %d\n", QSPI_ALIGN_REQ);
+			return -EAGAIN;
+		}
+	}
+
+	for (i = 0; i < sgt->nents; i++) {
+		dma_ptr_sg = sg_dma_address(sgt->sgl + i);
+		dma_len_sg = sg_dma_len(sgt->sgl + i);
+
+		ret = qcom_qspi_alloc_desc(ctrl, dma_ptr_sg, dma_len_sg);
+		if (ret)
+			goto cleanup;
+	}
+	return 0;
+
+cleanup:
+	for (i = 0; i < ctrl->n_cmd_desc; i++)
+		dma_pool_free(ctrl->dma_cmd_pool, ctrl->virt_cmd_desc[i],
+				  ctrl->dma_cmd_desc[i]);
+	ctrl->n_cmd_desc = 0;
+	return ret;
+}
+
+static void qcom_qspi_dma_xfer(struct qcom_qspi *ctrl)
+{
+	/* Setup new interrupts */
+	writel(DMA_CHAIN_DONE, ctrl->base + MSTR_INT_EN);
+
+	/* kick off transfer */
+	writel((u32)((ctrl->dma_cmd_desc)[0]), ctrl->base + NEXT_DMA_DESC_ADDR);
+}
+
+/* Switch to DMA if transfer length exceeds this */
+#define QSPI_MAX_BYTES_FIFO 64
+
+static bool qcom_qspi_can_dma(struct spi_controller *ctlr,
+			 struct spi_device *slv, struct spi_transfer *xfer)
+{
+	return xfer->len > QSPI_MAX_BYTES_FIFO;
+}
+
 static int qcom_qspi_transfer_one(struct spi_master *master,
 				  struct spi_device *slv,
 				  struct spi_transfer *xfer)
@@ -266,6 +405,7 @@ static int qcom_qspi_transfer_one(struct spi_master *master,
 	int ret;
 	unsigned long speed_hz;
 	unsigned long flags;
+	u32 mstr_cfg;
 
 	speed_hz = slv->max_speed_hz;
 	if (xfer->speed_hz)
@@ -276,6 +416,7 @@ static int qcom_qspi_transfer_one(struct spi_master *master,
 		return ret;
 
 	spin_lock_irqsave(&ctrl->lock, flags);
+	mstr_cfg = readl(ctrl->base + MSTR_CONFIG);
 
 	/* We are half duplex, so either rx or tx will be set */
 	if (xfer->rx_buf) {
@@ -290,10 +431,36 @@ static int qcom_qspi_transfer_one(struct spi_master *master,
 	ctrl->xfer.is_last = list_is_last(&xfer->transfer_list,
 					  &master->cur_msg->transfers);
 	ctrl->xfer.rem_bytes = xfer->len;
+
+	if (xfer->rx_sg.nents || xfer->tx_sg.nents) {
+		/* do DMA transfer */
+		if (!(mstr_cfg & DMA_ENABLE)) {
+			mstr_cfg |= DMA_ENABLE;
+			writel(mstr_cfg, ctrl->base + MSTR_CONFIG);
+		}
+
+		ret = qcom_qspi_setup_dma_desc(ctrl, xfer);
+		if (ret != -EAGAIN) {
+			if (!ret)
+				qcom_qspi_dma_xfer(ctrl);
+			goto exit;
+		}
+		dev_warn_once(ctrl->dev, "DMA failure, falling back to PIO\n");
+		ret = 0; /* We'll retry w/ PIO */
+	}
+
+	if (mstr_cfg & DMA_ENABLE) {
+		mstr_cfg &= ~DMA_ENABLE;
+		writel(mstr_cfg, ctrl->base + MSTR_CONFIG);
+	}
 	qcom_qspi_pio_xfer(ctrl);
 
+exit:
 	spin_unlock_irqrestore(&ctrl->lock, flags);
 
+	if (ret)
+		return ret;
+
 	/* We'll call spi_finalize_current_transfer() when done */
 	return 1;
 }
@@ -328,6 +495,16 @@ static int qcom_qspi_prepare_message(struct spi_master *master,
 	return 0;
 }
 
+static int qcom_qspi_alloc_dma(struct qcom_qspi *ctrl)
+{
+	ctrl->dma_cmd_pool = dmam_pool_create("qspi cmd desc pool",
+		ctrl->dev, sizeof(struct qspi_cmd_desc), 0, 0);
+	if (!ctrl->dma_cmd_pool)
+		return -ENOMEM;
+
+	return 0;
+}
+
 static irqreturn_t pio_read(struct qcom_qspi *ctrl)
 {
 	u32 rd_fifo_status;
@@ -426,6 +603,7 @@ static irqreturn_t qcom_qspi_irq(int irq, void *dev_id)
 	int_status = readl(ctrl->base + MSTR_INT_STATUS);
 	writel(int_status, ctrl->base + MSTR_INT_STATUS);
 
+	/* PIO mode handling */
 	if (ctrl->xfer.dir == QSPI_WRITE) {
 		if (int_status & WR_FIFO_EMPTY)
 			ret = pio_write(ctrl);
@@ -449,6 +627,22 @@ static irqreturn_t qcom_qspi_irq(int irq, void *dev_id)
 		spi_finalize_current_transfer(dev_get_drvdata(ctrl->dev));
 	}
 
+	/* DMA mode handling */
+	if (int_status & DMA_CHAIN_DONE) {
+		int i;
+
+		writel(0, ctrl->base + MSTR_INT_EN);
+		ctrl->xfer.rem_bytes = 0;
+
+		for (i = 0; i < ctrl->n_cmd_desc; i++)
+			dma_pool_free(ctrl->dma_cmd_pool, ctrl->virt_cmd_desc[i],
+					  ctrl->dma_cmd_desc[i]);
+		ctrl->n_cmd_desc = 0;
+
+		ret = IRQ_HANDLED;
+		spi_finalize_current_transfer(dev_get_drvdata(ctrl->dev));
+	}
+
 	spin_unlock(&ctrl->lock);
 	return ret;
 }
@@ -517,7 +711,13 @@ static int qcom_qspi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (ret)
+		return dev_err_probe(dev, ret, "could not set DMA mask\n");
+
 	master->max_speed_hz = 300000000;
+	master->max_dma_len = 65536; /* as per HPG */
+	master->dma_alignment = QSPI_ALIGN_REQ;
 	master->num_chipselect = QSPI_NUM_CS;
 	master->bus_num = -1;
 	master->dev.of_node = pdev->dev.of_node;
@@ -528,6 +728,8 @@ static int qcom_qspi_probe(struct platform_device *pdev)
 	master->prepare_message = qcom_qspi_prepare_message;
 	master->transfer_one = qcom_qspi_transfer_one;
 	master->handle_err = qcom_qspi_handle_err;
+	if (of_property_read_bool(pdev->dev.of_node, "iommus"))
+		master->can_dma = qcom_qspi_can_dma;
 	master->auto_runtime_pm = true;
 
