soi: Don't call DMA sync API when not needed

Merge series from Andy Shevchenko <andriy.shevchenko@linux.intel.com>:

A couple of fixes to avoid calling DMA sync API when it's not needed.
This doesn't stop from discussing if IOMMU code is doing the right thing,
i.e. dereferences SG list when orig_nents == 0, but this is a separate
story.

63 files changed, 2241 insertions, 933 deletions

diff --git a/Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml b/Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml
new file mode 100644
index 000000000000..b820c5613dcc
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml
@@ -0,0 +1,65 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/airoha,en7581-snand.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: SPI-NAND flash controller for Airoha ARM SoCs
+
+maintainers:
+  - Lorenzo Bianconi <lorenzo@kernel.org>
+
+allOf:
+  - $ref: spi-controller.yaml#
+
+properties:
+  compatible:
+    const: airoha,en7581-snand
+
+  reg:
+    items:
+      - description: spi base address
+      - description: nfi2spi base address
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: spi
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/en7523-clk.h>
+
+    soc {
+      #address-cells = <2>;
+      #size-cells = <2>;
+
+      spi@1fa10000 {
+        compatible = "airoha,en7581-snand";
+        reg = <0x0 0x1fa10000 0x0 0x140>,
+              <0x0 0x1fa11000 0x0 0x160>;
+
+        clocks = <&scuclk EN7523_CLK_SPI>;
+        clock-names = "spi";
+
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        flash@0 {
+          compatible = "spi-nand";
+          reg = <0>;
+          spi-tx-bus-width = <1>;
+          spi-rx-bus-width = <2>;
+        };
+      };
+    };
diff --git a/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml b/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
index cca81f89e252..d48ecd6cd5ad 100644
--- a/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
+++ b/Documentation/devicetree/bindings/spi/cdns,qspi-nor.yaml
@@ -68,12 +68,13 @@ properties:
       - items:
           - enum:
               - amd,pensando-elba-qspi
-              - ti,k2g-qspi
-              - ti,am654-ospi
               - intel,lgm-qspi
-              - xlnx,versal-ospi-1.0
               - intel,socfpga-qspi
+              - mobileye,eyeq5-ospi
               - starfive,jh7110-qspi
+              - ti,am654-ospi
+              - ti,k2g-qspi
+              - xlnx,versal-ospi-1.0
           - const: cdns,qspi-nor
       - const: cdns,qspi-nor
 
@@ -145,7 +146,6 @@ required:
   - reg
   - interrupts
   - clocks
-  - cdns,fifo-depth
   - cdns,fifo-width
   - cdns,trigger-address
   - '#address-cells'
diff --git a/Documentation/devicetree/bindings/spi/marvell,armada-3700-spi.yaml b/Documentation/devicetree/bindings/spi/marvell,armada-3700-spi.yaml
new file mode 100644
index 000000000000..61caa1d86188
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/marvell,armada-3700-spi.yaml
@@ -0,0 +1,55 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/marvell,armada-3700-spi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Marvell Armada 3700 SPI Controller
+
+description:
+  The SPI controller on Marvell Armada 3700 SoC.
+
+maintainers:
+  - Kousik Sanagavarapu <five231003@gmail.com>
+
+allOf:
+  - $ref: spi-controller.yaml#
+
+properties:
+  compatible:
+    const: marvell,armada-3700-spi
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  clocks:
+    maxItems: 1
+
+  num-cs:
+    maxItems: 1
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    spi0: spi@10600 {
+        compatible = "marvell,armada-3700-spi";
+        #address-cells = <1>;
+        #size-cells = <0>;
+        reg = <0x10600 0x5d>;
+        clocks = <&nb_perih_clk 7>;
+        interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
+        num-cs = <4>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml b/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml
index 00acbbb0f65d..49649fc3f95a 100644
--- a/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml
+++ b/Documentation/devicetree/bindings/spi/renesas,sh-msiof.yaml
@@ -54,6 +54,7 @@ properties:
               - renesas,msiof-r8a779a0      # R-Car V3U
               - renesas,msiof-r8a779f0      # R-Car S4-8
               - renesas,msiof-r8a779g0      # R-Car V4H
+              - renesas,msiof-r8a779h0      # R-Car V4M
           - const: renesas,rcar-gen4-msiof  # generic R-Car Gen4
                                             # compatible device
       - items:
diff --git a/Documentation/devicetree/bindings/spi/spi-armada-3700.txt b/Documentation/devicetree/bindings/spi/spi-armada-3700.txt
deleted file mode 100644
index 1564aa8c02cd..000000000000
--- a/Documentation/devicetree/bindings/spi/spi-armada-3700.txt
+++ /dev/null
@@ -1,25 +0,0 @@
-* Marvell Armada 3700 SPI Controller
-
-Required Properties:
-
-- compatible: should be "marvell,armada-3700-spi"
-- reg: physical base address of the controller and length of memory mapped
-       region.
-- interrupts: The interrupt number. The interrupt specifier format depends on
-	      the interrupt controller and of its driver.
-- clocks: Must contain the clock source, usually from the North Bridge clocks.
-- num-cs: The number of chip selects that is supported by this SPI Controller
-- #address-cells: should be 1.
-- #size-cells: should be 0.
-
-Example:
-
-	spi0: spi@10600 {
-		compatible = "marvell,armada-3700-spi";
-		#address-cells = <1>;
-		#size-cells = <0>;
-		reg = <0x10600 0x5d>;
-		clocks = <&nb_perih_clk 7>;
-		interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>;
-		num-cs = <4>;
-	};
diff --git a/Documentation/devicetree/bindings/spi/ti,qspi.yaml b/Documentation/devicetree/bindings/spi/ti,qspi.yaml
new file mode 100644
index 000000000000..626a915b3d77
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/ti,qspi.yaml
@@ -0,0 +1,96 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/spi/ti,qspi.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: TI QSPI controller
+
+maintainers:
+  - Kousik Sanagavarapu <five231003@gmail.com>
+
+allOf:
+  - $ref: spi-controller.yaml#
+
+properties:
+  compatible:
+    enum:
+      - ti,am4372-qspi
+      - ti,dra7xxx-qspi
+
+  reg:
+    items:
+      - description: base registers
+      - description: mapped memory
+
+  reg-names:
+    items:
+      - const: qspi_base
+      - const: qspi_mmap
+
+  clocks:
+    maxItems: 1
+
+  clock-names:
+    items:
+      - const: fck
+
+  interrupts:
+    maxItems: 1
+
+  num-cs:
+    minimum: 1
+    maximum: 4
+    default: 1
+
+  ti,hwmods:
+    description:
+      Name of the hwmod associated to the QSPI.  This is for legacy
+      platforms only.
+    $ref: /schemas/types.yaml#/definitions/string
+    deprecated: true
+
+  syscon-chipselects:
+    description:
+      Handle to system control region containing QSPI chipselect register
+      and offset of that register.
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    items:
+      - items:
+          - description: phandle to system control register
+          - description: register offset
+
+  spi-max-frequency:
+    description: Maximum SPI clocking speed of the controller in Hz.
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - clocks
+  - clock-names
+  - interrupts
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/dra7.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    spi@4b300000 {
+        compatible = "ti,dra7xxx-qspi";
+        reg = <0x4b300000 0x100>,
+              <0x5c000000 0x4000000>;
+        reg-names = "qspi_base", "qspi_mmap";
+        syscon-chipselects = <&scm_conf 0x558>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+        clocks = <&l4per2_clkctrl DRA7_L4PER2_QSPI_CLKCTRL 25>;
+        clock-names = "fck";
+        num-cs = <4>;
+        spi-max-frequency = <48000000>;
+        interrupts = <GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH>;
+    };
+...
diff --git a/Documentation/devicetree/bindings/spi/ti_qspi.txt b/Documentation/devicetree/bindings/spi/ti_qspi.txt
deleted file mode 100644
index 47b184bce414..000000000000
--- a/Documentation/devicetree/bindings/spi/ti_qspi.txt
+++ /dev/null
@@ -1,53 +0,0 @@
-TI QSPI controller.
-
-Required properties:
-- compatible : should be "ti,dra7xxx-qspi" or "ti,am4372-qspi".
-- reg: Should contain QSPI registers location and length.
-- reg-names: Should contain the resource reg names.
-	- qspi_base: Qspi configuration register Address space
-	- qspi_mmap: Memory mapped Address space
-	- (optional) qspi_ctrlmod: Control module Address space
-- interrupts: should contain the qspi interrupt number.
-- #address-cells, #size-cells : Must be present if the device has sub-nodes
-- ti,hwmods: Name of the hwmod associated to the QSPI
-
-Recommended properties:
-- spi-max-frequency: Definition as per
-                     Documentation/devicetree/bindings/spi/spi-bus.txt
-
-Optional properties:
-- syscon-chipselects: Handle to system control region contains QSPI
-		      chipselect register and offset of that register.
-
-NOTE: TI QSPI controller requires different pinmux and IODelay
-parameters for Mode-0 and Mode-3 operations, which needs to be set up by
-the bootloader (U-Boot). Default configuration only supports Mode-0
-operation. Hence, "spi-cpol" and "spi-cpha" DT properties cannot be
-specified in the slave nodes of TI QSPI controller without appropriate
-modification to bootloader.
-
-Example:
-
-For am4372:
-qspi: qspi@47900000 {
-	compatible = "ti,am4372-qspi";
-	reg = <0x47900000 0x100>, <0x30000000 0x4000000>;
-	reg-names = "qspi_base", "qspi_mmap";
-	#address-cells = <1>;
-	#size-cells = <0>;
-	spi-max-frequency = <25000000>;
-	ti,hwmods = "qspi";
-};
-
-For dra7xx:
-qspi: qspi@4b300000 {
-	compatible = "ti,dra7xxx-qspi";
-	reg = <0x4b300000 0x100>,
-	      <0x5c000000 0x4000000>,
-	reg-names = "qspi_base", "qspi_mmap";
-	syscon-chipselects = <&scm_conf 0x558>;
-	#address-cells = <1>;
-	#size-cells = <0>;
-	spi-max-frequency = <48000000>;
-	ti,hwmods = "qspi";
-};
diff --git a/Documentation/spi/index.rst b/Documentation/spi/index.rst
index 06c34ea11bcf..824ce42ed4f0 100644
--- a/Documentation/spi/index.rst
+++ b/Documentation/spi/index.rst
@@ -10,7 +10,6 @@ Serial Peripheral Interface (SPI)
    spi-summary
    spidev
    butterfly
-   pxa2xx
    spi-lm70llp
    spi-sc18is602
 
diff --git a/Documentation/spi/pxa2xx.rst b/Documentation/spi/pxa2xx.rst
deleted file mode 100644
index 19479b801826..000000000000
--- a/Documentation/spi/pxa2xx.rst
+++ /dev/null
@@ -1,211 +0,0 @@
-==============================
-PXA2xx SPI on SSP driver HOWTO
-==============================
-
-This a mini HOWTO on the pxa2xx_spi driver. The driver turns a PXA2xx
-synchronous serial port into an SPI host controller
-(see Documentation/spi/spi-summary.rst). The driver has the following features
-
-- Support for any PXA2xx and compatible SSP.
-- SSP PIO and SSP DMA data transfers.
-- External and Internal (SSPFRM) chip selects.
-- Per peripheral device (chip) configuration.
-- Full suspend, freeze, resume support.
-
-The driver is built around a &struct spi_message FIFO serviced by kernel
-thread. The kernel thread, spi_pump_messages(), drives message FIFO and
-is responsible for queuing SPI transactions and setting up and launching
-the DMA or interrupt driven transfers.
-
-Declaring PXA2xx host controllers
----------------------------------
-Typically, for a legacy platform, an SPI host controller is defined in the
-arch/.../mach-*/board-*.c as a "platform device". The host controller configuration
-is passed to the driver via a table found in include/linux/spi/pxa2xx_spi.h::
-
-  struct pxa2xx_spi_controller {
-	u16 num_chipselect;
-	u8 enable_dma;
-	...
-  };
-
-The "pxa2xx_spi_controller.num_chipselect" field is used to determine the number of
-peripheral devices (chips) attached to this SPI host controller.
-
-The "pxa2xx_spi_controller.enable_dma" field informs the driver that SSP DMA should
-be used. This caused the driver to acquire two DMA channels: Rx channel and
-Tx channel. The Rx channel has a higher DMA service priority than the Tx channel.
-See the "PXA2xx Developer Manual" section "DMA Controller".
-
-For the new platforms the description of the controller and peripheral devices
-comes from Device Tree or ACPI.
-
-NSSP HOST SAMPLE
-----------------
-Below is a sample configuration using the PXA255 NSSP for a legacy platform::
-
-  static struct resource pxa_spi_nssp_resources[] = {
-	[0] = {
-		.start	= __PREG(SSCR0_P(2)), /* Start address of NSSP */
-		.end	= __PREG(SSCR0_P(2)) + 0x2c, /* Range of registers */
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= IRQ_NSSP, /* NSSP IRQ */
-		.end	= IRQ_NSSP,
-		.flags	= IORESOURCE_IRQ,
-	},
-  };
-
-  static struct pxa2xx_spi_controller pxa_nssp_controller_info = {
-	.num_chipselect = 1, /* Matches the number of chips attached to NSSP */
-	.enable_dma = 1, /* Enables NSSP DMA */
-  };
-
-  static struct platform_device pxa_spi_nssp = {
-	.name = "pxa2xx-spi", /* MUST BE THIS VALUE, so device match driver */
-	.id = 2, /* Bus number, MUST MATCH SSP number 1..n */
-	.resource = pxa_spi_nssp_resources,
-	.num_resources = ARRAY_SIZE(pxa_spi_nssp_resources),
-	.dev = {
-		.platform_data = &pxa_nssp_controller_info, /* Passed to driver */
-	},
-  };
-
-  static struct platform_device *devices[] __initdata = {
-	&pxa_spi_nssp,
-  };
-
-  static void __init board_init(void)
-  {
-	(void)platform_add_device(devices, ARRAY_SIZE(devices));
-  }
-
-Declaring peripheral devices
-----------------------------
-Typically, for a legacy platform, each SPI peripheral device (chip) is defined in the
-arch/.../mach-*/board-*.c using the "spi_board_info" structure found in
-"linux/spi/spi.h". See "Documentation/spi/spi-summary.rst" for additional
-information.
-
-Each peripheral device (chip) attached to the PXA2xx must provide specific chip configuration
-information via the structure "pxa2xx_spi_chip" found in
-"include/linux/spi/pxa2xx_spi.h". The PXA2xx host controller driver will use
-the configuration whenever the driver communicates with the peripheral
-device. All fields are optional.
-
-::
-
-  struct pxa2xx_spi_chip {
-	u8 tx_threshold;
-	u8 rx_threshold;
-	u8 dma_burst_size;
-	u32 timeout;
-  };
-
-The "pxa2xx_spi_chip.tx_threshold" and "pxa2xx_spi_chip.rx_threshold" fields are
-used to configure the SSP hardware FIFO. These fields are critical to the
-performance of pxa2xx_spi driver and misconfiguration will result in rx
-FIFO overruns (especially in PIO mode transfers). Good default values are::
-
-	.tx_threshold = 8,
-	.rx_threshold = 8,
-
-The range is 1 to 16 where zero indicates "use default".
-
-The "pxa2xx_spi_chip.dma_burst_size" field is used to configure PXA2xx DMA
-engine and is related the "spi_device.bits_per_word" field.  Read and understand
-the PXA2xx "Developer Manual" sections on the DMA controller and SSP Controllers
-to determine the correct value. An SSP configured for byte-wide transfers would
-use a value of 8. The driver will determine a reasonable default if
-dma_burst_size == 0.
-
-The "pxa2xx_spi_chip.timeout" fields is used to efficiently handle
-trailing bytes in the SSP receiver FIFO. The correct value for this field is
-dependent on the SPI bus speed ("spi_board_info.max_speed_hz") and the specific
-peripheral device. Please note that the PXA2xx SSP 1 does not support trailing byte
-timeouts and must busy-wait any trailing bytes.
-
-NOTE: the SPI driver cannot control the chip select if SSPFRM is used, so the
-chipselect is dropped after each spi_transfer.  Most devices need chip select
-asserted around the complete message. Use SSPFRM as a GPIO (through a descriptor)
-to accommodate these chips.
-
-
-NSSP PERIPHERAL SAMPLE
-----------------------
-For a legacy platform or in some other cases, the pxa2xx_spi_chip structure
-is passed to the pxa2xx_spi driver in the "spi_board_info.controller_data"
-field. Below is a sample configuration using the PXA255 NSSP.
-
-::
-
-  static struct pxa2xx_spi_chip cs8415a_chip_info = {
-	.tx_threshold = 8, /* SSP hardware FIFO threshold */
-	.rx_threshold = 8, /* SSP hardware FIFO threshold */
-	.dma_burst_size = 8, /* Byte wide transfers used so 8 byte bursts */
-	.timeout = 235, /* See Intel documentation */
-  };
-
-  static struct pxa2xx_spi_chip cs8405a_chip_info = {
-	.tx_threshold = 8, /* SSP hardware FIFO threshold */
-	.rx_threshold = 8, /* SSP hardware FIFO threshold */
-	.dma_burst_size = 8, /* Byte wide transfers used so 8 byte bursts */
-	.timeout = 235, /* See Intel documentation */
-  };
-
-  static struct spi_board_info streetracer_spi_board_info[] __initdata = {
-	{
-		.modalias = "cs8415a", /* Name of spi_driver for this device */
-		.max_speed_hz = 3686400, /* Run SSP as fast a possible */
-		.bus_num = 2, /* Framework bus number */
-		.chip_select = 0, /* Framework chip select */
-		.platform_data = NULL; /* No spi_driver specific config */
-		.controller_data = &cs8415a_chip_info, /* Host controller config */
-		.irq = STREETRACER_APCI_IRQ, /* Peripheral device interrupt */
-	},
-	{
-		.modalias = "cs8405a", /* Name of spi_driver for this device */
-		.max_speed_hz = 3686400, /* Run SSP as fast a possible */
-		.bus_num = 2, /* Framework bus number */
-		.chip_select = 1, /* Framework chip select */
-		.controller_data = &cs8405a_chip_info, /* Host controller config */
-		.irq = STREETRACER_APCI_IRQ, /* Peripheral device interrupt */
-	},
-  };
-
-  static void __init streetracer_init(void)
-  {
-	spi_register_board_info(streetracer_spi_board_info,
-				ARRAY_SIZE(streetracer_spi_board_info));
-  }
-
-
-DMA and PIO I/O Support
------------------------
-The pxa2xx_spi driver supports both DMA and interrupt driven PIO message
-transfers.  The driver defaults to PIO mode and DMA transfers must be enabled
-by setting the "enable_dma" flag in the "pxa2xx_spi_controller" structure.
-For the newer platforms, that are known to support DMA, the driver will enable
-it automatically and try it first with a possible fallback to PIO. The DMA
-mode supports both coherent and stream based DMA mappings.
-
-The following logic is used to determine the type of I/O to be used on
-a per "spi_transfer" basis::
-
-  if spi_message.len > 65536 then
-	if spi_message.is_dma_mapped or rx_dma_buf != 0 or tx_dma_buf != 0 then
-		reject premapped transfers
-
-	print "rate limited" warning
-	use PIO transfers
-
-  if enable_dma and the size is in the range [DMA burst size..65536] then
-	use streaming DMA mode
-
-  otherwise
-	use PIO transfer
-
-THANKS TO
----------
-David Brownell and others for mentoring the development of this driver.
diff --git a/Documentation/spi/spi-summary.rst b/Documentation/spi/spi-summary.rst
index 546de37d6caf..7f8accfae6f9 100644
--- a/Documentation/spi/spi-summary.rst
+++ b/Documentation/spi/spi-summary.rst
@@ -348,7 +348,6 @@ SPI protocol drivers somewhat resemble platform device drivers::
 	static struct spi_driver CHIP_driver = {
 		.driver = {
 			.name		= "CHIP",
-			.owner		= THIS_MODULE,
 			.pm		= &CHIP_pm_ops,
 		},
 
@@ -419,10 +418,6 @@ any more such messages.
     to make extra copies unless the hardware requires it (e.g. working
     around hardware errata that force the use of bounce buffering).
 
-    If standard dma_map_single() handling of these buffers is inappropriate,
-    you can use spi_message.is_dma_mapped to tell the controller driver
-    that you've already provided the relevant DMA addresses.
-
   - The basic I/O primitive is spi_async().  Async requests may be
     issued in any context (irq handler, task, etc) and completion
     is reported using a callback provided with the message.
diff --git a/MAINTAINERS b/MAINTAINERS
index aea47e04c3a5..893ca3d7a623 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -653,6 +653,15 @@ S:	Supported
 F:	fs/aio.c
 F:	include/linux/*aio*.h
 
+AIROHA SPI SNFI DRIVER
+M:	Lorenzo Bianconi <lorenzo@kernel.org>
+M:	Ray Liu <ray.liu@airoha.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-spi@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml
+F:	drivers/spi/spi-airoha-snfi.c
+
 AIRSPY MEDIA DRIVER
 L:	linux-media@vger.kernel.org
 S:	Orphan
@@ -21857,7 +21866,7 @@ F:	Documentation/devicetree/bindings/sound/tas2552.txt
 F:	Documentation/devicetree/bindings/sound/tas2562.yaml
 F:	Documentation/devicetree/bindings/sound/tas2770.yaml
 F:	Documentation/devicetree/bindings/sound/tas27xx.yaml
-F:	Documentation/devicetree/bindings/sound/ti,pcm1681.txt
+F:	Documentation/devicetree/bindings/sound/ti,pcm1681.yaml
 F:	Documentation/devicetree/bindings/sound/ti,pcm3168a.yaml
 F:	Documentation/devicetree/bindings/sound/ti,tlv320*.yaml
 F:	Documentation/devicetree/bindings/sound/tlv320adcx140.yaml
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 661b3fc43275..1e4cd502340e 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -7,7 +7,6 @@
 #include <linux/clk-provider.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
-#include <linux/spi/pxa2xx_spi.h>
 #include <linux/platform_data/i2c-pxa.h>
 #include <linux/soc/pxa/cpu.h>
 
@@ -665,23 +664,6 @@ struct platform_device pxa27x_device_gpio = {
 	.resource	= pxa_resource_gpio,
 };
 
-/* pxa2xx-spi platform-device ID equals respective SSP platform-device ID + 1.
- * See comment in arch/arm/mach-pxa/ssp.c::ssp_probe() */
-void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info)
-{
-	struct platform_device *pd;
-
-	pd = platform_device_alloc("pxa2xx-spi", id);
-	if (pd == NULL) {
-		printk(KERN_ERR "pxa2xx-spi: failed to allocate device id %d\n",
-		       id);
-		return;
-	}
-
-	pd->dev.platform_data = info;
-	platform_device_add(pd);
-}
-
 static struct resource pxa_dma_resource[] = {
 	[0] = {
 		.start	= 0x40000000,
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index cc691b199429..3c5f5a3cb480 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -18,10 +18,10 @@
 #include <linux/i2c.h>
 #include <linux/platform_data/i2c-pxa.h>
 #include <linux/platform_data/pca953x.h>
+#include <linux/property.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
 #include <linux/spi/corgi_lcd.h>
-#include <linux/spi/pxa2xx_spi.h>
 #include <linux/mtd/sharpsl.h>
 #include <linux/mtd/physmap.h>
 #include <linux/input-event-codes.h>
@@ -569,10 +569,6 @@ static struct spi_board_info spitz_spi_devices[] = {
 	},
 };
 
-static struct pxa2xx_spi_controller spitz_spi_info = {
-	.num_chipselect	= 3,
-};
-
 static struct gpiod_lookup_table spitz_spi_gpio_table = {
 	.dev_id = "spi2",
 	.table = {
@@ -583,8 +579,21 @@ static struct gpiod_lookup_table spitz_spi_gpio_table = {
 	},
 };
 
