Merge tag 'mmc-v4.4' of git://git.linaro.org/people/ulf.hansson/mmc

Pull MMC updates from Ulf Hansson:
 "MMC core:
   - Add new API to set VCCQ voltage - mmc_regulator_set_vqmmc()
   - Add new ioctl to allow userspace to send multi commands
   - Wait for card busy signalling before starting SDIO requests
   - Remove MMC_CLKGATE
   - Enable tuning for DDR50 mode
   - Some code clean-up/improvements to mmc pwrseq
   - Use highest priority for eMMC restart handler
   - Add DT bindings for eMMC hardware reset support
   - Extend the mmc_send_tuning() API
   - Improve ios show for debugfs
   - A couple of code optimizations

  MMC host:
   - Some generic OF improvements
   - Various code clean-ups
   - sirf: Add support for DDR50
   - sunxi: Add support for card busy detection
   - mediatek: Use MMC_CAP_RUNTIME_RESUME
   - mediatek: Add support for eMMC HW-reset
   - mediatek: Add support for HS400
   - dw_mmc: Convert to use the new mmc_regulator_set_vqmmc() API
   - dw_mmc: Add external DMA interface support
   - dw_mmc: Some various improvements
   - dw_mmc-rockchip: MMC tuning with the clock phase framework
   - sdhci: Properly clear IRQs during resume
   - sdhci: Enable tuning for DDR50 mode
   - sdhci-of-esdhc: Use IRQ mode for card detection
   - sdhci-of-esdhc: Support both BE and LE host controller
   - sdhci-pci: Build o2micro support in the same module
   - sdhci-pci: Support for new Intel host controllers
   - sdhci-acpi: Support for new Intel host controllers"

* tag 'mmc-v4.4' of git://git.linaro.org/people/ulf.hansson/mmc: (73 commits)
  mmc: dw_mmc: fix the wrong setting for UHS-DDR50 mode
  mmc: dw_mmc: fix the CardThreshold boundary at CardThrCtl register
  mmc: dw_mmc: NULL dereference in error message
  mmc: pwrseq: Use highest priority for eMMC restart handler
  mmc: mediatek: add HS400 support
  mmc: mmc: extend the mmc_send_tuning()
  mmc: mediatek: add implement of ops->hw_reset()
  mmc: mediatek: fix got GPD checksum error interrupt when data transfer
  mmc: mediatek: change the argument "ddr" to "timing"
  mmc: mediatek: make cmd_ints_mask to const
  mmc: dt-bindings: update Mediatek MMC bindings
  mmc: core: Add DT bindings for eMMC hardware reset support
  mmc: omap_hsmmc: Enable omap_hsmmc for Keystone 2
  mmc: sdhci-acpi: Add more ACPI HIDs for Intel controllers
  mmc: sdhci-pci: Add more PCI IDs for Intel controllers
  arm: lpc18xx_defconfig: remove CONFIG_MMC_DW_IDMAC
  arm: hisi_defconfig: remove CONFIG_MMC_DW_IDMAC
  arm: exynos_defconfig: remove CONFIG_MMC_DW_IDMAC
  arc: axs10x_defconfig: remove CONFIG_MMC_DW_IDMAC
  mips: pistachio_defconfig: remove CONFIG_MMC_DW_IDMAC
  ...

67 files changed, 1703 insertions, 910 deletions

diff --git a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
index b7943f3f9995..dedfb02c744a 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
@@ -22,6 +22,8 @@ Optional properties:
   - voltage-ranges : two cells are required, first cell specifies minimum
     slot voltage (mV), second cell specifies maximum slot voltage (mV).
     Several ranges could be specified.
+  - little-endian : If the host controller is little-endian mode, specify
+    this property. The default endian mode is big-endian.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mmc/mmc.txt b/Documentation/devicetree/bindings/mmc/mmc.txt
index 0384fc3f64e8..f693baf87264 100644
--- a/Documentation/devicetree/bindings/mmc/mmc.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc.txt
@@ -37,6 +37,7 @@ Optional properties:
 - sd-uhs-sdr104: SD UHS SDR104 speed is supported
 - sd-uhs-ddr50: SD UHS DDR50 speed is supported
 - cap-power-off-card: powering off the card is safe
+- cap-mmc-hw-reset: eMMC hardware reset is supported
 - cap-sdio-irq: enable SDIO IRQ signalling on this interface
 - full-pwr-cycle: full power cycle of the card is supported
 - mmc-ddr-1_8v: eMMC high-speed DDR mode(1.8V I/O) is supported
diff --git a/Documentation/devicetree/bindings/mmc/mtk-sd.txt b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
index a1adfa495ad3..0120c7f1109c 100644
--- a/Documentation/devicetree/bindings/mmc/mtk-sd.txt
+++ b/Documentation/devicetree/bindings/mmc/mtk-sd.txt
@@ -17,6 +17,11 @@ Required properties:
 - vmmc-supply: power to the Core
 - vqmmc-supply: power to the IO
 