 	ret = devm_pm_opp_set_clkname(&pdev->dev, "core");
@@ -540,6 +742,10 @@ static int qcom_qspi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = qcom_qspi_alloc_dma(ctrl);
+	if (ret)
+		return ret;
+
 	pm_runtime_use_autosuspend(dev);
 	pm_runtime_set_autosuspend_delay(dev, 250);
 	pm_runtime_enable(dev);
diff --git a/drivers/spi/spi-rzv2m-csi.c b/drivers/spi/spi-rzv2m-csi.c
new file mode 100644
index 000000000000..14ad65da930d
--- /dev/null
+++ b/drivers/spi/spi-rzv2m-csi.c
@@ -0,0 +1,667 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Renesas RZ/V2M Clocked Serial Interface (CSI) driver
+ *
+ * Copyright (C) 2023 Renesas Electronics Corporation
+ */
+
+#include <linux/clk.h>
+#include <linux/count_zeros.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/spi/spi.h>
+
+/* Registers */
+#define CSI_MODE		0x00	/* CSI mode control */
+#define CSI_CLKSEL		0x04	/* CSI clock select */
+#define CSI_CNT			0x08	/* CSI control */
+#define CSI_INT			0x0C	/* CSI interrupt status */
+#define CSI_IFIFOL		0x10	/* CSI receive FIFO level display */
+#define CSI_OFIFOL		0x14	/* CSI transmit FIFO level display */
+#define CSI_IFIFO		0x18	/* CSI receive window */
+#define CSI_OFIFO		0x1C	/* CSI transmit window */
+#define CSI_FIFOTRG		0x20	/* CSI FIFO trigger level */
+
+/* CSI_MODE */
+#define CSI_MODE_CSIE		BIT(7)
+#define CSI_MODE_TRMD		BIT(6)
+#define CSI_MODE_CCL		BIT(5)
+#define CSI_MODE_DIR		BIT(4)
+#define CSI_MODE_CSOT		BIT(0)
+
+#define CSI_MODE_SETUP		0x00000040
+
+/* CSI_CLKSEL */
+#define CSI_CLKSEL_CKP		BIT(17)
+#define CSI_CLKSEL_DAP		BIT(16)
+#define CSI_CLKSEL_SLAVE	BIT(15)
+#define CSI_CLKSEL_CKS		GENMASK(14, 1)
+
+/* CSI_CNT */
+#define CSI_CNT_CSIRST		BIT(28)
+#define CSI_CNT_R_TRGEN		BIT(19)
+#define CSI_CNT_UNDER_E		BIT(13)
+#define CSI_CNT_OVERF_E		BIT(12)
+#define CSI_CNT_TREND_E		BIT(9)
+#define CSI_CNT_CSIEND_E	BIT(8)
+#define CSI_CNT_T_TRGR_E	BIT(4)
+#define CSI_CNT_R_TRGR_E	BIT(0)
+
+/* CSI_INT */
+#define CSI_INT_UNDER		BIT(13)
+#define CSI_INT_OVERF		BIT(12)
+#define CSI_INT_TREND		BIT(9)
+#define CSI_INT_CSIEND		BIT(8)
+#define CSI_INT_T_TRGR		BIT(4)
+#define CSI_INT_R_TRGR		BIT(0)
+
+/* CSI_FIFOTRG */
+#define CSI_FIFOTRG_R_TRG       GENMASK(2, 0)
+
+#define CSI_FIFO_SIZE_BYTES	32
+#define CSI_FIFO_HALF_SIZE	16
+#define CSI_EN_DIS_TIMEOUT_US	100
+#define CSI_CKS_MAX		0x3FFF
+
+#define UNDERRUN_ERROR		BIT(0)
+#define OVERFLOW_ERROR		BIT(1)
+#define TX_TIMEOUT_ERROR	BIT(2)
+#define RX_TIMEOUT_ERROR	BIT(3)
+
+#define CSI_MAX_SPI_SCKO	8000000
+
+struct rzv2m_csi_priv {
+	void __iomem *base;
+	struct clk *csiclk;
+	struct clk *pclk;
+	struct device *dev;
+	struct spi_controller *controller;
+	const u8 *txbuf;
+	u8 *rxbuf;
+	int buffer_len;
+	int bytes_sent;
+	int bytes_received;
+	int bytes_to_transfer;
+	int words_to_transfer;
+	unsigned char bytes_per_word;
+	wait_queue_head_t wait;
+	u8 errors;
+	u32 status;
+};
+
+static const unsigned char x_trg[] = {
+	0, 1, 1, 2, 2, 2, 2, 3,
+	3, 3, 3, 3, 3, 3, 3, 4,
+	4, 4, 4, 4, 4, 4, 4, 4,
+	4, 4, 4, 4, 4, 4, 4, 5
+};
+
+static const unsigned char x_trg_words[] = {
+	1,  2,  2,  4,  4,  4,  4,  8,
+	8,  8,  8,  8,  8,  8,  8,  16,
+	16, 16, 16, 16, 16, 16, 16, 16,
+	16, 16, 16, 16, 16, 16, 16, 32
+};
+
+static void rzv2m_csi_reg_write_bit(const struct rzv2m_csi_priv *csi,
+				    int reg_offs, int bit_mask, u32 value)
+{
+	int nr_zeros;
+	u32 tmp;
+
+	nr_zeros = count_trailing_zeros(bit_mask);
+	value <<= nr_zeros;
+
+	tmp = (readl(csi->base + reg_offs) & ~bit_mask) | value;
+	writel(tmp, csi->base + reg_offs);
+}
+
+static int rzv2m_csi_sw_reset(struct rzv2m_csi_priv *csi, int assert)
+{
+	u32 reg;
+
+	rzv2m_csi_reg_write_bit(csi, CSI_CNT, CSI_CNT_CSIRST, assert);
+
+	if (assert) {
+		return readl_poll_timeout(csi->base + CSI_MODE, reg,
+					  !(reg & CSI_MODE_CSOT), 0,
+					  CSI_EN_DIS_TIMEOUT_US);
+	}
+
+	return 0;
+}
+
+static int rzv2m_csi_start_stop_operation(const struct rzv2m_csi_priv *csi,
+					  int enable, bool wait)
+{
+	u32 reg;
+
+	rzv2m_csi_reg_write_bit(csi, CSI_MODE, CSI_MODE_CSIE, enable);
+
+	if (!enable && wait)
+		return readl_poll_timeout(csi->base + CSI_MODE, reg,
+					  !(reg & CSI_MODE_CSOT), 0,
+					  CSI_EN_DIS_TIMEOUT_US);
+
+	return 0;
+}
+
+static int rzv2m_csi_fill_txfifo(struct rzv2m_csi_priv *csi)
+{
+	int i;
+
+	if (readl(csi->base + CSI_OFIFOL))
+		return -EIO;
+
+	if (csi->bytes_per_word == 2) {
+		u16 *buf = (u16 *)csi->txbuf;
+
+		for (i = 0; i < csi->words_to_transfer; i++)
+			writel(buf[i], csi->base + CSI_OFIFO);
+	} else {
+		u8 *buf = (u8 *)csi->txbuf;
+
+		for (i = 0; i < csi->words_to_transfer; i++)
+			writel(buf[i], csi->base + CSI_OFIFO);
+	}
+
+	csi->txbuf += csi->bytes_to_transfer;
+	csi->bytes_sent += csi->bytes_to_transfer;
+
+	return 0;
+}
+
+static int rzv2m_csi_read_rxfifo(struct rzv2m_csi_priv *csi)
+{
+	int i;
+
+	if (readl(csi->base + CSI_IFIFOL) != csi->bytes_to_transfer)
+		return -EIO;
+
+	if (csi->bytes_per_word == 2) {
+		u16 *buf = (u16 *)csi->rxbuf;
+
+		for (i = 0; i < csi->words_to_transfer; i++)
+			buf[i] = (u16)readl(csi->base + CSI_IFIFO);
+	} else {
+		u8 *buf = (u8 *)csi->rxbuf;
+
+		for (i = 0; i < csi->words_to_transfer; i++)
+			buf[i] = (u8)readl(csi->base + CSI_IFIFO);
+	}
+
+	csi->rxbuf += csi->bytes_to_transfer;
+	csi->bytes_received += csi->bytes_to_transfer;
+
+	return 0;
+}
+
+static inline void rzv2m_csi_calc_current_transfer(struct rzv2m_csi_priv *csi)
+{
+	int bytes_transferred = max_t(int, csi->bytes_received, csi->bytes_sent);
+	int bytes_remaining = csi->buffer_len - bytes_transferred;
+	int to_transfer;
+
+	if (csi->txbuf)
+		/*
+		 * Leaving a little bit of headroom in the FIFOs makes it very
+		 * hard to raise an overflow error (which is only possible
+		 * when IP transmits and receives at the same time).
+		 */
+		to_transfer = min_t(int, CSI_FIFO_HALF_SIZE, bytes_remaining);
+	else
+		to_transfer = min_t(int, CSI_FIFO_SIZE_BYTES, bytes_remaining);
+
+	if (csi->bytes_per_word == 2)
+		to_transfer >>= 1;
+
+	/*
+	 * We can only choose a trigger level from a predefined set of values.
+	 * This will pick a value that is the greatest possible integer that's
+	 * less than or equal to the number of bytes we need to transfer.
+	 * This may result in multiple smaller transfers.
+	 */
+	csi->words_to_transfer = x_trg_words[to_transfer - 1];
+
+	if (csi->bytes_per_word == 2)
+		csi->bytes_to_transfer = csi->words_to_transfer << 1;
+	else
+		csi->bytes_to_transfer = csi->words_to_transfer;
+}
+
+static inline void rzv2m_csi_set_rx_fifo_trigger_level(struct rzv2m_csi_priv *csi)
+{
+	rzv2m_csi_reg_write_bit(csi, CSI_FIFOTRG, CSI_FIFOTRG_R_TRG,
+				x_trg[csi->words_to_transfer - 1]);
+}
+
+static inline void rzv2m_csi_enable_rx_trigger(struct rzv2m_csi_priv *csi,
+					       bool enable)
+{
+	rzv2m_csi_reg_write_bit(csi, CSI_CNT, CSI_CNT_R_TRGEN, enable);
+}
+
+static void rzv2m_csi_disable_irqs(const struct rzv2m_csi_priv *csi,
+				   u32 enable_bits)
+{
+	u32 cnt = readl(csi->base + CSI_CNT);
+
+	writel(cnt & ~enable_bits, csi->base + CSI_CNT);
+}
+
+static void rzv2m_csi_disable_all_irqs(struct rzv2m_csi_priv *csi)
+{
+	rzv2m_csi_disable_irqs(csi, CSI_CNT_R_TRGR_E | CSI_CNT_T_TRGR_E |
+			       CSI_CNT_CSIEND_E | CSI_CNT_TREND_E |
+			       CSI_CNT_OVERF_E | CSI_CNT_UNDER_E);
+}
+
+static inline void rzv2m_csi_clear_irqs(struct rzv2m_csi_priv *csi, u32 irqs)
+{
+	writel(irqs, csi->base + CSI_INT);
+}
+
+static void rzv2m_csi_clear_all_irqs(struct rzv2m_csi_priv *csi)
+{
+	rzv2m_csi_clear_irqs(csi, CSI_INT_UNDER | CSI_INT_OVERF |
+			     CSI_INT_TREND | CSI_INT_CSIEND |  CSI_INT_T_TRGR |
+			     CSI_INT_R_TRGR);
+}
+
+static void rzv2m_csi_enable_irqs(struct rzv2m_csi_priv *csi, u32 enable_bits)
+{
+	u32 cnt = readl(csi->base + CSI_CNT);
+
+	writel(cnt | enable_bits, csi->base + CSI_CNT);
+}
+
+static int rzv2m_csi_wait_for_interrupt(struct rzv2m_csi_priv *csi,
+					u32 wait_mask, u32 enable_bits)
+{
+	int ret;
+
+	rzv2m_csi_enable_irqs(csi, enable_bits);
+
+	ret = wait_event_timeout(csi->wait,
+				 ((csi->status & wait_mask) == wait_mask) ||
+				 csi->errors, HZ);
+
+	rzv2m_csi_disable_irqs(csi, enable_bits);
+
+	if (csi->errors)
+		return -EIO;
+
+	if (!ret)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int rzv2m_csi_wait_for_tx_empty(struct rzv2m_csi_priv *csi)
+{
+	int ret;
+
+	if (readl(csi->base + CSI_OFIFOL) == 0)
+		return 0;
+
+	ret = rzv2m_csi_wait_for_interrupt(csi, CSI_INT_TREND, CSI_CNT_TREND_E);
+
+	if (ret == -ETIMEDOUT)
+		csi->errors |= TX_TIMEOUT_ERROR;
+
+	return ret;
+}
+
+static inline int rzv2m_csi_wait_for_rx_ready(struct rzv2m_csi_priv *csi)
+{
+	int ret;
+
+	if (readl(csi->base + CSI_IFIFOL) == csi->bytes_to_transfer)
+		return 0;
+
+	ret = rzv2m_csi_wait_for_interrupt(csi, CSI_INT_R_TRGR,
+					   CSI_CNT_R_TRGR_E);
+
+	if (ret == -ETIMEDOUT)
+		csi->errors |= RX_TIMEOUT_ERROR;
+
+	return ret;
+}
+
+static irqreturn_t rzv2m_csi_irq_handler(int irq, void *data)
+{
+	struct rzv2m_csi_priv *csi = (struct rzv2m_csi_priv *)data;
+
+	csi->status = readl(csi->base + CSI_INT);
+	rzv2m_csi_disable_irqs(csi, csi->status);
+
+	if (csi->status & CSI_INT_OVERF)
+		csi->errors |= OVERFLOW_ERROR;
+	if (csi->status & CSI_INT_UNDER)
+		csi->errors |= UNDERRUN_ERROR;
+
+	wake_up(&csi->wait);
+
+	return IRQ_HANDLED;
+}
+
+static void rzv2m_csi_setup_clock(struct rzv2m_csi_priv *csi, u32 spi_hz)
+{
+	unsigned long csiclk_rate = clk_get_rate(csi->csiclk);
+	unsigned long pclk_rate = clk_get_rate(csi->pclk);
+	unsigned long csiclk_rate_limit = pclk_rate >> 1;
+	u32 cks;
+
+	/*
+	 * There is a restriction on the frequency of CSICLK, it has to be <=
+	 * PCLK / 2.
+	 */
+	if (csiclk_rate > csiclk_rate_limit) {
+		clk_set_rate(csi->csiclk, csiclk_rate >> 1);
+		csiclk_rate = clk_get_rate(csi->csiclk);
+	} else if ((csiclk_rate << 1) <= csiclk_rate_limit) {
+		clk_set_rate(csi->csiclk, csiclk_rate << 1);
+		csiclk_rate = clk_get_rate(csi->csiclk);
+	}
+
+	spi_hz = spi_hz > CSI_MAX_SPI_SCKO ? CSI_MAX_SPI_SCKO : spi_hz;
+
+	cks = DIV_ROUND_UP(csiclk_rate, spi_hz << 1);
+	if (cks > CSI_CKS_MAX)
+		cks = CSI_CKS_MAX;
+
+	dev_dbg(csi->dev, "SPI clk rate is %ldHz\n", csiclk_rate / (cks << 1));
+
+	rzv2m_csi_reg_write_bit(csi, CSI_CLKSEL, CSI_CLKSEL_CKS, cks);
+}
+
+static void rzv2m_csi_setup_operating_mode(struct rzv2m_csi_priv *csi,
+					   struct spi_transfer *t)
+{
+	if (t->rx_buf && !t->tx_buf)
+		/* Reception-only mode */
+		rzv2m_csi_reg_write_bit(csi, CSI_MODE, CSI_MODE_TRMD, 0);
+	else
+		/* Send and receive mode */
+		rzv2m_csi_reg_write_bit(csi, CSI_MODE, CSI_MODE_TRMD, 1);
+
+	csi->bytes_per_word = t->bits_per_word / 8;
+	rzv2m_csi_reg_write_bit(csi, CSI_MODE, CSI_MODE_CCL,
+				csi->bytes_per_word == 2);
+}
+
+static int rzv2m_csi_setup(struct spi_device *spi)
+{
+	struct rzv2m_csi_priv *csi = spi_controller_get_devdata(spi->controller);
+	int ret;
+
+	rzv2m_csi_sw_reset(csi, 0);
+
+	writel(CSI_MODE_SETUP, csi->base + CSI_MODE);
+
+	/* Setup clock polarity and phase timing */
+	rzv2m_csi_reg_write_bit(csi, CSI_CLKSEL, CSI_CLKSEL_CKP,
+				!(spi->mode & SPI_CPOL));
+	rzv2m_csi_reg_write_bit(csi, CSI_CLKSEL, CSI_CLKSEL_DAP,
+				!(spi->mode & SPI_CPHA));
+
+	/* Setup serial data order */
+	rzv2m_csi_reg_write_bit(csi, CSI_MODE, CSI_MODE_DIR,
+				!!(spi->mode & SPI_LSB_FIRST));
+
+	/* Set the operation mode as master */
+	rzv2m_csi_reg_write_bit(csi, CSI_CLKSEL, CSI_CLKSEL_SLAVE, 0);
+
+	/* Give the IP a SW reset */
+	ret = rzv2m_csi_sw_reset(csi, 1);
+	if (ret)
+		return ret;
+	rzv2m_csi_sw_reset(csi, 0);
+
+	/*
+	 * We need to enable the communication so that the clock will settle
+	 * for the right polarity before enabling the CS.
+	 */
+	rzv2m_csi_start_stop_operation(csi, 1, false);
+	udelay(10);
+	rzv2m_csi_start_stop_operation(csi, 0, false);
+
+	return 0;
+}
+
+static int rzv2m_csi_pio_transfer(struct rzv2m_csi_priv *csi)
+{
+	bool tx_completed = csi->txbuf ? false : true;
+	bool rx_completed = csi->rxbuf ? false : true;
+	int ret = 0;
+
+	/* Make sure the TX FIFO is empty */
+	writel(0, csi->base + CSI_OFIFOL);
+
+	csi->bytes_sent = 0;
+	csi->bytes_received = 0;
+	csi->errors = 0;
+
+	rzv2m_csi_disable_all_irqs(csi);
+	rzv2m_csi_clear_all_irqs(csi);
+	rzv2m_csi_enable_rx_trigger(csi, true);
+
+	while (!tx_completed || !rx_completed) {
+		/*
+		 * Decide how many words we are going to transfer during
+		 * this cycle (for both TX and RX), then set the RX FIFO trigger
+		 * level accordingly. No need to set a trigger level for the
+		 * TX FIFO, as this IP comes with an interrupt that fires when
+		 * the TX FIFO is empty.
+		 */
+		rzv2m_csi_calc_current_transfer(csi);
+		rzv2m_csi_set_rx_fifo_trigger_level(csi);
+
+		rzv2m_csi_enable_irqs(csi, CSI_INT_OVERF | CSI_INT_UNDER);
+
+		/* Make sure the RX FIFO is empty */
+		writel(0, csi->base + CSI_IFIFOL);
+
+		writel(readl(csi->base + CSI_INT), csi->base + CSI_INT);
+		csi->status = 0;
+
+		rzv2m_csi_start_stop_operation(csi, 1, false);
+
+		/* TX */
+		if (csi->txbuf) {
+			ret = rzv2m_csi_fill_txfifo(csi);
+			if (ret)
+				break;
+
+			ret = rzv2m_csi_wait_for_tx_empty(csi);
+			if (ret)
+				break;
+
+			if (csi->bytes_sent == csi->buffer_len)
+				tx_completed = true;
+		}
+
+		/*
+		 * Make sure the RX FIFO contains the desired number of words.
+		 * We then either flush its content, or we copy it onto
+		 * csi->rxbuf.
+		 */
+		ret = rzv2m_csi_wait_for_rx_ready(csi);
+		if (ret)
+			break;
+
+		/* RX */
+		if (csi->rxbuf) {
+			rzv2m_csi_start_stop_operation(csi, 0, false);
+
+			ret = rzv2m_csi_read_rxfifo(csi);
+			if (ret)
+				break;
+
+			if (csi->bytes_received == csi->buffer_len)
+				rx_completed = true;
+		}
+
+		ret = rzv2m_csi_start_stop_operation(csi, 0, true);
+		if (ret)
+			goto pio_quit;
+
+		if (csi->errors) {
+			ret = -EIO;
+			goto pio_quit;
+		}
+	}
+
+	rzv2m_csi_start_stop_operation(csi, 0, true);
+
+pio_quit:
+	rzv2m_csi_disable_all_irqs(csi);
+	rzv2m_csi_enable_rx_trigger(csi, false);
+	rzv2m_csi_clear_all_irqs(csi);
+
+	return ret;
+}
+
+static int rzv2m_csi_transfer_one(struct spi_controller *controller,
+				  struct spi_device *spi,
+				  struct spi_transfer *transfer)
+{
+	struct rzv2m_csi_priv *csi = spi_controller_get_devdata(controller);
+	struct device *dev = csi->dev;
+	int ret;
+
+	csi->txbuf = transfer->tx_buf;
+	csi->rxbuf = transfer->rx_buf;
+	csi->buffer_len = transfer->len;
+
+	rzv2m_csi_setup_operating_mode(csi, transfer);
+
+	rzv2m_csi_setup_clock(csi, transfer->speed_hz);
+
+	ret = rzv2m_csi_pio_transfer(csi);
+	if (ret) {
+		if (csi->errors & UNDERRUN_ERROR)
+			dev_err(dev, "Underrun error\n");
+		if (csi->errors & OVERFLOW_ERROR)
+			dev_err(dev, "Overflow error\n");
+		if (csi->errors & TX_TIMEOUT_ERROR)
+			dev_err(dev, "TX timeout error\n");
+		if (csi->errors & RX_TIMEOUT_ERROR)
+			dev_err(dev, "RX timeout error\n");
+	}
+
+	return ret;
+}
+
+static int rzv2m_csi_probe(struct platform_device *pdev)
+{
+	struct spi_controller *controller;
+	struct device *dev = &pdev->dev;
+	struct rzv2m_csi_priv *csi;
+	struct reset_control *rstc;
+	int irq;
+	int ret;
+
+	controller = devm_spi_alloc_master(dev, sizeof(*csi));
+	if (!controller)
+		return -ENOMEM;
+
+	csi = spi_controller_get_devdata(controller);
+	platform_set_drvdata(pdev, csi);
+
+	csi->dev = dev;
+	csi->controller = controller;
+
+	csi->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(csi->base))
+		return PTR_ERR(csi->base);
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	csi->csiclk = devm_clk_get(dev, "csiclk");
+	if (IS_ERR(csi->csiclk))
+		return dev_err_probe(dev, PTR_ERR(csi->csiclk),
+				     "could not get csiclk\n");
+
+	csi->pclk = devm_clk_get(dev, "pclk");
+	if (IS_ERR(csi->pclk))
+		return dev_err_probe(dev, PTR_ERR(csi->pclk),
+				     "could not get pclk\n");
+
+	rstc = devm_reset_control_get_shared(dev, NULL);
+	if (IS_ERR(rstc))
+		return dev_err_probe(dev, PTR_ERR(rstc), "Missing reset ctrl\n");
+
+	init_waitqueue_head(&csi->wait);
+
+	controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
+	controller->dev.of_node = pdev->dev.of_node;
+	controller->bits_per_word_mask = SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
+	controller->setup = rzv2m_csi_setup;
+	controller->transfer_one = rzv2m_csi_transfer_one;
+	controller->use_gpio_descriptors = true;
+
+	ret = devm_request_irq(dev, irq, rzv2m_csi_irq_handler, 0,
+			       dev_name(dev), csi);
+	if (ret)
+		return dev_err_probe(dev, ret, "cannot request IRQ\n");
+
+	/*
+	 * The reset also affects other HW that is not under the control
+	 * of Linux. Therefore, all we can do is make sure the reset is
+	 * deasserted.
+	 */
+	reset_control_deassert(rstc);
+
+	/* Make sure the IP is in SW reset state */
+	ret = rzv2m_csi_sw_reset(csi, 1);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(csi->csiclk);
+	if (ret)
+		return dev_err_probe(dev, ret, "could not enable csiclk\n");
+
+	ret = spi_register_controller(controller);
+	if (ret) {
+		clk_disable_unprepare(csi->csiclk);
+		return dev_err_probe(dev, ret, "register controller failed\n");
+	}
+
+	return 0;
+}
+
+static int rzv2m_csi_remove(struct platform_device *pdev)
+{
+	struct rzv2m_csi_priv *csi = platform_get_drvdata(pdev);
+
+	spi_unregister_controller(csi->controller);
+	rzv2m_csi_sw_reset(csi, 1);
+	clk_disable_unprepare(csi->csiclk);
+
+	return 0;
+}
+
+static const struct of_device_id rzv2m_csi_match[] = {
+	{ .compatible = "renesas,rzv2m-csi" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, rzv2m_csi_match);
+
+static struct platform_driver rzv2m_csi_drv = {
+	.probe = rzv2m_csi_probe,
+	.remove = rzv2m_csi_remove,
+	.driver = {
+		.name = "rzv2m_csi",
+		.of_match_table = rzv2m_csi_match,
+	},
+};
+module_platform_driver(rzv2m_csi_drv);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Fabrizio Castro <castro.fabrizio.jz@renesas.com>");
+MODULE_DESCRIPTION("Clocked Serial Interface Driver");
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 7ac17f0d18a9..fd55697144cc 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -19,7 +19,6 @@
 #include <linux/platform_data/spi-s3c64xx.h>
 