+static const struct property_entry spitz_spi_properties[] = {
+	PROPERTY_ENTRY_U32("num-cs", 3),
+	{ }
+};
+
+static const struct software_node spitz_spi_node = {
+	.properties = spitz_spi_properties,
+};
+
 static void __init spitz_spi_init(void)
 {
+	struct platform_device *pd;
+	int id = 2;
+	int err;
+
 	if (machine_is_akita())
 		gpiod_add_lookup_table(&akita_lcdcon_gpio_table);
 	else
@@ -592,7 +601,21 @@ static void __init spitz_spi_init(void)
 
 	gpiod_add_lookup_table(&spitz_ads7846_gpio_table);
 	gpiod_add_lookup_table(&spitz_spi_gpio_table);
-	pxa2xx_set_spi_info(2, &spitz_spi_info);
+
+	/* pxa2xx-spi platform-device ID equals respective SSP platform-device ID + 1 */
+	pd = platform_device_alloc("pxa2xx-spi", id);
+	if (pd == NULL) {
+		pr_err("pxa2xx-spi: failed to allocate device id %d\n", id);
+	} else {
+		err = device_add_software_node(&pd->dev, &spitz_spi_node);
+		if (err) {
+			platform_device_put(pd);
+			pr_err("pxa2xx-spi: failed to add software node\n");
+		} else {
+			platform_device_add(pd);
+		}
+	}
+
 	spi_register_board_info(ARRAY_AND_SIZE(spitz_spi_devices));
 }
 #else
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index b50d0b470849..00b5c007a2bb 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -103,6 +103,15 @@ config GPIO_REGMAP
 	select REGMAP
 	tristate
 
+config GPIO_SWNODE_UNDEFINED
+	bool
+	help
+	  This adds a special place holder for software nodes to contain an
+	  undefined GPIO reference, this is primarily used by SPI to allow a
+	  list of GPIO chip selects to mark a certain chip select as being
+	  controlled the SPI device's internal chip select mechanism and not
+	  a GPIO.
+
 # put drivers in the right section, in alphabetical order
 
 # This symbol is selected by both I2C and SPI expanders
diff --git a/drivers/gpio/gpiolib-swnode.c b/drivers/gpio/gpiolib-swnode.c
index fa52bdb1a29a..cec1ab878af8 100644
--- a/drivers/gpio/gpiolib-swnode.c
+++ b/drivers/gpio/gpiolib-swnode.c
@@ -4,8 +4,13 @@
  *
  * Copyright 2022 Google LLC
  */
+
+#define pr_fmt(fmt) "gpiolib: swnode: " fmt
+
 #include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/printk.h>
 #include <linux/property.h>
@@ -17,6 +22,8 @@
 #include "gpiolib.h"
 #include "gpiolib-swnode.h"
 
+#define GPIOLIB_SWNODE_UNDEFINED_NAME "swnode-gpio-undefined"
+
 static void swnode_format_propname(const char *con_id, char *propname,
 				   size_t max_size)
 {
@@ -40,6 +47,14 @@ static struct gpio_device *swnode_get_gpio_device(struct fwnode_handle *fwnode)
 	if (!gdev_node || !gdev_node->name)
 		return ERR_PTR(-EINVAL);
 
+	/*
+	 * Check for a special node that identifies undefined GPIOs, this is
+	 * primarily used as a key for internal chip selects in SPI bindings.
+	 */
+	if (IS_ENABLED(CONFIG_GPIO_SWNODE_UNDEFINED) &&
+	    !strcmp(gdev_node->name, GPIOLIB_SWNODE_UNDEFINED_NAME))
+		return ERR_PTR(-ENOENT);
+
 	gdev = gpio_device_find_by_label(gdev_node->name);
 	return gdev ?: ERR_PTR(-EPROBE_DEFER);
 }
@@ -121,3 +136,32 @@ int swnode_gpio_count(const struct fwnode_handle *fwnode, const char *con_id)
 
 	return count ?: -ENOENT;
 }
+
+#if IS_ENABLED(CONFIG_GPIO_SWNODE_UNDEFINED)
+/*
+ * A special node that identifies undefined GPIOs, this is primarily used as
+ * a key for internal chip selects in SPI bindings.
+ */
+const struct software_node swnode_gpio_undefined = {
+	.name = GPIOLIB_SWNODE_UNDEFINED_NAME,
+};
+EXPORT_SYMBOL_NS_GPL(swnode_gpio_undefined, GPIO_SWNODE);
+
+static int __init swnode_gpio_init(void)
+{
+	int ret;
+
+	ret = software_node_register(&swnode_gpio_undefined);
+	if (ret < 0)
+		pr_err("failed to register swnode: %d\n", ret);
+
+	return ret;
+}
+subsys_initcall(swnode_gpio_init);
+
+static void __exit swnode_gpio_cleanup(void)
+{
+	software_node_unregister(&swnode_gpio_undefined);
+}
+__exitcall(swnode_gpio_cleanup);
+#endif
diff --git a/drivers/soc/pxa/ssp.c b/drivers/soc/pxa/ssp.c
index 7af04e8b8163..854d32e04558 100644
--- a/drivers/soc/pxa/ssp.c
+++ b/drivers/soc/pxa/ssp.c
@@ -25,7 +25,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/platform_device.h>
-#include <linux/spi/pxa2xx_spi.h>
+#include <linux/pxa2xx_ssp.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index bc7021da2fe9..a2c99ff33e0a 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -57,6 +57,16 @@ config SPI_MEM
 
 comment "SPI Master Controller Drivers"
 
+config SPI_AIROHA_SNFI
+	tristate "Airoha SPI NAND Flash Interface"
+	depends on ARCH_AIROHA || COMPILE_TEST
+	depends on SPI_MASTER
+	select REGMAP_MMIO
+	help
+	  This enables support for SPI-NAND mode on the Airoha NAND
+	  Flash Interface found on Airoha ARM SoCs. This controller
+	  is implemented as a SPI-MEM controller.
+
 config SPI_ALTERA
 	tristate "Altera SPI Controller platform driver"
 	select SPI_ALTERA_CORE
@@ -216,11 +226,11 @@ config SPI_BCMBCA_HSSPI
 	  explicitly.
 
 config SPI_BITBANG
-	tristate "Utilities for Bitbanging SPI masters"
+	tristate "Utilities for Bitbanging SPI host controllers"
 	help
 	  With a few GPIO pins, your system can bitbang the SPI protocol.
 	  Select this to get SPI support through I/O pins (GPIO, parallel
-	  port, etc).  Or, some systems' SPI master controller drivers use
+	  port, etc).  Or, some systems' SPI host controller drivers use
 	  this code to manage the per-word or per-transfer accesses to the
 	  hardware shift registers.
 
@@ -246,7 +256,7 @@ config SPI_CADENCE
 
 config SPI_CADENCE_QUADSPI
 	tristate "Cadence Quad SPI controller"
-	depends on OF && (ARM || ARM64 || X86 || RISCV || COMPILE_TEST)
+	depends on OF && (ARM || ARM64 || X86 || RISCV || MIPS || COMPILE_TEST)
 	help
 	  Enable support for the Cadence Quad SPI Flash controller.
 
@@ -284,6 +294,7 @@ config SPI_COLDFIRE_QSPI
 config SPI_CS42L43
 	tristate "Cirrus Logic CS42L43 SPI controller"
 	depends on MFD_CS42L43 && PINCTRL_CS42L43
+	select GPIO_SWNODE_UNDEFINED
 	help
 	  This enables support for the SPI controller inside the Cirrus Logic
 	  CS42L43 audio codec.
@@ -817,12 +828,11 @@ config SPI_PPC4xx
 
 config SPI_PXA2XX
 	tristate "PXA2xx SSP SPI master"
-	depends on ARCH_PXA || ARCH_MMP || PCI || ACPI || COMPILE_TEST
+	depends on ARCH_PXA || ARCH_MMP || (X86 && (PCI || ACPI)) || COMPILE_TEST
 	select PXA_SSP if ARCH_PXA || ARCH_MMP
 	help
 	  This enables using a PXA2xx or Sodaville SSP port as a SPI master
-	  controller. The driver can be configured to use any SSP port and
-	  additional documentation can be found a Documentation/spi/pxa2xx.rst.
+	  controller. The driver can be configured to use any SSP port.
 
 config SPI_PXA2XX_PCI
 	def_tristate SPI_PXA2XX && PCI && COMMON_CLK
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 4ff8d725ba5e..e694254dec04 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_SPI_SPIDEV)		+= spidev.o
 obj-$(CONFIG_SPI_LOOPBACK_TEST)		+= spi-loopback-test.o
 