+Optional properties:
+- assigned-clocks: PLL of the source clock
+- assigned-clock-parents: parent of source clock, used for HS400 mode to get 400Mhz source clock
+- hs400-ds-delay: HS400 DS delay setting
+
 Examples:
 mmc0: mmc@11230000 {
 	compatible = "mediatek,mt8173-mmc", "mediatek,mt8135-mmc";
@@ -24,9 +29,13 @@ mmc0: mmc@11230000 {
 	interrupts = <GIC_SPI 39 IRQ_TYPE_LEVEL_LOW>;
 	vmmc-supply = <&mt6397_vemc_3v3_reg>;
 	vqmmc-supply = <&mt6397_vio18_reg>;
-	clocks = <&pericfg CLK_PERI_MSDC30_0>, <&topckgen CLK_TOP_MSDC50_0_H_SEL>;
+	clocks = <&pericfg CLK_PERI_MSDC30_0>,
+	         <&topckgen CLK_TOP_MSDC50_0_H_SEL>;
 	clock-names = "source", "hclk";
 	pinctrl-names = "default", "state_uhs";
 	pinctrl-0 = <&mmc0_pins_default>;
 	pinctrl-1 = <&mmc0_pins_uhs>;
+	assigned-clocks = <&topckgen CLK_TOP_MSDC50_0_SEL>;
+	assigned-clock-parents = <&topckgen CLK_TOP_MSDCPLL_D2>;
+	hs400-ds-delay = <0x14015>;
 };
diff --git a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
index d38942f6c5ae..cae29eb5733d 100644
--- a/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
+++ b/Documentation/devicetree/bindings/mmc/renesas,mmcif.txt
@@ -6,11 +6,12 @@ and the properties used by the MMCIF device.
 
 Required properties:
 
-- compatible: must contain one of the following
+- compatible: should be "renesas,mmcif-<soctype>", "renesas,sh-mmcif" as a
+  fallback. Examples with <soctype> are:
 	- "renesas,mmcif-r8a7740" for the MMCIF found in r8a7740 SoCs
 	- "renesas,mmcif-r8a7790" for the MMCIF found in r8a7790 SoCs
 	- "renesas,mmcif-r8a7791" for the MMCIF found in r8a7791 SoCs
-	- "renesas,sh-mmcif" for the generic MMCIF
+	- "renesas,mmcif-r8a7794" for the MMCIF found in r8a7794 SoCs
 
 - clocks: reference to the functional clock
 
diff --git a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
index c327c2d6f23d..3dc13b68fc3f 100644
--- a/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/rockchip-dw-mshc.txt
@@ -14,6 +14,19 @@ Required Properties:
 							before RK3288
 	- "rockchip,rk3288-dw-mshc": for Rockchip RK3288
 
+Optional Properties:
+* clocks: from common clock binding: if ciu_drive and ciu_sample are
+  specified in clock-names, should contain handles to these clocks.
+
+* clock-names: Apart from the clock-names described in synopsys-dw-mshc.txt
+  two more clocks "ciu-drive" and "ciu-sample" are supported. They are used
+  to control the clock phases, "ciu-sample" is required for tuning high-
+  speed modes.
+
+* rockchip,default-sample-phase: The default phase to set ciu_sample at
+  probing, low speeds or in case where all phases work at tuning time.
+  If not specified 0 deg will be used.
+
 Example:
 
 	rkdwmmc0@12200000 {
diff --git a/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
index 346c6095a615..8636f5ae97e5 100644
--- a/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
+++ b/Documentation/devicetree/bindings/mmc/synopsys-dw-mshc.txt
@@ -75,6 +75,12 @@ Optional properties:
 * vmmc-supply: The phandle to the regulator to use for vmmc.  If this is
   specified we'll defer probe until we can find this regulator.
 
+* dmas: List of DMA specifiers with the controller specific format as described
+  in the generic DMA client binding. Refer to dma.txt for details.
+
+* dma-names: request names for generic DMA client binding. Must be "rx-tx".
+  Refer to dma.txt for details.
+
 Aliases:
 
 - All the MSHC controller nodes should be represented in the aliases node using
@@ -95,6 +101,23 @@ board specific portions as listed below.
 		#size-cells = <0>;
 	};
 