 #define MAX_SPI_PORTS		12
-#define S3C64XX_SPI_QUIRK_POLL		(1 << 0)
 #define S3C64XX_SPI_QUIRK_CS_AUTO	(1 << 1)
 #define AUTOSUSPEND_TIMEOUT	2000
 
@@ -59,6 +58,8 @@
 #define S3C64XX_SPI_MODE_BUS_TSZ_HALFWORD	(1<<17)
 #define S3C64XX_SPI_MODE_BUS_TSZ_WORD		(2<<17)
 #define S3C64XX_SPI_MODE_BUS_TSZ_MASK		(3<<17)
+#define S3C64XX_SPI_MODE_RX_RDY_LVL		GENMASK(16, 11)
+#define S3C64XX_SPI_MODE_RX_RDY_LVL_SHIFT	11
 #define S3C64XX_SPI_MODE_SELF_LOOPBACK		(1<<3)
 #define S3C64XX_SPI_MODE_RXDMA_ON		(1<<2)
 #define S3C64XX_SPI_MODE_TXDMA_ON		(1<<1)
@@ -115,8 +116,10 @@
 
 #define S3C64XX_SPI_TRAILCNT		S3C64XX_SPI_MAX_TRAILCNT
 
+#define S3C64XX_SPI_POLLING_SIZE	32
+
 #define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t)
-#define is_polling(x)	(x->port_conf->quirks & S3C64XX_SPI_QUIRK_POLL)
+#define is_polling(x)	(x->cntrlr_info->polling)
 
 #define RXBUSY    (1<<2)
 #define TXBUSY    (1<<3)
@@ -553,7 +556,7 @@ static int s3c64xx_wait_for_dma(struct s3c64xx_spi_driver_data *sdd,
 }
 
 static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
-				struct spi_transfer *xfer)
+				struct spi_transfer *xfer, bool use_irq)
 {
 	void __iomem *regs = sdd->regs;
 	unsigned long val;
@@ -562,11 +565,24 @@ static int s3c64xx_wait_for_pio(struct s3c64xx_spi_driver_data *sdd,
 	u32 cpy_len;
 	u8 *buf;
 	int ms;
+	unsigned long time_us;
 
-	/* millisecs to xfer 'len' bytes @ 'cur_speed' */
-	ms = xfer->len * 8 * 1000 / sdd->cur_speed;
+	/* microsecs to xfer 'len' bytes @ 'cur_speed' */
+	time_us = (xfer->len * 8 * 1000 * 1000) / sdd->cur_speed;
+	ms = (time_us / 1000);
 	ms += 10; /* some tolerance */
 
+	/* sleep during signal transfer time */
+	status = readl(regs + S3C64XX_SPI_STATUS);
+	if (RX_FIFO_LVL(status, sdd) < xfer->len)
+		usleep_range(time_us / 2, time_us);
+
+	if (use_irq) {
+		val = msecs_to_jiffies(ms);
+		if (!wait_for_completion_timeout(&sdd->xfer_completion, val))
+			return -EIO;
+	}
+
 	val = msecs_to_loops(ms);
 	do {
 		status = readl(regs + S3C64XX_SPI_STATUS);
@@ -729,10 +745,13 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master,
 	void *rx_buf = NULL;
 	int target_len = 0, origin_len = 0;
 	int use_dma = 0;
+	bool use_irq = false;
 	int status;
 	u32 speed;
 	u8 bpw;
 	unsigned long flags;
+	u32 rdy_lv;
+	u32 val;
 
 	reinit_completion(&sdd->xfer_completion);
 
@@ -753,17 +772,46 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master,
 	    sdd->rx_dma.ch && sdd->tx_dma.ch) {
 		use_dma = 1;
 