 # SPI master controller drivers (bus)
+obj-$(CONFIG_SPI_AIROHA_SNFI)		+= spi-airoha-snfi.o
 obj-$(CONFIG_SPI_ALTERA)		+= spi-altera-platform.o
 obj-$(CONFIG_SPI_ALTERA_CORE)		+= spi-altera-core.o
 obj-$(CONFIG_SPI_ALTERA_DFL)		+= spi-altera-dfl.o
diff --git a/drivers/spi/spi-airoha-snfi.c b/drivers/spi/spi-airoha-snfi.c
new file mode 100644
index 000000000000..9d97ec98881c
--- /dev/null
+++ b/drivers/spi/spi-airoha-snfi.c
@@ -0,0 +1,1129 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ * Author: Ray Liu <ray.liu@airoha.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/errno.h>
+#include <linux/limits.h>
+#include <linux/math.h>
+#include <linux/minmax.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/property.h>
+#include <linux/regmap.h>
+#include <linux/sizes.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+#include <linux/types.h>
+#include <asm/unaligned.h>
+
+/* SPI */
+#define REG_SPI_CTRL_BASE			0x1FA10000
+
+#define REG_SPI_CTRL_READ_MODE			0x0000
+#define REG_SPI_CTRL_READ_IDLE_EN		0x0004
+#define REG_SPI_CTRL_SIDLY			0x0008
+#define REG_SPI_CTRL_CSHEXT			0x000c
+#define REG_SPI_CTRL_CSLEXT			0x0010
+
+#define REG_SPI_CTRL_MTX_MODE_TOG		0x0014
+#define SPI_CTRL_MTX_MODE_TOG			GENMASK(3, 0)
+
+#define REG_SPI_CTRL_RDCTL_FSM			0x0018
+#define SPI_CTRL_RDCTL_FSM			GENMASK(3, 0)
+
+#define REG_SPI_CTRL_MACMUX_SEL			0x001c
+
+#define REG_SPI_CTRL_MANUAL_EN			0x0020
+#define SPI_CTRL_MANUAL_EN			BIT(0)
+
+#define REG_SPI_CTRL_OPFIFO_EMPTY		0x0024
+#define SPI_CTRL_OPFIFO_EMPTY			BIT(0)
+
+#define REG_SPI_CTRL_OPFIFO_WDATA		0x0028
+#define SPI_CTRL_OPFIFO_LEN			GENMASK(8, 0)
+#define SPI_CTRL_OPFIFO_OP			GENMASK(13, 9)
+
+#define REG_SPI_CTRL_OPFIFO_FULL		0x002c
+#define SPI_CTRL_OPFIFO_FULL			BIT(0)
+
+#define REG_SPI_CTRL_OPFIFO_WR			0x0030
+#define SPI_CTRL_OPFIFO_WR			BIT(0)
+
+#define REG_SPI_CTRL_DFIFO_FULL			0x0034
+#define SPI_CTRL_DFIFO_FULL			BIT(0)
+
+#define REG_SPI_CTRL_DFIFO_WDATA		0x0038
+#define SPI_CTRL_DFIFO_WDATA			GENMASK(7, 0)
+
+#define REG_SPI_CTRL_DFIFO_EMPTY		0x003c
+#define SPI_CTRL_DFIFO_EMPTY			BIT(0)
+
+#define REG_SPI_CTRL_DFIFO_RD			0x0040
+#define SPI_CTRL_DFIFO_RD			BIT(0)
+
+#define REG_SPI_CTRL_DFIFO_RDATA		0x0044
+#define SPI_CTRL_DFIFO_RDATA			GENMASK(7, 0)
+
+#define REG_SPI_CTRL_DUMMY			0x0080
+#define SPI_CTRL_CTRL_DUMMY			GENMASK(3, 0)
+
+#define REG_SPI_CTRL_PROBE_SEL			0x0088
+#define REG_SPI_CTRL_INTERRUPT			0x0090
+#define REG_SPI_CTRL_INTERRUPT_EN		0x0094
+#define REG_SPI_CTRL_SI_CK_SEL			0x009c
+#define REG_SPI_CTRL_SW_CFGNANDADDR_VAL		0x010c
+#define REG_SPI_CTRL_SW_CFGNANDADDR_EN		0x0110
+#define REG_SPI_CTRL_SFC_STRAP			0x0114
+
+#define REG_SPI_CTRL_NFI2SPI_EN			0x0130
+#define SPI_CTRL_NFI2SPI_EN			BIT(0)
+
+/* NFI2SPI */
+#define REG_SPI_NFI_CNFG			0x0000
+#define SPI_NFI_DMA_MODE			BIT(0)
+#define SPI_NFI_READ_MODE			BIT(1)
+#define SPI_NFI_DMA_BURST_EN			BIT(2)
+#define SPI_NFI_HW_ECC_EN			BIT(8)
+#define SPI_NFI_AUTO_FDM_EN			BIT(9)
+#define SPI_NFI_OPMODE				GENMASK(14, 12)
+
+#define REG_SPI_NFI_PAGEFMT			0x0004
+#define SPI_NFI_PAGE_SIZE			GENMASK(1, 0)
+#define SPI_NFI_SPARE_SIZE			GENMASK(5, 4)
+
+#define REG_SPI_NFI_CON				0x0008
+#define SPI_NFI_FIFO_FLUSH			BIT(0)
+#define SPI_NFI_RST				BIT(1)
+#define SPI_NFI_RD_TRIG				BIT(8)
+#define SPI_NFI_WR_TRIG				BIT(9)
+#define SPI_NFI_SEC_NUM				GENMASK(15, 12)
+
+#define REG_SPI_NFI_INTR_EN			0x0010
+#define SPI_NFI_RD_DONE_EN			BIT(0)
+#define SPI_NFI_WR_DONE_EN			BIT(1)
+#define SPI_NFI_RST_DONE_EN			BIT(2)
+#define SPI_NFI_ERASE_DONE_EN			BIT(3)
+#define SPI_NFI_BUSY_RETURN_EN			BIT(4)
+#define SPI_NFI_ACCESS_LOCK_EN			BIT(5)
+#define SPI_NFI_AHB_DONE_EN			BIT(6)
+#define SPI_NFI_ALL_IRQ_EN					\
+	(SPI_NFI_RD_DONE_EN | SPI_NFI_WR_DONE_EN |		\
+	 SPI_NFI_RST_DONE_EN | SPI_NFI_ERASE_DONE_EN |		\
+	 SPI_NFI_BUSY_RETURN_EN | SPI_NFI_ACCESS_LOCK_EN |	\
+	 SPI_NFI_AHB_DONE_EN)
+
+#define REG_SPI_NFI_INTR			0x0014
+#define SPI_NFI_AHB_DONE			BIT(6)
+
+#define REG_SPI_NFI_CMD				0x0020
+
+#define REG_SPI_NFI_ADDR_NOB			0x0030
+#define SPI_NFI_ROW_ADDR_NOB			GENMASK(6, 4)
+
+#define REG_SPI_NFI_STA				0x0060
+#define REG_SPI_NFI_FIFOSTA			0x0064
+#define REG_SPI_NFI_STRADDR			0x0080
+#define REG_SPI_NFI_FDM0L			0x00a0
+#define REG_SPI_NFI_FDM0M			0x00a4
+#define REG_SPI_NFI_FDM7L			0x00d8
+#define REG_SPI_NFI_FDM7M			0x00dc
+#define REG_SPI_NFI_FIFODATA0			0x0190
+#define REG_SPI_NFI_FIFODATA1			0x0194
+#define REG_SPI_NFI_FIFODATA2			0x0198
+#define REG_SPI_NFI_FIFODATA3			0x019c
+#define REG_SPI_NFI_MASTERSTA			0x0224
+
+#define REG_SPI_NFI_SECCUS_SIZE			0x022c
+#define SPI_NFI_CUS_SEC_SIZE			GENMASK(12, 0)
+#define SPI_NFI_CUS_SEC_SIZE_EN			BIT(16)
+
+#define REG_SPI_NFI_RD_CTL2			0x0510
+#define REG_SPI_NFI_RD_CTL3			0x0514
+
+#define REG_SPI_NFI_PG_CTL1			0x0524
+#define SPI_NFI_PG_LOAD_CMD			GENMASK(15, 8)
+
+#define REG_SPI_NFI_PG_CTL2			0x0528
+#define REG_SPI_NFI_NOR_PROG_ADDR		0x052c
+#define REG_SPI_NFI_NOR_RD_ADDR			0x0534
+
+#define REG_SPI_NFI_SNF_MISC_CTL		0x0538
+#define SPI_NFI_DATA_READ_WR_MODE		GENMASK(18, 16)
+
+#define REG_SPI_NFI_SNF_MISC_CTL2		0x053c
+#define SPI_NFI_READ_DATA_BYTE_NUM		GENMASK(12, 0)
+#define SPI_NFI_PROG_LOAD_BYTE_NUM		GENMASK(28, 16)
+
+#define REG_SPI_NFI_SNF_STA_CTL1		0x0550
+#define SPI_NFI_READ_FROM_CACHE_DONE		BIT(25)
+#define SPI_NFI_LOAD_TO_CACHE_DONE		BIT(26)
+
+#define REG_SPI_NFI_SNF_STA_CTL2		0x0554
+
+#define REG_SPI_NFI_SNF_NFI_CNFG		0x055c
+#define SPI_NFI_SPI_MODE			BIT(0)
+
+/* SPI NAND Protocol OP */
+#define SPI_NAND_OP_GET_FEATURE			0x0f
+#define SPI_NAND_OP_SET_FEATURE			0x1f
+#define SPI_NAND_OP_PAGE_READ			0x13
+#define SPI_NAND_OP_READ_FROM_CACHE_SINGLE	0x03
+#define SPI_NAND_OP_READ_FROM_CACHE_SINGLE_FAST	0x0b
+#define SPI_NAND_OP_READ_FROM_CACHE_DUAL	0x3b
+#define SPI_NAND_OP_READ_FROM_CACHE_QUAD	0x6b
+#define SPI_NAND_OP_WRITE_ENABLE		0x06
+#define SPI_NAND_OP_WRITE_DISABLE		0x04
+#define SPI_NAND_OP_PROGRAM_LOAD_SINGLE		0x02
+#define SPI_NAND_OP_PROGRAM_LOAD_QUAD		0x32
+#define SPI_NAND_OP_PROGRAM_LOAD_RAMDOM_SINGLE	0x84
+#define SPI_NAND_OP_PROGRAM_LOAD_RAMDON_QUAD	0x34
+#define SPI_NAND_OP_PROGRAM_EXECUTE		0x10
+#define SPI_NAND_OP_READ_ID			0x9f
+#define SPI_NAND_OP_BLOCK_ERASE			0xd8
+#define SPI_NAND_OP_RESET			0xff
+#define SPI_NAND_OP_DIE_SELECT			0xc2
+
+#define SPI_NAND_CACHE_SIZE			(SZ_4K + SZ_256)
+#define SPI_MAX_TRANSFER_SIZE			511
+
+enum airoha_snand_mode {
+	SPI_MODE_AUTO,
+	SPI_MODE_MANUAL,
+	SPI_MODE_DMA,
+};
+
+enum airoha_snand_cs {
+	SPI_CHIP_SEL_HIGH,
+	SPI_CHIP_SEL_LOW,
+};
+
+struct airoha_snand_dev {
+	size_t buf_len;
+
+	u8 *txrx_buf;
+	dma_addr_t dma_addr;
+
+	u64 cur_page_num;
+	bool data_need_update;
+};
+
+struct airoha_snand_ctrl {
+	struct device *dev;
+	struct regmap *regmap_ctrl;
+	struct regmap *regmap_nfi;
+	struct clk *spi_clk;
+
+	struct {
+		size_t page_size;
+		size_t sec_size;
+		u8 sec_num;
+		u8 spare_size;
+	} nfi_cfg;
+};
+
+static int airoha_snand_set_fifo_op(struct airoha_snand_ctrl *as_ctrl,
+				    u8 op_cmd, int op_len)
+{
+	int err;
+	u32 val;
+
+	err = regmap_write(as_ctrl->regmap_ctrl, REG_SPI_CTRL_OPFIFO_WDATA,
+			   FIELD_PREP(SPI_CTRL_OPFIFO_LEN, op_len) |
+			   FIELD_PREP(SPI_CTRL_OPFIFO_OP, op_cmd));
+	if (err)
+		return err;
+
+	err = regmap_read_poll_timeout(as_ctrl->regmap_ctrl,
+				       REG_SPI_CTRL_OPFIFO_FULL,
+				       val, !(val & SPI_CTRL_OPFIFO_FULL),
+				       0, 250 * USEC_PER_MSEC);
+	if (err)
+		return err;
+
+	err = regmap_write(as_ctrl->regmap_ctrl, REG_SPI_CTRL_OPFIFO_WR,
+			   SPI_CTRL_OPFIFO_WR);
+	if (err)
+		return err;
+
+	return regmap_read_poll_timeout(as_ctrl->regmap_ctrl,
+					REG_SPI_CTRL_OPFIFO_EMPTY,
+					val, (val & SPI_CTRL_OPFIFO_EMPTY),
+					0, 250 * USEC_PER_MSEC);
+}
+
+static int airoha_snand_set_cs(struct airoha_snand_ctrl *as_ctrl, u8 cs)
+{
+	return airoha_snand_set_fifo_op(as_ctrl, cs, sizeof(cs));
+}
+
+static int airoha_snand_write_data_to_fifo(struct airoha_snand_ctrl *as_ctrl,
+					   const u8 *data, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++) {
+		int err;
+		u32 val;
+
+		/* 1. Wait until dfifo is not full */
+		err = regmap_read_poll_timeout(as_ctrl->regmap_ctrl,
+					       REG_SPI_CTRL_DFIFO_FULL, val,
+					       !(val & SPI_CTRL_DFIFO_FULL),
+					       0, 250 * USEC_PER_MSEC);
+		if (err)
+			return err;
+
+		/* 2. Write data to register DFIFO_WDATA */
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_DFIFO_WDATA,
+				   FIELD_PREP(SPI_CTRL_DFIFO_WDATA, data[i]));
+		if (err)
+			return err;
+
+		/* 3. Wait until dfifo is not full */
+		err = regmap_read_poll_timeout(as_ctrl->regmap_ctrl,
+					       REG_SPI_CTRL_DFIFO_FULL, val,
+					       !(val & SPI_CTRL_DFIFO_FULL),
+					       0, 250 * USEC_PER_MSEC);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_snand_read_data_from_fifo(struct airoha_snand_ctrl *as_ctrl,
+					    u8 *ptr, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++) {
+		int err;
+		u32 val;
+
+		/* 1. wait until dfifo is not empty */
+		err = regmap_read_poll_timeout(as_ctrl->regmap_ctrl,
+					       REG_SPI_CTRL_DFIFO_EMPTY, val,
+					       !(val & SPI_CTRL_DFIFO_EMPTY),
+					       0, 250 * USEC_PER_MSEC);
+		if (err)
+			return err;
+
+		/* 2. read from dfifo to register DFIFO_RDATA */
+		err = regmap_read(as_ctrl->regmap_ctrl,
+				  REG_SPI_CTRL_DFIFO_RDATA, &val);
+		if (err)
+			return err;
+
+		ptr[i] = FIELD_GET(SPI_CTRL_DFIFO_RDATA, val);
+		/* 3. enable register DFIFO_RD to read next byte */
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_DFIFO_RD, SPI_CTRL_DFIFO_RD);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_snand_set_mode(struct airoha_snand_ctrl *as_ctrl,
+				 enum airoha_snand_mode mode)
+{
+	int err;
+
+	switch (mode) {
+	case SPI_MODE_MANUAL: {
+		u32 val;
+
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_NFI2SPI_EN, 0);
+		if (err)
+			return err;
+
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_READ_IDLE_EN, 0);
+		if (err)
+			return err;
+
+		err = regmap_read_poll_timeout(as_ctrl->regmap_ctrl,
+					       REG_SPI_CTRL_RDCTL_FSM, val,
+					       !(val & SPI_CTRL_RDCTL_FSM),
+					       0, 250 * USEC_PER_MSEC);
+		if (err)
+			return err;
+
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_MTX_MODE_TOG, 9);
+		if (err)
+			return err;
+
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_MANUAL_EN, SPI_CTRL_MANUAL_EN);
+		if (err)
+			return err;
+		break;
+	}
+	case SPI_MODE_DMA:
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_NFI2SPI_EN,
+				   SPI_CTRL_MANUAL_EN);
+		if (err < 0)
+			return err;
+
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_MTX_MODE_TOG, 0x0);
+		if (err < 0)
+			return err;
+
+		err = regmap_write(as_ctrl->regmap_ctrl,
+				   REG_SPI_CTRL_MANUAL_EN, 0x0);
+		if (err < 0)
+			return err;
+		break;
+	case SPI_MODE_AUTO:
+	default:
+		break;
+	}
+
+	return regmap_write(as_ctrl->regmap_ctrl, REG_SPI_CTRL_DUMMY, 0);
+}
+
+static int airoha_snand_write_data(struct airoha_snand_ctrl *as_ctrl, u8 cmd,
+				   const u8 *data, int len)
+{
+	int i, data_len;
+
+	for (i = 0; i < len; i += data_len) {
+		int err;
+
+		data_len = min(len, SPI_MAX_TRANSFER_SIZE);
+		err = airoha_snand_set_fifo_op(as_ctrl, cmd, data_len);
+		if (err)
+			return err;
+
+		err = airoha_snand_write_data_to_fifo(as_ctrl, &data[i],
+						      data_len);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_snand_read_data(struct airoha_snand_ctrl *as_ctrl, u8 *data,
+				  int len)
+{
+	int i, data_len;
+
+	for (i = 0; i < len; i += data_len) {
+		int err;
+
+		data_len = min(len, SPI_MAX_TRANSFER_SIZE);
+		err = airoha_snand_set_fifo_op(as_ctrl, 0xc, data_len);
+		if (err)
+			return err;
+
+		err = airoha_snand_read_data_from_fifo(as_ctrl, &data[i],
+						       data_len);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
+static int airoha_snand_nfi_init(struct airoha_snand_ctrl *as_ctrl)
+{
+	int err;
+
+	/* switch to SNFI mode */
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_NFI_CNFG,
+			   SPI_NFI_SPI_MODE);
+	if (err)
+		return err;
+
+	/* Enable DMA */
+	return regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_INTR_EN,
+				  SPI_NFI_ALL_IRQ_EN, SPI_NFI_AHB_DONE_EN);
+}
+
+static int airoha_snand_nfi_config(struct airoha_snand_ctrl *as_ctrl)
+{
+	int err;
+	u32 val;
+
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+			   SPI_NFI_FIFO_FLUSH | SPI_NFI_RST);
+	if (err)
+		return err;
+
+	/* auto FDM */
+	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+				SPI_NFI_AUTO_FDM_EN);
+	if (err)
+		return err;
+
+	/* HW ECC */
+	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+				SPI_NFI_HW_ECC_EN);
+	if (err)
+		return err;
+
+	/* DMA Burst */
+	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+			      SPI_NFI_DMA_BURST_EN);
+	if (err)
+		return err;
+
+	/* page format */
+	switch (as_ctrl->nfi_cfg.spare_size) {
+	case 26:
+		val = FIELD_PREP(SPI_NFI_SPARE_SIZE, 0x1);
+		break;
+	case 27:
+		val = FIELD_PREP(SPI_NFI_SPARE_SIZE, 0x2);
+		break;
+	case 28:
+		val = FIELD_PREP(SPI_NFI_SPARE_SIZE, 0x3);
+		break;
+	default:
+		val = FIELD_PREP(SPI_NFI_SPARE_SIZE, 0x0);
+		break;
+	}
+
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_PAGEFMT,
+				 SPI_NFI_SPARE_SIZE, val);
+	if (err)
+		return err;
+
+	switch (as_ctrl->nfi_cfg.page_size) {
+	case 2048:
+		val = FIELD_PREP(SPI_NFI_PAGE_SIZE, 0x1);
+		break;
+	case 4096:
+		val = FIELD_PREP(SPI_NFI_PAGE_SIZE, 0x2);
+		break;
+	default:
+		val = FIELD_PREP(SPI_NFI_PAGE_SIZE, 0x0);
+		break;
+	}
+
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_PAGEFMT,
+				 SPI_NFI_PAGE_SIZE, val);
+	if (err)
+		return err;
+
+	/* sec num */
+	val = FIELD_PREP(SPI_NFI_SEC_NUM, as_ctrl->nfi_cfg.sec_num);
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+				 SPI_NFI_SEC_NUM, val);
+	if (err)
+		return err;
+
+	/* enable cust sec size */
+	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SECCUS_SIZE,
+			      SPI_NFI_CUS_SEC_SIZE_EN);
+	if (err)
+		return err;
+
+	/* set cust sec size */
+	val = FIELD_PREP(SPI_NFI_CUS_SEC_SIZE, as_ctrl->nfi_cfg.sec_size);
+	return regmap_update_bits(as_ctrl->regmap_nfi,
+				  REG_SPI_NFI_SECCUS_SIZE,
+				  SPI_NFI_CUS_SEC_SIZE, val);
+}
+
+static bool airoha_snand_is_page_ops(const struct spi_mem_op *op)
+{
+	if (op->addr.nbytes != 2)
+		return false;
+
+	if (op->addr.buswidth != 1 && op->addr.buswidth != 2 &&
+	    op->addr.buswidth != 4)
+		return false;
+
+	switch (op->data.dir) {
+	case SPI_MEM_DATA_IN:
+		if (op->dummy.nbytes * BITS_PER_BYTE / op->dummy.buswidth > 0xf)
+			return false;
+
+		/* quad in / quad out */
+		if (op->addr.buswidth == 4)
+			return op->data.buswidth == 4;
+
+		if (op->addr.buswidth == 2)
+			return op->data.buswidth == 2;
+
+		/* standard spi */
+		return op->data.buswidth == 4 || op->data.buswidth == 2 ||
+		       op->data.buswidth == 1;
+	case SPI_MEM_DATA_OUT:
+		return !op->dummy.nbytes && op->addr.buswidth == 1 &&
+		       (op->data.buswidth == 4 || op->data.buswidth == 1);
+	default:
+		return false;
+	}
+}
+
+static int airoha_snand_adjust_op_size(struct spi_mem *mem,
+				       struct spi_mem_op *op)
+{
+	size_t max_len;
+
+	if (airoha_snand_is_page_ops(op)) {
+		struct airoha_snand_ctrl *as_ctrl;
+
+		as_ctrl = spi_controller_get_devdata(mem->spi->controller);
+		max_len = as_ctrl->nfi_cfg.sec_size;
+		max_len += as_ctrl->nfi_cfg.spare_size;
+		max_len *= as_ctrl->nfi_cfg.sec_num;
+
+		if (op->data.nbytes > max_len)
+			op->data.nbytes = max_len;
+	} else {
+		max_len = 1 + op->addr.nbytes + op->dummy.nbytes;
+		if (max_len >= 160)
+			return -EOPNOTSUPP;
+
+		if (op->data.nbytes > 160 - max_len)
+			op->data.nbytes = 160 - max_len;
+	}
+
+	return 0;
+}
+
+static bool airoha_snand_supports_op(struct spi_mem *mem,
+				     const struct spi_mem_op *op)
+{
+	if (!spi_mem_default_supports_op(mem, op))
+		return false;
+
+	if (op->cmd.buswidth != 1)
+		return false;
+
+	if (airoha_snand_is_page_ops(op))
+		return true;
+
+	return (!op->addr.nbytes || op->addr.buswidth == 1) &&
+	       (!op->dummy.nbytes || op->dummy.buswidth == 1) &&
+	       (!op->data.nbytes || op->data.buswidth == 1);
+}
+
+static int airoha_snand_dirmap_create(struct spi_mem_dirmap_desc *desc)
+{
+	struct airoha_snand_dev *as_dev = spi_get_ctldata(desc->mem->spi);
+
+	if (!as_dev->txrx_buf)
+		return -EINVAL;
+
+	if (desc->info.offset + desc->info.length > U32_MAX)
+		return -EINVAL;
+
+	if (!airoha_snand_supports_op(desc->mem, &desc->info.op_tmpl))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc,
+					u64 offs, size_t len, void *buf)
+{
+	struct spi_device *spi = desc->mem->spi;
+	struct airoha_snand_dev *as_dev = spi_get_ctldata(spi);
+	struct spi_mem_op *op = &desc->info.op_tmpl;
+	struct airoha_snand_ctrl *as_ctrl;
+	u32 val, rd_mode;
+	int err;
+
+	if (!as_dev->data_need_update)
+		return len;
+
+	as_dev->data_need_update = false;
+
+	switch (op->cmd.opcode) {
+	case SPI_NAND_OP_READ_FROM_CACHE_DUAL:
+		rd_mode = 1;
+		break;
+	case SPI_NAND_OP_READ_FROM_CACHE_QUAD:
+		rd_mode = 2;
+		break;
+	default:
+		rd_mode = 0;
+		break;
+	}
+
+	as_ctrl = spi_controller_get_devdata(spi->controller);
+	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_DMA);
+	if (err < 0)
+		return err;
+
+	err = airoha_snand_nfi_config(as_ctrl);
+	if (err)
+		return err;
+
+	dma_sync_single_for_device(as_ctrl->dev, as_dev->dma_addr,
+				   as_dev->buf_len, DMA_BIDIRECTIONAL);
+
+	/* set dma addr */
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_STRADDR,
+			   as_dev->dma_addr);
+	if (err)
+		return err;
+
+	/* set cust sec size */
+	val = as_ctrl->nfi_cfg.sec_size * as_ctrl->nfi_cfg.sec_num;
+	val = FIELD_PREP(SPI_NFI_READ_DATA_BYTE_NUM, val);
+	err = regmap_update_bits(as_ctrl->regmap_nfi,
+				 REG_SPI_NFI_SNF_MISC_CTL2,
+				 SPI_NFI_READ_DATA_BYTE_NUM, val);
+	if (err)
+		return err;
+
+	/* set read command */
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_RD_CTL2,
+			   op->cmd.opcode);
+	if (err)
+		return err;
+
+	/* set read mode */
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_MISC_CTL,
+			   FIELD_PREP(SPI_NFI_DATA_READ_WR_MODE, rd_mode));
+	if (err)
+		return err;
+
+	/* set read addr */
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_RD_CTL3, 0x0);
+	if (err)
+		return err;
+
+	/* set nfi read */
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+				 SPI_NFI_OPMODE,
+				 FIELD_PREP(SPI_NFI_OPMODE, 6));
+	if (err)
+		return err;
+
+	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+			      SPI_NFI_READ_MODE | SPI_NFI_DMA_MODE);
+	if (err)
+		return err;
+
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_CMD, 0x0);
+	if (err)
+		return err;
+
+	/* trigger dma start read */
+	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+				SPI_NFI_RD_TRIG);
+	if (err)
+		return err;
+
+	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+			      SPI_NFI_RD_TRIG);
+	if (err)
+		return err;
+
+	err = regmap_read_poll_timeout(as_ctrl->regmap_nfi,
+				       REG_SPI_NFI_SNF_STA_CTL1, val,
+				       (val & SPI_NFI_READ_FROM_CACHE_DONE),
+				       0, 1 * USEC_PER_SEC);
+	if (err)
+		return err;
+
+	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_STA_CTL1,
+			      SPI_NFI_READ_FROM_CACHE_DONE);
+	if (err)
+		return err;
+
+	err = regmap_read_poll_timeout(as_ctrl->regmap_nfi, REG_SPI_NFI_INTR,
+				       val, (val & SPI_NFI_AHB_DONE), 0,
+				       1 * USEC_PER_SEC);
+	if (err)
+		return err;
+
+	/* DMA read need delay for data ready from controller to DRAM */
+	udelay(1);
+
+	dma_sync_single_for_cpu(as_ctrl->dev, as_dev->dma_addr,
+				as_dev->buf_len, DMA_BIDIRECTIONAL);
+	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL);
+	if (err < 0)
+		return err;
+
+	memcpy(buf, as_dev->txrx_buf + offs, len);
+
+	return len;
+}
+
+static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc,
+					 u64 offs, size_t len, const void *buf)
+{
+	struct spi_device *spi = desc->mem->spi;
+	struct airoha_snand_dev *as_dev = spi_get_ctldata(spi);
+	struct spi_mem_op *op = &desc->info.op_tmpl;
+	struct airoha_snand_ctrl *as_ctrl;
+	u32 wr_mode, val;
+	int err;
+
+	as_ctrl = spi_controller_get_devdata(spi->controller);
+	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL);
+	if (err < 0)
+		return err;
+
+	dma_sync_single_for_cpu(as_ctrl->dev, as_dev->dma_addr,
+				as_dev->buf_len, DMA_BIDIRECTIONAL);
+	memcpy(as_dev->txrx_buf + offs, buf, len);
+	dma_sync_single_for_device(as_ctrl->dev, as_dev->dma_addr,
+				   as_dev->buf_len, DMA_BIDIRECTIONAL);
+
+	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_DMA);
+	if (err < 0)
+		return err;
+
+	err = airoha_snand_nfi_config(as_ctrl);
+	if (err)
+		return err;
+
+	if (op->cmd.opcode == SPI_NAND_OP_PROGRAM_LOAD_QUAD ||
+	    op->cmd.opcode == SPI_NAND_OP_PROGRAM_LOAD_RAMDON_QUAD)
+		wr_mode = BIT(1);
+	else
+		wr_mode = 0;
+
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_STRADDR,
+			   as_dev->dma_addr);
+	if (err)
+		return err;
+
+	val = FIELD_PREP(SPI_NFI_PROG_LOAD_BYTE_NUM,
+			 as_ctrl->nfi_cfg.sec_size * as_ctrl->nfi_cfg.sec_num);
+	err = regmap_update_bits(as_ctrl->regmap_nfi,
+				 REG_SPI_NFI_SNF_MISC_CTL2,
+				 SPI_NFI_PROG_LOAD_BYTE_NUM, val);
+	if (err)
+		return err;
+
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_PG_CTL1,
+			   FIELD_PREP(SPI_NFI_PG_LOAD_CMD,
+				      op->cmd.opcode));
+	if (err)
+		return err;
+
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_MISC_CTL,
+			   FIELD_PREP(SPI_NFI_DATA_READ_WR_MODE, wr_mode));
+	if (err)
+		return err;
+
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_PG_CTL2, 0x0);
+	if (err)
+		return err;
+
+	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+				SPI_NFI_READ_MODE);
+	if (err)
+		return err;
+
+	err = regmap_update_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+				 SPI_NFI_OPMODE,
+				 FIELD_PREP(SPI_NFI_OPMODE, 3));
+	if (err)
+		return err;
+
+	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CNFG,
+			      SPI_NFI_DMA_MODE);
+	if (err)
+		return err;
+
+	err = regmap_write(as_ctrl->regmap_nfi, REG_SPI_NFI_CMD, 0x80);
+	if (err)
+		return err;
+
+	err = regmap_clear_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+				SPI_NFI_WR_TRIG);
+	if (err)
+		return err;
+
+	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_CON,
+			      SPI_NFI_WR_TRIG);
+	if (err)
+		return err;
+
+	err = regmap_read_poll_timeout(as_ctrl->regmap_nfi, REG_SPI_NFI_INTR,
+				       val, (val & SPI_NFI_AHB_DONE), 0,
+				       1 * USEC_PER_SEC);
+	if (err)
+		return err;
+
+	err = regmap_read_poll_timeout(as_ctrl->regmap_nfi,
+				       REG_SPI_NFI_SNF_STA_CTL1, val,
+				       (val & SPI_NFI_LOAD_TO_CACHE_DONE),
+				       0, 1 * USEC_PER_SEC);
+	if (err)
+		return err;
+
+	err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_STA_CTL1,
+			      SPI_NFI_LOAD_TO_CACHE_DONE);
+	if (err)
+		return err;
+
+	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL);
+	if (err < 0)
+		return err;
+
+	return len;
+}
+
+static int airoha_snand_exec_op(struct spi_mem *mem,
+				const struct spi_mem_op *op)
+{
+	struct airoha_snand_dev *as_dev = spi_get_ctldata(mem->spi);
+	u8 data[8], cmd, opcode = op->cmd.opcode;
+	struct airoha_snand_ctrl *as_ctrl;
+	int i, err;
+
+	as_ctrl = spi_controller_get_devdata(mem->spi->controller);
+	if (opcode == SPI_NAND_OP_PROGRAM_EXECUTE &&
+	    op->addr.val == as_dev->cur_page_num) {
+		as_dev->data_need_update = true;
+	} else if (opcode == SPI_NAND_OP_PAGE_READ) {
+		if (!as_dev->data_need_update &&
+		    op->addr.val == as_dev->cur_page_num)
+			return 0;
+
+		as_dev->data_need_update = true;
+		as_dev->cur_page_num = op->addr.val;
+	}
+
+	/* switch to manual mode */
+	err = airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL);
+	if (err < 0)
+		return err;
+
+	err = airoha_snand_set_cs(as_ctrl, SPI_CHIP_SEL_LOW);
+	if (err < 0)
+		return err;
+
+	/* opcode */
+	err = airoha_snand_write_data(as_ctrl, 0x8, &opcode, sizeof(opcode));
+	if (err)
+		return err;
+
+	/* addr part */
+	cmd = opcode == SPI_NAND_OP_GET_FEATURE ? 0x11 : 0x8;
+	put_unaligned_be64(op->addr.val, data);
+
+	for (i = ARRAY_SIZE(data) - op->addr.nbytes;
+	     i < ARRAY_SIZE(data); i++) {
+		err = airoha_snand_write_data(as_ctrl, cmd, &data[i],
+					      sizeof(data[0]));
+		if (err)
+			return err;
+	}
+
+	/* dummy */
+	data[0] = 0xff;
+	for (i = 0; i < op->dummy.nbytes; i++) {
+		err = airoha_snand_write_data(as_ctrl, 0x8, &data[0],
+					      sizeof(data[0]));
+		if (err)
+			return err;
+	}
+
+	/* data */
+	if (op->data.dir == SPI_MEM_DATA_IN) {
+		err = airoha_snand_read_data(as_ctrl, op->data.buf.in,
+					     op->data.nbytes);
+		if (err)
+			return err;
+	} else {
+		err = airoha_snand_write_data(as_ctrl, 0x8, op->data.buf.out,
+					      op->data.nbytes);
+		if (err)
+			return err;
+	}
+
+	return airoha_snand_set_cs(as_ctrl, SPI_CHIP_SEL_HIGH);
+}
+
+static const struct spi_controller_mem_ops airoha_snand_mem_ops = {
+	.adjust_op_size = airoha_snand_adjust_op_size,
+	.supports_op = airoha_snand_supports_op,
+	.exec_op = airoha_snand_exec_op,
+	.dirmap_create = airoha_snand_dirmap_create,
+	.dirmap_read = airoha_snand_dirmap_read,
+	.dirmap_write = airoha_snand_dirmap_write,
+};
+
+static int airoha_snand_setup(struct spi_device *spi)
+{
+	struct airoha_snand_ctrl *as_ctrl;
+	struct airoha_snand_dev *as_dev;
+
+	as_ctrl = spi_controller_get_devdata(spi->controller);
+
+	as_dev = devm_kzalloc(as_ctrl->dev, sizeof(*as_dev), GFP_KERNEL);
+	if (!as_dev)
+		return -ENOMEM;
+
+	/* prepare device buffer */
+	as_dev->buf_len = SPI_NAND_CACHE_SIZE;
+	as_dev->txrx_buf = devm_kzalloc(as_ctrl->dev, as_dev->buf_len,
+					GFP_KERNEL);
+	if (!as_dev->txrx_buf)
+		return -ENOMEM;
+
+	as_dev->dma_addr = dma_map_single(as_ctrl->dev, as_dev->txrx_buf,
+					  as_dev->buf_len, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(as_ctrl->dev, as_dev->dma_addr))
+		return -ENOMEM;
+
+	as_dev->data_need_update = true;
+	spi_set_ctldata(spi, as_dev);
+
+	return 0;
+}
+
+static void airoha_snand_cleanup(struct spi_device *spi)
+{
+	struct airoha_snand_dev *as_dev = spi_get_ctldata(spi);
+	struct airoha_snand_ctrl *as_ctrl;
+
+	as_ctrl = spi_controller_get_devdata(spi->controller);
+	dma_unmap_single(as_ctrl->dev, as_dev->dma_addr,
+			 as_dev->buf_len, DMA_BIDIRECTIONAL);
+	spi_set_ctldata(spi, NULL);
+}
+
+static int airoha_snand_nfi_setup(struct airoha_snand_ctrl *as_ctrl)
+{
+	u32 val, sec_size, sec_num;
+	int err;
+
+	err = regmap_read(as_ctrl->regmap_nfi, REG_SPI_NFI_CON, &val);
+	if (err)
+		return err;
+
+	sec_num = FIELD_GET(SPI_NFI_SEC_NUM, val);
+
+	err = regmap_read(as_ctrl->regmap_nfi, REG_SPI_NFI_SECCUS_SIZE, &val);
+	if (err)
+		return err;
+
+	sec_size = FIELD_GET(SPI_NFI_CUS_SEC_SIZE, val);
+
+	/* init default value */
+	as_ctrl->nfi_cfg.sec_size = sec_size;
+	as_ctrl->nfi_cfg.sec_num = sec_num;
+	as_ctrl->nfi_cfg.page_size = round_down(sec_size * sec_num, 1024);
+	as_ctrl->nfi_cfg.spare_size = 16;
+
+	err = airoha_snand_nfi_init(as_ctrl);
+	if (err)
+		return err;
+
+	return airoha_snand_nfi_config(as_ctrl);
+}
+
+static const struct regmap_config spi_ctrl_regmap_config = {
+	.name		= "ctrl",
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= REG_SPI_CTRL_NFI2SPI_EN,
+};
+
+static const struct regmap_config spi_nfi_regmap_config = {
+	.name		= "nfi",
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= REG_SPI_NFI_SNF_NFI_CNFG,
+};
+
+static const struct of_device_id airoha_snand_ids[] = {
+	{ .compatible	= "airoha,en7581-snand" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, airoha_snand_ids);
+
+static int airoha_snand_probe(struct platform_device *pdev)
+{
+	struct airoha_snand_ctrl *as_ctrl;
+	struct device *dev = &pdev->dev;
+	struct spi_controller *ctrl;
+	void __iomem *base;
+	int err;
+
+	ctrl = devm_spi_alloc_host(dev, sizeof(*as_ctrl));
+	if (!ctrl)
+		return -ENOMEM;
+
+	as_ctrl = spi_controller_get_devdata(ctrl);
+	as_ctrl->dev = dev;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	as_ctrl->regmap_ctrl = devm_regmap_init_mmio(dev, base,
+						     &spi_ctrl_regmap_config);
+	if (IS_ERR(as_ctrl->regmap_ctrl))
+		return dev_err_probe(dev, PTR_ERR(as_ctrl->regmap_ctrl),
+				     "failed to init spi ctrl regmap\n");
+
+	base = devm_platform_ioremap_resource(pdev, 1);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	as_ctrl->regmap_nfi = devm_regmap_init_mmio(dev, base,
+						    &spi_nfi_regmap_config);
+	if (IS_ERR(as_ctrl->regmap_nfi))
+		return dev_err_probe(dev, PTR_ERR(as_ctrl->regmap_nfi),
+				     "failed to init spi nfi regmap\n");
+
+	as_ctrl->spi_clk = devm_clk_get_enabled(dev, "spi");
+	if (IS_ERR(as_ctrl->spi_clk))
+		return dev_err_probe(dev, PTR_ERR(as_ctrl->spi_clk),
+				     "unable to get spi clk\n");
+
+	err = dma_set_mask(as_ctrl->dev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	ctrl->num_chipselect = 2;
+	ctrl->mem_ops = &airoha_snand_mem_ops;
+	ctrl->bits_per_word_mask = SPI_BPW_MASK(8);
+	ctrl->mode_bits = SPI_RX_DUAL;
+	ctrl->setup = airoha_snand_setup;
+	ctrl->cleanup = airoha_snand_cleanup;
+	device_set_node(&ctrl->dev, dev_fwnode(dev));
+
+	err = airoha_snand_nfi_setup(as_ctrl);
+	if (err)
+		return err;
+
+	return devm_spi_register_controller(dev, ctrl);
+}
+
+static struct platform_driver airoha_snand_driver = {
+	.driver = {
+		.name = "airoha-spi",
+		.of_match_table = airoha_snand_ids,
+	},
+	.probe = airoha_snand_probe,
+};
+module_platform_driver(airoha_snand_driver);
+
+MODULE_DESCRIPTION("Airoha SPI-NAND Flash Controller Driver");
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_AUTHOR("Ray Liu <ray.liu@airoha.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-altera-platform.c b/drivers/spi/spi-altera-platform.c
index 72e7a0f21793..585393802e9f 100644
--- a/drivers/spi/spi-altera-platform.c
+++ b/drivers/spi/spi-altera-platform.c
@@ -169,4 +169,3 @@ module_platform_driver(altera_spi_driver);
 MODULE_DESCRIPTION("Altera SPI driver");
 MODULE_AUTHOR("Thomas Chou <thomas@wytron.com.tw>");
 MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/spi/spi-amd.c b/drivers/spi/spi-amd.c
index 5d9b246b6963..2245ad54b03a 100644
--- a/drivers/spi/spi-amd.c
+++ b/drivers/spi/spi-amd.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/spi/spi.h>
 #include <linux/iopoll.h>
+#include <linux/spi/spi-mem.h>
 