+[board specific internal DMA resources]
+
+	dwmmc0@12200000 {
+		clock-frequency = <400000000>;
+		clock-freq-min-max = <400000 200000000>;
+		num-slots = <1>;
+		broken-cd;
+		fifo-depth = <0x80>;
+		card-detect-delay = <200>;
+		vmmc-supply = <&buck8>;
+		bus-width = <8>;
+		cap-mmc-highspeed;
+		cap-sd-highspeed;
+	};
+
+[board specific generic DMA request binding]
+
 	dwmmc0@12200000 {
 		clock-frequency = <400000000>;
 		clock-freq-min-max = <400000 200000000>;
@@ -106,4 +129,6 @@ board specific portions as listed below.
 		bus-width = <8>;
 		cap-mmc-highspeed;
 		cap-sd-highspeed;
+		dmas = <&pdma 12>;
+		dma-names = "rx-tx";
 	};
diff --git a/Documentation/mmc/mmc-dev-attrs.txt b/Documentation/mmc/mmc-dev-attrs.txt
index 189bab09255a..caa555706f89 100644
--- a/Documentation/mmc/mmc-dev-attrs.txt
+++ b/Documentation/mmc/mmc-dev-attrs.txt
@@ -72,13 +72,3 @@ Note on raw_rpmb_size_mult:
 	"raw_rpmb_size_mult" is a mutliple of 128kB block.
 	RPMB size in byte is calculated by using the following equation:
 	RPMB partition size = 128kB x raw_rpmb_size_mult
-
-SD/MMC/SDIO Clock Gating Attribute
-==================================
-
-Read and write access is provided to following attribute.
-This attribute appears only if CONFIG_MMC_CLKGATE is enabled.
-
-	clkgate_delay	Tune the clock gating delay with desired value in milliseconds.
-
-echo <desired delay> > /sys/class/mmc_host/mmcX/clkgate_delay
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 562dac6a7f78..c92c0ef1e9d2 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -89,7 +89,6 @@ CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
 CONFIG_EXT4_FS=y
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 83a6d8d5cc58..cfac24e0e7b6 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -95,7 +95,6 @@ CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
 CONFIG_EXT4_FS=y
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index f1e1c84e0dda..9922a118a15a 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -96,7 +96,6 @@ CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_EXT3_FS=y
 CONFIG_EXT4_FS=y
diff --git a/arch/arm/boot/dts/rk3288-veyron-sdmmc.dtsi b/arch/arm/boot/dts/rk3288-veyron-sdmmc.dtsi
index b5334ecff13c..fec076eb7aef 100644
--- a/arch/arm/boot/dts/rk3288-veyron-sdmmc.dtsi
+++ b/arch/arm/boot/dts/rk3288-veyron-sdmmc.dtsi
@@ -90,7 +90,7 @@
 	regulators {
 		vccio_sd: LDO_REG4 {
 			regulator-name = "vccio_sd";
-			regulator-min-microvolt = <3300000>;
+			regulator-min-microvolt = <1800000>;
 			regulator-max-microvolt = <3300000>;
 			regulator-state-mem {
 				regulator-off-in-suspend;
@@ -116,7 +116,12 @@
 	cap-sd-highspeed;
 	card-detect-delay = <200>;
 	cd-gpios = <&gpio7 5 GPIO_ACTIVE_LOW>;
+	rockchip,default-sample-phase = <90>;
 	num-slots = <1>;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
 	vmmc-supply = <&vcc33_sd>;
 	vqmmc-supply = <&vccio_sd>;
 };
diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi
index 275c78ccc0f3..860cea0a7613 100644
--- a/arch/arm/boot/dts/rk3288-veyron.dtsi
+++ b/arch/arm/boot/dts/rk3288-veyron.dtsi
@@ -149,7 +149,9 @@
 	broken-cd;
 	bus-width = <8>;
 	cap-mmc-highspeed;
+	rockchip,default-sample-phase = <158>;
 	disable-wp;
+	mmc-hs200-1_8v;
 	mmc-pwrseq = <&emmc_pwrseq>;
 	non-removable;
 	num-slots = <1>;
@@ -355,6 +357,10 @@
 	num-slots = <1>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&sdio0_clk &sdio0_cmd &sdio0_bus4>;
+	sd-uhs-sdr12;
+	sd-uhs-sdr25;
+	sd-uhs-sdr50;
+	sd-uhs-sdr104;
 	vmmc-supply = <&vcc33_sys>;
 	vqmmc-supply = <&vcc18_wl>;
 };
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index 906e938fb6bf..4e7c6b7392af 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -222,8 +222,9 @@