-	} else if (xfer->len > fifo_len) {
+	} else if (xfer->len >= fifo_len) {
 		tx_buf = xfer->tx_buf;
 		rx_buf = xfer->rx_buf;
 		origin_len = xfer->len;
-
 		target_len = xfer->len;
-		if (xfer->len > fifo_len)
-			xfer->len = fifo_len;
+		xfer->len = fifo_len - 1;
 	}
 
 	do {
+		/* transfer size is greater than 32, change to IRQ mode */
+		if (!use_dma && xfer->len > S3C64XX_SPI_POLLING_SIZE)
+			use_irq = true;
+
+		if (use_irq) {
+			reinit_completion(&sdd->xfer_completion);
+
+			rdy_lv = xfer->len;
+			/* Setup RDY_FIFO trigger Level
+			 * RDY_LVL =
+			 * fifo_lvl up to 64 byte -> N bytes
+			 *               128 byte -> RDY_LVL * 2 bytes
+			 *               256 byte -> RDY_LVL * 4 bytes
+			 */
+			if (fifo_len == 128)
+				rdy_lv /= 2;
+			else if (fifo_len == 256)
+				rdy_lv /= 4;
+
+			val = readl(sdd->regs + S3C64XX_SPI_MODE_CFG);
+			val &= ~S3C64XX_SPI_MODE_RX_RDY_LVL;
+			val |= (rdy_lv << S3C64XX_SPI_MODE_RX_RDY_LVL_SHIFT);
+			writel(val, sdd->regs + S3C64XX_SPI_MODE_CFG);
+
+			/* Enable FIFO_RDY_EN IRQ */
+			val = readl(sdd->regs + S3C64XX_SPI_INT_EN);
+			writel((val | S3C64XX_SPI_INT_RX_FIFORDY_EN),
+					sdd->regs + S3C64XX_SPI_INT_EN);
+
+		}
+
 		spin_lock_irqsave(&sdd->lock, flags);
 
 		/* Pending only which is to be done */
@@ -785,7 +833,7 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master,
 		if (use_dma)
 			status = s3c64xx_wait_for_dma(sdd, xfer);
 		else
-			status = s3c64xx_wait_for_pio(sdd, xfer);
+			status = s3c64xx_wait_for_pio(sdd, xfer, use_irq);
 
 		if (status) {
 			dev_err(&spi->dev,
@@ -824,8 +872,8 @@ static int s3c64xx_spi_transfer_one(struct spi_master *master,
 			if (xfer->rx_buf)
 				xfer->rx_buf += xfer->len;
 
-			if (target_len > fifo_len)
-				xfer->len = fifo_len;
+			if (target_len >= fifo_len)
+				xfer->len = fifo_len - 1;
 			else
 				xfer->len = target_len;
 		}
@@ -995,6 +1043,14 @@ static irqreturn_t s3c64xx_spi_irq(int irq, void *data)
 		dev_err(&spi->dev, "TX underrun\n");
 	}
 
+	if (val & S3C64XX_SPI_ST_RX_FIFORDY) {
+		complete(&sdd->xfer_completion);
+		/* No pending clear irq, turn-off INT_EN_RX_FIFO_RDY */
+		val = readl(sdd->regs + S3C64XX_SPI_INT_EN);
+		writel((val & ~S3C64XX_SPI_INT_RX_FIFORDY_EN),
+				sdd->regs + S3C64XX_SPI_INT_EN);
+	}
+
 	/* Clear the pending irq by setting and then clearing it */
 	writel(clr, sdd->regs + S3C64XX_SPI_PENDING_CLR);
 	writel(0, sdd->regs + S3C64XX_SPI_PENDING_CLR);
@@ -1068,6 +1124,7 @@ static struct s3c64xx_spi_info *s3c64xx_spi_parse_dt(struct device *dev)
 	}
 
 	sci->no_cs = of_property_read_bool(dev->of_node, "no-cs-readback");
+	sci->polling = !of_property_present(dev->of_node, "dmas");
 
 	return sci;
 }
@@ -1103,29 +1160,23 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 			return PTR_ERR(sci);
 	}
 
-	if (!sci) {
-		dev_err(&pdev->dev, "platform_data missing!\n");
-		return -ENODEV;
-	}
+	if (!sci)
+		return dev_err_probe(&pdev->dev, -ENODEV,
+				     "Platform_data missing!\n");
 
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (mem_res == NULL) {
-		dev_err(&pdev->dev, "Unable to get SPI MEM resource\n");
-		return -ENXIO;
-	}
+	if (!mem_res)
+		return dev_err_probe(&pdev->dev, -ENXIO,
+				     "Unable to get SPI MEM resource\n");
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_warn(&pdev->dev, "Failed to get IRQ: %d\n", irq);
-		return irq;
-	}
+	if (irq < 0)
+		return dev_err_probe(&pdev->dev, irq, "Failed to get IRQ\n");
 
-	master = spi_alloc_master(&pdev->dev,
-				sizeof(struct s3c64xx_spi_driver_data));
-	if (master == NULL) {
-		dev_err(&pdev->dev, "Unable to allocate SPI Master\n");
-		return -ENOMEM;
-	}
+	master = devm_spi_alloc_master(&pdev->dev, sizeof(*sdd));
+	if (!master)
+		return dev_err_probe(&pdev->dev, -ENOMEM,
+				     "Unable to allocate SPI Master\n");
 
 	platform_set_drvdata(pdev, master);
 
@@ -1137,11 +1188,9 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 	sdd->sfr_start = mem_res->start;
 	if (pdev->dev.of_node) {
 		ret = of_alias_get_id(pdev->dev.of_node, "spi");
-		if (ret < 0) {
-			dev_err(&pdev->dev, "failed to get alias id, errno %d\n",
-				ret);
-			goto err_deref_master;
-		}
+		if (ret < 0)
+			return dev_err_probe(&pdev->dev, ret,
+					     "Failed to get alias id\n");
 		sdd->port_id = ret;
 	} else {
 		sdd->port_id = pdev->id;
@@ -1175,59 +1224,31 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 		master->can_dma = s3c64xx_spi_can_dma;
 
 	sdd->regs = devm_ioremap_resource(&pdev->dev, mem_res);
-	if (IS_ERR(sdd->regs)) {
-		ret = PTR_ERR(sdd->regs);
-		goto err_deref_master;
-	}
+	if (IS_ERR(sdd->regs))
+		return PTR_ERR(sdd->regs);
 
-	if (sci->cfg_gpio && sci->cfg_gpio()) {
-		dev_err(&pdev->dev, "Unable to config gpio\n");
-		ret = -EBUSY;
-		goto err_deref_master;
-	}
+	if (sci->cfg_gpio && sci->cfg_gpio())
+		return dev_err_probe(&pdev->dev, -EBUSY,
+				     "Unable to config gpio\n");
 
 	/* Setup clocks */
-	sdd->clk = devm_clk_get(&pdev->dev, "spi");
-	if (IS_ERR(sdd->clk)) {
-		dev_err(&pdev->dev, "Unable to acquire clock 'spi'\n");
-		ret = PTR_ERR(sdd->clk);
-		goto err_deref_master;
-	}
-
-	ret = clk_prepare_enable(sdd->clk);
-	if (ret) {
-		dev_err(&pdev->dev, "Couldn't enable clock 'spi'\n");
-		goto err_deref_master;
-	}
+	sdd->clk = devm_clk_get_enabled(&pdev->dev, "spi");
+	if (IS_ERR(sdd->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(sdd->clk),
+				     "Unable to acquire clock 'spi'\n");
 
 	sprintf(clk_name, "spi_busclk%d", sci->src_clk_nr);
-	sdd->src_clk = devm_clk_get(&pdev->dev, clk_name);
-	if (IS_ERR(sdd->src_clk)) {
-		dev_err(&pdev->dev,
-			"Unable to acquire clock '%s'\n", clk_name);
-		ret = PTR_ERR(sdd->src_clk);
-		goto err_disable_clk;
-	}
-
-	ret = clk_prepare_enable(sdd->src_clk);
-	if (ret) {
-		dev_err(&pdev->dev, "Couldn't enable clock '%s'\n", clk_name);
-		goto err_disable_clk;
-	}
+	sdd->src_clk = devm_clk_get_enabled(&pdev->dev, clk_name);
+	if (IS_ERR(sdd->src_clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(sdd->src_clk),
+				     "Unable to acquire clock '%s'\n",
+				     clk_name);
 
 	if (sdd->port_conf->clk_ioclk) {
-		sdd->ioclk = devm_clk_get(&pdev->dev, "spi_ioclk");
-		if (IS_ERR(sdd->ioclk)) {
-			dev_err(&pdev->dev, "Unable to acquire 'ioclk'\n");
-			ret = PTR_ERR(sdd->ioclk);
-			goto err_disable_src_clk;
-		}
-
-		ret = clk_prepare_enable(sdd->ioclk);
-		if (ret) {
-			dev_err(&pdev->dev, "Couldn't enable clock 'ioclk'\n");
-			goto err_disable_src_clk;
-		}
+		sdd->ioclk = devm_clk_get_enabled(&pdev->dev, "spi_ioclk");
+		if (IS_ERR(sdd->ioclk))
+			return dev_err_probe(&pdev->dev, PTR_ERR(sdd->ioclk),
+					     "Unable to acquire 'ioclk'\n");
 	}
 
 	pm_runtime_set_autosuspend_delay(&pdev->dev, AUTOSUSPEND_TIMEOUT);
@@ -1275,14 +1296,6 @@ err_pm_put:
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
 
-	clk_disable_unprepare(sdd->ioclk);
-err_disable_src_clk:
-	clk_disable_unprepare(sdd->src_clk);
-err_disable_clk:
-	clk_disable_unprepare(sdd->clk);
-err_deref_master:
-	spi_master_put(master);
-
 	return ret;
 }
 
@@ -1300,12 +1313,6 @@ static void s3c64xx_spi_remove(struct platform_device *pdev)
 		dma_release_channel(sdd->tx_dma.ch);
 	}
 
-	clk_disable_unprepare(sdd->ioclk);
-
-	clk_disable_unprepare(sdd->src_clk);
-
-	clk_disable_unprepare(sdd->clk);
-
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_set_suspended(&pdev->dev);
diff --git a/drivers/spi/spi-sc18is602.c b/drivers/spi/spi-sc18is602.c
index 70012333020b..d52ed67243f7 100644
--- a/drivers/spi/spi-sc18is602.c
+++ b/drivers/spi/spi-sc18is602.c
@@ -337,7 +337,7 @@ static struct i2c_driver sc18is602_driver = {
 		.name = "sc18is602",
 		.of_match_table = of_match_ptr(sc18is602_of_match),
 	},
-	.probe_new = sc18is602_probe,
+	.probe = sc18is602_probe,
 	.id_table = sc18is602_id,
 };
 
diff --git a/drivers/spi/spi-sn-f-ospi.c b/drivers/spi/spi-sn-f-ospi.c
index a2bd9dcde075..d64d3f75c726 100644
--- a/drivers/spi/spi-sn-f-ospi.c
+++ b/drivers/spi/spi-sn-f-ospi.c
@@ -526,7 +526,7 @@ static int f_ospi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 static bool f_ospi_supports_op_width(struct spi_mem *mem,
 				     const struct spi_mem_op *op)
 {
-	u8 width_available[] = { 0, 1, 2, 4, 8 };
+	static const u8 width_available[] = { 0, 1, 2, 4, 8 };
 	u8 width_op[] = { op->cmd.buswidth, op->addr.buswidth,
 			  op->dummy.buswidth, op->data.buswidth };
 	bool is_match_found;
@@ -566,7 +566,7 @@ static bool f_ospi_supports_op(struct spi_mem *mem,
 
 static int f_ospi_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 {
-	op->data.nbytes = min((int)op->data.nbytes, (int)(OSPI_DAT_SIZE_MAX));
+	op->data.nbytes = min_t(int, op->data.nbytes, OSPI_DAT_SIZE_MAX);
 
 	return 0;
 }
@@ -634,18 +634,12 @@ static int f_ospi_probe(struct platform_device *pdev)
 		goto err_put_ctlr;
 	}
 
-	ospi->clk = devm_clk_get(dev, NULL);
+	ospi->clk = devm_clk_get_enabled(dev, NULL);
 	if (IS_ERR(ospi->clk)) {
 		ret = PTR_ERR(ospi->clk);
 		goto err_put_ctlr;
 	}
 
-	ret = clk_prepare_enable(ospi->clk);
-	if (ret) {
-		dev_err(dev, "Failed to enable the clock\n");
-		goto err_disable_clk;
-	}
-
 	mutex_init(&ospi->mlock);
 
 	ret = f_ospi_init(ospi);
@@ -661,9 +655,6 @@ static int f_ospi_probe(struct platform_device *pdev)
 err_destroy_mutex:
 	mutex_destroy(&ospi->mlock);
 
-err_disable_clk:
-	clk_disable_unprepare(ospi->clk);
-
 err_put_ctlr:
 	spi_controller_put(ctlr);
 
@@ -674,8 +665,6 @@ static void f_ospi_remove(struct platform_device *pdev)
 {
 	struct f_ospi *ospi = platform_get_drvdata(pdev);
 