 #define AMD_SPI_CTRL0_REG	0x00
 #define AMD_SPI_EXEC_CMD	BIT(16)
@@ -35,6 +36,7 @@
 
 #define AMD_SPI_FIFO_SIZE	70
 #define AMD_SPI_MEM_SIZE	200
+#define AMD_SPI_MAX_DATA	64
 
 #define AMD_SPI_ENA_REG		0x20
 #define AMD_SPI_ALT_SPD_SHIFT	20
@@ -358,6 +360,115 @@ fin_msg:
 	return message->status;
 }
 
+static bool amd_spi_supports_op(struct spi_mem *mem,
+				const struct spi_mem_op *op)
+{
+	/* bus width is number of IO lines used to transmit */
+	if (op->cmd.buswidth > 1 || op->addr.buswidth > 1 ||
+	    op->data.buswidth > 1 || op->data.nbytes > AMD_SPI_MAX_DATA)
+		return false;
+
+	return spi_mem_default_supports_op(mem, op);
+}
+
+static int amd_spi_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
+{
+	op->data.nbytes = clamp_val(op->data.nbytes, 0, AMD_SPI_MAX_DATA);
+	return 0;
+}
+
+static void amd_spi_set_addr(struct amd_spi *amd_spi,
+			     const struct spi_mem_op *op)
+{
+	u8 nbytes = op->addr.nbytes;
+	u64 addr_val = op->addr.val;
+	int base_addr, i;
+
+	base_addr = AMD_SPI_FIFO_BASE + nbytes;
+
+	for (i = 0; i < nbytes; i++) {
+		amd_spi_writereg8(amd_spi, base_addr - i - 1, addr_val &
+				  GENMASK(7, 0));
+		addr_val >>= 8;
+	}
+}
+
+static void amd_spi_mem_data_out(struct amd_spi *amd_spi,
+				 const struct spi_mem_op *op)
+{
+	int base_addr = AMD_SPI_FIFO_BASE + op->addr.nbytes;
+	u8 *buf = (u8 *)op->data.buf.out;
+	u32 nbytes = op->data.nbytes;
+	int i;
+
+	amd_spi_set_opcode(amd_spi, op->cmd.opcode);
+	amd_spi_set_addr(amd_spi, op);
+
+	for (i = 0; i < nbytes; i++)
+		amd_spi_writereg8(amd_spi, (base_addr + i), buf[i]);
+
+	amd_spi_set_tx_count(amd_spi, op->addr.nbytes + op->data.nbytes);
+	amd_spi_set_rx_count(amd_spi, 0);
+	amd_spi_clear_fifo_ptr(amd_spi);
+	amd_spi_execute_opcode(amd_spi);
+}
+
+static void amd_spi_mem_data_in(struct amd_spi *amd_spi,
+				const struct spi_mem_op *op)
+{
+	int offset = (op->addr.nbytes == 0) ? 0 : 1;
+	u8 *buf = (u8 *)op->data.buf.in;
+	u32 nbytes = op->data.nbytes;
+	int base_addr, i;
+
+	base_addr = AMD_SPI_FIFO_BASE + op->addr.nbytes + offset;
+
+	amd_spi_set_opcode(amd_spi, op->cmd.opcode);
+	amd_spi_set_addr(amd_spi, op);
+	amd_spi_set_tx_count(amd_spi, op->addr.nbytes);
+	amd_spi_set_rx_count(amd_spi, op->data.nbytes + 1);
+	amd_spi_clear_fifo_ptr(amd_spi);
+	amd_spi_execute_opcode(amd_spi);
+	amd_spi_busy_wait(amd_spi);
+
+	for (i = 0; i < nbytes; i++)
+		buf[i] = amd_spi_readreg8(amd_spi, base_addr + i);
+}
+
+static int amd_spi_exec_mem_op(struct spi_mem *mem,
+			       const struct spi_mem_op *op)
+{
+	struct amd_spi *amd_spi;
+	int ret;
+
+	amd_spi = spi_controller_get_devdata(mem->spi->controller);
+
+	ret = amd_set_spi_freq(amd_spi, mem->spi->max_speed_hz);
+	if (ret)
+		return ret;
+
+	switch (op->data.dir) {
+	case SPI_MEM_DATA_IN:
+		amd_spi_mem_data_in(amd_spi, op);
+		break;
+	case SPI_MEM_DATA_OUT:
+		fallthrough;
+	case SPI_MEM_NO_DATA:
+		amd_spi_mem_data_out(amd_spi, op);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+static const struct spi_controller_mem_ops amd_spi_mem_ops = {
+	.exec_op = amd_spi_exec_mem_op,
+	.adjust_op_size = amd_spi_adjust_op_size,
+	.supports_op = amd_spi_supports_op,
+};
+
 static int amd_spi_host_transfer(struct spi_controller *host,
 				   struct spi_message *msg)
 {
@@ -409,6 +520,7 @@ static int amd_spi_probe(struct platform_device *pdev)
 	host->min_speed_hz = AMD_SPI_MIN_HZ;
 	host->setup = amd_spi_host_setup;
 	host->transfer_one_message = amd_spi_host_transfer;
+	host->mem_ops = &amd_spi_mem_ops;
 	host->max_transfer_size = amd_spi_max_transfer_size;
 	host->max_message_size = amd_spi_max_transfer_size;
 
diff --git a/drivers/spi/spi-armada-3700.c b/drivers/spi/spi-armada-3700.c
index 3c9ed412932f..02c1e625742d 100644
--- a/drivers/spi/spi-armada-3700.c
+++ b/drivers/spi/spi-armada-3700.c
@@ -339,7 +339,7 @@ static irqreturn_t a3700_spi_interrupt(int irq, void *dev_id)
 static bool a3700_spi_wait_completion(struct spi_device *spi)
 {
 	struct a3700_spi *a3700_spi;
-	unsigned int timeout;
+	unsigned long time_left;
 	unsigned int ctrl_reg;
 	unsigned long timeout_jiffies;
 
@@ -361,12 +361,12 @@ static bool a3700_spi_wait_completion(struct spi_device *spi)
 		     a3700_spi->wait_mask);
 
 	timeout_jiffies = msecs_to_jiffies(A3700_SPI_TIMEOUT);
-	timeout = wait_for_completion_timeout(&a3700_spi->done,
-					      timeout_jiffies);
+	time_left = wait_for_completion_timeout(&a3700_spi->done,
+						timeout_jiffies);
 
 	a3700_spi->wait_mask = 0;
 
-	if (timeout)
+	if (time_left)
 		return true;
 
 	/* there might be the case that right after we checked the
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index bad34998454a..b62f57390d8f 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -987,8 +987,6 @@ static void atmel_spi_pdc_next_xfer(struct spi_controller *host,
  * For DMA, tx_buf/tx_dma have the same relationship as rx_buf/rx_dma:
  *  - The buffer is either valid for CPU access, else NULL
  *  - If the buffer is valid, so is its DMA address
- *
- * This driver manages the dma address unless message->is_dma_mapped.
  */
 static int
 atmel_spi_dma_map_xfer(struct atmel_spi *as, struct spi_transfer *xfer)
@@ -1374,8 +1372,7 @@ static int atmel_spi_one_transfer(struct spi_controller *host,
 	 * DMA map early, for performance (empties dcache ASAP) and
 	 * better fault reporting.
 	 */
-	if ((!host->cur_msg->is_dma_mapped)
-		&& as->use_pdc) {
+	if (as->use_pdc) {
 		if (atmel_spi_dma_map_xfer(as, xfer) < 0)
 			return -ENOMEM;
 	}
@@ -1454,8 +1451,7 @@ static int atmel_spi_one_transfer(struct spi_controller *host,
 		}
 	}
 
-	if (!host->cur_msg->is_dma_mapped
-		&& as->use_pdc)
+	if (as->use_pdc)
 		atmel_spi_dma_unmap_xfer(host, xfer);
 
 	if (as->use_pdc)
diff --git a/drivers/spi/spi-au1550.c b/drivers/spi/spi-au1550.c
index 825d2f1cdff8..16f200bb3d17 100644
--- a/drivers/spi/spi-au1550.c
+++ b/drivers/spi/spi-au1550.c
@@ -314,11 +314,8 @@ static int au1550_spi_dma_txrxb(struct spi_device *spi, struct spi_transfer *t)
 
 	hw->tx = t->tx_buf;
 	hw->rx = t->rx_buf;
-	dma_tx_addr = t->tx_dma;
-	dma_rx_addr = t->rx_dma;
 
 	/*
-	 * check if buffers are already dma mapped, map them otherwise:
 	 * - first map the TX buffer, so cache data gets written to memory
 	 * - then map the RX buffer, so that cache entries (with
 	 *   soon-to-be-stale data) get removed
@@ -326,23 +323,17 @@ static int au1550_spi_dma_txrxb(struct spi_device *spi, struct spi_transfer *t)
 	 * use temp rx buffer (preallocated or realloc to fit) for rx dma
 	 */
 	if (t->tx_buf) {
-		if (t->tx_dma == 0) {	/* if DMA_ADDR_INVALID, map it */
-			dma_tx_addr = dma_map_single(hw->dev,
-					(void *)t->tx_buf,
-					t->len, DMA_TO_DEVICE);
-			if (dma_mapping_error(hw->dev, dma_tx_addr))
-				dev_err(hw->dev, "tx dma map error\n");
-		}
+		dma_tx_addr = dma_map_single(hw->dev, (void *)t->tx_buf,
+					     t->len, DMA_TO_DEVICE);
+		if (dma_mapping_error(hw->dev, dma_tx_addr))
+			dev_err(hw->dev, "tx dma map error\n");
 	}
 
 	if (t->rx_buf) {
-		if (t->rx_dma == 0) {	/* if DMA_ADDR_INVALID, map it */
-			dma_rx_addr = dma_map_single(hw->dev,
-					(void *)t->rx_buf,
-					t->len, DMA_FROM_DEVICE);
-			if (dma_mapping_error(hw->dev, dma_rx_addr))
-				dev_err(hw->dev, "rx dma map error\n");
-		}
+		dma_rx_addr = dma_map_single(hw->dev, (void *)t->rx_buf,
+					     t->len, DMA_FROM_DEVICE);
+		if (dma_mapping_error(hw->dev, dma_rx_addr))
+			dev_err(hw->dev, "rx dma map error\n");
 	} else {
 		if (t->len > hw->dma_rx_tmpbuf_size) {
 			int ret;
@@ -398,10 +389,10 @@ static int au1550_spi_dma_txrxb(struct spi_device *spi, struct spi_transfer *t)
 			DMA_FROM_DEVICE);
 	}
 	/* unmap buffers if mapped above */
-	if (t->rx_buf && t->rx_dma == 0)
+	if (t->rx_buf)
 		dma_unmap_single(hw->dev, dma_rx_addr, t->len,
 			DMA_FROM_DEVICE);
-	if (t->tx_buf && t->tx_dma == 0)
+	if (t->tx_buf)
 		dma_unmap_single(hw->dev, dma_tx_addr, t->len,
 			DMA_TO_DEVICE);
 
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index a0e2204fc039..ca5cc67555c5 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * polling/bitbanging SPI master controller driver utilities
+ * Polling/bitbanging SPI host controller controller driver utilities
  */
 
 #include <linux/spinlock.h>
@@ -11,6 +11,7 @@
 #include <linux/errno.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/time64.h>
 
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
@@ -168,8 +169,8 @@ int spi_bitbang_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 	if (!hz)
 		hz = spi->max_speed_hz;
 	if (hz) {
-		cs->nsecs = (1000000000/2) / hz;
-		if (cs->nsecs > (MAX_UDELAY_MS * 1000 * 1000))
+		cs->nsecs = (NSEC_PER_SEC / 2) / hz;
+		if (cs->nsecs > (MAX_UDELAY_MS * NSEC_PER_MSEC))
 			return -EINVAL;
 	}
 
@@ -393,12 +394,12 @@ int spi_bitbang_init(struct spi_bitbang *bitbang)
 EXPORT_SYMBOL_GPL(spi_bitbang_init);
 
 /**
- * spi_bitbang_start - start up a polled/bitbanging SPI master driver
+ * spi_bitbang_start - start up a polled/bitbanging SPI host controller driver
  * @bitbang: driver handle
  *
  * Caller should have zero-initialized all parts of the structure, and then
- * provided callbacks for chip selection and I/O loops.  If the master has
- * a transfer method, its final step should call spi_bitbang_transfer; or,
+ * provided callbacks for chip selection and I/O loops.  If the host controller has
+ * a transfer method, its final step should call spi_bitbang_transfer(); or,
  * that's the default if the transfer routine is not initialized.  It should
  * also set up the bus number and number of chipselects.
  *
@@ -406,9 +407,9 @@ EXPORT_SYMBOL_GPL(spi_bitbang_init);
  * hardware that basically exposes a shift register) or per-spi_transfer
  * (which takes better advantage of hardware like fifos or DMA engines).
  *
- * Drivers using per-word I/O loops should use (or call) spi_bitbang_setup,
- * spi_bitbang_cleanup and spi_bitbang_setup_transfer to handle those spi
- * master methods.  Those methods are the defaults if the bitbang->txrx_bufs
+ * Drivers using per-word I/O loops should use (or call) spi_bitbang_setup(),
+ * spi_bitbang_cleanup() and spi_bitbang_setup_transfer() to handle those SPI
+ * host controller methods.  Those methods are the defaults if the bitbang->txrx_bufs
  * routine isn't initialized.
  *
  * This routine registers the spi_controller, which will process requests in a
@@ -417,7 +418,7 @@ EXPORT_SYMBOL_GPL(spi_bitbang_init);
  *
  * On success, this routine will take a reference to the controller. The caller
  * is responsible for calling spi_bitbang_stop() to decrement the reference and
- * spi_controller_put() as counterpart of spi_alloc_master() to prevent a memory
+ * spi_controller_put() as counterpart of spi_alloc_host() to prevent a memory
  * leak.
  */
 int spi_bitbang_start(struct spi_bitbang *bitbang)
@@ -450,4 +451,4 @@ void spi_bitbang_stop(struct spi_bitbang *bitbang)
 EXPORT_SYMBOL_GPL(spi_bitbang_stop);
 
 MODULE_LICENSE("GPL");
-
+MODULE_DESCRIPTION("Utilities for Bitbanging SPI host controllers");
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 350b3dab3a05..05ebb03d319f 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -42,6 +42,7 @@ static_assert(CQSPI_MAX_CHIPSELECT <= SPI_CS_CNT_MAX);
 #define CQSPI_NO_SUPPORT_WR_COMPLETION	BIT(3)
 #define CQSPI_SLOW_SRAM		BIT(4)
 #define CQSPI_NEEDS_APB_AHB_HAZARD_WAR	BIT(5)
+#define CQSPI_RD_NO_IRQ			BIT(6)
 
 /* Capabilities */
 #define CQSPI_SUPPORTS_OCTAL		BIT(0)
@@ -102,6 +103,8 @@ struct cqspi_st {
 	bool			apb_ahb_hazard;
 
 	bool			is_jh7110; /* Flag for StarFive JH7110 SoC */
+
+	const struct cqspi_driver_platdata *ddata;
 };
 
 struct cqspi_driver_platdata {
@@ -117,6 +120,7 @@ struct cqspi_driver_platdata {
 /* Operation timeout value */
 #define CQSPI_TIMEOUT_MS			500
 #define CQSPI_READ_TIMEOUT_MS			10
+#define CQSPI_BUSYWAIT_TIMEOUT_US		500
 
 /* Runtime_pm autosuspend delay */
 #define CQSPI_AUTOSUSPEND_TIMEOUT		2000
@@ -295,13 +299,27 @@ struct cqspi_driver_platdata {
 
 #define CQSPI_REG_VERSAL_DMA_VAL		0x602
 
-static int cqspi_wait_for_bit(void __iomem *reg, const u32 mask, bool clr)
+static int cqspi_wait_for_bit(const struct cqspi_driver_platdata *ddata,
+			      void __iomem *reg, const u32 mask, bool clr,
+			      bool busywait)
 {
+	u64 timeout_us = CQSPI_TIMEOUT_MS * USEC_PER_MSEC;
 	u32 val;
 
+	if (busywait) {
+		int ret = readl_relaxed_poll_timeout(reg, val,
+						     (((clr ? ~val : val) & mask) == mask),
+						     0, CQSPI_BUSYWAIT_TIMEOUT_US);
+
+		if (ret != -ETIMEDOUT)
+			return ret;
+
+		timeout_us -= CQSPI_BUSYWAIT_TIMEOUT_US;
+	}
+
 	return readl_relaxed_poll_timeout(reg, val,
 					  (((clr ? ~val : val) & mask) == mask),
-					  10, CQSPI_TIMEOUT_MS * 1000);
+					  10, timeout_us);
 }
 
 static bool cqspi_is_idle(struct cqspi_st *cqspi)
@@ -334,11 +352,8 @@ static u32 cqspi_get_versal_dma_status(struct cqspi_st *cqspi)
 static irqreturn_t cqspi_irq_handler(int this_irq, void *dev)
 {
 	struct cqspi_st *cqspi = dev;
+	const struct cqspi_driver_platdata *ddata = cqspi->ddata;
 	unsigned int irq_status;
-	struct device *device = &cqspi->pdev->dev;
-	const struct cqspi_driver_platdata *ddata;
-
-	ddata = of_device_get_match_data(device);
 
 	/* Read interrupt status */
 	irq_status = readl(cqspi->iobase + CQSPI_REG_IRQSTATUS);
@@ -434,8 +449,8 @@ static int cqspi_exec_flash_cmd(struct cqspi_st *cqspi, unsigned int reg)
 	writel(reg, reg_base + CQSPI_REG_CMDCTRL);
 
 	/* Polling for completion. */
-	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_CMDCTRL,
-				 CQSPI_REG_CMDCTRL_INPROGRESS_MASK, 1);
+	ret = cqspi_wait_for_bit(cqspi->ddata, reg_base + CQSPI_REG_CMDCTRL,
+				 CQSPI_REG_CMDCTRL_INPROGRESS_MASK, 1, true);
 	if (ret) {
 		dev_err(&cqspi->pdev->dev,
 			"Flash command execution timed out.\n");
@@ -492,8 +507,11 @@ static int cqspi_enable_dtr(struct cqspi_flash_pdata *f_pdata,
 		if (ret)
 			return ret;
 	} else {
-		reg &= ~CQSPI_REG_CONFIG_DTR_PROTO;
-		reg &= ~CQSPI_REG_CONFIG_DUAL_OPCODE;
+		unsigned int mask = CQSPI_REG_CONFIG_DTR_PROTO | CQSPI_REG_CONFIG_DUAL_OPCODE;
+		/* Shortcut if DTR is already disabled. */
+		if ((reg & mask) == 0)
+			return 0;
+		reg &= ~mask;
 	}
 
 	writel(reg, reg_base + CQSPI_REG_CONFIG);
@@ -700,6 +718,7 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
 				       const size_t n_rx)
 {
 	struct cqspi_st *cqspi = f_pdata->cqspi;
+	bool use_irq = !(cqspi->ddata && cqspi->ddata->quirks & CQSPI_RD_NO_IRQ);
 	struct device *dev = &cqspi->pdev->dev;
 	void __iomem *reg_base = cqspi->iobase;
 	void __iomem *ahb_base = cqspi->ahb_base;
@@ -723,17 +742,20 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
 	 * all the read interrupts disabled for max performance.
 	 */
 
-	if (!cqspi->slow_sram)
+	if (use_irq && cqspi->slow_sram)
+		writel(CQSPI_REG_IRQ_WATERMARK, reg_base + CQSPI_REG_IRQMASK);
+	else if (use_irq)
 		writel(CQSPI_IRQ_MASK_RD, reg_base + CQSPI_REG_IRQMASK);
 	else
-		writel(CQSPI_REG_IRQ_WATERMARK, reg_base + CQSPI_REG_IRQMASK);
+		writel(0, reg_base + CQSPI_REG_IRQMASK);
 
 	reinit_completion(&cqspi->transfer_complete);
 	writel(CQSPI_REG_INDIRECTRD_START_MASK,
 	       reg_base + CQSPI_REG_INDIRECTRD);
 
 	while (remaining > 0) {
-		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+		if (use_irq &&
+		    !wait_for_completion_timeout(&cqspi->transfer_complete,
 						 msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS)))
 			ret = -ETIMEDOUT;
 
@@ -775,7 +797,7 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
 			bytes_to_read = cqspi_get_rd_sram_level(cqspi);
 		}
 
-		if (remaining > 0) {
+		if (use_irq && remaining > 0) {
 			reinit_completion(&cqspi->transfer_complete);
 			if (cqspi->slow_sram)
 				writel(CQSPI_REG_IRQ_WATERMARK, reg_base + CQSPI_REG_IRQMASK);
@@ -783,8 +805,8 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
 	}
 
 	/* Check indirect done status */
-	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_INDIRECTRD,
-				 CQSPI_REG_INDIRECTRD_DONE_MASK, 0);
+	ret = cqspi_wait_for_bit(cqspi->ddata, reg_base + CQSPI_REG_INDIRECTRD,
+				 CQSPI_REG_INDIRECTRD_DONE_MASK, 0, true);
 	if (ret) {
 		dev_err(dev, "Indirect read completion error (%i)\n", ret);
 		goto failrd;
@@ -1084,8 +1106,8 @@ static int cqspi_indirect_write_execute(struct cqspi_flash_pdata *f_pdata,
 	}
 
 	/* Check indirect done status */
-	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_INDIRECTWR,
-				 CQSPI_REG_INDIRECTWR_DONE_MASK, 0);
+	ret = cqspi_wait_for_bit(cqspi->ddata, reg_base + CQSPI_REG_INDIRECTWR,
+				 CQSPI_REG_INDIRECTWR_DONE_MASK, 0, false);
 	if (ret) {
 		dev_err(dev, "Indirect write completion error (%i)\n", ret);
 		goto failwr;
@@ -1358,16 +1380,13 @@ static ssize_t cqspi_read(struct cqspi_flash_pdata *f_pdata,
 			  const struct spi_mem_op *op)
 {
 	struct cqspi_st *cqspi = f_pdata->cqspi;
-	struct device *dev = &cqspi->pdev->dev;
-	const struct cqspi_driver_platdata *ddata;
+	const struct cqspi_driver_platdata *ddata = cqspi->ddata;
 	loff_t from = op->addr.val;
 	size_t len = op->data.nbytes;
 	u_char *buf = op->data.buf.in;
 	u64 dma_align = (u64)(uintptr_t)buf;
 	int ret;
 