 	sdmmc: dwmmc@ff0c0000 {
 		compatible = "rockchip,rk3288-dw-mshc";
 		clock-freq-min-max = <400000 150000000>;
-		clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>;
-		clock-names = "biu", "ciu";
+		clocks = <&cru HCLK_SDMMC>, <&cru SCLK_SDMMC>,
+			 <&cru SCLK_SDMMC_DRV>, <&cru SCLK_SDMMC_SAMPLE>;
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
 		reg = <0xff0c0000 0x4000>;
@@ -233,8 +234,9 @@
 	sdio0: dwmmc@ff0d0000 {
 		compatible = "rockchip,rk3288-dw-mshc";
 		clock-freq-min-max = <400000 150000000>;
-		clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>;
-		clock-names = "biu", "ciu";
+		clocks = <&cru HCLK_SDIO0>, <&cru SCLK_SDIO0>,
+			 <&cru SCLK_SDIO0_DRV>, <&cru SCLK_SDIO0_SAMPLE>;
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
 		reg = <0xff0d0000 0x4000>;
@@ -244,8 +246,9 @@
 	sdio1: dwmmc@ff0e0000 {
 		compatible = "rockchip,rk3288-dw-mshc";
 		clock-freq-min-max = <400000 150000000>;
-		clocks = <&cru HCLK_SDIO1>, <&cru SCLK_SDIO1>;
-		clock-names = "biu", "ciu";
+		clocks = <&cru HCLK_SDIO1>, <&cru SCLK_SDIO1>,
+			 <&cru SCLK_SDIO1_DRV>, <&cru SCLK_SDIO1_SAMPLE>;
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 		reg = <0xff0e0000 0x4000>;
@@ -255,8 +258,9 @@
 	emmc: dwmmc@ff0f0000 {
 		compatible = "rockchip,rk3288-dw-mshc";
 		clock-freq-min-max = <400000 150000000>;
-		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>;
-		clock-names = "biu", "ciu";
+		clocks = <&cru HCLK_EMMC>, <&cru SCLK_EMMC>,
+			 <&cru SCLK_EMMC_DRV>, <&cru SCLK_EMMC_SAMPLE>;
+		clock-names = "biu", "ciu", "ciu-drive", "ciu-sample";
 		fifo-depth = <0x100>;
 		interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>;
 		reg = <0xff0f0000 0x4000>;
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 1ff2bfa2e183..13ba48c4b03b 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -166,7 +166,6 @@ CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_S3C=y
 CONFIG_MMC_SDHCI_S3C_DMA=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
 CONFIG_MMC_DW_EXYNOS=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_MAX77686=y
diff --git a/arch/arm/configs/hisi_defconfig b/arch/arm/configs/hisi_defconfig
index 5997dbc69822..b2e340b272ee 100644
--- a/arch/arm/configs/hisi_defconfig
+++ b/arch/arm/configs/hisi_defconfig
@@ -69,7 +69,6 @@ CONFIG_NOP_USB_XCEIV=y
 CONFIG_MMC=y
 CONFIG_RTC_CLASS=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
 CONFIG_MMC_DW_PLTFM=y
 CONFIG_RTC_DRV_PL031=y
 CONFIG_DMADEVICES=y
diff --git a/arch/arm/configs/lpc18xx_defconfig b/arch/arm/configs/lpc18xx_defconfig
index 1c47f86c3970..b7e8cdab51f9 100644
--- a/arch/arm/configs/lpc18xx_defconfig
+++ b/arch/arm/configs/lpc18xx_defconfig
@@ -119,7 +119,6 @@ CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_ROOT_HUB_TT=y
 CONFIG_MMC=y
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_PCA9532=y
diff --git a/arch/mips/configs/pistachio_defconfig b/arch/mips/configs/pistachio_defconfig
index 642b50946943..8b7429127a1d 100644
--- a/arch/mips/configs/pistachio_defconfig
+++ b/arch/mips/configs/pistachio_defconfig
@@ -257,7 +257,6 @@ CONFIG_MMC=y
 CONFIG_MMC_BLOCK_MINORS=16
 CONFIG_MMC_TEST=m
 CONFIG_MMC_DW=y
-CONFIG_MMC_DW_IDMAC=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_RTC_CLASS=y
diff --git a/drivers/clk/rockchip/clk-mmc-phase.c b/drivers/clk/rockchip/clk-mmc-phase.c
index 9b613426e968..bc24e5a002e7 100644
--- a/drivers/clk/rockchip/clk-mmc-phase.c
+++ b/drivers/clk/rockchip/clk-mmc-phase.c
@@ -45,8 +45,8 @@ static unsigned long rockchip_mmc_recalc(struct clk_hw *hw,
 #define PSECS_PER_SEC 1000000000000LL
 