-	clk_disable_unprepare(ospi->clk);
-
 	mutex_destroy(&ospi->mlock);
 }
 
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index d6598e4116bd..6d10fa4ab783 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 //
-// STMicroelectronics STM32 SPI Controller driver (master mode only)
+// STMicroelectronics STM32 SPI Controller driver
 //
 // Copyright (C) 2017, STMicroelectronics - All Rights Reserved
 // Author(s): Amelie Delaunay <amelie.delaunay@st.com> for STMicroelectronics.
@@ -117,6 +117,7 @@
 #define STM32H7_SPI_CFG2_CPHA		BIT(24)
 #define STM32H7_SPI_CFG2_CPOL		BIT(25)
 #define STM32H7_SPI_CFG2_SSM		BIT(26)
+#define STM32H7_SPI_CFG2_SSIOP		BIT(28)
 #define STM32H7_SPI_CFG2_AFCNTR		BIT(31)
 
 /* STM32H7_SPI_IER bit fields */
@@ -170,6 +171,10 @@
  */
 #define SPI_DMA_MIN_BYTES	16
 
+/* STM32 SPI driver helpers */
+#define STM32_SPI_MASTER_MODE(stm32_spi) (!(stm32_spi)->device_mode)
+#define STM32_SPI_DEVICE_MODE(stm32_spi) ((stm32_spi)->device_mode)
+
 /**
  * struct stm32_spi_reg - stm32 SPI register & bitfield desc
  * @reg:		register offset
@@ -190,6 +195,7 @@ struct stm32_spi_reg {
  * @cpol: clock polarity register and polarity bit
  * @cpha: clock phase register and phase bit
  * @lsb_first: LSB transmitted first register and bit
+ * @cs_high: chips select active value
  * @br: baud rate register and bitfields
  * @rx: SPI RX data register
  * @tx: SPI TX data register
@@ -201,6 +207,7 @@ struct stm32_spi_regspec {
 	const struct stm32_spi_reg cpol;
 	const struct stm32_spi_reg cpha;
 	const struct stm32_spi_reg lsb_first;
+	const struct stm32_spi_reg cs_high;
 	const struct stm32_spi_reg br;
 	const struct stm32_spi_reg rx;
 	const struct stm32_spi_reg tx;
@@ -258,7 +265,7 @@ struct stm32_spi_cfg {
 /**
  * struct stm32_spi - private data of the SPI controller
  * @dev: driver model representation of the controller
- * @master: controller master interface
+ * @ctrl: controller interface
  * @cfg: compatible configuration data
  * @base: virtual memory area
  * @clk: hw kernel clock feeding the SPI clock generator
@@ -280,10 +287,11 @@ struct stm32_spi_cfg {
  * @dma_tx: dma channel for TX transfer
  * @dma_rx: dma channel for RX transfer
  * @phys_addr: SPI registers physical base address
+ * @device_mode: the controller is configured as SPI device
  */
 struct stm32_spi {
 	struct device *dev;
-	struct spi_master *master;
+	struct spi_controller *ctrl;
 	const struct stm32_spi_cfg *cfg;
 	void __iomem *base;
 	struct clk *clk;
@@ -307,6 +315,8 @@ struct stm32_spi {
 	struct dma_chan *dma_tx;
 	struct dma_chan *dma_rx;
 	dma_addr_t phys_addr;
+
+	bool device_mode;
 };
 
 static const struct stm32_spi_regspec stm32f4_spi_regspec = {
@@ -318,6 +328,7 @@ static const struct stm32_spi_regspec stm32f4_spi_regspec = {
 	.cpol = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_CPOL },
 	.cpha = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_CPHA },
 	.lsb_first = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_LSBFRST },
+	.cs_high = {},
 	.br = { STM32F4_SPI_CR1, STM32F4_SPI_CR1_BR, STM32F4_SPI_CR1_BR_SHIFT },
 
 	.rx = { STM32F4_SPI_DR },
@@ -336,6 +347,7 @@ static const struct stm32_spi_regspec stm32h7_spi_regspec = {
 	.cpol = { STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_CPOL },
 	.cpha = { STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_CPHA },
 	.lsb_first = { STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_LSBFRST },
+	.cs_high = { STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_SSIOP },
 	.br = { STM32H7_SPI_CFG1, STM32H7_SPI_CFG1_MBR,
 		STM32H7_SPI_CFG1_MBR_SHIFT },
 
@@ -437,9 +449,9 @@ static int stm32_spi_prepare_mbr(struct stm32_spi *spi, u32 speed_hz,
 	div = DIV_ROUND_CLOSEST(spi->clk_rate & ~0x1, speed_hz);
 
 	/*
-	 * SPI framework set xfer->speed_hz to master->max_speed_hz if
-	 * xfer->speed_hz is greater than master->max_speed_hz, and it returns
-	 * an error when xfer->speed_hz is lower than master->min_speed_hz, so
+	 * SPI framework set xfer->speed_hz to ctrl->max_speed_hz if
+	 * xfer->speed_hz is greater than ctrl->max_speed_hz, and it returns
+	 * an error when xfer->speed_hz is lower than ctrl->min_speed_hz, so
 	 * no need to check it there.
 	 * However, we need to ensure the following calculations.
 	 */
@@ -657,9 +669,9 @@ static void stm32f4_spi_disable(struct stm32_spi *spi)
 	}
 
 	if (spi->cur_usedma && spi->dma_tx)
-		dmaengine_terminate_all(spi->dma_tx);
+		dmaengine_terminate_async(spi->dma_tx);
 	if (spi->cur_usedma && spi->dma_rx)
-		dmaengine_terminate_all(spi->dma_rx);
+		dmaengine_terminate_async(spi->dma_rx);
 
 	stm32_spi_clr_bits(spi, STM32F4_SPI_CR1, STM32F4_SPI_CR1_SPE);
 
@@ -696,9 +708,9 @@ static void stm32h7_spi_disable(struct stm32_spi *spi)
 	}
 
 	if (spi->cur_usedma && spi->dma_tx)
-		dmaengine_terminate_all(spi->dma_tx);
+		dmaengine_terminate_async(spi->dma_tx);
 	if (spi->cur_usedma && spi->dma_rx)
-		dmaengine_terminate_all(spi->dma_rx);
+		dmaengine_terminate_async(spi->dma_rx);
 
 	stm32_spi_clr_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_SPE);
 
@@ -714,19 +726,19 @@ static void stm32h7_spi_disable(struct stm32_spi *spi)
 
 /**
  * stm32_spi_can_dma - Determine if the transfer is eligible for DMA use
- * @master: controller master interface
+ * @ctrl: controller interface
  * @spi_dev: pointer to the spi device
  * @transfer: pointer to spi transfer
  *
  * If driver has fifo and the current transfer size is greater than fifo size,
  * use DMA. Otherwise use DMA for transfer longer than defined DMA min bytes.
  */
-static bool stm32_spi_can_dma(struct spi_master *master,
+static bool stm32_spi_can_dma(struct spi_controller *ctrl,
 			      struct spi_device *spi_dev,
 			      struct spi_transfer *transfer)
 {
 	unsigned int dma_size;
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 
 	if (spi->cfg->has_fifo)
 		dma_size = spi->fifo_size;
@@ -742,12 +754,12 @@ static bool stm32_spi_can_dma(struct spi_master *master,
 /**
  * stm32f4_spi_irq_event - Interrupt handler for SPI controller events
  * @irq: interrupt line
- * @dev_id: SPI controller master interface
+ * @dev_id: SPI controller ctrl interface
  */
 static irqreturn_t stm32f4_spi_irq_event(int irq, void *dev_id)
 {
-	struct spi_master *master = dev_id;
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct spi_controller *ctrl = dev_id;
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 	u32 sr, mask = 0;
 	bool end = false;
 
@@ -830,14 +842,14 @@ end_irq:
 /**
  * stm32f4_spi_irq_thread - Thread of interrupt handler for SPI controller
  * @irq: interrupt line
- * @dev_id: SPI controller master interface
+ * @dev_id: SPI controller interface
  */
 static irqreturn_t stm32f4_spi_irq_thread(int irq, void *dev_id)
 {
-	struct spi_master *master = dev_id;
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct spi_controller *ctrl = dev_id;
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 
-	spi_finalize_current_transfer(master);
+	spi_finalize_current_transfer(ctrl);
 	stm32f4_spi_disable(spi);
 
 	return IRQ_HANDLED;
@@ -846,12 +858,12 @@ static irqreturn_t stm32f4_spi_irq_thread(int irq, void *dev_id)
 /**
  * stm32h7_spi_irq_thread - Thread of interrupt handler for SPI controller
  * @irq: interrupt line
- * @dev_id: SPI controller master interface
+ * @dev_id: SPI controller interface
  */
 static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 {
-	struct spi_master *master = dev_id;
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct spi_controller *ctrl = dev_id;
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 	u32 sr, ier, mask;
 	unsigned long flags;
 	bool end = false;
@@ -931,7 +943,7 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 
 	if (end) {
 		stm32h7_spi_disable(spi);
-		spi_finalize_current_transfer(master);
+		spi_finalize_current_transfer(ctrl);
 	}
 
 	return IRQ_HANDLED;
@@ -939,13 +951,13 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 
 /**
  * stm32_spi_prepare_msg - set up the controller to transfer a single message
- * @master: controller master interface
+ * @ctrl: controller interface
  * @msg: pointer to spi message
  */
-static int stm32_spi_prepare_msg(struct spi_master *master,
+static int stm32_spi_prepare_msg(struct spi_controller *ctrl,
 				 struct spi_message *msg)
 {
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 	struct spi_device *spi_dev = msg->spi;
 	struct device_node *np = spi_dev->dev.of_node;
 	unsigned long flags;
@@ -971,6 +983,11 @@ static int stm32_spi_prepare_msg(struct spi_master *master,
 	else
 		clrb |= spi->cfg->regs->lsb_first.mask;
 
+	if (STM32_SPI_DEVICE_MODE(spi) && spi_dev->mode & SPI_CS_HIGH)
+		setb |= spi->cfg->regs->cs_high.mask;
+	else
+		clrb |= spi->cfg->regs->cs_high.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),
@@ -984,9 +1001,9 @@ static int stm32_spi_prepare_msg(struct spi_master *master,
 	if (spi->cfg->set_number_of_data) {
 		int ret;
 
-		ret = spi_split_transfers_maxwords(master, msg,
-						   STM32H7_SPI_TSIZE_MAX,
-						   GFP_KERNEL | GFP_DMA);
+		ret = spi_split_transfers_maxsize(ctrl, msg,
+						  STM32H7_SPI_TSIZE_MAX,
+						  GFP_KERNEL | GFP_DMA);
 		if (ret)
 			return ret;
 	}
@@ -1016,7 +1033,7 @@ static void stm32f4_spi_dma_tx_cb(void *data)
 	struct stm32_spi *spi = data;
 
 	if (spi->cur_comm == SPI_SIMPLEX_TX || spi->cur_comm == SPI_3WIRE_TX) {
-		spi_finalize_current_transfer(spi->master);
+		spi_finalize_current_transfer(spi->ctrl);
 		stm32f4_spi_disable(spi);
 	}
 }
@@ -1031,7 +1048,7 @@ static void stm32_spi_dma_rx_cb(void *data)
 {
 	struct stm32_spi *spi = data;
 
-	spi_finalize_current_transfer(spi->master);
+	spi_finalize_current_transfer(spi->ctrl);
 	spi->cfg->disable(spi);
 }
 
@@ -1161,7 +1178,8 @@ static int stm32h7_spi_transfer_one_irq(struct stm32_spi *spi)
 	if (spi->tx_buf)
 		stm32h7_spi_write_txfifo(spi);
 
-	stm32_spi_set_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_CSTART);
+	if (STM32_SPI_MASTER_MODE(spi))
+		stm32_spi_set_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_CSTART);
 
 	writel_relaxed(ier, spi->base + STM32H7_SPI_IER);
 
@@ -1208,7 +1226,8 @@ static void stm32h7_spi_transfer_one_dma_start(struct stm32_spi *spi)
 
 	stm32_spi_enable(spi);
 
-	stm32_spi_set_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_CSTART);
+	if (STM32_SPI_MASTER_MODE(spi))
+		stm32_spi_set_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_CSTART);
 }
 