-	ddata = of_device_get_match_data(dev);
-
 	ret = cqspi_read_setup(f_pdata, op);
 	if (ret)
 		return ret;
@@ -1511,8 +1530,8 @@ static int cqspi_of_get_pdata(struct cqspi_st *cqspi)
 	cqspi->is_decoded_cs = of_property_read_bool(np, "cdns,is-decoded-cs");
 
 	if (of_property_read_u32(np, "cdns,fifo-depth", &cqspi->fifo_depth)) {
-		dev_err(dev, "couldn't determine fifo-depth\n");
-		return -ENXIO;
+		/* Zero signals FIFO depth should be runtime detected. */
+		cqspi->fifo_depth = 0;
 	}
 
 	if (of_property_read_u32(np, "cdns,fifo-width", &cqspi->fifo_width)) {
@@ -1542,8 +1561,6 @@ static void cqspi_controller_init(struct cqspi_st *cqspi)
 {
 	u32 reg;
 
-	cqspi_controller_enable(cqspi, 0);
-
 	/* Configure the remap address register, no remap */
 	writel(0, cqspi->iobase + CQSPI_REG_REMAP);
 
@@ -1577,8 +1594,29 @@ static void cqspi_controller_init(struct cqspi_st *cqspi)
 		reg |= CQSPI_REG_CONFIG_DMA_MASK;
 		writel(reg, cqspi->iobase + CQSPI_REG_CONFIG);
 	}
+}
 
-	cqspi_controller_enable(cqspi, 1);
+static void cqspi_controller_detect_fifo_depth(struct cqspi_st *cqspi)
+{
+	struct device *dev = &cqspi->pdev->dev;
+	u32 reg, fifo_depth;
+
+	/*
+	 * Bits N-1:0 are writable while bits 31:N are read as zero, with 2^N
+	 * the FIFO depth.
+	 */
+	writel(U32_MAX, cqspi->iobase + CQSPI_REG_SRAMPARTITION);
+	reg = readl(cqspi->iobase + CQSPI_REG_SRAMPARTITION);
+	fifo_depth = reg + 1;
+
+	/* FIFO depth of zero means no value from devicetree was provided. */
+	if (cqspi->fifo_depth == 0) {
+		cqspi->fifo_depth = fifo_depth;
+		dev_dbg(dev, "using FIFO depth of %u\n", fifo_depth);
+	} else if (fifo_depth != cqspi->fifo_depth) {
+		dev_warn(dev, "detected FIFO depth (%u) different from config (%u)\n",
+			 fifo_depth, cqspi->fifo_depth);
+	}
 }
 
 static int cqspi_request_mmap_dma(struct cqspi_st *cqspi)
@@ -1731,6 +1769,7 @@ static int cqspi_probe(struct platform_device *pdev)
 	cqspi->pdev = pdev;
 	cqspi->host = host;
 	cqspi->is_jh7110 = false;
+	cqspi->ddata = ddata = of_device_get_match_data(dev);
 	platform_set_drvdata(pdev, cqspi);
 
 	/* Obtain configuration from OF. */
@@ -1822,7 +1861,6 @@ static int cqspi_probe(struct platform_device *pdev)
 	/* write completion is supported by default */
 	cqspi->wr_completion = true;
 
-	ddata  = of_device_get_match_data(dev);
 	if (ddata) {
 		if (ddata->quirks & CQSPI_NEEDS_WR_DELAY)
 			cqspi->wr_delay = 50 * DIV_ROUND_UP(NSEC_PER_SEC,
@@ -1864,7 +1902,10 @@ static int cqspi_probe(struct platform_device *pdev)
 	}
 
 	cqspi_wait_idle(cqspi);
+	cqspi_controller_enable(cqspi, 0);
+	cqspi_controller_detect_fifo_depth(cqspi);
 	cqspi_controller_init(cqspi);
+	cqspi_controller_enable(cqspi, 1);
 	cqspi->current_cs = -1;
 	cqspi->sclk = 0;
 
@@ -1947,7 +1988,9 @@ static int cqspi_runtime_resume(struct device *dev)
 
 	clk_prepare_enable(cqspi->clk);
 	cqspi_wait_idle(cqspi);
+	cqspi_controller_enable(cqspi, 0);
 	cqspi_controller_init(cqspi);
+	cqspi_controller_enable(cqspi, 1);
 
 	cqspi->current_cs = -1;
 	cqspi->sclk = 0;
@@ -2012,6 +2055,12 @@ static const struct cqspi_driver_platdata pensando_cdns_qspi = {
 	.quirks = CQSPI_NEEDS_APB_AHB_HAZARD_WAR | CQSPI_DISABLE_DAC_MODE,
 };
 
+static const struct cqspi_driver_platdata mobileye_eyeq5_ospi = {
+	.hwcaps_mask = CQSPI_SUPPORTS_OCTAL,
+	.quirks = CQSPI_DISABLE_DAC_MODE | CQSPI_NO_SUPPORT_WR_COMPLETION |
+			CQSPI_RD_NO_IRQ,
+};
+
 static const struct of_device_id cqspi_dt_ids[] = {
 	{
 		.compatible = "cdns,qspi-nor",
@@ -2045,6 +2094,10 @@ static const struct of_device_id cqspi_dt_ids[] = {
 		.compatible = "amd,pensando-elba-qspi",
 		.data = &pensando_cdns_qspi,
 	},
+	{
+		.compatible = "mobileye,eyeq5-ospi",
+		.data = &mobileye_eyeq5_ospi,
+	},
 	{ /* end of table */ }
 };
 
diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c
index 8648b8eb080d..2209e9fc378f 100644
--- a/drivers/spi/spi-cadence-xspi.c
+++ b/drivers/spi/spi-cadence-xspi.c
@@ -486,20 +486,14 @@ static irqreturn_t cdns_xspi_irq_handler(int this_irq, void *dev)
 static int cdns_xspi_of_get_plat_data(struct platform_device *pdev)
 {
 	struct device_node *node_prop = pdev->dev.of_node;
-	struct device_node *node_child;
 	unsigned int cs;
 
-	for_each_child_of_node(node_prop, node_child) {
-		if (!of_device_is_available(node_child))
-			continue;
-
+	for_each_available_child_of_node_scoped(node_prop, node_child) {
 		if (of_property_read_u32(node_child, "reg", &cs)) {
 			dev_err(&pdev->dev, "Couldn't get memory chip select\n");
-			of_node_put(node_child);
 			return -ENXIO;
 		} else if (cs >= CDNS_XSPI_MAX_BANKS) {
 			dev_err(&pdev->dev, "reg (cs) parameter value too large\n");
-			of_node_put(node_child);
 			return -ENXIO;
 		}
 	}
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index b341b6908df0..e83cd0510f20 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -500,7 +500,6 @@ static const struct dev_pm_ops mcfqspi_pm = {
 
 static struct platform_driver mcfqspi_driver = {
 	.driver.name	= DRIVER_NAME,
-	.driver.owner	= THIS_MODULE,
 	.driver.pm	= &mcfqspi_pm,
 	.probe		= mcfqspi_probe,
 	.remove_new	= mcfqspi_remove,
diff --git a/drivers/spi/spi-cs42l43.c b/drivers/spi/spi-cs42l43.c
index aabef9fc84bd..9d747ea69926 100644
--- a/drivers/spi/spi-cs42l43.c
+++ b/drivers/spi/spi-cs42l43.c
@@ -5,10 +5,14 @@
 // Copyright (C) 2022-2023 Cirrus Logic, Inc. and
 //                         Cirrus Logic International Semiconductor Ltd.
 
+#include <linux/acpi.h>
+#include <linux/array_size.h>
 #include <linux/bits.h>
 #include <linux/bitfield.h>
 #include <linux/device.h>
 #include <linux/errno.h>
+#include <linux/gpio/machine.h>
+#include <linux/gpio/property.h>
 #include <linux/mfd/cs42l43.h>
 #include <linux/mfd/cs42l43-regs.h>
 #include <linux/mod_devicetable.h>
@@ -16,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/property.h>
 #include <linux/regmap.h>
 #include <linux/spi/spi.h>
 #include <linux/units.h>
@@ -39,6 +44,44 @@ static const unsigned int cs42l43_clock_divs[] = {
 	2, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30
 };
 
+static const struct software_node ampl = {
+	.name			= "cs35l56-left",
+};
+
+static const struct software_node ampr = {
+	.name			= "cs35l56-right",
+};
+
+static struct spi_board_info ampl_info = {
+	.modalias		= "cs35l56",
+	.max_speed_hz		= 20 * HZ_PER_MHZ,
+	.chip_select		= 0,
+	.mode			= SPI_MODE_0,
+	.swnode			= &ampl,
+};
+
+static struct spi_board_info ampr_info = {
+	.modalias		= "cs35l56",
+	.max_speed_hz		= 20 * HZ_PER_MHZ,
+	.chip_select		= 1,
+	.mode			= SPI_MODE_0,
+	.swnode			= &ampr,
+};
+
+static const struct software_node cs42l43_gpiochip_swnode = {
+	.name			= "cs42l43-pinctrl",
+};
+
+static const struct software_node_ref_args cs42l43_cs_refs[] = {
+	SOFTWARE_NODE_REFERENCE(&cs42l43_gpiochip_swnode, 0, GPIO_ACTIVE_LOW),
+	SOFTWARE_NODE_REFERENCE(&swnode_gpio_undefined),
+};
+
+static const struct property_entry cs42l43_cs_props[] = {
+	PROPERTY_ENTRY_REF_ARRAY("cs-gpios", cs42l43_cs_refs),
+	{}
+};
+
 static int cs42l43_spi_tx(struct regmap *regmap, const u8 *buf, unsigned int len)
 {
 	const u8 *end = buf + len;
@@ -203,16 +246,59 @@ static size_t cs42l43_spi_max_length(struct spi_device *spi)
 	return CS42L43_SPI_MAX_LENGTH;
 }
 
+static bool cs42l43_has_sidecar(struct fwnode_handle *fwnode)
+{
+	static const u32 func_smart_amp = 0x1;
+	struct fwnode_handle *child_fwnode, *ext_fwnode;
+	unsigned int val;
+	u32 function;
+	int ret;
+
+	fwnode_for_each_child_node(fwnode, child_fwnode) {
+		acpi_handle handle = ACPI_HANDLE_FWNODE(child_fwnode);
+
+		ret = acpi_get_local_address(handle, &function);
+		if (ret || function != func_smart_amp)
+			continue;
+
+		ext_fwnode = fwnode_get_named_child_node(child_fwnode,
+				"mipi-sdca-function-expansion-subproperties");
+		if (!ext_fwnode)
+			continue;
+
+		ret = fwnode_property_read_u32(ext_fwnode,
+					       "01fa-sidecar-instances",
+					       &val);
+
+		fwnode_handle_put(ext_fwnode);
+
+		if (ret)
+			continue;
+
+		fwnode_handle_put(child_fwnode);
+
+		return !!val;
+	}
+
+	return false;
+}
+
 static void cs42l43_release_of_node(void *data)
 {
 	fwnode_handle_put(data);
 }
 
+static void cs42l43_release_sw_node(void *data)
+{
+	software_node_unregister(&cs42l43_gpiochip_swnode);
+}
+
 static int cs42l43_spi_probe(struct platform_device *pdev)
 {
 	struct cs42l43 *cs42l43 = dev_get_drvdata(pdev->dev.parent);
 	struct cs42l43_spi *priv;
 	struct fwnode_handle *fwnode = dev_fwnode(cs42l43->dev);
+	bool has_sidecar = cs42l43_has_sidecar(fwnode);
 	int ret;
 
 	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
@@ -259,21 +345,45 @@ static int cs42l43_spi_probe(struct platform_device *pdev)
 
 	if (is_of_node(fwnode)) {
 		fwnode = fwnode_get_named_child_node(fwnode, "spi");
-		ret = devm_add_action(priv->dev, cs42l43_release_of_node, fwnode);
-		if (ret) {
-			fwnode_handle_put(fwnode);
+		ret = devm_add_action_or_reset(priv->dev, cs42l43_release_of_node, fwnode);
+		if (ret)
 			return ret;
-		}
 	}
 
-	device_set_node(&priv->ctlr->dev, fwnode);
+	if (has_sidecar) {
+		ret = software_node_register(&cs42l43_gpiochip_swnode);
+		if (ret)
+			return dev_err_probe(priv->dev, ret,
+					     "Failed to register gpio swnode\n");
+
+		ret = devm_add_action_or_reset(priv->dev, cs42l43_release_sw_node, NULL);
+		if (ret)
+			return ret;
+
+		ret = device_create_managed_software_node(&priv->ctlr->dev,
+							  cs42l43_cs_props, NULL);
+		if (ret)
+			return dev_err_probe(priv->dev, ret, "Failed to add swnode\n");
+	} else {
+		device_set_node(&priv->ctlr->dev, fwnode);
+	}
 
 	ret = devm_spi_register_controller(priv->dev, priv->ctlr);
-	if (ret) {
-		dev_err(priv->dev, "Failed to register SPI controller: %d\n", ret);
+	if (ret)
+		return dev_err_probe(priv->dev, ret,
+				     "Failed to register SPI controller\n");
+
+	if (has_sidecar) {
+		if (!spi_new_device(priv->ctlr, &ampl_info))
+			return dev_err_probe(priv->dev, -ENODEV,
+					     "Failed to create left amp slave\n");
+
+		if (!spi_new_device(priv->ctlr, &ampr_info))
+			return dev_err_probe(priv->dev, -ENODEV,
+					     "Failed to create right amp slave\n");
 	}
 
-	return ret;
+	return 0;
 }
 
 static const struct platform_device_id cs42l43_spi_id_table[] = {
@@ -291,6 +401,7 @@ static struct platform_driver cs42l43_spi_driver = {
 };
 module_platform_driver(cs42l43_spi_driver);
 
+MODULE_IMPORT_NS(GPIO_SWNODE);
 MODULE_DESCRIPTION("CS42L43 SPI Driver");
 MODULE_AUTHOR("Lucas Tanure <tanureal@opensource.cirrus.com>");
 MODULE_AUTHOR("Maciej Strozek <mstrozek@opensource.cirrus.com>");
diff --git a/drivers/spi/spi-dw-core.c b/drivers/spi/spi-dw-core.c
index 0274c9295514..ddfdb903047a 100644
--- a/drivers/spi/spi-dw-core.c
+++ b/drivers/spi/spi-dw-core.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/bitops.h>
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
@@ -421,10 +422,7 @@ static int dw_spi_transfer_one(struct spi_controller *host,
 	int ret;
 
 	dws->dma_mapped = 0;
-	dws->n_bytes =
-		roundup_pow_of_two(DIV_ROUND_UP(transfer->bits_per_word,
-						BITS_PER_BYTE));
-
+	dws->n_bytes = roundup_pow_of_two(BITS_TO_BYTES(transfer->bits_per_word));
 	dws->tx = (void *)transfer->tx_buf;
 	dws->tx_len = transfer->len / dws->n_bytes;
 	dws->rx = transfer->rx_buf;
@@ -837,6 +835,20 @@ static void dw_spi_hw_init(struct device *dev, struct dw_spi *dws)
 	}
 
 	/*
+	 * Try to detect the number of native chip-selects if the platform
+	 * driver didn't set it up. There can be up to 16 lines configured.
+	 */
+	if (!dws->num_cs) {
+		u32 ser;
+
+		dw_writel(dws, DW_SPI_SER, 0xffff);
+		ser = dw_readl(dws, DW_SPI_SER);
+		dw_writel(dws, DW_SPI_SER, 0);
+
+		dws->num_cs = hweight16(ser);
+	}
+
+	/*
 	 * Try to detect the FIFO depth if not set by interface driver,
 	 * the depth could be from 2 to 256 from HW spec
 	 */
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index cc74cbe03431..819907e332c4 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -320,7 +320,11 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 	struct resource *mem;
 	struct dw_spi *dws;
 	int ret;
-	int num_cs;
+
+	if (device_property_read_bool(&pdev->dev, "spi-slave")) {
+		dev_warn(&pdev->dev, "spi-slave is not yet supported\n");
+		return -ENODEV;
+	}
 
 	dwsmmio = devm_kzalloc(&pdev->dev, sizeof(struct dw_spi_mmio),
 			GFP_KERNEL);
@@ -364,11 +368,8 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 				     &dws->reg_io_width))
 		dws->reg_io_width = 4;
 
-	num_cs = 4;
-
-	device_property_read_u32(&pdev->dev, "num-cs", &num_cs);
-
-	dws->num_cs = num_cs;
+	/* Rely on the auto-detection if no property specified */
+	device_property_read_u32(&pdev->dev, "num-cs", &dws->num_cs);
 
 	init_func = device_get_match_data(&pdev->dev);
 	if (init_func) {
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 6cafeee8ee2a..fc267c6437ae 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -164,8 +164,8 @@ struct dw_spi {
 	u32			max_freq;	/* max bus freq supported */
 
 	u32			reg_io_width;	/* DR I/O width in bytes */
+	u32			num_cs;		/* chip select lines */
 	u16			bus_num;
-	u16			num_cs;		/* supported slave numbers */
 	void (*set_cs)(struct spi_device *spi, bool enable);
 
 	/* Current message transfer state info */
diff --git a/drivers/spi/spi-fsl-cpm.c b/drivers/spi/spi-fsl-cpm.c
index 47c7a5c6257f..e335132080bf 100644
--- a/drivers/spi/spi-fsl-cpm.c
+++ b/drivers/spi/spi-fsl-cpm.c
@@ -98,19 +98,13 @@ static void fsl_spi_cpm_bufs_start(struct mpc8xxx_spi *mspi)
 	mpc8xxx_spi_write_reg(&reg_base->command, SPCOM_STR);
 }
 
-int fsl_spi_cpm_bufs(struct mpc8xxx_spi *mspi,
-		     struct spi_transfer *t, bool is_dma_mapped)
+int fsl_spi_cpm_bufs(struct mpc8xxx_spi *mspi, struct spi_transfer *t)
 {
 	struct device *dev = mspi->dev;
 	struct fsl_spi_reg __iomem *reg_base = mspi->reg_base;
 
-	if (is_dma_mapped) {
-		mspi->map_tx_dma = 0;
-		mspi->map_rx_dma = 0;
-	} else {
-		mspi->map_tx_dma = 1;
-		mspi->map_rx_dma = 1;
-	}
+	mspi->map_tx_dma = 1;
+	mspi->map_rx_dma = 1;
 
 	if (!t->tx_buf) {
 		mspi->tx_dma = mspi->dma_dummy_tx;
@@ -147,7 +141,7 @@ int fsl_spi_cpm_bufs(struct mpc8xxx_spi *mspi,
 			return -ENOMEM;
 		}
 	} else if (t->tx_buf) {
-		mspi->tx_dma = t->tx_dma;
+		mspi->tx_dma = 0;
 	}
 
 	if (mspi->map_rx_dma) {
diff --git a/drivers/spi/spi-fsl-cpm.h b/drivers/spi/spi-fsl-cpm.h
index 160f999708b6..e012abba055f 100644
--- a/drivers/spi/spi-fsl-cpm.h
+++ b/drivers/spi/spi-fsl-cpm.h
@@ -20,7 +20,7 @@
 #ifdef CONFIG_FSL_SOC
 extern void fsl_spi_cpm_reinit_txrx(struct mpc8xxx_spi *mspi);
 extern int fsl_spi_cpm_bufs(struct mpc8xxx_spi *mspi,
-			    struct spi_transfer *t, bool is_dma_mapped);
+			    struct spi_transfer *t);
 extern void fsl_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi);
 extern void fsl_spi_cpm_irq(struct mpc8xxx_spi *mspi, u32 events);
 extern int fsl_spi_cpm_init(struct mpc8xxx_spi *mspi);
@@ -28,8 +28,7 @@ extern void fsl_spi_cpm_free(struct mpc8xxx_spi *mspi);
 #else
 static inline void fsl_spi_cpm_reinit_txrx(struct mpc8xxx_spi *mspi) { }
 static inline int fsl_spi_cpm_bufs(struct mpc8xxx_spi *mspi,
-				   struct spi_transfer *t,
-				   bool is_dma_mapped) { return 0; }
+				   struct spi_transfer *t) { return 0; }
 static inline void fsl_spi_cpm_bufs_complete(struct mpc8xxx_spi *mspi) { }
 static inline void fsl_spi_cpm_irq(struct mpc8xxx_spi *mspi, u32 events) { }
 static inline int fsl_spi_cpm_init(struct mpc8xxx_spi *mspi) { return 0; }
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 38defdcf9370..0a2730cd07c6 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1458,7 +1458,6 @@ static void dspi_shutdown(struct platform_device *pdev)
 static struct platform_driver fsl_dspi_driver = {
 	.driver.name		= DRIVER_NAME,
 	.driver.of_match_table	= fsl_dspi_dt_ids,
-	.driver.owner		= THIS_MODULE,
 	.driver.pm		= &dspi_pm,
 	.probe			= dspi_probe,
 	.remove_new		= dspi_remove,
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 92a662d1b55c..aa5ed254be46 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -553,7 +553,7 @@ static int fsl_lpspi_dma_transfer(struct spi_controller *controller,
 {
 	struct dma_async_tx_descriptor *desc_tx, *desc_rx;
 	unsigned long transfer_timeout;
-	unsigned long timeout;
+	unsigned long time_left;
 	struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg;
 	int ret;
 
@@ -594,9 +594,9 @@ static int fsl_lpspi_dma_transfer(struct spi_controller *controller,
 							       transfer->len);
 
 		/* Wait eDMA to finish the data transfer.*/
-		timeout = wait_for_completion_timeout(&fsl_lpspi->dma_tx_completion,
-						      transfer_timeout);
-		if (!timeout) {
+		time_left = wait_for_completion_timeout(&fsl_lpspi->dma_tx_completion,
+							transfer_timeout);
+		if (!time_left) {
 			dev_err(fsl_lpspi->dev, "I/O Error in DMA TX\n");
 			dmaengine_terminate_all(controller->dma_tx);
 			dmaengine_terminate_all(controller->dma_rx);
@@ -604,9 +604,9 @@ static int fsl_lpspi_dma_transfer(struct spi_controller *controller,
 			return -ETIMEDOUT;
 		}
 
-		timeout = wait_for_completion_timeout(&fsl_lpspi->dma_rx_completion,
-						      transfer_timeout);
-		if (!timeout) {
+		time_left = wait_for_completion_timeout(&fsl_lpspi->dma_rx_completion,
+							transfer_timeout);
+		if (!time_left) {
 			dev_err(fsl_lpspi->dev, "I/O Error in DMA RX\n");
 			dmaengine_terminate_all(controller->dma_tx);
 			dmaengine_terminate_all(controller->dma_rx);
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 97faf984801f..997e07c0a24a 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -249,8 +249,7 @@ static int fsl_spi_cpu_bufs(struct mpc8xxx_spi *mspi,
 	return 0;
 }
 
-static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
-			    bool is_dma_mapped)
+static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_controller_get_devdata(spi->controller);
 	struct fsl_spi_reg __iomem *reg_base;
@@ -274,7 +273,7 @@ static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
 	reinit_completion(&mpc8xxx_spi->done);
 
 	if (mpc8xxx_spi->flags & SPI_CPM_MODE)
-		ret = fsl_spi_cpm_bufs(mpc8xxx_spi, t, is_dma_mapped);
+		ret = fsl_spi_cpm_bufs(mpc8xxx_spi, t);
 	else
 		ret = fsl_spi_cpu_bufs(mpc8xxx_spi, t, len);
 	if (ret)
@@ -353,7 +352,7 @@ static int fsl_spi_transfer_one(struct spi_controller *controller,
 	if (status < 0)
 		return status;
 	if (t->len)
-		status = fsl_spi_bufs(spi, t, !!t->tx_dma || !!t->rx_dma);
+		status = fsl_spi_bufs(spi, t);
 	if (status > 0)
 		return -EMSGSIZE;
 
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index c3e5cee18bea..f4006c82f867 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1405,7 +1405,7 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 {
 	struct dma_async_tx_descriptor *desc_tx, *desc_rx;
 	unsigned long transfer_timeout;
-	unsigned long timeout;
+	unsigned long time_left;
 	struct spi_controller *controller = spi_imx->controller;
 	struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg;
 	struct scatterlist *last_sg = sg_last(rx->sgl, rx->nents);
@@ -1471,18 +1471,18 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 	transfer_timeout = spi_imx_calculate_timeout(spi_imx, transfer->len);
 