 /*
- * Each fine delay is between 40ps-80ps. Assume each fine delay is 60ps to
- * simplify calculations. So 45degs could be anywhere between 33deg and 66deg.
+ * Each fine delay is between 44ps-77ps. Assume each fine delay is 60ps to
+ * simplify calculations. So 45degs could be anywhere between 33deg and 57.8deg.
  */
 #define ROCKCHIP_MMC_DELAY_ELEMENT_PSEC 60
 
@@ -69,7 +69,7 @@ static int rockchip_mmc_get_phase(struct clk_hw *hw)
 
 		delay_num = (raw_value & ROCKCHIP_MMC_DELAYNUM_MASK);
 		delay_num >>= ROCKCHIP_MMC_DELAYNUM_OFFSET;
-		degrees += delay_num * factor / 10000;
+		degrees += DIV_ROUND_CLOSEST(delay_num * factor, 10000);
 	}
 
 	return degrees % 360;
@@ -82,25 +82,41 @@ static int rockchip_mmc_set_phase(struct clk_hw *hw, int degrees)
 	u8 nineties, remainder;
 	u8 delay_num;
 	u32 raw_value;
-	u64 delay;
-
-	/* allow 22 to be 22.5 */
-	degrees++;
-	/* floor to 22.5 increment */
-	degrees -= ((degrees) * 10 % 225) / 10;
+	u32 delay;
 
 	nineties = degrees / 90;
-	/* 22.5 multiples */
-	remainder = (degrees % 90) / 22;
-
-	delay = PSECS_PER_SEC;
-	do_div(delay, rate);
-	/* / 360 / 22.5 */
-	do_div(delay, 16);
-	do_div(delay, ROCKCHIP_MMC_DELAY_ELEMENT_PSEC);
-
+	remainder = (degrees % 90);
+
+	/*
+	 * Due to the inexact nature of the "fine" delay, we might
+	 * actually go non-monotonic.  We don't go _too_ monotonic
+	 * though, so we should be OK.  Here are options of how we may
+	 * work:
+	 *
+	 * Ideally we end up with:
+	 *   1.0, 2.0, ..., 69.0, 70.0, ...,  89.0, 90.0
+	 *
+	 * On one extreme (if delay is actually 44ps):
+	 *   .73, 1.5, ..., 50.6, 51.3, ...,  65.3, 90.0
+	 * The other (if delay is actually 77ps):
+	 *   1.3, 2.6, ..., 88.6. 89.8, ..., 114.0, 90
+	 *
+	 * It's possible we might make a delay that is up to 25
+	 * degrees off from what we think we're making.  That's OK
+	 * though because we should be REALLY far from any bad range.
+	 */
+
+	/*
+	 * Convert to delay; do a little extra work to make sure we
+	 * don't overflow 32-bit / 64-bit numbers.
+	 */
+	delay = 10000000; /* PSECS_PER_SEC / 10000 / 10 */
 	delay *= remainder;
-	delay_num = (u8) min(delay, 255ULL);
+	delay = DIV_ROUND_CLOSEST(delay,
+			(rate / 1000) * 36 *
+				(ROCKCHIP_MMC_DELAY_ELEMENT_PSEC / 10));
+
+	delay_num = (u8) min_t(u32, delay, 255);
 
 	raw_value = delay_num ? ROCKCHIP_MMC_DELAY_SEL : 0;
 	raw_value |= delay_num << ROCKCHIP_MMC_DELAYNUM_OFFSET;
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index c742cfd7674e..23b6c8e8701c 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -387,6 +387,24 @@ out:
 	return ERR_PTR(err);
 }
 
+static int mmc_blk_ioctl_copy_to_user(struct mmc_ioc_cmd __user *ic_ptr,
+				      struct mmc_blk_ioc_data *idata)
+{
+	struct mmc_ioc_cmd *ic = &idata->ic;
+
+	if (copy_to_user(&(ic_ptr->response), ic->response,
+			 sizeof(ic->response)))
+		return -EFAULT;
+
+	if (!idata->ic.write_flag) {
+		if (copy_to_user((void __user *)(unsigned long)ic->data_ptr,
+				 idata->buf, idata->buf_bytes))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
 static int ioctl_rpmb_card_status_poll(struct mmc_card *card, u32 *status,
 				       u32 retries_max)
 {
@@ -447,12 +465,9 @@ out:
 	return err;
 }
 
-static int mmc_blk_ioctl_cmd(struct block_device *bdev,
-	struct mmc_ioc_cmd __user *ic_ptr)
+static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md,
+			       struct mmc_blk_ioc_data *idata)
 {
-	struct mmc_blk_ioc_data *idata;
-	struct mmc_blk_data *md;
-	struct mmc_card *card;
 	struct mmc_command cmd = {0};
 	struct mmc_data data = {0};
 	struct mmc_request mrq = {NULL};
@@ -461,33 +476,12 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
 	int is_rpmb = false;
 	u32 status = 0;
 
-	/*
-	 * The caller must have CAP_SYS_RAWIO, and must be calling this on the
-	 * whole block device, not on a partition.  This prevents overspray
-	 * between sibling partitions.
-	 */
-	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
-		return -EPERM;
-
-	idata = mmc_blk_ioctl_copy_from_user(ic_ptr);
-	if (IS_ERR(idata))
-		return PTR_ERR(idata);
-
-	md = mmc_blk_get(bdev->bd_disk);
-	if (!md) {
-		err = -EINVAL;
-		goto cmd_err;
-	}
+	if (!card || !md || !idata)
+		return -EINVAL;
 
 	if (md->area_type & MMC_BLK_DATA_AREA_RPMB)
 		is_rpmb = true;
 