 /**
@@ -1302,7 +1321,7 @@ static int stm32_spi_transfer_one_dma(struct stm32_spi *spi,
 
 dma_submit_error:
 	if (spi->dma_rx)
-		dmaengine_terminate_all(spi->dma_rx);
+		dmaengine_terminate_sync(spi->dma_rx);
 
 dma_desc_error:
 	stm32_spi_clr_bits(spi, spi->cfg->regs->dma_rx_en.reg,
@@ -1536,16 +1555,18 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 	spi->cfg->set_bpw(spi);
 
 	/* Update spi->cur_speed with real clock speed */
-	mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz,
-				    spi->cfg->baud_rate_div_min,
-				    spi->cfg->baud_rate_div_max);
-	if (mbr < 0) {
-		ret = mbr;
-		goto out;
-	}
+	if (STM32_SPI_MASTER_MODE(spi)) {
+		mbr = stm32_spi_prepare_mbr(spi, transfer->speed_hz,
+					    spi->cfg->baud_rate_div_min,
+					    spi->cfg->baud_rate_div_max);
+		if (mbr < 0) {
+			ret = mbr;
+			goto out;
+		}
 
-	transfer->speed_hz = spi->cur_speed;
-	stm32_spi_set_mbr(spi, mbr);
+		transfer->speed_hz = spi->cur_speed;
+		stm32_spi_set_mbr(spi, mbr);
+	}
 
 	comm_type = stm32_spi_communication_type(spi_dev, transfer);
 	ret = spi->cfg->set_mode(spi, comm_type);
@@ -1554,7 +1575,7 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 
 	spi->cur_comm = comm_type;
 
-	if (spi->cfg->set_data_idleness)
+	if (STM32_SPI_MASTER_MODE(spi) && spi->cfg->set_data_idleness)
 		spi->cfg->set_data_idleness(spi, transfer->len);
 
 	if (spi->cur_bpw <= 8)
@@ -1575,7 +1596,8 @@ static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 	dev_dbg(spi->dev,
 		"data frame of %d-bit, data packet of %d data frames\n",
 		spi->cur_bpw, spi->cur_fthlv);
-	dev_dbg(spi->dev, "speed set to %dHz\n", spi->cur_speed);
+	if (STM32_SPI_MASTER_MODE(spi))
+		dev_dbg(spi->dev, "speed set to %dHz\n", spi->cur_speed);
 	dev_dbg(spi->dev, "transfer of %d bytes (%d data frames)\n",
 		spi->cur_xferlen, nb_words);
 	dev_dbg(spi->dev, "dma %s\n",
@@ -1589,18 +1611,18 @@ out:
 
 /**
  * stm32_spi_transfer_one - transfer a single spi_transfer
- * @master: controller master interface
+ * @ctrl: controller interface
  * @spi_dev: pointer to the spi device
  * @transfer: pointer to spi transfer
  *
  * It must return 0 if the transfer is finished or 1 if the transfer is still
  * in progress.
  */
-static int stm32_spi_transfer_one(struct spi_master *master,
+static int stm32_spi_transfer_one(struct spi_controller *ctrl,
 				  struct spi_device *spi_dev,
 				  struct spi_transfer *transfer)
 {
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 	int ret;
 
 	spi->tx_buf = transfer->tx_buf;
@@ -1608,8 +1630,8 @@ static int stm32_spi_transfer_one(struct spi_master *master,
 	spi->tx_len = spi->tx_buf ? transfer->len : 0;
 	spi->rx_len = spi->rx_buf ? transfer->len : 0;
 
-	spi->cur_usedma = (master->can_dma &&
-			   master->can_dma(master, spi_dev, transfer));
+	spi->cur_usedma = (ctrl->can_dma &&
+			   ctrl->can_dma(ctrl, spi_dev, transfer));
 
 	ret = stm32_spi_transfer_one_setup(spi, spi_dev, transfer);
 	if (ret) {
@@ -1625,13 +1647,13 @@ static int stm32_spi_transfer_one(struct spi_master *master,
 
 /**
  * stm32_spi_unprepare_msg - relax the hardware
- * @master: controller master interface
+ * @ctrl: controller interface
  * @msg: pointer to the spi message
  */
-static int stm32_spi_unprepare_msg(struct spi_master *master,
+static int stm32_spi_unprepare_msg(struct spi_controller *ctrl,
 				   struct spi_message *msg)
 {
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 
 	spi->cfg->disable(spi);
 
@@ -1670,12 +1692,13 @@ static int stm32f4_spi_config(struct stm32_spi *spi)
 }
 
 /**
- * stm32h7_spi_config - Configure SPI controller as SPI master
+ * stm32h7_spi_config - Configure SPI controller
  * @spi: pointer to the spi controller data structure
  */
 static int stm32h7_spi_config(struct stm32_spi *spi)
 {
 	unsigned long flags;
+	u32 cr1 = 0, cfg2 = 0;
 
 	spin_lock_irqsave(&spi->lock, flags);
 
@@ -1683,24 +1706,28 @@ static int stm32h7_spi_config(struct stm32_spi *spi)
 	stm32_spi_clr_bits(spi, STM32H7_SPI_I2SCFGR,
 			   STM32H7_SPI_I2SCFGR_I2SMOD);
 
-	/*
-	 * - SS input value high
-	 * - transmitter half duplex direction
-	 * - automatic communication suspend when RX-Fifo is full
-	 */
-	stm32_spi_set_bits(spi, STM32H7_SPI_CR1, STM32H7_SPI_CR1_SSI |
-						 STM32H7_SPI_CR1_HDDIR |
-						 STM32H7_SPI_CR1_MASRX);
+	if (STM32_SPI_DEVICE_MODE(spi)) {
+		/* Use native device select */
+		cfg2 &= ~STM32H7_SPI_CFG2_SSM;
+	} else {
+		/*
+		 * - Transmitter half duplex direction
+		 * - Automatic communication suspend when RX-Fifo is full
+		 * - SS input value high
+		 */
+		cr1 |= STM32H7_SPI_CR1_HDDIR | STM32H7_SPI_CR1_MASRX | STM32H7_SPI_CR1_SSI;
 
-	/*
-	 * - Set the master mode (default Motorola mode)
-	 * - Consider 1 master/n slaves configuration and
-	 *   SS input value is determined by the SSI bit
-	 * - keep control of all associated GPIOs
-	 */
-	stm32_spi_set_bits(spi, STM32H7_SPI_CFG2, STM32H7_SPI_CFG2_MASTER |
-						  STM32H7_SPI_CFG2_SSM |
-						  STM32H7_SPI_CFG2_AFCNTR);
+		/*
+		 * - Set the master mode (default Motorola mode)
+		 * - Consider 1 master/n devices configuration and
+		 *   SS input value is determined by the SSI bit
+		 * - keep control of all associated GPIOs
+		 */
+		cfg2 |= STM32H7_SPI_CFG2_MASTER | STM32H7_SPI_CFG2_SSM | STM32H7_SPI_CFG2_AFCNTR;
+	}
+
+	stm32_spi_set_bits(spi, STM32H7_SPI_CR1, cr1);
+	stm32_spi_set_bits(spi, STM32H7_SPI_CFG2, cfg2);
 
 	spin_unlock_irqrestore(&spi->lock, flags);
 
@@ -1756,24 +1783,38 @@ static const struct of_device_id stm32_spi_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, stm32_spi_of_match);
 
+static int stm32h7_spi_device_abort(struct spi_controller *ctrl)
+{
+	spi_finalize_current_transfer(ctrl);
+	return 0;
+}
+
 static int stm32_spi_probe(struct platform_device *pdev)
 {
-	struct spi_master *master;
+	struct spi_controller *ctrl;
 	struct stm32_spi *spi;
 	struct resource *res;
 	struct reset_control *rst;
+	struct device_node *np = pdev->dev.of_node;
+	bool device_mode;
 	int ret;
 
-	master = devm_spi_alloc_master(&pdev->dev, sizeof(struct stm32_spi));
-	if (!master) {
-		dev_err(&pdev->dev, "spi master allocation failed\n");
+	device_mode = of_property_read_bool(np, "spi-slave");
+
+	if (device_mode)
+		ctrl = devm_spi_alloc_slave(&pdev->dev, sizeof(struct stm32_spi));
+	else
+		ctrl = devm_spi_alloc_master(&pdev->dev, sizeof(struct stm32_spi));
+	if (!ctrl) {
+		dev_err(&pdev->dev, "spi controller allocation failed\n");
 		return -ENOMEM;
 	}
-	platform_set_drvdata(pdev, master);
+	platform_set_drvdata(pdev, ctrl);
 
-	spi = spi_master_get_devdata(master);
+	spi = spi_controller_get_devdata(ctrl);
 	spi->dev = &pdev->dev;
-	spi->master = master;
+	spi->ctrl = ctrl;
+	spi->device_mode = device_mode;
 	spin_lock_init(&spi->lock);
 
 	spi->cfg = (const struct stm32_spi_cfg *)
@@ -1794,7 +1835,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	ret = devm_request_threaded_irq(&pdev->dev, spi->irq,
 					spi->cfg->irq_handler_event,
 					spi->cfg->irq_handler_thread,
-					IRQF_ONESHOT, pdev->name, master);
+					IRQF_ONESHOT, pdev->name, ctrl);
 	if (ret) {
 		dev_err(&pdev->dev, "irq%d request failed: %d\n", spi->irq,
 			ret);
@@ -1843,19 +1884,21 @@ static int stm32_spi_probe(struct platform_device *pdev)
 		goto err_clk_disable;
 	}
 
-	master->dev.of_node = pdev->dev.of_node;
-	master->auto_runtime_pm = true;
-	master->bus_num = pdev->id;
-	master->mode_bits = SPI_CPHA | SPI_CPOL | SPI_CS_HIGH | SPI_LSB_FIRST |
-			    SPI_3WIRE;
-	master->bits_per_word_mask = spi->cfg->get_bpw_mask(spi);
-	master->max_speed_hz = spi->clk_rate / spi->cfg->baud_rate_div_min;
-	master->min_speed_hz = spi->clk_rate / spi->cfg->baud_rate_div_max;
-	master->use_gpio_descriptors = true;
-	master->prepare_message = stm32_spi_prepare_msg;
-	master->transfer_one = stm32_spi_transfer_one;
-	master->unprepare_message = stm32_spi_unprepare_msg;
-	master->flags = spi->cfg->flags;
+	ctrl->dev.of_node = pdev->dev.of_node;
+	ctrl->auto_runtime_pm = true;
+	ctrl->bus_num = pdev->id;
+	ctrl->mode_bits = SPI_CPHA | SPI_CPOL | SPI_CS_HIGH | SPI_LSB_FIRST |
+			  SPI_3WIRE;
+	ctrl->bits_per_word_mask = spi->cfg->get_bpw_mask(spi);
+	ctrl->max_speed_hz = spi->clk_rate / spi->cfg->baud_rate_div_min;
+	ctrl->min_speed_hz = spi->clk_rate / spi->cfg->baud_rate_div_max;
+	ctrl->use_gpio_descriptors = true;
+	ctrl->prepare_message = stm32_spi_prepare_msg;
+	ctrl->transfer_one = stm32_spi_transfer_one;
+	ctrl->unprepare_message = stm32_spi_unprepare_msg;
+	ctrl->flags = spi->cfg->flags;
+	if (STM32_SPI_DEVICE_MODE(spi))
+		ctrl->slave_abort = stm32h7_spi_device_abort;
 
 	spi->dma_tx = dma_request_chan(spi->dev, "tx");
 	if (IS_ERR(spi->dma_tx)) {
@@ -1866,7 +1909,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
 
 		dev_warn(&pdev->dev, "failed to request tx dma channel\n");
 	} else {
-		master->dma_tx = spi->dma_tx;
+		ctrl->dma_tx = spi->dma_tx;
 	}
 
 	spi->dma_rx = dma_request_chan(spi->dev, "rx");
@@ -1878,11 +1921,11 @@ static int stm32_spi_probe(struct platform_device *pdev)
 
 		dev_warn(&pdev->dev, "failed to request rx dma channel\n");
 	} else {
-		master->dma_rx = spi->dma_rx;
+		ctrl->dma_rx = spi->dma_rx;
 	}
 
 	if (spi->dma_tx || spi->dma_rx)
-		master->can_dma = stm32_spi_can_dma;
+		ctrl->can_dma = stm32_spi_can_dma;
 
 	pm_runtime_set_autosuspend_delay(&pdev->dev,
 					 STM32_SPI_AUTOSUSPEND_DELAY);
@@ -1891,9 +1934,9 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	pm_runtime_get_noresume(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
-	ret = spi_register_master(master);
+	ret = spi_register_controller(ctrl);
 	if (ret) {
-		dev_err(&pdev->dev, "spi master registration failed: %d\n",
+		dev_err(&pdev->dev, "spi controller registration failed: %d\n",
 			ret);
 		goto err_pm_disable;
 	}
@@ -1901,7 +1944,8 @@ static int stm32_spi_probe(struct platform_device *pdev)
 	pm_runtime_mark_last_busy(&pdev->dev);
 	pm_runtime_put_autosuspend(&pdev->dev);
 