 	/* Wait SDMA to finish the data transfer.*/
-	timeout = wait_for_completion_timeout(&spi_imx->dma_tx_completion,
+	time_left = wait_for_completion_timeout(&spi_imx->dma_tx_completion,
 						transfer_timeout);
-	if (!timeout) {
+	if (!time_left) {
 		dev_err(spi_imx->dev, "I/O Error in DMA TX\n");
 		dmaengine_terminate_all(controller->dma_tx);
 		dmaengine_terminate_all(controller->dma_rx);
 		return -ETIMEDOUT;
 	}
 
-	timeout = wait_for_completion_timeout(&spi_imx->dma_rx_completion,
-					      transfer_timeout);
-	if (!timeout) {
+	time_left = wait_for_completion_timeout(&spi_imx->dma_rx_completion,
+						transfer_timeout);
+	if (!time_left) {
 		dev_err(&controller->dev, "I/O Error in DMA RX\n");
 		spi_imx->devtype_data->reset(spi_imx);
 		dmaengine_terminate_all(controller->dma_rx);
@@ -1501,7 +1501,7 @@ static int spi_imx_pio_transfer(struct spi_device *spi,
 {
 	struct spi_imx_data *spi_imx = spi_controller_get_devdata(spi->controller);
 	unsigned long transfer_timeout;
-	unsigned long timeout;
+	unsigned long time_left;
 
 	spi_imx->tx_buf = transfer->tx_buf;
 	spi_imx->rx_buf = transfer->rx_buf;
@@ -1517,9 +1517,9 @@ static int spi_imx_pio_transfer(struct spi_device *spi,
 
 	transfer_timeout = spi_imx_calculate_timeout(spi_imx, transfer->len);
 
-	timeout = wait_for_completion_timeout(&spi_imx->xfer_done,
-					      transfer_timeout);
-	if (!timeout) {
+	time_left = wait_for_completion_timeout(&spi_imx->xfer_done,
+						transfer_timeout);
+	if (!time_left) {
 		dev_err(&spi->dev, "I/O Error in PIO\n");
 		spi_imx->devtype_data->reset(spi_imx);
 		return -ETIMEDOUT;
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index fee8893d2751..31a878d9458d 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -396,7 +396,6 @@ MODULE_DEVICE_TABLE(of, spi_loopback_test_of_match);
 static struct spi_driver spi_loopback_test_driver = {
 	.driver = {
 		.name = "spi-loopback-test",
-		.owner = THIS_MODULE,
 		.of_match_table = spi_loopback_test_of_match,
 	},
 	.probe = spi_loopback_test_probe,
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index e4cb22fe0075..36c2f52cd6b8 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -748,7 +748,7 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id)
 	u32 cmd, reg_val, cnt, remainder, len;
 	struct spi_controller *host = dev_id;
 	struct mtk_spi *mdata = spi_controller_get_devdata(host);
-	struct spi_transfer *trans = mdata->cur_transfer;
+	struct spi_transfer *xfer = mdata->cur_transfer;
 
 	reg_val = readl(mdata->base + SPI_STATUS0_REG);
 	if (reg_val & MTK_SPI_PAUSE_INT_STATUS)
@@ -762,42 +762,40 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id)
 		return IRQ_HANDLED;
 	}
 
-	if (!host->can_dma(host, NULL, trans)) {
-		if (trans->rx_buf) {
+	if (!host->can_dma(host, NULL, xfer)) {
+		if (xfer->rx_buf) {
 			cnt = mdata->xfer_len / 4;
 			ioread32_rep(mdata->base + SPI_RX_DATA_REG,
-				     trans->rx_buf + mdata->num_xfered, cnt);
+				     xfer->rx_buf + mdata->num_xfered, cnt);
 			remainder = mdata->xfer_len % 4;
 			if (remainder > 0) {
 				reg_val = readl(mdata->base + SPI_RX_DATA_REG);
-				memcpy(trans->rx_buf +
-					mdata->num_xfered +
-					(cnt * 4),
+				memcpy(xfer->rx_buf + (cnt * 4) + mdata->num_xfered,
 					&reg_val,
 					remainder);
 			}
 		}
 
 		mdata->num_xfered += mdata->xfer_len;
-		if (mdata->num_xfered == trans->len) {
+		if (mdata->num_xfered == xfer->len) {
 			spi_finalize_current_transfer(host);
 			return IRQ_HANDLED;
 		}
 
-		len = trans->len - mdata->num_xfered;
+		len = xfer->len - mdata->num_xfered;
 		mdata->xfer_len = min(MTK_SPI_MAX_FIFO_SIZE, len);
 		mtk_spi_setup_packet(host);
 
-		if (trans->tx_buf) {
+		if (xfer->tx_buf) {
 			cnt = mdata->xfer_len / 4;
 			iowrite32_rep(mdata->base + SPI_TX_DATA_REG,
-					trans->tx_buf + mdata->num_xfered, cnt);
+					xfer->tx_buf + mdata->num_xfered, cnt);
 
 			remainder = mdata->xfer_len % 4;
 			if (remainder > 0) {
 				reg_val = 0;
 				memcpy(&reg_val,
-					trans->tx_buf + (cnt * 4) + mdata->num_xfered,
+					xfer->tx_buf + (cnt * 4) + mdata->num_xfered,
 					remainder);
 				writel(reg_val, mdata->base + SPI_TX_DATA_REG);
 			}
@@ -809,21 +807,21 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id)
 	}
 
 	if (mdata->tx_sgl)
-		trans->tx_dma += mdata->xfer_len;
+		xfer->tx_dma += mdata->xfer_len;
 	if (mdata->rx_sgl)
-		trans->rx_dma += mdata->xfer_len;
+		xfer->rx_dma += mdata->xfer_len;
 
 	if (mdata->tx_sgl && (mdata->tx_sgl_len == 0)) {
 		mdata->tx_sgl = sg_next(mdata->tx_sgl);
 		if (mdata->tx_sgl) {
-			trans->tx_dma = sg_dma_address(mdata->tx_sgl);
+			xfer->tx_dma = sg_dma_address(mdata->tx_sgl);
 			mdata->tx_sgl_len = sg_dma_len(mdata->tx_sgl);
 		}
 	}
 	if (mdata->rx_sgl && (mdata->rx_sgl_len == 0)) {
 		mdata->rx_sgl = sg_next(mdata->rx_sgl);
 		if (mdata->rx_sgl) {
-			trans->rx_dma = sg_dma_address(mdata->rx_sgl);
+			xfer->rx_dma = sg_dma_address(mdata->rx_sgl);
 			mdata->rx_sgl_len = sg_dma_len(mdata->rx_sgl);
 		}
 	}
@@ -841,7 +839,7 @@ static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id)
 
 	mtk_spi_update_mdata_len(host);
 	mtk_spi_setup_packet(host);
-	mtk_spi_setup_dma_addr(host, trans);
+	mtk_spi_setup_dma_addr(host, xfer);
 	mtk_spi_enable_transfer(host);
 
 	return IRQ_HANDLED;
diff --git a/drivers/spi/spi-mt7621.c b/drivers/spi/spi-mt7621.c
index 4e9053d03d5a..3770b8e096a4 100644
--- a/drivers/spi/spi-mt7621.c
+++ b/drivers/spi/spi-mt7621.c
@@ -52,6 +52,8 @@
 #define MT7621_CPOL		BIT(4)
 #define MT7621_LSB_FIRST	BIT(3)
 
+#define MT7621_NATIVE_CS_COUNT	2
+
 struct mt7621_spi {
 	struct spi_controller	*host;
 	void __iomem		*base;
@@ -75,10 +77,11 @@ static inline void mt7621_spi_write(struct mt7621_spi *rs, u32 reg, u32 val)
 	iowrite32(val, rs->base + reg);
 }
 
-static void mt7621_spi_set_cs(struct spi_device *spi, int enable)
+static void mt7621_spi_set_native_cs(struct spi_device *spi, bool enable)
 {
 	struct mt7621_spi *rs = spidev_to_mt7621_spi(spi);
 	int cs = spi_get_chipselect(spi, 0);
+	bool active = spi->mode & SPI_CS_HIGH ? enable : !enable;
 	u32 polar = 0;
 	u32 host;
 
@@ -94,7 +97,7 @@ static void mt7621_spi_set_cs(struct spi_device *spi, int enable)
 
 	rs->pending_write = 0;
 
-	if (enable)
+	if (active)
 		polar = BIT(cs);
 	mt7621_spi_write(rs, MT7621_SPI_POLAR, polar);
 }
@@ -154,6 +157,23 @@ static inline int mt7621_spi_wait_till_ready(struct mt7621_spi *rs)
 	return -ETIMEDOUT;
 }
 
+static int mt7621_spi_prepare_message(struct spi_controller *host,
+				      struct spi_message *m)
+{
+	struct mt7621_spi *rs = spi_controller_get_devdata(host);
+	struct spi_device *spi = m->spi;
+	unsigned int speed = spi->max_speed_hz;
+	struct spi_transfer *t = NULL;
+
+	mt7621_spi_wait_till_ready(rs);
+
+	list_for_each_entry(t, &m->transfers, transfer_list)
+		if (t->speed_hz < speed)
+			speed = t->speed_hz;
+
+	return mt7621_spi_prepare(spi, speed);
+}
+
 static void mt7621_spi_read_half_duplex(struct mt7621_spi *rs,
 					int rx_len, u8 *buf)
 {
@@ -243,59 +263,30 @@ static void mt7621_spi_write_half_duplex(struct mt7621_spi *rs,
 	}
 
 	rs->pending_write = len;
+	mt7621_spi_flush(rs);
 }
 
-static int mt7621_spi_transfer_one_message(struct spi_controller *host,
-					   struct spi_message *m)
+static int mt7621_spi_transfer_one(struct spi_controller *host,
+				   struct spi_device *spi,
+				   struct spi_transfer *t)
 {
 	struct mt7621_spi *rs = spi_controller_get_devdata(host);
-	struct spi_device *spi = m->spi;
-	unsigned int speed = spi->max_speed_hz;
-	struct spi_transfer *t = NULL;
-	int status = 0;
-
-	mt7621_spi_wait_till_ready(rs);
 
-	list_for_each_entry(t, &m->transfers, transfer_list)
-		if (t->speed_hz < speed)
-			speed = t->speed_hz;
-
-	if (mt7621_spi_prepare(spi, speed)) {
-		status = -EIO;
-		goto msg_done;
-	}
-
-	/* Assert CS */
-	mt7621_spi_set_cs(spi, 1);
-
-	m->actual_length = 0;
-	list_for_each_entry(t, &m->transfers, transfer_list) {
-		if ((t->rx_buf) && (t->tx_buf)) {
-			/*
-			 * This controller will shift some extra data out
-			 * of spi_opcode if (mosi_bit_cnt > 0) &&
-			 * (cmd_bit_cnt == 0). So the claimed full-duplex
-			 * support is broken since we have no way to read
-			 * the MISO value during that bit.
-			 */
-			status = -EIO;
-			goto msg_done;
-		} else if (t->rx_buf) {
-			mt7621_spi_read_half_duplex(rs, t->len, t->rx_buf);
-		} else if (t->tx_buf) {
-			mt7621_spi_write_half_duplex(rs, t->len, t->tx_buf);
-		}
-		m->actual_length += t->len;
+	if ((t->rx_buf) && (t->tx_buf)) {
+		/*
+		 * This controller will shift some extra data out
+		 * of spi_opcode if (mosi_bit_cnt > 0) &&
+		 * (cmd_bit_cnt == 0). So the claimed full-duplex
+		 * support is broken since we have no way to read
+		 * the MISO value during that bit.
+		 */
+		return -EIO;
+	} else if (t->rx_buf) {
+		mt7621_spi_read_half_duplex(rs, t->len, t->rx_buf);
+	} else if (t->tx_buf) {
+		mt7621_spi_write_half_duplex(rs, t->len, t->tx_buf);
 	}
 
-	/* Flush data and deassert CS */
-	mt7621_spi_flush(rs);
-	mt7621_spi_set_cs(spi, 0);
-
-msg_done:
-	m->status = status;
-	spi_finalize_current_message(host);
-
 	return 0;
 }
 
@@ -353,10 +344,14 @@ static int mt7621_spi_probe(struct platform_device *pdev)
 	host->mode_bits = SPI_LSB_FIRST;
 	host->flags = SPI_CONTROLLER_HALF_DUPLEX;
 	host->setup = mt7621_spi_setup;
-	host->transfer_one_message = mt7621_spi_transfer_one_message;
+	host->prepare_message = mt7621_spi_prepare_message;
+	host->set_cs = mt7621_spi_set_native_cs;
+	host->transfer_one = mt7621_spi_transfer_one;
 	host->bits_per_word_mask = SPI_BPW_MASK(8);
 	host->dev.of_node = pdev->dev.of_node;
-	host->num_chipselect = 2;
+	host->max_native_cs = MT7621_NATIVE_CS_COUNT;
+	host->num_chipselect = MT7621_NATIVE_CS_COUNT;
+	host->use_gpio_descriptors = true;
 
 	dev_set_drvdata(&pdev->dev, host);
 
diff --git a/drivers/spi/spi-mux.c b/drivers/spi/spi-mux.c
index bd988f53753e..5d72e3d59df8 100644
--- a/drivers/spi/spi-mux.c
+++ b/drivers/spi/spi-mux.c
@@ -68,6 +68,8 @@ static int spi_mux_select(struct spi_device *spi)
 
 	priv->current_cs = spi_get_chipselect(spi, 0);
 
+	spi_setup(priv->spi);
+
 	return 0;
 }
 
diff --git a/drivers/spi/spi-oc-tiny.c b/drivers/spi/spi-oc-tiny.c
index 6ea38f5e7d64..7d8c5cd680d1 100644
--- a/drivers/spi/spi-oc-tiny.c
+++ b/drivers/spi/spi-oc-tiny.c
@@ -184,8 +184,6 @@ static irqreturn_t tiny_spi_irq(int irq, void *dev)
 }
 
 #ifdef CONFIG_OF
-#include <linux/of_gpio.h>
-
 static int tiny_spi_of_probe(struct platform_device *pdev)
 {
 	struct tiny_spi *hw = platform_get_drvdata(pdev);
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index ddf1c684bcc7..7e3083b83534 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -131,6 +131,7 @@ struct omap2_mcspi {
 	unsigned int		pin_dir:1;
 	size_t			max_xfer_len;
 	u32			ref_clk_hz;
+	bool			use_multi_mode;
 };
 
 struct omap2_mcspi_cs {
@@ -256,10 +257,15 @@ static void omap2_mcspi_set_cs(struct spi_device *spi, bool enable)
 
 		l = mcspi_cached_chconf0(spi);
 
-		if (enable)
+		/* Only enable chip select manually if single mode is used */
+		if (mcspi->use_multi_mode) {
 			l &= ~OMAP2_MCSPI_CHCONF_FORCE;
-		else
-			l |= OMAP2_MCSPI_CHCONF_FORCE;
+		} else {
+			if (enable)
+				l &= ~OMAP2_MCSPI_CHCONF_FORCE;
+			else
+				l |= OMAP2_MCSPI_CHCONF_FORCE;
+		}
 
 		mcspi_write_chconf0(spi, l);
 
@@ -283,7 +289,12 @@ static void omap2_mcspi_set_mode(struct spi_controller *ctlr)
 		l |= (OMAP2_MCSPI_MODULCTRL_MS);
 	} else {
 		l &= ~(OMAP2_MCSPI_MODULCTRL_MS);
-		l |= OMAP2_MCSPI_MODULCTRL_SINGLE;
+
+		/* Enable single mode if needed */
+		if (mcspi->use_multi_mode)
+			l &= ~OMAP2_MCSPI_MODULCTRL_SINGLE;
+		else
+			l |= OMAP2_MCSPI_MODULCTRL_SINGLE;
 	}
 	mcspi_write_reg(ctlr, OMAP2_MCSPI_MODULCTRL, l);
 
@@ -1175,13 +1186,6 @@ static int omap2_mcspi_transfer_one(struct spi_controller *ctlr,
 		    t->bits_per_word == spi->bits_per_word)
 			par_override = 0;
 	}
-	if (cd && cd->cs_per_word) {
-		chconf = mcspi->ctx.modulctrl;
-		chconf &= ~OMAP2_MCSPI_MODULCTRL_SINGLE;
-		mcspi_write_reg(ctlr, OMAP2_MCSPI_MODULCTRL, chconf);
-		mcspi->ctx.modulctrl =
-			mcspi_read_cs_reg(spi, OMAP2_MCSPI_MODULCTRL);
-	}
 
 	chconf = mcspi_cached_chconf0(spi);
 	chconf &= ~OMAP2_MCSPI_CHCONF_TRM_MASK;
@@ -1240,14 +1244,6 @@ out:
 		status = omap2_mcspi_setup_transfer(spi, NULL);
 	}
 
-	if (cd && cd->cs_per_word) {
-		chconf = mcspi->ctx.modulctrl;
-		chconf |= OMAP2_MCSPI_MODULCTRL_SINGLE;
-		mcspi_write_reg(ctlr, OMAP2_MCSPI_MODULCTRL, chconf);
-		mcspi->ctx.modulctrl =
-			mcspi_read_cs_reg(spi, OMAP2_MCSPI_MODULCTRL);
-	}
-
 	omap2_mcspi_set_enable(spi, 0);
 
 	if (spi_get_csgpiod(spi, 0))
@@ -1265,15 +1261,72 @@ static int omap2_mcspi_prepare_message(struct spi_controller *ctlr,
 	struct omap2_mcspi	*mcspi = spi_controller_get_devdata(ctlr);
 	struct omap2_mcspi_regs	*ctx = &mcspi->ctx;
 	struct omap2_mcspi_cs	*cs;
+	struct spi_transfer	*tr;
+	u8 bits_per_word;
+
+	/*
+	 * The conditions are strict, it is mandatory to check each transfer of the list to see if
+	 * multi-mode is applicable.
+	 */
+	mcspi->use_multi_mode = true;
+	list_for_each_entry(tr, &msg->transfers, transfer_list) {
+		if (!tr->bits_per_word)
+			bits_per_word = msg->spi->bits_per_word;
+		else
+			bits_per_word = tr->bits_per_word;
 
-	/* Only a single channel can have the FORCE bit enabled
+		/*
+		 * Check if this transfer contains only one word;
+		 * OR contains 1 to 4 words, with bits_per_word == 8 and no delay between each word
+		 * OR contains 1 to 2 words, with bits_per_word == 16 and no delay between each word
+		 *
+		 * If one of the two last case is true, this also change the bits_per_word of this
+		 * transfer to make it a bit faster.
+		 * It's not an issue to change the bits_per_word here even if the multi-mode is not
+		 * applicable for this message, the signal on the wire will be the same.
+		 */
+		if (bits_per_word < 8 && tr->len == 1) {
+			/* multi-mode is applicable, only one word (1..7 bits) */
+		} else if (tr->word_delay.value == 0 && bits_per_word == 8 && tr->len <= 4) {
+			/* multi-mode is applicable, only one "bigger" word (8,16,24,32 bits) */
+			tr->bits_per_word = tr->len * bits_per_word;
+		} else if (tr->word_delay.value == 0 && bits_per_word == 16 && tr->len <= 2) {
+			/* multi-mode is applicable, only one "bigger" word (16,32 bits) */
+			tr->bits_per_word = tr->len * bits_per_word / 2;
+		} else if (bits_per_word >= 8 && tr->len == bits_per_word / 8) {
+			/* multi-mode is applicable, only one word (9..15,17..32 bits) */
+		} else {
+			/* multi-mode is not applicable: more than one word in the transfer */
+			mcspi->use_multi_mode = false;
+		}
+
+		/* Check if transfer asks to change the CS status after the transfer */
+		if (!tr->cs_change)
+			mcspi->use_multi_mode = false;
+
+		/*
+		 * If at least one message is not compatible, switch back to single mode
+		 *
+		 * The bits_per_word of certain transfer can be different, but it will have no
+		 * impact on the signal itself.
+		 */
+		if (!mcspi->use_multi_mode)
+			break;
+	}
+
+	omap2_mcspi_set_mode(ctlr);
+
+	/* In single mode only a single channel can have the FORCE bit enabled
 	 * in its chconf0 register.
 	 * Scan all channels and disable them except the current one.
 	 * A FORCE can remain from a last transfer having cs_change enabled
+	 *
+	 * In multi mode all FORCE bits must be disabled.
 	 */
 	list_for_each_entry(cs, &ctx->cs, node) {
-		if (msg->spi->controller_state == cs)
+		if (msg->spi->controller_state == cs && !mcspi->use_multi_mode) {
 			continue;
+		}
 
 		if ((cs->chconf0 & OMAP2_MCSPI_CHCONF_FORCE)) {
 			cs->chconf0 &= ~OMAP2_MCSPI_CHCONF_FORCE;
diff --git a/drivers/spi/spi-pic32-sqi.c b/drivers/spi/spi-pic32-sqi.c
index 3f1e5b27776b..0031063a7e25 100644
--- a/drivers/spi/spi-pic32-sqi.c
+++ b/drivers/spi/spi-pic32-sqi.c
@@ -344,7 +344,7 @@ static int pic32_sqi_one_message(struct spi_controller *host,
 	struct spi_transfer *xfer;
 	struct pic32_sqi *sqi;
 	int ret = 0, mode;
-	unsigned long timeout;
+	unsigned long time_left;
 	u32 val;
 
 	sqi = spi_controller_get_devdata(host);
@@ -410,8 +410,8 @@ static int pic32_sqi_one_message(struct spi_controller *host,
 	writel(val, sqi->regs + PESQI_BD_CTRL_REG);
 
 	/* wait for xfer completion */
-	timeout = wait_for_completion_timeout(&sqi->xfer_done, 5 * HZ);
-	if (timeout == 0) {
+	time_left = wait_for_completion_timeout(&sqi->xfer_done, 5 * HZ);
+	if (time_left == 0) {
 		dev_err(&sqi->host->dev, "wait timedout/interrupted\n");
 		ret = -ETIMEDOUT;
 		msg->status = ret;
diff --git a/drivers/spi/spi-pic32.c b/drivers/spi/spi-pic32.c
index 709edb70ad7d..b8bcc220e96d 100644
--- a/drivers/spi/spi-pic32.c
+++ b/drivers/spi/spi-pic32.c
@@ -498,7 +498,7 @@ static int pic32_spi_one_transfer(struct spi_controller *host,
 {
 	struct pic32_spi *pic32s;
 	bool dma_issued = false;
-	unsigned long timeout;
+	unsigned long time_left;
 	int ret;
 
 	pic32s = spi_controller_get_devdata(host);
@@ -545,8 +545,8 @@ static int pic32_spi_one_transfer(struct spi_controller *host,
 	}
 
 	/* wait for completion */
-	timeout = wait_for_completion_timeout(&pic32s->xfer_done, 2 * HZ);
-	if (timeout == 0) {
+	time_left = wait_for_completion_timeout(&pic32s->xfer_done, 2 * HZ);
+	if (time_left == 0) {
 		dev_err(&spi->dev, "wait error/timedout\n");
 		if (dma_issued) {
 			dmaengine_terminate_all(host->dma_rx);
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index be563f0dd03a..08cb6e96ac94 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -6,17 +6,22 @@
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
  */
 
-#include <linux/device.h>
+#include <linux/atomic.h>
+#include <linux/dev_printk.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
+#include <linux/errno.h>
+#include <linux/irqreturn.h>
 #include <linux/scatterlist.h>
-#include <linux/sizes.h>
+#include <linux/string.h>
+#include <linux/types.h>
 
-#include <linux/spi/pxa2xx_spi.h>
 #include <linux/spi/spi.h>
 
 #include "spi-pxa2xx.h"
 