-	card = md->queue.card;
-	if (IS_ERR(card)) {
-		err = PTR_ERR(card);
-		goto cmd_done;
-	}
-
 	cmd.opcode = idata->ic.opcode;
 	cmd.arg = idata->ic.arg;
 	cmd.flags = idata->ic.flags;
@@ -530,23 +524,21 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
 
 	mrq.cmd = &cmd;
 
-	mmc_get_card(card);
-
 	err = mmc_blk_part_switch(card, md);
 	if (err)
-		goto cmd_rel_host;
+		return err;
 
 	if (idata->ic.is_acmd) {
 		err = mmc_app_cmd(card->host, card);
 		if (err)
-			goto cmd_rel_host;
+			return err;
 	}
 
 	if (is_rpmb) {
 		err = mmc_set_blockcount(card, data.blocks,
 			idata->ic.write_flag & (1 << 31));
 		if (err)
-			goto cmd_rel_host;
+			return err;
 	}
 
 	if ((MMC_EXTRACT_INDEX_FROM_ARG(cmd.arg) == EXT_CSD_SANITIZE_START) &&
@@ -557,7 +549,7 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
 			pr_err("%s: ioctl_do_sanitize() failed. err = %d",
 			       __func__, err);
 
-		goto cmd_rel_host;
+		return err;
 	}
 
 	mmc_wait_for_req(card->host, &mrq);
@@ -565,14 +557,12 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
 	if (cmd.error) {
 		dev_err(mmc_dev(card->host), "%s: cmd error %d\n",
 						__func__, cmd.error);
-		err = cmd.error;
-		goto cmd_rel_host;
+		return cmd.error;
 	}
 	if (data.error) {
 		dev_err(mmc_dev(card->host), "%s: data error %d\n",
 						__func__, data.error);
-		err = data.error;
-		goto cmd_rel_host;
+		return data.error;
 	}
 
 	/*
@@ -582,18 +572,7 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
 	if (idata->ic.postsleep_min_us)
 		usleep_range(idata->ic.postsleep_min_us, idata->ic.postsleep_max_us);
 
-	if (copy_to_user(&(ic_ptr->response), cmd.resp, sizeof(cmd.resp))) {
-		err = -EFAULT;
-		goto cmd_rel_host;
-	}
-
-	if (!idata->ic.write_flag) {
-		if (copy_to_user((void __user *)(unsigned long) idata->ic.data_ptr,
-						idata->buf, idata->buf_bytes)) {
-			err = -EFAULT;
-			goto cmd_rel_host;
-		}
-	}
+	memcpy(&(idata->ic.response), cmd.resp, sizeof(cmd.resp));
 
 	if (is_rpmb) {
 		/*
@@ -607,24 +586,132 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev,
 					__func__, status, err);
 	}
 
-cmd_rel_host:
+	return err;
+}
+
+static int mmc_blk_ioctl_cmd(struct block_device *bdev,
+			     struct mmc_ioc_cmd __user *ic_ptr)
+{
+	struct mmc_blk_ioc_data *idata;
+	struct mmc_blk_data *md;
+	struct mmc_card *card;
+	int err = 0, ioc_err = 0;
+
+	idata = mmc_blk_ioctl_copy_from_user(ic_ptr);
+	if (IS_ERR(idata))
+		return PTR_ERR(idata);
+
+	md = mmc_blk_get(bdev->bd_disk);
+	if (!md) {
+		err = -EINVAL;
+		goto cmd_err;
+	}
+
+	card = md->queue.card;
+	if (IS_ERR(card)) {
+		err = PTR_ERR(card);
+		goto cmd_done;
+	}
+
+	mmc_get_card(card);
+
+	ioc_err = __mmc_blk_ioctl_cmd(card, md, idata);
+
 	mmc_put_card(card);
 