-	dev_info(&pdev->dev, "driver initialized\n");
+	dev_info(&pdev->dev, "driver initialized (%s mode)\n",
+		 STM32_SPI_MASTER_MODE(spi) ? "master" : "device");
 
 	return 0;
 
@@ -1923,12 +1967,12 @@ err_clk_disable:
 
 static void stm32_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master = platform_get_drvdata(pdev);
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct spi_controller *ctrl = platform_get_drvdata(pdev);
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 
 	pm_runtime_get_sync(&pdev->dev);
 
-	spi_unregister_master(master);
+	spi_unregister_controller(ctrl);
 	spi->cfg->disable(spi);
 
 	pm_runtime_disable(&pdev->dev);
@@ -1936,10 +1980,10 @@ static void stm32_spi_remove(struct platform_device *pdev)
 	pm_runtime_set_suspended(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
 
-	if (master->dma_tx)
-		dma_release_channel(master->dma_tx);
-	if (master->dma_rx)
-		dma_release_channel(master->dma_rx);
+	if (ctrl->dma_tx)
+		dma_release_channel(ctrl->dma_tx);
+	if (ctrl->dma_rx)
+		dma_release_channel(ctrl->dma_rx);
 
 	clk_disable_unprepare(spi->clk);
 
@@ -1949,8 +1993,8 @@ static void stm32_spi_remove(struct platform_device *pdev)
 
 static int __maybe_unused stm32_spi_runtime_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 
 	clk_disable_unprepare(spi->clk);
 
@@ -1959,8 +2003,8 @@ static int __maybe_unused stm32_spi_runtime_suspend(struct device *dev)
 
 static int __maybe_unused stm32_spi_runtime_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 	int ret;
 
 	ret = pinctrl_pm_select_default_state(dev);
@@ -1972,10 +2016,10 @@ static int __maybe_unused stm32_spi_runtime_resume(struct device *dev)
 
 static int __maybe_unused stm32_spi_suspend(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
 	int ret;
 
-	ret = spi_master_suspend(master);
+	ret = spi_controller_suspend(ctrl);
 	if (ret)
 		return ret;
 
@@ -1984,15 +2028,15 @@ static int __maybe_unused stm32_spi_suspend(struct device *dev)
 
 static int __maybe_unused stm32_spi_resume(struct device *dev)
 {
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct stm32_spi *spi = spi_master_get_devdata(master);
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
+	struct stm32_spi *spi = spi_controller_get_devdata(ctrl);
 	int ret;
 
 	ret = pm_runtime_force_resume(dev);
 	if (ret)
 		return ret;
 
-	ret = spi_master_resume(master);
+	ret = spi_controller_resume(ctrl);
 	if (ret) {
 		clk_disable_unprepare(spi->clk);
 		return ret;
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index 7532c85a352c..30d541612253 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -42,7 +42,9 @@
 #define SUN6I_TFR_CTL_CS_MANUAL			BIT(6)
 #define SUN6I_TFR_CTL_CS_LEVEL			BIT(7)
 #define SUN6I_TFR_CTL_DHB			BIT(8)
+#define SUN6I_TFR_CTL_SDC			BIT(11)
 #define SUN6I_TFR_CTL_FBS			BIT(12)
+#define SUN6I_TFR_CTL_SDM			BIT(13)
 #define SUN6I_TFR_CTL_XCH			BIT(31)
 
 #define SUN6I_INT_CTL_REG		0x10
@@ -85,6 +87,11 @@
 #define SUN6I_TXDATA_REG		0x200
 #define SUN6I_RXDATA_REG		0x300
 
+struct sun6i_spi_cfg {
+	unsigned long		fifo_depth;
+	bool			has_clk_ctl;
+};
+
 struct sun6i_spi {
 	struct spi_master	*master;
 	void __iomem		*base_addr;
@@ -99,7 +106,7 @@ struct sun6i_spi {
 	const u8		*tx_buf;
 	u8			*rx_buf;
 	int			len;
-	unsigned long		fifo_depth;
+	const struct sun6i_spi_cfg *cfg;
 };
 
 static inline u32 sun6i_spi_read(struct sun6i_spi *sspi, u32 reg)
@@ -156,7 +163,7 @@ static inline void sun6i_spi_fill_fifo(struct sun6i_spi *sspi)
 	u8 byte;
 
 	/* See how much data we can fit */
-	cnt = sspi->fifo_depth - sun6i_spi_get_tx_fifo_count(sspi);
+	cnt = sspi->cfg->fifo_depth - sun6i_spi_get_tx_fifo_count(sspi);
 
 	len = min((int)cnt, sspi->len);
 
@@ -256,7 +263,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 				  struct spi_transfer *tfr)
 {
 	struct sun6i_spi *sspi = spi_master_get_devdata(master);
-	unsigned int mclk_rate, div, div_cdr1, div_cdr2, timeout;
+	unsigned int div, div_cdr1, div_cdr2, timeout;
 	unsigned int start, end, tx_time;
 	unsigned int trig_level;
 	unsigned int tx_len = 0, rx_len = 0;
@@ -289,14 +296,14 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 		 * the hardcoded value used in old generation of Allwinner
 		 * SPI controller. (See spi-sun4i.c)
 		 */
-		trig_level = sspi->fifo_depth / 4 * 3;
+		trig_level = sspi->cfg->fifo_depth / 4 * 3;
 	} else {
 		/*
 		 * Setup FIFO DMA request trigger level
 		 * We choose 1/2 of the full fifo depth, that value will
 		 * be used as DMA burst length.
 		 */
-		trig_level = sspi->fifo_depth / 2;
+		trig_level = sspi->cfg->fifo_depth / 2;
 
 		if (tfr->tx_buf)
 			reg |= SUN6I_FIFO_CTL_TF_DRQ_EN;
@@ -346,39 +353,65 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 
 	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg);
 
-	/* Ensure that we have a parent clock fast enough */
-	mclk_rate = clk_get_rate(sspi->mclk);
-	if (mclk_rate < (2 * tfr->speed_hz)) {
-		clk_set_rate(sspi->mclk, 2 * tfr->speed_hz);
-		mclk_rate = clk_get_rate(sspi->mclk);
-	}
+	if (sspi->cfg->has_clk_ctl) {
+		unsigned int mclk_rate = clk_get_rate(sspi->mclk);
 
-	/*
-	 * Setup clock divider.
-	 *
-	 * We have two choices there. Either we can use the clock
-	 * divide rate 1, which is calculated thanks to this formula:
-	 * SPI_CLK = MOD_CLK / (2 ^ cdr)
-	 * Or we can use CDR2, which is calculated with the formula:
-	 * SPI_CLK = MOD_CLK / (2 * (cdr + 1))
-	 * Wether we use the former or the latter is set through the
-	 * DRS bit.
-	 *
-	 * First try CDR2, and if we can't reach the expected
-	 * frequency, fall back to CDR1.
-	 */
-	div_cdr1 = DIV_ROUND_UP(mclk_rate, tfr->speed_hz);
-	div_cdr2 = DIV_ROUND_UP(div_cdr1, 2);
-	if (div_cdr2 <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) {
-		reg = SUN6I_CLK_CTL_CDR2(div_cdr2 - 1) | SUN6I_CLK_CTL_DRS;
-		tfr->effective_speed_hz = mclk_rate / (2 * div_cdr2);
+		/* Ensure that we have a parent clock fast enough */
+		if (mclk_rate < (2 * tfr->speed_hz)) {
+			clk_set_rate(sspi->mclk, 2 * tfr->speed_hz);
+			mclk_rate = clk_get_rate(sspi->mclk);
+		}
+
+		/*
+		 * Setup clock divider.
+		 *
+		 * We have two choices there. Either we can use the clock
+		 * divide rate 1, which is calculated thanks to this formula:
+		 * SPI_CLK = MOD_CLK / (2 ^ cdr)
+		 * Or we can use CDR2, which is calculated with the formula:
+		 * SPI_CLK = MOD_CLK / (2 * (cdr + 1))
+		 * Wether we use the former or the latter is set through the
+		 * DRS bit.
+		 *
+		 * First try CDR2, and if we can't reach the expected
+		 * frequency, fall back to CDR1.
+		 */
+		div_cdr1 = DIV_ROUND_UP(mclk_rate, tfr->speed_hz);
+		div_cdr2 = DIV_ROUND_UP(div_cdr1, 2);
+		if (div_cdr2 <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) {
+			reg = SUN6I_CLK_CTL_CDR2(div_cdr2 - 1) | SUN6I_CLK_CTL_DRS;
+			tfr->effective_speed_hz = mclk_rate / (2 * div_cdr2);
+		} else {
+			div = min(SUN6I_CLK_CTL_CDR1_MASK, order_base_2(div_cdr1));
+			reg = SUN6I_CLK_CTL_CDR1(div);
+			tfr->effective_speed_hz = mclk_rate / (1 << div);
+		}
+
+		sun6i_spi_write(sspi, SUN6I_CLK_CTL_REG, reg);
 	} else {
-		div = min(SUN6I_CLK_CTL_CDR1_MASK, order_base_2(div_cdr1));
-		reg = SUN6I_CLK_CTL_CDR1(div);
-		tfr->effective_speed_hz = mclk_rate / (1 << div);
+		clk_set_rate(sspi->mclk, tfr->speed_hz);
+		tfr->effective_speed_hz = clk_get_rate(sspi->mclk);
+
+		/*
+		 * Configure work mode.
+		 *
+		 * There are three work modes depending on the controller clock
+		 * frequency:
+		 * - normal sample mode           : CLK <= 24MHz SDM=1 SDC=0
+		 * - delay half-cycle sample mode : CLK <= 40MHz SDM=0 SDC=0
+		 * - delay one-cycle sample mode  : CLK >= 80MHz SDM=0 SDC=1
+		 */
+		reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
+		reg &= ~(SUN6I_TFR_CTL_SDM | SUN6I_TFR_CTL_SDC);
+
+		if (tfr->effective_speed_hz <= 24000000)
+			reg |= SUN6I_TFR_CTL_SDM;
+		else if (tfr->effective_speed_hz >= 80000000)
+			reg |= SUN6I_TFR_CTL_SDC;
+
+		sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg);
 	}
 
-	sun6i_spi_write(sspi, SUN6I_CLK_CTL_REG, reg);
 	/* Finally enable the bus - doing so before might raise SCK to HIGH */
 	reg = sun6i_spi_read(sspi, SUN6I_GBL_CTL_REG);
 	reg |= SUN6I_GBL_CTL_BUS_ENABLE;
@@ -410,9 +443,9 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	reg = SUN6I_INT_CTL_TC;
 
 	if (!use_dma) {
-		if (rx_len > sspi->fifo_depth)
+		if (rx_len > sspi->cfg->fifo_depth)
 			reg |= SUN6I_INT_CTL_RF_RDY;
-		if (tx_len > sspi->fifo_depth)
+		if (tx_len > sspi->cfg->fifo_depth)
 			reg |= SUN6I_INT_CTL_TF_ERQ;
 	}
 
@@ -422,7 +455,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
 	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH);
 
-	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	tx_time = spi_controller_xfer_timeout(master, tfr);
 	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
 					      msecs_to_jiffies(tx_time));
@@ -543,7 +576,7 @@ static bool sun6i_spi_can_dma(struct spi_master *master,
 	 * the fifo length we can just fill the fifo and wait for a single
 	 * irq, so don't bother setting up dma
 	 */
-	return xfer->len > sspi->fifo_depth;
+	return xfer->len > sspi->cfg->fifo_depth;
 }
 
 static int sun6i_spi_probe(struct platform_device *pdev)
@@ -582,7 +615,7 @@ static int sun6i_spi_probe(struct platform_device *pdev)
 	}
 
 	sspi->master = master;
-	sspi->fifo_depth = (unsigned long)of_device_get_match_data(&pdev->dev);
+	sspi->cfg = of_device_get_match_data(&pdev->dev);
 
 	master->max_speed_hz = 100 * 1000 * 1000;
 	master->min_speed_hz = 3 * 1000;
@@ -695,9 +728,27 @@ static void sun6i_spi_remove(struct platform_device *pdev)
 		dma_release_channel(master->dma_rx);
 }
 