+struct device;
+
 static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data,
 					     bool error)
 {
@@ -63,8 +68,6 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 			   enum dma_transfer_direction dir,
 			   struct spi_transfer *xfer)
 {
-	struct chip_data *chip =
-		spi_get_ctldata(drv_data->controller->cur_msg->spi);
 	enum dma_slave_buswidth width;
 	struct dma_slave_config cfg;
 	struct dma_chan *chan;
@@ -89,14 +92,14 @@ pxa2xx_spi_dma_prepare_one(struct driver_data *drv_data,
 	if (dir == DMA_MEM_TO_DEV) {
 		cfg.dst_addr = drv_data->ssp->phys_base + SSDR;
 		cfg.dst_addr_width = width;
-		cfg.dst_maxburst = chip->dma_burst_size;
+		cfg.dst_maxburst = drv_data->controller_info->dma_burst_size;
 
 		sgt = &xfer->tx_sg;
 		chan = drv_data->controller->dma_tx;
 	} else {
 		cfg.src_addr = drv_data->ssp->phys_base + SSDR;
 		cfg.src_addr_width = width;
-		cfg.src_maxburst = chip->dma_burst_size;
+		cfg.src_maxburst = drv_data->controller_info->dma_burst_size;
 
 		sgt = &xfer->rx_sg;
 		chan = drv_data->controller->dma_rx;
@@ -220,24 +223,3 @@ void pxa2xx_spi_dma_release(struct driver_data *drv_data)
 		controller->dma_tx = NULL;
 	}
 }
-
-int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
-					   struct spi_device *spi,
-					   u8 bits_per_word, u32 *burst_code,
-					   u32 *threshold)
-{
-	struct pxa2xx_spi_chip *chip_info = spi->controller_data;
-	struct driver_data *drv_data = spi_controller_get_devdata(spi->controller);
-	u32 dma_burst_size = drv_data->controller_info->dma_burst_size;
-
-	/*
-	 * If the DMA burst size is given in chip_info we use that,
-	 * otherwise we use the default. Also we use the default FIFO
-	 * thresholds for now.
-	 */
-	*burst_code = chip_info ? chip_info->dma_burst_size : dma_burst_size;
-	*threshold = SSCR1_RxTresh(RX_THRESH_DFLT)
-		   | SSCR1_TxTresh(TX_THRESH_DFLT);
-
-	return 0;
-}
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 861b21c63504..6d2efdb0e95f 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -6,15 +6,21 @@
  * Copyright (C) 2016, 2021 Intel Corporation
  */
 #include <linux/clk-provider.h>
+#include <linux/device.h>
+#include <linux/err.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
-
-#include <linux/spi/pxa2xx_spi.h>
+#include <linux/property.h>
+#include <linux/sprintf.h>
+#include <linux/string.h>
+#include <linux/types.h>
 
 #include <linux/dmaengine.h>
 #include <linux/platform_data/dma-dw.h>
 
+#include "spi-pxa2xx.h"
+
 #define PCI_DEVICE_ID_INTEL_QUARK_X1000		0x0935
 #define PCI_DEVICE_ID_INTEL_BYT			0x0f0e
 #define PCI_DEVICE_ID_INTEL_MRFLD		0x1194
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index f2a856f6a99e..efe76d0c21bb 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -5,27 +5,29 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/atomic.h>
 #include <linux/bitops.h>
+#include <linux/bug.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/device.h>
 #include <linux/dmaengine.h>
 #include <linux/err.h>
-#include <linux/errno.h>
 #include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/ioport.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/math64.h>
+#include <linux/minmax.h>
 #include <linux/mod_devicetable.h>
-#include <linux/of.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
 #include <linux/slab.h>
+#include <linux/types.h>
 
-#include <linux/spi/pxa2xx_spi.h>
 #include <linux/spi/spi.h>
 
 #include "spi-pxa2xx.h"
@@ -64,6 +66,14 @@ MODULE_ALIAS("platform:pxa2xx-spi");
 				| CE4100_SSCR1_RFT | CE4100_SSCR1_TFT | SSCR1_MWDS \
 				| SSCR1_SPH | SSCR1_SPO | SSCR1_LBM)
 
+struct chip_data {
+	u32 cr1;
+	u32 dds_rate;
+	u32 threshold;
+	u16 lpss_rx_threshold;
+	u16 lpss_tx_threshold;
+};
+
 #define LPSS_GENERAL_REG_RXTO_HOLDOFF_DISABLE	BIT(24)
 #define LPSS_CS_CONTROL_SW_MODE			BIT(0)
 #define LPSS_CS_CONTROL_CS_HIGH			BIT(1)
@@ -932,11 +942,11 @@ static bool pxa2xx_spi_can_dma(struct spi_controller *controller,
 			       struct spi_device *spi,
 			       struct spi_transfer *xfer)
 {
-	struct chip_data *chip = spi_get_ctldata(spi);
+	struct driver_data *drv_data = spi_controller_get_devdata(controller);
 
-	return chip->enable_dma &&
+	return drv_data->controller_info->enable_dma &&
 	       xfer->len <= MAX_DMA_LEN &&
-	       xfer->len >= chip->dma_burst_size;
+	       xfer->len >= drv_data->controller_info->dma_burst_size;
 }
 
 static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
@@ -944,11 +954,9 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 				   struct spi_transfer *transfer)
 {
 	struct driver_data *drv_data = spi_controller_get_devdata(controller);
-	struct spi_message *message = controller->cur_msg;
 	struct chip_data *chip = spi_get_ctldata(spi);
-	u32 dma_thresh = chip->dma_threshold;
-	u32 dma_burst = chip->dma_burst_size;
 	u32 change_mask = pxa2xx_spi_get_ssrc1_change_mask(drv_data);
+	u32 dma_thresh;
 	u32 clk_div;
 	u8 bits;
 	u32 speed;
@@ -958,17 +966,7 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 	int dma_mapped;
 
 	/* Check if we can DMA this transfer */
-	if (transfer->len > MAX_DMA_LEN && chip->enable_dma) {
-
-		/* Reject already-mapped transfers; PIO won't always work */
-		if (message->is_dma_mapped
-				|| transfer->rx_dma || transfer->tx_dma) {
-			dev_err(&spi->dev,
-				"Mapped transfer length of %u is greater than %d\n",
-				transfer->len, MAX_DMA_LEN);
-			return -EINVAL;
-		}
-
+	if (transfer->len > MAX_DMA_LEN && drv_data->controller_info->enable_dma) {
 		/* Warn ... we force this to PIO mode */
 		dev_warn_ratelimited(&spi->dev,
 				     "DMA disabled for transfer length %u greater than %d\n",
@@ -1004,19 +1002,8 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 		drv_data->read = drv_data->rx ? u32_reader : null_reader;
 		drv_data->write = drv_data->tx ? u32_writer : null_writer;
 	}
-	/*
-	 * If bits per word is changed in DMA mode, then must check
-	 * the thresholds and burst also.
-	 */
-	if (chip->enable_dma) {
-		if (pxa2xx_spi_set_dma_burst_and_threshold(chip,
-						spi,
-						bits, &dma_burst,
-						&dma_thresh))
-			dev_warn_ratelimited(&spi->dev,
-					     "DMA burst size reduced to match bits_per_word\n");
-	}
 
+	dma_thresh = SSCR1_RxTresh(RX_THRESH_DFLT) | SSCR1_TxTresh(TX_THRESH_DFLT);
 	dma_mapped = controller->can_dma &&
 		     controller->can_dma(controller, spi, transfer) &&
 		     controller->cur_msg_mapped;
@@ -1079,7 +1066,7 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 		pxa_ssp_disable(drv_data->ssp);
 
 	if (!pxa25x_ssp_comp(drv_data))
-		pxa2xx_spi_write(drv_data, SSTO, chip->timeout);
+		pxa2xx_spi_write(drv_data, SSTO, TIMOUT_DFLT);
 
 	/* First set CR1 without interrupt and service enables */
 	pxa2xx_spi_update(drv_data, SSCR1, change_mask, cr1);
@@ -1163,7 +1150,6 @@ static int pxa2xx_spi_unprepare_transfer(struct spi_controller *controller)
 
 static int setup(struct spi_device *spi)
 {
-	struct pxa2xx_spi_chip *chip_info;
 	struct chip_data *chip;
 	const struct lpss_config *config;
 	struct driver_data *drv_data =
@@ -1209,42 +1195,19 @@ static int setup(struct spi_device *spi)
 		break;
 	}
 
+	if (drv_data->ssp_type == CE4100_SSP) {
+		if (spi_get_chipselect(spi, 0) > 4) {
+			dev_err(&spi->dev, "failed setup: cs number must not be > 4.\n");
+			return -EINVAL;
+		}
+	}
+
 	/* Only allocate on the first setup */
 	chip = spi_get_ctldata(spi);
 	if (!chip) {
 		chip = kzalloc(sizeof(struct chip_data), GFP_KERNEL);
 		if (!chip)
 			return -ENOMEM;
-
-		if (drv_data->ssp_type == CE4100_SSP) {
-			if (spi_get_chipselect(spi, 0) > 4) {
-				dev_err(&spi->dev,
-					"failed setup: cs number must not be > 4.\n");
-				kfree(chip);
-				return -EINVAL;
-			}
-		}
-		chip->enable_dma = drv_data->controller_info->enable_dma;
-		chip->timeout = TIMOUT_DFLT;
-	}
-
-	/*
-	 * Protocol drivers may change the chip settings, so...
-	 * if chip_info exists, use it.
-	 */
-	chip_info = spi->controller_data;
-
-	/* chip_info isn't always needed */
-	if (chip_info) {
-		if (chip_info->timeout)
-			chip->timeout = chip_info->timeout;
-		if (chip_info->tx_threshold)
-			tx_thres = chip_info->tx_threshold;
-		if (chip_info->tx_hi_threshold)
-			tx_hi_thres = chip_info->tx_hi_threshold;
-		if (chip_info->rx_threshold)
-			rx_thres = chip_info->rx_threshold;
-		chip->dma_threshold = 0;
 	}
 
 	chip->cr1 = 0;
@@ -1266,25 +1229,6 @@ static int setup(struct spi_device *spi)
 		chip->lpss_tx_threshold = tx_thres;
 	}
 
-	/*
-	 * Set DMA burst and threshold outside of chip_info path so that if
-	 * chip_info goes away after setting chip->enable_dma, the burst and
-	 * threshold can still respond to changes in bits_per_word.
-	 */
-	if (chip->enable_dma) {
-		/* Set up legal burst and threshold for DMA */
-		if (pxa2xx_spi_set_dma_burst_and_threshold(chip, spi,
-						spi->bits_per_word,
-						&chip->dma_burst_size,
-						&chip->dma_threshold)) {
-			dev_warn(&spi->dev,
-				 "in setup: DMA burst size reduced to match bits_per_word\n");
-		}
-		dev_dbg(&spi->dev,
-			"in setup: DMA burst size set to %u\n",
-			chip->dma_burst_size);
-	}
-
 	switch (drv_data->ssp_type) {
 	case QUARK_X1000_SSP:
 		chip->threshold = (QUARK_X1000_SSCR1_RxTresh(rx_thres)
@@ -1326,19 +1270,52 @@ static bool pxa2xx_spi_idma_filter(struct dma_chan *chan, void *param)
 	return param == chan->device->dev;
 }
 
+static int
+pxa2xx_spi_init_ssp(struct platform_device *pdev, struct ssp_device *ssp, enum pxa_ssp_type type)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	int status;
+	u64 uid;
+
+	ssp->mmio_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+	if (IS_ERR(ssp->mmio_base))
+		return PTR_ERR(ssp->mmio_base);
+
+	ssp->phys_base = res->start;
+
+	ssp->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(ssp->clk))
+		return PTR_ERR(ssp->clk);
+
+	ssp->irq = platform_get_irq(pdev, 0);
+	if (ssp->irq < 0)
+		return ssp->irq;
+
+	ssp->type = type;
+	ssp->dev = dev;
+
+	status = acpi_dev_uid_to_integer(ACPI_COMPANION(dev), &uid);
+	if (status)
+		ssp->port_id = -1;
+	else
+		ssp->port_id = uid;
+
+	return 0;
+}
+
 static struct pxa2xx_spi_controller *
 pxa2xx_spi_init_pdata(struct platform_device *pdev)
 {
 	struct pxa2xx_spi_controller *pdata;
 	struct device *dev = &pdev->dev;
 	struct device *parent = dev->parent;
-	struct ssp_device *ssp;
-	struct resource *res;
 	enum pxa_ssp_type type = SSP_UNDEFINED;
+	struct ssp_device *ssp = NULL;
 	const void *match;
 	bool is_lpss_priv;
+	u32 num_cs = 1;
 	int status;
-	u64 uid;
 
 	is_lpss_priv = platform_get_resource_byname(pdev, IORESOURCE_MEM, "lpss_priv");
 
@@ -1353,6 +1330,12 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 			return ERR_PTR(status);
 
 		type = (enum pxa_ssp_type)value;
+	} else {
+		ssp = pxa_ssp_request(pdev->id, pdev->name);
+		if (ssp) {
+			type = ssp->type;
+			pxa_ssp_free(ssp);
+		}
 	}
 
 	/* Validate the SSP type correctness */
@@ -1363,14 +1346,6 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 	if (!pdata)
 		return ERR_PTR(-ENOMEM);
 
-	ssp = &pdata->ssp;
-
-	ssp->mmio_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
-	if (IS_ERR(ssp->mmio_base))
-		return ERR_CAST(ssp->mmio_base);
-
-	ssp->phys_base = res->start;
-
 	/* Platforms with iDMA 64-bit */
 	if (is_lpss_priv) {
 		pdata->tx_param = parent;
@@ -1378,28 +1353,22 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 		pdata->dma_filter = pxa2xx_spi_idma_filter;
 	}
 
-	ssp->clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(ssp->clk))
-		return ERR_CAST(ssp->clk);
-
-	ssp->irq = platform_get_irq(pdev, 0);
-	if (ssp->irq < 0)
-		return ERR_PTR(ssp->irq);
-
-	ssp->type = type;
-	ssp->dev = dev;
-
-	status = acpi_dev_uid_to_integer(ACPI_COMPANION(dev), &uid);
-	if (status)
-		ssp->port_id = -1;
-	else
-		ssp->port_id = uid;
+	/* Read number of chip select pins, if provided */
+	device_property_read_u32(dev, "num-cs", &num_cs);
 
+	pdata->num_chipselect = num_cs;
 	pdata->is_target = device_property_read_bool(dev, "spi-slave");
-	pdata->num_chipselect = 1;
 	pdata->enable_dma = true;
 	pdata->dma_burst_size = 1;
 
+	/* If SSP has been already enumerated, use it */
+	if (ssp)
+		return pdata;
+
+	status = pxa2xx_spi_init_ssp(pdev, &pdata->ssp, type);
+	if (status)
+		return ERR_PTR(status);
+
 	return pdata;
 }
 
@@ -1446,20 +1415,17 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	platform_info = dev_get_platdata(dev);
 	if (!platform_info) {
 		platform_info = pxa2xx_spi_init_pdata(pdev);
-		if (IS_ERR(platform_info)) {
-			dev_err(&pdev->dev, "missing platform data\n");
-			return PTR_ERR(platform_info);
-		}
+		if (IS_ERR(platform_info))
+			return dev_err_probe(dev, PTR_ERR(platform_info), "missing platform data\n");
 	}
+	dev_dbg(dev, "DMA burst size set to %u\n", platform_info->dma_burst_size);
 
 	ssp = pxa_ssp_request(pdev->id, pdev->name);
 	if (!ssp)
 		ssp = &platform_info->ssp;
 
-	if (!ssp->mmio_base) {
-		dev_err(&pdev->dev, "failed to get SSP\n");
-		return -ENODEV;
-	}
+	if (!ssp->mmio_base)
+		return dev_err_probe(dev, -ENODEV, "failed to get SSP\n");
 
 	if (platform_info->is_target)
 		controller = devm_spi_alloc_target(dev, sizeof(*drv_data));
@@ -1467,8 +1433,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 		controller = devm_spi_alloc_host(dev, sizeof(*drv_data));
 
 	if (!controller) {
-		dev_err(&pdev->dev, "cannot alloc spi_controller\n");
-		status = -ENOMEM;
+		status = dev_err_probe(dev, -ENOMEM, "cannot alloc spi_controller\n");
 		goto out_error_controller_alloc;
 	}
 	drv_data = spi_controller_get_devdata(controller);
@@ -1522,7 +1487,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	status = request_irq(ssp->irq, ssp_int, IRQF_SHARED, dev_name(dev),
 			drv_data);
 	if (status < 0) {
-		dev_err(&pdev->dev, "cannot get IRQ %d\n", ssp->irq);
+		dev_err_probe(dev, status, "cannot get IRQ %d\n", ssp->irq);
 		goto out_error_controller_alloc;
 	}
 
@@ -1638,7 +1603,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, drv_data);
 	status = spi_register_controller(controller);
 	if (status) {
-		dev_err(&pdev->dev, "problem registering SPI controller\n");
+		dev_err_probe(dev, status, "problem registering SPI controller\n");
 		goto out_error_pm_runtime_enabled;
 	}
 
@@ -1741,7 +1706,6 @@ static const struct dev_pm_ops pxa2xx_spi_pm_ops = {
 	RUNTIME_PM_OPS(pxa2xx_spi_runtime_suspend, pxa2xx_spi_runtime_resume, NULL)
 };
 
-#ifdef CONFIG_ACPI
 static const struct acpi_device_id pxa2xx_spi_acpi_match[] = {
 	{ "80860F0E", LPSS_BYT_SSP },
 	{ "8086228E", LPSS_BSW_SSP },
@@ -1752,9 +1716,8 @@ static const struct acpi_device_id pxa2xx_spi_acpi_match[] = {
 	{}
 };
 MODULE_DEVICE_TABLE(acpi, pxa2xx_spi_acpi_match);
-#endif
 
-static const struct of_device_id pxa2xx_spi_of_match[] __maybe_unused = {
+static const struct of_device_id pxa2xx_spi_of_match[] = {
 	{ .compatible = "marvell,mmp2-ssp", .data = (void *)MMP2_SSP },
 	{}
 };
@@ -1764,8 +1727,8 @@ static struct platform_driver driver = {
 	.driver = {
 		.name	= "pxa2xx-spi",
 		.pm	= pm_ptr(&pxa2xx_spi_pm_ops),
-		.acpi_match_table = ACPI_PTR(pxa2xx_spi_acpi_match),
-		.of_match_table = of_match_ptr(pxa2xx_spi_of_match),
+		.acpi_match_table = pxa2xx_spi_acpi_match,
+		.of_match_table = pxa2xx_spi_of_match,
 	},
 	.probe = pxa2xx_spi_probe,
 	.remove_new = pxa2xx_spi_remove,
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index 45cdbbc71c4b..93e1e471e1c6 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -7,15 +7,34 @@
 #ifndef SPI_PXA2XX_H
 #define SPI_PXA2XX_H
 
-#include <linux/interrupt.h>
-#include <linux/io.h>
+#include <linux/dmaengine.h>
+#include <linux/irqreturn.h>
 #include <linux/types.h>
 #include <linux/sizes.h>
 
 #include <linux/pxa2xx_ssp.h>
 
 struct gpio_desc;
-struct pxa2xx_spi_controller;
+
+/*
+ * The platform data for SSP controller devices
+ * (resides in device.platform_data).
+ */
+struct pxa2xx_spi_controller {
+	u8 num_chipselect;
+	u8 enable_dma;
+	u8 dma_burst_size;
+	bool is_target;
+
+	/* DMA engine specific config */
+	dma_filter_fn dma_filter;
+	void *tx_param;
+	void *rx_param;
+
+	/* For non-PXA arches */
+	struct ssp_device ssp;
+};
+
 struct spi_controller;
 struct spi_device;
 struct spi_transfer;
@@ -56,18 +75,6 @@ struct driver_data {
 	struct gpio_desc *gpiod_ready;
 };
 
-struct chip_data {
-	u32 cr1;
-	u32 dds_rate;
-	u32 timeout;
-	u8 enable_dma;
-	u32 dma_burst_size;
-	u32 dma_threshold;
-	u32 threshold;
-	u16 lpss_rx_threshold;
-	u16 lpss_tx_threshold;
-};
-
 static inline u32 pxa2xx_spi_read(const struct driver_data *drv_data, u32 reg)
 {
 	return pxa_ssp_read_reg(drv_data->ssp, reg);
@@ -123,10 +130,5 @@ extern void pxa2xx_spi_dma_start(struct driver_data *drv_data);
 extern void pxa2xx_spi_dma_stop(struct driver_data *drv_data);
 extern int pxa2xx_spi_dma_setup(struct driver_data *drv_data);
 extern void pxa2xx_spi_dma_release(struct driver_data *drv_data);
-extern int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
-						  struct spi_device *spi,
-						  u8 bits_per_word,
-						  u32 *burst_code,
-						  u32 *threshold);
 
 #endif /* SPI_PXA2XX_H */
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 8e81f1a8623f..7f95d22fb1ac 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -24,7 +24,6 @@
 #include <linux/reset.h>
 #include <linux/sh_dma.h>
 #include <linux/spi/spi.h>
-#include <linux/spi/rspi.h>
 #include <linux/spinlock.h>
 
 #define RSPI_SPCR		0x00	/* Control Register */
@@ -1131,16 +1130,12 @@ static struct dma_chan *rspi_request_dma_chan(struct device *dev,
 static int rspi_request_dma(struct device *dev, struct spi_controller *ctlr,
 			    const struct resource *res)
 {
-	const struct rspi_plat_data *rspi_pd = dev_get_platdata(dev);
 	unsigned int dma_tx_id, dma_rx_id;
 
 	if (dev->of_node) {
 		/* In the OF case we will get the slave IDs from the DT */
 		dma_tx_id = 0;
 		dma_rx_id = 0;
-	} else if (rspi_pd && rspi_pd->dma_tx_id && rspi_pd->dma_rx_id) {
-		dma_tx_id = rspi_pd->dma_tx_id;
-		dma_rx_id = rspi_pd->dma_rx_id;
 	} else {
 		/* The driver assumes no error. */
 		return 0;
@@ -1290,7 +1285,6 @@ static int rspi_probe(struct platform_device *pdev)
 	struct spi_controller *ctlr;
 	struct rspi_data *rspi;
 	int ret;
-	const struct rspi_plat_data *rspi_pd;
 	const struct spi_ops *ops;
 	unsigned long clksrc;
 
@@ -1305,11 +1299,7 @@ static int rspi_probe(struct platform_device *pdev)
 			goto error1;
 	} else {
 		ops = (struct spi_ops *)pdev->id_entry->driver_data;
-		rspi_pd = dev_get_platdata(&pdev->dev);
-		if (rspi_pd && rspi_pd->num_chipselect)
-			ctlr->num_chipselect = rspi_pd->num_chipselect;
-		else
-			ctlr->num_chipselect = 2; /* default */
+		ctlr->num_chipselect = 2; /* default */
 	}
 
 	rspi = spi_controller_get_devdata(ctlr);
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index f726d8670428..833c58c88e40 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -950,7 +950,7 @@ static struct s3c64xx_spi_csinfo *s3c64xx_get_target_ctrldata(
 				struct spi_device *spi)
 {
 	struct s3c64xx_spi_csinfo *cs;
-	struct device_node *target_np, *data_np = NULL;
+	struct device_node *target_np;
 	u32 fb_delay = 0;
 
 	target_np = spi->dev.of_node;
@@ -963,7 +963,8 @@ static struct s3c64xx_spi_csinfo *s3c64xx_get_target_ctrldata(
 	if (!cs)
 		return ERR_PTR(-ENOMEM);
 
-	data_np = of_get_child_by_name(target_np, "controller-data");
+	struct device_node *data_np __free(device_node) =
+			of_get_child_by_name(target_np, "controller-data");
 	if (!data_np) {
 		dev_info(&spi->dev, "feedback delay set to default (0)\n");
 		return cs;
@@ -971,7 +972,6 @@ static struct s3c64xx_spi_csinfo *s3c64xx_get_target_ctrldata(
 
 	of_property_read_u32(data_np, "samsung,spi-feedback-delay", &fb_delay);
 	cs->fb_delay = fb_delay;
-	of_node_put(data_np);
 	return cs;
 }
 