+	err = mmc_blk_ioctl_copy_to_user(ic_ptr, idata);
+
 cmd_done:
 	mmc_blk_put(md);
 cmd_err:
 	kfree(idata->buf);
 	kfree(idata);
-	return err;
+	return ioc_err ? ioc_err : err;
+}
+
+static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev,
+				   struct mmc_ioc_multi_cmd __user *user)
+{
+	struct mmc_blk_ioc_data **idata = NULL;
+	struct mmc_ioc_cmd __user *cmds = user->cmds;
+	struct mmc_card *card;
+	struct mmc_blk_data *md;
+	int i, err = 0, ioc_err = 0;
+	__u64 num_of_cmds;
+
+	if (copy_from_user(&num_of_cmds, &user->num_of_cmds,
+			   sizeof(num_of_cmds)))
+		return -EFAULT;
+
+	if (num_of_cmds > MMC_IOC_MAX_CMDS)
+		return -EINVAL;
+
+	idata = kcalloc(num_of_cmds, sizeof(*idata), GFP_KERNEL);
+	if (!idata)
+		return -ENOMEM;
+
+	for (i = 0; i < num_of_cmds; i++) {
+		idata[i] = mmc_blk_ioctl_copy_from_user(&cmds[i]);
+		if (IS_ERR(idata[i])) {
+			err = PTR_ERR(idata[i]);
+			num_of_cmds = i;
+			goto cmd_err;
+		}
+	}
+
+	md = mmc_blk_get(bdev->bd_disk);
+	if (!md)
+		goto cmd_err;
+
+	card = md->queue.card;
+	if (IS_ERR(card)) {
+		err = PTR_ERR(card);
+		goto cmd_done;
+	}
+
+	mmc_get_card(card);
+
+	for (i = 0; i < num_of_cmds && !ioc_err; i++)
+		ioc_err = __mmc_blk_ioctl_cmd(card, md, idata[i]);
+
+	mmc_put_card(card);
+
+	/* copy to user if data and response */
+	for (i = 0; i < num_of_cmds && !err; i++)
+		err = mmc_blk_ioctl_copy_to_user(&cmds[i], idata[i]);
+
+cmd_done:
+	mmc_blk_put(md);
+cmd_err:
+	for (i = 0; i < num_of_cmds; i++) {
+		kfree(idata[i]->buf);
+		kfree(idata[i]);
+	}
+	kfree(idata);
+	return ioc_err ? ioc_err : err;
 }
 
 static int mmc_blk_ioctl(struct block_device *bdev, fmode_t mode,
 	unsigned int cmd, unsigned long arg)
 {
-	int ret = -EINVAL;
-	if (cmd == MMC_IOC_CMD)
-		ret = mmc_blk_ioctl_cmd(bdev, (struct mmc_ioc_cmd __user *)arg);
-	return ret;
+	/*
+	 * The caller must have CAP_SYS_RAWIO, and must be calling this on the
+	 * whole block device, not on a partition.  This prevents overspray
+	 * between sibling partitions.
+	 */
+	if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains))
+		return -EPERM;
+
+	switch (cmd) {
+	case MMC_IOC_CMD:
+		return mmc_blk_ioctl_cmd(bdev,
+				(struct mmc_ioc_cmd __user *)arg);
+	case MMC_IOC_MULTI_CMD:
+		return mmc_blk_ioctl_multi_cmd(bdev,
+				(struct mmc_ioc_multi_cmd __user *)arg);
+	default:
+		return -EINVAL;
+	}
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/drivers/mmc/core/Kconfig b/drivers/mmc/core/Kconfig
index 9ebee72d9c3f..4c33d7690f2f 100644
--- a/drivers/mmc/core/Kconfig
+++ b/drivers/mmc/core/Kconfig
@@ -1,13 +1,3 @@
 #
 # MMC core configuration
 #
-
-config MMC_CLKGATE
-	bool "MMC host clock gating"
-	help
-	  This will attempt to aggressively gate the clock to the MMC card.
-	  This is done to save power due to gating off the logic and bus
-	  noise when the MMC card is not in use. Your host driver has to
-	  support handling this in order for it to be of any use.
-
-	  If unsure, say N.
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index a3eb20bdcd97..5ae89e48fd85 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -187,8 +187,6 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 
 		if (mrq->done)
 			mrq->done(mrq);
-
-		mmc_host_clk_release(host);
 	}
 }
 
@@ -206,6 +204,23 @@ static void __mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 		return;
 	}
 
+	/*
+	 * For sdio rw commands we must wait for card busy otherwise some
+	 * sdio devices won't work properly.
+	 */
+	if (mmc_is_io_op(mrq->cmd->opcode) && host->ops->card_busy) {
+		int tries = 500; /* Wait aprox 500ms at maximum */
+
+		while (host->ops->card_busy(host) && --tries)
+			mmc_delay(1);
+
+		if (tries == 0) {
+			mrq->cmd->error = -EBUSY;
+			mmc_request_done(host, mrq);
+			return;
+		}
+	}
+
 	host->ops->request(host, mrq);
 }
 
@@ -275,7 +290,6 @@ static int mmc_start_request(struct mmc_host *host, struct mmc_request *mrq)
 			mrq->stop->mrq = mrq;
 		}
 	}
-	mmc_host_clk_hold(host);
 	led_trigger_event(host->led, LED_FULL);
 	__mmc_start_request(host, mrq);
 
@@ -525,11 +539,8 @@ static void mmc_wait_for_req_done(struct mmc_host *host,
 static void mmc_pre_req(struct mmc_host *host, struct mmc_request *mrq,
 		 bool is_first_req)
 {
-	if (host->ops->pre_req) {
-		mmc_host_clk_hold(host);
+	if (host->ops->pre_req)
 		host->ops->pre_req(host, mrq, is_first_req);
-		mmc_host_clk_release(host);
-	}
 }
 