+static const struct sun6i_spi_cfg sun6i_a31_spi_cfg = {
+	.fifo_depth	= SUN6I_FIFO_DEPTH,
+	.has_clk_ctl	= true,
+};
+
+static const struct sun6i_spi_cfg sun8i_h3_spi_cfg = {
+	.fifo_depth	= SUN8I_FIFO_DEPTH,
+	.has_clk_ctl	= true,
+};
+
+static const struct sun6i_spi_cfg sun50i_r329_spi_cfg = {
+	.fifo_depth	= SUN8I_FIFO_DEPTH,
+};
+
 static const struct of_device_id sun6i_spi_match[] = {
-	{ .compatible = "allwinner,sun6i-a31-spi", .data = (void *)SUN6I_FIFO_DEPTH },
-	{ .compatible = "allwinner,sun8i-h3-spi",  .data = (void *)SUN8I_FIFO_DEPTH },
+	{ .compatible = "allwinner,sun6i-a31-spi", .data = &sun6i_a31_spi_cfg },
+	{ .compatible = "allwinner,sun8i-h3-spi",  .data = &sun8i_h3_spi_cfg },
+	{
+		.compatible = "allwinner,sun50i-r329-spi",
+		.data = &sun50i_r329_spi_cfg
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, sun6i_spi_match);
diff --git a/drivers/spi/spi-xcomm.c b/drivers/spi/spi-xcomm.c
index 5d23411f2a3e..ae6218bcd02a 100644
--- a/drivers/spi/spi-xcomm.c
+++ b/drivers/spi/spi-xcomm.c
@@ -241,7 +241,7 @@ static struct i2c_driver spi_xcomm_driver = {
 		.name	= "spi-xcomm",
 	},
 	.id_table	= spi_xcomm_ids,
-	.probe_new	= spi_xcomm_probe,
+	.probe		= spi_xcomm_probe,
 };
 module_i2c_driver(spi_xcomm_driver);
 
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 8d009275a59d..d13dc15cc191 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -64,7 +64,8 @@ static_assert(N_SPI_MINORS > 0 && N_SPI_MINORS <= 256);
 				| SPI_NO_CS | SPI_READY | SPI_TX_DUAL \
 				| SPI_TX_QUAD | SPI_TX_OCTAL | SPI_RX_DUAL \
 				| SPI_RX_QUAD | SPI_RX_OCTAL \
-				| SPI_RX_CPHA_FLIP)
+				| SPI_RX_CPHA_FLIP | SPI_3WIRE_HIZ \
+				| SPI_MOSI_IDLE_LOW)
 
 struct spidev_data {
 	dev_t			devt;
diff --git a/include/linux/platform_data/spi-s3c64xx.h b/include/linux/platform_data/spi-s3c64xx.h
index 3101152ce449..1d6e6c424fc6 100644
--- a/include/linux/platform_data/spi-s3c64xx.h
+++ b/include/linux/platform_data/spi-s3c64xx.h
@@ -36,6 +36,7 @@ struct s3c64xx_spi_info {
 	int src_clk_nr;
 	int num_cs;
 	bool no_cs;
+	bool polling;
 	int (*cfg_gpio)(void);
 };
 
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index cfe42f8cd7a4..32c94eae8926 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -1261,6 +1261,23 @@ static inline bool spi_is_bpw_supported(struct spi_device *spi, u32 bpw)
 	return false;
 }
 
+/**
+ * spi_controller_xfer_timeout - Compute a suitable timeout value
+ * @ctlr: SPI device
+ * @xfer: Transfer descriptor
+ *
+ * Compute a relevant timeout value for the given transfer. We derive the time
+ * that it would take on a single data line and take twice this amount of time
+ * with a minimum of 500ms to avoid false positives on loaded systems.
+ *
+ * Returns: Transfer timeout value in milliseconds.
+ */
+static inline unsigned int spi_controller_xfer_timeout(struct spi_controller *ctlr,
+						       struct spi_transfer *xfer)
+{
+	return max(xfer->len * 8 * 2 / (xfer->speed_hz / 1000), 500U);
+}
+
 /*---------------------------------------------------------------------------*/
 
 /* SPI transfer replacement methods which make use of spi_res */
diff --git a/include/uapi/linux/spi/spi.h b/include/uapi/linux/spi/spi.h
index 9d5f58059703..ca56e477d161 100644
--- a/include/uapi/linux/spi/spi.h
+++ b/include/uapi/linux/spi/spi.h
@@ -28,6 +28,7 @@
 #define	SPI_RX_OCTAL		_BITUL(14)	/* receive with 8 wires */
 #define	SPI_3WIRE_HIZ		_BITUL(15)	/* high impedance turnaround */
 #define	SPI_RX_CPHA_FLIP	_BITUL(16)	/* flip CPHA on Rx only xfer */
+#define SPI_MOSI_IDLE_LOW	_BITUL(17)	/* leave mosi line low when idle */
 
 /*
  * All the bits defined above should be covered by SPI_MODE_USER_MASK.
@@ -37,6 +38,6 @@
  * These bits must not overlap. A static assert check should make sure of that.
  * If adding extra bits, make sure to increase the bit index below as well.
  */
-#define SPI_MODE_USER_MASK	(_BITUL(17) - 1)
+#define SPI_MODE_USER_MASK	(_BITUL(18) - 1)
 
 #endif /* _UAPI_SPI_H */
diff --git a/tools/spi/spidev_test.c b/tools/spi/spidev_test.c
index b0ca44c70e83..9179942d7f15 100644
--- a/tools/spi/spidev_test.c
+++ b/tools/spi/spidev_test.c
@@ -172,28 +172,37 @@ static void transfer(int fd, uint8_t const *tx, uint8_t const *rx, size_t len)
 
 static void print_usage(const char *prog)
 {
-	printf("Usage: %s [-DsbdlHOLC3vpNR24SI]\n", prog);
-	puts("  -D --device   device to use (default /dev/spidev1.1)\n"
-	     "  -s --speed    max speed (Hz)\n"
-	     "  -d --delay    delay (usec)\n"
-	     "  -b --bpw      bits per word\n"
-	     "  -i --input    input data from a file (e.g. \"test.bin\")\n"
-	     "  -o --output   output data to a file (e.g. \"results.bin\")\n"
-	     "  -l --loop     loopback\n"
-	     "  -H --cpha     clock phase\n"
-	     "  -O --cpol     clock polarity\n"
-	     "  -L --lsb      least significant bit first\n"
-	     "  -C --cs-high  chip select active high\n"
-	     "  -3 --3wire    SI/SO signals shared\n"
-	     "  -v --verbose  Verbose (show tx buffer)\n"
-	     "  -p            Send data (e.g. \"1234\\xde\\xad\")\n"
-	     "  -N --no-cs    no chip select\n"
-	     "  -R --ready    slave pulls low to pause\n"
-	     "  -2 --dual     dual transfer\n"
-	     "  -4 --quad     quad transfer\n"
-	     "  -8 --octal    octal transfer\n"
-	     "  -S --size     transfer size\n"
-	     "  -I --iter     iterations\n");
+	printf("Usage: %s [-2348CDFHILMNORSZbdilopsv]\n", prog);
+	puts("general device settings:\n"
+		 "  -D --device         device to use (default /dev/spidev1.1)\n"
+		 "  -s --speed          max speed (Hz)\n"
+		 "  -d --delay          delay (usec)\n"
+		 "  -l --loop           loopback\n"
+		 "spi mode:\n"
+		 "  -H --cpha           clock phase\n"
+		 "  -O --cpol           clock polarity\n"
+		 "  -F --rx-cpha-flip   flip CPHA on Rx only xfer\n"
+		 "number of wires for transmission:\n"
+		 "  -2 --dual           dual transfer\n"
+		 "  -4 --quad           quad transfer\n"
+		 "  -8 --octal          octal transfer\n"
+		 "  -3 --3wire          SI/SO signals shared\n"
+		 "  -Z --3wire-hiz      high impedance turnaround\n"
+		 "data:\n"
+		 "  -i --input          input data from a file (e.g. \"test.bin\")\n"
+		 "  -o --output         output data to a file (e.g. \"results.bin\")\n"
+		 "  -p                  Send data (e.g. \"1234\\xde\\xad\")\n"
+		 "  -S --size           transfer size\n"
+		 "  -I --iter           iterations\n"
+		 "additional parameters:\n"
+		 "  -b --bpw            bits per word\n"
+		 "  -L --lsb            least significant bit first\n"
+		 "  -C --cs-high        chip select active high\n"
+		 "  -N --no-cs          no chip select\n"
+		 "  -R --ready          slave pulls low to pause\n"
+		 "  -M --mosi-idle-low  leave mosi line low when idle\n"
+		 "misc:\n"
+		 "  -v --verbose        Verbose (show tx buffer)\n");
 	exit(1);
 }
 
@@ -201,31 +210,34 @@ static void parse_opts(int argc, char *argv[])
 {
 	while (1) {
 		static const struct option lopts[] = {
-			{ "device",  1, 0, 'D' },
-			{ "speed",   1, 0, 's' },
-			{ "delay",   1, 0, 'd' },
-			{ "bpw",     1, 0, 'b' },
-			{ "input",   1, 0, 'i' },
-			{ "output",  1, 0, 'o' },
-			{ "loop",    0, 0, 'l' },
-			{ "cpha",    0, 0, 'H' },
-			{ "cpol",    0, 0, 'O' },
-			{ "lsb",     0, 0, 'L' },
-			{ "cs-high", 0, 0, 'C' },
-			{ "3wire",   0, 0, '3' },
-			{ "no-cs",   0, 0, 'N' },
-			{ "ready",   0, 0, 'R' },
-			{ "dual",    0, 0, '2' },
-			{ "verbose", 0, 0, 'v' },
-			{ "quad",    0, 0, '4' },
-			{ "octal",   0, 0, '8' },
-			{ "size",    1, 0, 'S' },
-			{ "iter",    1, 0, 'I' },
+			{ "device",        1, 0, 'D' },
+			{ "speed",         1, 0, 's' },
+			{ "delay",         1, 0, 'd' },
+			{ "loop",          0, 0, 'l' },
+			{ "cpha",          0, 0, 'H' },
+			{ "cpol",          0, 0, 'O' },
+			{ "rx-cpha-flip",  0, 0, 'F' },
+			{ "dual",          0, 0, '2' },
+			{ "quad",          0, 0, '4' },
+			{ "octal",         0, 0, '8' },
+			{ "3wire",         0, 0, '3' },
+			{ "3wire-hiz",     0, 0, 'Z' },
+			{ "input",         1, 0, 'i' },
+			{ "output",        1, 0, 'o' },
+			{ "size",          1, 0, 'S' },
+			{ "iter",          1, 0, 'I' },
+			{ "bpw",           1, 0, 'b' },
+			{ "lsb",           0, 0, 'L' },
+			{ "cs-high",       0, 0, 'C' },
+			{ "no-cs",         0, 0, 'N' },
+			{ "ready",         0, 0, 'R' },
+			{ "mosi-idle-low", 0, 0, 'M' },
+			{ "verbose",       0, 0, 'v' },
 			{ NULL, 0, 0, 0 },
 		};
 		int c;
 
-		c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3NR248p:vS:I:",
+		c = getopt_long(argc, argv, "D:s:d:b:i:o:lHOLC3ZFMNR248p:vS:I:",
 				lopts, NULL);
 
 		if (c == -1)
@@ -268,6 +280,15 @@ static void parse_opts(int argc, char *argv[])
 		case '3':
 			mode |= SPI_3WIRE;
 			break;
+		case 'Z':
+			mode |= SPI_3WIRE_HIZ;
+			break;
+		case 'F':
+			mode |= SPI_RX_CPHA_FLIP;
+			break;
+		case 'M':
+			mode |= SPI_MOSI_IDLE_LOW;
+			break;
 		case 'N':
 			mode |= SPI_NO_CS;
 			break;