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index 11d8bd27b3e9..2ee6755b43f5 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -206,7 +206,8 @@ static int sun4i_spi_transfer_one(struct spi_controller *host,
 				  struct spi_transfer *tfr)
 {
 	struct sun4i_spi *sspi = spi_controller_get_devdata(host);
-	unsigned int mclk_rate, div, timeout;
+	unsigned int mclk_rate, div;
+	unsigned long time_left;
 	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
@@ -327,10 +328,10 @@ static int sun4i_spi_transfer_one(struct spi_controller *host,
 
 	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
 	start = jiffies;
-	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(tx_time));
+	time_left = wait_for_completion_timeout(&sspi->done,
+						msecs_to_jiffies(tx_time));
 	end = jiffies;
-	if (!timeout) {
+	if (!time_left) {
 		dev_warn(&host->dev,
 			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
 			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index cd018ea1abf1..5c26bf056293 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -277,7 +277,8 @@ static int sun6i_spi_transfer_one(struct spi_controller *host,
 				  struct spi_transfer *tfr)
 {
 	struct sun6i_spi *sspi = spi_controller_get_devdata(host);
-	unsigned int div, div_cdr1, div_cdr2, timeout;
+	unsigned int div, div_cdr1, div_cdr2;
+	unsigned long time_left;
 	unsigned int start, end, tx_time;
 	unsigned int trig_level;
 	unsigned int tx_len = 0, rx_len = 0, nbits = 0;
@@ -488,26 +489,26 @@ static int sun6i_spi_transfer_one(struct spi_controller *host,
 
 	tx_time = spi_controller_xfer_timeout(host, tfr);
 	start = jiffies;
-	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(tx_time));
+	time_left = wait_for_completion_timeout(&sspi->done,
+						msecs_to_jiffies(tx_time));
 
 	if (!use_dma) {
 		sun6i_spi_drain_fifo(sspi);
 	} else {
-		if (timeout && rx_len) {
+		if (time_left && rx_len) {
 			/*
 			 * Even though RX on the peripheral side has finished
 			 * RX DMA might still be in flight
 			 */
-			timeout = wait_for_completion_timeout(&sspi->dma_rx_done,
-							      timeout);
-			if (!timeout)
+			time_left = wait_for_completion_timeout(&sspi->dma_rx_done,
+								time_left);
+			if (!time_left)
 				dev_warn(&host->dev, "RX DMA timeout\n");
 		}
 	}
 
 	end = jiffies;
-	if (!timeout) {
+	if (!time_left) {
 		dev_warn(&host->dev,
 			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
 			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
diff --git a/drivers/spi/spi-xlp.c b/drivers/spi/spi-xlp.c
index 49302364b7bd..2fec18b68449 100644
--- a/drivers/spi/spi-xlp.c
+++ b/drivers/spi/spi-xlp.c
@@ -270,7 +270,7 @@ static int xlp_spi_xfer_block(struct  xlp_spi_priv *xs,
 		const unsigned char *tx_buf,
 		unsigned char *rx_buf, int xfer_len, int cmd_cont)
 {
-	int timeout;
+	unsigned long time_left;
 	u32 intr_mask = 0;
 
 	xs->tx_buf = tx_buf;
@@ -299,11 +299,11 @@ static int xlp_spi_xfer_block(struct  xlp_spi_priv *xs,
 	intr_mask |= XLP_SPI_INTR_DONE;
 	xlp_spi_reg_write(xs, xs->cs, XLP_SPI_INTR_EN, intr_mask);
 
-	timeout = wait_for_completion_timeout(&xs->done,
-				msecs_to_jiffies(1000));
+	time_left = wait_for_completion_timeout(&xs->done,
+						msecs_to_jiffies(1000));
 	/* Disable interrupts */
 	xlp_spi_reg_write(xs, xs->cs, XLP_SPI_INTR_EN, 0x0);
-	if (!timeout) {
+	if (!time_left) {
 		dev_err(&xs->dev, "xfer timedout!\n");
 		goto out;
 	}
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index a2c467d9e92f..f94420858c22 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -312,7 +312,7 @@ static const struct attribute_group *spi_master_groups[] = {
 
 static void spi_statistics_add_transfer_stats(struct spi_statistics __percpu *pcpu_stats,
 					      struct spi_transfer *xfer,
-					      struct spi_controller *ctlr)
+					      struct spi_message *msg)
 {
 	int l2len = min(fls(xfer->len), SPI_STATISTICS_HISTO_SIZE) - 1;
 	struct spi_statistics *stats;
@@ -328,11 +328,9 @@ static void spi_statistics_add_transfer_stats(struct spi_statistics __percpu *pc
 	u64_stats_inc(&stats->transfer_bytes_histo[l2len]);
 
 	u64_stats_add(&stats->bytes, xfer->len);
-	if ((xfer->tx_buf) &&
-	    (xfer->tx_buf != ctlr->dummy_tx))
+	if (spi_valid_txbuf(msg, xfer))
 		u64_stats_add(&stats->bytes_tx, xfer->len);
-	if ((xfer->rx_buf) &&
-	    (xfer->rx_buf != ctlr->dummy_rx))
+	if (spi_valid_rxbuf(msg, xfer))
 		u64_stats_add(&stats->bytes_rx, xfer->len);
 
 	u64_stats_update_end(&stats->syncp);
@@ -597,10 +595,16 @@ EXPORT_SYMBOL_GPL(spi_alloc_device);
 
 static void spi_dev_set_name(struct spi_device *spi)
 {
-	struct acpi_device *adev = ACPI_COMPANION(&spi->dev);
+	struct device *dev = &spi->dev;
+	struct fwnode_handle *fwnode = dev_fwnode(dev);
 
-	if (adev) {
-		dev_set_name(&spi->dev, "spi-%s", acpi_dev_name(adev));
+	if (is_acpi_device_node(fwnode)) {
+		dev_set_name(dev, "spi-%s", acpi_dev_name(to_acpi_device_node(fwnode)));
+		return;
+	}
+
+	if (is_software_node(fwnode)) {
+		dev_set_name(dev, "spi-%pfwP", fwnode);
 		return;
 	}
 
@@ -822,14 +826,10 @@ struct spi_device *spi_new_device(struct spi_controller *ctlr,
 	proxy->controller_data = chip->controller_data;
 	proxy->controller_state = NULL;
 	/*
-	 * spi->chip_select[i] gives the corresponding physical CS for logical CS i
-	 * logical CS number is represented by setting the ith bit in spi->cs_index_mask
-	 * So, for example, if spi->cs_index_mask = 0x01 then logical CS number is 0 and
-	 * spi->chip_select[0] will give the physical CS.
-	 * By default spi->chip_select[0] will hold the physical CS number so, set
-	 * spi->cs_index_mask as 0x01.
+	 * By default spi->chip_select[0] will hold the physical CS number,
+	 * so set bit 0 in spi->cs_index_mask.
 	 */
-	proxy->cs_index_mask = 0x01;
+	proxy->cs_index_mask = BIT(0);
 
 	if (chip->swnode) {
 		status = device_add_software_node(&proxy->dev, chip->swnode);
@@ -1022,20 +1022,45 @@ static void spi_res_release(struct spi_controller *ctlr, struct spi_message *mes
 }
 
 /*-------------------------------------------------------------------------*/
+#define spi_for_each_valid_cs(spi, idx)				\
+	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++)		\
+		if (!(spi->cs_index_mask & BIT(idx))) {} else
+
 static inline bool spi_is_last_cs(struct spi_device *spi)
 {
 	u8 idx;
 	bool last = false;
 
-	for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
-		if (spi->cs_index_mask & BIT(idx)) {
-			if (spi->controller->last_cs[idx] == spi_get_chipselect(spi, idx))
-				last = true;
-		}
+	spi_for_each_valid_cs(spi, idx) {
+		if (spi->controller->last_cs[idx] == spi_get_chipselect(spi, idx))
+			last = true;
 	}
 	return last;
 }
 
+static void spi_toggle_csgpiod(struct spi_device *spi, u8 idx, bool enable, bool activate)
+{
+	/*
+	 * Historically ACPI has no means of the GPIO polarity and
+	 * thus the SPISerialBus() resource defines it on the per-chip
+	 * basis. In order to avoid a chain of negations, the GPIO
+	 * polarity is considered being Active High. Even for the cases
+	 * when _DSD() is involved (in the updated versions of ACPI)
+	 * the GPIO CS polarity must be defined Active High to avoid
+	 * ambiguity. That's why we use enable, that takes SPI_CS_HIGH
+	 * into account.
+	 */
+	if (has_acpi_companion(&spi->dev))
+		gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx), !enable);
+	else
+		/* Polarity handled by GPIO library */
+		gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx), activate);
+
+	if (activate)
+		spi_delay_exec(&spi->cs_setup, NULL);
+	else
+		spi_delay_exec(&spi->cs_inactive, NULL);
+}
 
 static void spi_set_cs(struct spi_device *spi, bool enable, bool force)
 {
@@ -1072,31 +1097,9 @@ static void spi_set_cs(struct spi_device *spi, bool enable, bool force)
 
 	if (spi_is_csgpiod(spi)) {
 		if (!(spi->mode & SPI_NO_CS)) {
-			/*
-			 * Historically ACPI has no means of the GPIO polarity and
-			 * thus the SPISerialBus() resource defines it on the per-chip
-			 * basis. In order to avoid a chain of negations, the GPIO
-			 * polarity is considered being Active High. Even for the cases
-			 * when _DSD() is involved (in the updated versions of ACPI)
-			 * the GPIO CS polarity must be defined Active High to avoid
-			 * ambiguity. That's why we use enable, that takes SPI_CS_HIGH
-			 * into account.
-			 */
-			for (idx = 0; idx < SPI_CS_CNT_MAX; idx++) {
-				if ((spi->cs_index_mask & BIT(idx)) && spi_get_csgpiod(spi, idx)) {
-					if (has_acpi_companion(&spi->dev))
-						gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx),
-									 !enable);
-					else
-						/* Polarity handled by GPIO library */
-						gpiod_set_value_cansleep(spi_get_csgpiod(spi, idx),
-									 activate);
-
-					if (activate)
-						spi_delay_exec(&spi->cs_setup, NULL);
-					else
-						spi_delay_exec(&spi->cs_inactive, NULL);
-				}
+			spi_for_each_valid_cs(spi, idx) {
+				if (spi_get_csgpiod(spi, idx))
+					spi_toggle_csgpiod(spi, idx, enable, activate);
 			}
 		}
 		/* Some SPI masters need both GPIO CS & slave_select */
@@ -1205,12 +1208,10 @@ static void spi_unmap_buf_attrs(struct spi_controller *ctlr,
 				enum dma_data_direction dir,
 				unsigned long attrs)
 {
-	if (sgt->orig_nents) {
-		dma_unmap_sgtable(dev, sgt, dir, attrs);
-		sg_free_table(sgt);
-		sgt->orig_nents = 0;
-		sgt->nents = 0;
-	}
+	dma_unmap_sgtable(dev, sgt, dir, attrs);
+	sg_free_table(sgt);
+	sgt->orig_nents = 0;
+	sgt->nents = 0;
 }
 
 void spi_unmap_buf(struct spi_controller *ctlr, struct device *dev,
@@ -1242,6 +1243,7 @@ static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 	else
 		rx_dev = ctlr->dev.parent;
 
+	ret = -ENOMSG;
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		/* The sync is done before each transfer. */
 		unsigned long attrs = DMA_ATTR_SKIP_CPU_SYNC;
@@ -1271,6 +1273,9 @@ static int __spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 			}
 		}
 	}
+	/* No transfer has been mapped, bail out with success */
+	if (ret)
+		return 0;
 
 	ctlr->cur_rx_dma_dev = rx_dev;
 	ctlr->cur_tx_dma_dev = tx_dev;
@@ -1306,7 +1311,7 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg)
 	return 0;
 }
 
-static void spi_dma_sync_for_device(struct spi_controller *ctlr,
+static void spi_dma_sync_for_device(struct spi_controller *ctlr, struct spi_message *msg,
 				    struct spi_transfer *xfer)
 {
 	struct device *rx_dev = ctlr->cur_rx_dma_dev;
@@ -1315,13 +1320,14 @@ static void spi_dma_sync_for_device(struct spi_controller *ctlr,
 	if (!ctlr->cur_msg_mapped)
 		return;
 
-	if (xfer->tx_sg.orig_nents)
-		dma_sync_sgtable_for_device(tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
-	if (xfer->rx_sg.orig_nents)
-		dma_sync_sgtable_for_device(rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
+	if (!ctlr->can_dma(ctlr, msg->spi, xfer))
+		return;
+
+	dma_sync_sgtable_for_device(tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
+	dma_sync_sgtable_for_device(rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
 }
 
-static void spi_dma_sync_for_cpu(struct spi_controller *ctlr,
+static void spi_dma_sync_for_cpu(struct spi_controller *ctlr, struct spi_message *msg,
 				 struct spi_transfer *xfer)
 {
 	struct device *rx_dev = ctlr->cur_rx_dma_dev;
@@ -1330,10 +1336,11 @@ static void spi_dma_sync_for_cpu(struct spi_controller *ctlr,
 	if (!ctlr->cur_msg_mapped)
 		return;
 
-	if (xfer->rx_sg.orig_nents)
-		dma_sync_sgtable_for_cpu(rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
-	if (xfer->tx_sg.orig_nents)
-		dma_sync_sgtable_for_cpu(tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
+	if (!ctlr->can_dma(ctlr, msg->spi, xfer))
+		return;
+
+	dma_sync_sgtable_for_cpu(rx_dev, &xfer->rx_sg, DMA_FROM_DEVICE);
+	dma_sync_sgtable_for_cpu(tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
 }
 #else /* !CONFIG_HAS_DMA */
 static inline int __spi_map_msg(struct spi_controller *ctlr,
@@ -1349,11 +1356,13 @@ static inline int __spi_unmap_msg(struct spi_controller *ctlr,
 }
 
 static void spi_dma_sync_for_device(struct spi_controller *ctrl,
+				    struct spi_message *msg,
 				    struct spi_transfer *xfer)
 {
 }
 
 static void spi_dma_sync_for_cpu(struct spi_controller *ctrl,
+				 struct spi_message *msg,
 				 struct spi_transfer *xfer)
 {
 }
@@ -1613,8 +1622,8 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		trace_spi_transfer_start(msg, xfer);
 
-		spi_statistics_add_transfer_stats(statm, xfer, ctlr);
-		spi_statistics_add_transfer_stats(stats, xfer, ctlr);
+		spi_statistics_add_transfer_stats(statm, xfer, msg);
+		spi_statistics_add_transfer_stats(stats, xfer, msg);
 
 		if (!ctlr->ptp_sts_supported) {
 			xfer->ptp_sts_word_pre = 0;
@@ -1625,10 +1634,10 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 			reinit_completion(&ctlr->xfer_completion);
 
 fallback_pio:
-			spi_dma_sync_for_device(ctlr, xfer);
+			spi_dma_sync_for_device(ctlr, msg, xfer);
 			ret = ctlr->transfer_one(ctlr, msg->spi, xfer);
 			if (ret < 0) {
-				spi_dma_sync_for_cpu(ctlr, xfer);
+				spi_dma_sync_for_cpu(ctlr, msg, xfer);
 
 				if (ctlr->cur_msg_mapped &&
 				   (xfer->error & SPI_TRANS_FAIL_NO_START)) {
@@ -1653,7 +1662,7 @@ fallback_pio:
 					msg->status = ret;
 			}
 
-			spi_dma_sync_for_cpu(ctlr, xfer);
+			spi_dma_sync_for_cpu(ctlr, msg, xfer);
 		} else {
 			if (xfer->len)
 				dev_err(&msg->spi->dev,
@@ -3709,9 +3718,6 @@ static int __spi_split_transfer_maxsize(struct spi_controller *ctlr,
 	 * to the same values as *xferp, so tx_buf, rx_buf and len
 	 * are all identical (as well as most others)
 	 * so we just have to fix up len and the pointers.
-	 *
-	 * This also includes support for the depreciated
-	 * spi_message.is_dma_mapped interface.
 	 */
 
 	/*
@@ -3725,12 +3731,8 @@ static int __spi_split_transfer_maxsize(struct spi_controller *ctlr,
 		/* Update rx_buf, tx_buf and DMA */
 		if (xfers[i].rx_buf)
 			xfers[i].rx_buf += offset;
-		if (xfers[i].rx_dma)
-			xfers[i].rx_dma += offset;
 		if (xfers[i].tx_buf)
 			xfers[i].tx_buf += offset;
-		if (xfers[i].tx_dma)
-			xfers[i].tx_dma += offset;
 
 		/* Update length */
 		xfers[i].len = min(maxsize, xfers[i].len - offset);
diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h
index 6c75c8bd44a0..832a60c2e0b9 100644
--- a/include/linux/gpio/property.h
+++ b/include/linux/gpio/property.h
@@ -5,7 +5,11 @@
 #include <dt-bindings/gpio/gpio.h> /* for GPIO_* flags */
 #include <linux/property.h>
 
+struct software_node;
+
 #define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \
 	PROPERTY_ENTRY_REF(_name_, _chip_node_, _idx_, _flags_)
 
+extern const struct software_node swnode_gpio_undefined;
+
 #endif /* __LINUX_GPIO_PROPERTY_H */
diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h
index 3b400b1919a9..9e3c15b4ac91 100644
--- a/include/linux/platform_data/spi-omap2-mcspi.h
+++ b/include/linux/platform_data/spi-omap2-mcspi.h
@@ -16,9 +16,6 @@ struct omap2_mcspi_platform_config {
 
 struct omap2_mcspi_device_config {
 	unsigned turbo_mode:1;
-
-	/* toggle chip select after every word */
-	unsigned cs_per_word:1;
 };
 
 #endif
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index cd1973e6ac4b..844a2743ca94 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -217,9 +217,9 @@ enum pxa_ssp_type {
 	PXA27x_SSP,
 	PXA3xx_SSP,
 	PXA168_SSP,
-	MMP2_SSP,
 	PXA910_SSP,
 	CE4100_SSP,
+	MMP2_SSP,
 	MRFLD_SSP,
 	QUARK_X1000_SSP,
 	/* Keep LPSS types sorted with lpss_platforms[] */
diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h
deleted file mode 100644
index ca2cd4e30ead..000000000000
--- a/include/linux/spi/pxa2xx_spi.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2005 Stephen Street / StreetFire Sound Labs
- */
-#ifndef __LINUX_SPI_PXA2XX_SPI_H
-#define __LINUX_SPI_PXA2XX_SPI_H
-
-#include <linux/dmaengine.h>
-#include <linux/types.h>
-
-#include <linux/pxa2xx_ssp.h>
-
-struct dma_chan;
-
-/*
- * The platform data for SSP controller devices
- * (resides in device.platform_data).
- */
-struct pxa2xx_spi_controller {
-	u16 num_chipselect;
-	u8 enable_dma;
-	u8 dma_burst_size;
-	bool is_target;
-
-	/* DMA engine specific config */
-	dma_filter_fn dma_filter;
-	void *tx_param;
-	void *rx_param;
-
-	/* For non-PXA arches */
-	struct ssp_device ssp;
-};
-
-/*
- * The controller specific data for SPI target devices
- * (resides in spi_board_info.controller_data),
- * copied to spi_device.platform_data ... mostly for
- * DMA tuning.
- */
-struct pxa2xx_spi_chip {
-	u8 tx_threshold;
-	u8 tx_hi_threshold;
-	u8 rx_threshold;
-	u8 dma_burst_size;
-	u32 timeout;
-};
-
-#if defined(CONFIG_ARCH_PXA) || defined(CONFIG_ARCH_MMP)
-
-#include <linux/clk.h>
-
-extern void pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_controller *info);
-
-#endif
-
-#endif	/* __LINUX_SPI_PXA2XX_SPI_H */
diff --git a/include/linux/spi/rspi.h b/include/linux/spi/rspi.h
deleted file mode 100644
index dbdfcc7a3db2..000000000000
--- a/include/linux/spi/rspi.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Renesas SPI driver
- *
- * Copyright (C) 2012  Renesas Solutions Corp.
- */
-
-#ifndef __LINUX_SPI_RENESAS_SPI_H__
-#define __LINUX_SPI_RENESAS_SPI_H__
-
-struct rspi_plat_data {
-	unsigned int dma_tx_id;
-	unsigned int dma_rx_id;
-
-	u16 num_chipselect;
-};
-
-#endif
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index c459809efee4..e8e1e798924f 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -453,6 +453,7 @@ extern struct spi_device *spi_new_ancillary_device(struct spi_device *spi, u8 ch
  * @last_cs_mode_high: was (mode & SPI_CS_HIGH) true on the last call to set_cs.
  * @last_cs: the last chip_select that is recorded by set_cs, -1 on non chip
  *           selected
+ * @last_cs_index_mask: bit mask the last chip selects that were used
  * @xfer_completion: used by core transfer_one_message()
  * @busy: message pump is busy
  * @running: message pump is running
@@ -955,8 +956,8 @@ struct spi_res {
  * struct spi_transfer - a read/write buffer pair
  * @tx_buf: data to be written (DMA-safe memory), or NULL
  * @rx_buf: data to be read (DMA-safe memory), or NULL
- * @tx_dma: DMA address of tx_buf, if @spi_message.is_dma_mapped
- * @rx_dma: DMA address of rx_buf, if @spi_message.is_dma_mapped
+ * @tx_dma: DMA address of tx_buf, currently not for client use
+ * @rx_dma: DMA address of rx_buf, currently not for client use
  * @tx_nbits: number of bits used for writing. If 0 the default
  *      (SPI_NBITS_SINGLE) is used.
  * @rx_nbits: number of bits used for reading. If 0 the default
@@ -1066,8 +1067,7 @@ struct spi_transfer {
 	/*
 	 * It's okay if tx_buf == rx_buf (right?).
 	 * For MicroWire, one buffer must be NULL.
-	 * Buffers must work with dma_*map_single() calls, unless
-	 * spi_message.is_dma_mapped reports a pre-existing mapping.
+	 * Buffers must work with dma_*map_single() calls.
 	 */
 	const void	*tx_buf;
 	void		*rx_buf;
@@ -1111,8 +1111,6 @@ struct spi_transfer {
  * struct spi_message - one multi-segment SPI transaction
  * @transfers: list of transfer segments in this transaction
  * @spi: SPI device to which the transaction is queued
- * @is_dma_mapped: if true, the caller provided both DMA and CPU virtual
- *	addresses for each transfer buffer
  * @pre_optimized: peripheral driver pre-optimized the message
  * @optimized: the message is in the optimized state
  * @prepared: spi_prepare_message was called for the this message
@@ -1146,8 +1144,6 @@ struct spi_message {
 
 	struct spi_device	*spi;
 
-	unsigned		is_dma_mapped:1;
-
 	/* spi_optimize_message() was called for this message */
 	bool			pre_optimized;
 	/* __spi_optimize_message() was called for this message */
diff --git a/include/linux/spi/xilinx_spi.h b/include/linux/spi/xilinx_spi.h
index 3934ce789d87..1b8d984668b6 100644
--- a/include/linux/spi/xilinx_spi.h
+++ b/include/linux/spi/xilinx_spi.h
@@ -2,19 +2,23 @@
 #ifndef __LINUX_SPI_XILINX_SPI_H
 #define __LINUX_SPI_XILINX_SPI_H
 
+#include <linux/types.h>
+
+struct spi_board_info;
+
 /**
  * struct xspi_platform_data - Platform data of the Xilinx SPI driver
- * @num_chipselect:	Number of chip select by the IP.
- * @little_endian:	If registers should be accessed little endian or not.
- * @bits_per_word:	Number of bits per word.
  * @devices:		Devices to add when the driver is probed.
  * @num_devices:	Number of devices in the devices array.
+ * @num_chipselect:	Number of chip select by the IP.
+ * @bits_per_word:	Number of bits per word.
+ * @force_irq:		If set, forces QSPI transaction requirements.
  */
 struct xspi_platform_data {
-	u16 num_chipselect;
-	u8 bits_per_word;
 	struct spi_board_info *devices;
 	u8 num_devices;
+	u8 num_chipselect;
+	u8 bits_per_word;
 	bool force_irq;
 };