 /**
@@ -544,11 +555,8 @@ static void mmc_pre_req(struct mmc_host *host, struct mmc_request *mrq,
 static void mmc_post_req(struct mmc_host *host, struct mmc_request *mrq,
 			 int err)
 {
-	if (host->ops->post_req) {
-		mmc_host_clk_hold(host);
+	if (host->ops->post_req)
 		host->ops->post_req(host, mrq, err);
-		mmc_host_clk_release(host);
-	}
 }
 
 /**
@@ -833,9 +841,9 @@ void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card)
 		unsigned int timeout_us, limit_us;
 
 		timeout_us = data->timeout_ns / 1000;
-		if (mmc_host_clk_rate(card->host))
+		if (card->host->ios.clock)
 			timeout_us += data->timeout_clks * 1000 /
-				(mmc_host_clk_rate(card->host) / 1000);
+				(card->host->ios.clock / 1000);
 
 		if (data->flags & MMC_DATA_WRITE)
 			/*
@@ -1033,8 +1041,6 @@ static inline void mmc_set_ios(struct mmc_host *host)
 		 ios->power_mode, ios->chip_select, ios->vdd,
 		 ios->bus_width, ios->timing);
 
-	if (ios->clock > 0)
-		mmc_set_ungated(host);
 	host->ops->set_ios(host, ios);
 }
 
@@ -1043,17 +1049,15 @@ static inline void mmc_set_ios(struct mmc_host *host)
  */
 void mmc_set_chip_select(struct mmc_host *host, int mode)
 {
-	mmc_host_clk_hold(host);
 	host->ios.chip_select = mode;
 	mmc_set_ios(host);
-	mmc_host_clk_release(host);
 }
 
 /*
  * Sets the host clock to the highest possible frequency that
  * is below "hz".
  */
-static void __mmc_set_clock(struct mmc_host *host, unsigned int hz)
+void mmc_set_clock(struct mmc_host *host, unsigned int hz)
 {
 	WARN_ON(hz && hz < host->f_min);
 
@@ -1064,68 +1068,6 @@ static void __mmc_set_clock(struct mmc_host *host, unsigned int hz)
 	mmc_set_ios(host);
 }
 
-void mmc_set_clock(struct mmc_host *host, unsigned int hz)
-{
-	mmc_host_clk_hold(host);
-	__mmc_set_clock(host, hz);
-	mmc_host_clk_release(host);
-}
-
-#ifdef CONFIG_MMC_CLKGATE
-/*
- * This gates the clock by setting it to 0 Hz.
- */
-void mmc_gate_clock(struct mmc_host *host)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&host->clk_lock, flags);
-	host->clk_old = host->ios.clock;
-	host->ios.clock = 0;
-	host->clk_gated = true;
-	spin_unlock_irqrestore(&host->clk_lock, flags);
-	mmc_set_ios(host);
-}
-
-/*
- * This restores the clock from gating by using the cached
- * clock value.
- */
-void mmc_ungate_clock(struct mmc_host *host)
-{
-	/*
-	 * We should previously have gated the clock, so the clock shall
-	 * be 0 here! The clock may however be 0 during initialization,
-	 * when some request operations are performed before setting
-	 * the frequency. When ungate is requested in that situation
-	 * we just ignore the call.
-	 */
-	if (host->clk_old) {
-		BUG_ON(host->ios.clock);
-		/* This call will also set host->clk_gated to false */
-		__mmc_set_clock(host, host->clk_old);
-	}
-}
-
-void mmc_set_ungated(struct mmc_host *host)
-{
-	unsigned long flags;
-
-	/*
-	 * We've been given a new frequency while the clock is gated,
-	 * so make sure we regard this as ungating it.
-	 */
-	spin_lock_irqsave(&host->clk_lock, flags);
-	host->clk_gated = false;
-	spin_unlock_irqrestore(&host->clk_lock, flags);
-}
-
-#else
-void mmc_set_ungated(struct mmc_host *host)
-{
-}
-#endif
-
 int mmc_execute_tuning(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
@@ -1140,9 +1082,7 @@ int mmc_execute_tuning(struct mmc_card *card)
 	else
 		opcode = MMC_SEND_TUNING_BLOCK;
 
-	mmc_host_clk_hold(host);
 	err = host->ops->execute_tuning(host, opcode);
-	mmc_host_clk_release(host);
 
 	if (err)
 		pr_err("%s: tuning execution failed\n", mmc_hostname(host));
@@ -1157,10 +1097,8 @@ int mmc_execute_tuning(struct mmc_card *card)
  */
 void mmc_set_bus_mode(struct mmc_host *host, unsigned int mode)
 {
-	mmc_host_clk_hold(host);
 	host->ios.bus_mode = mode;
 	mmc_set_ios(host);
-	mmc_host_clk_release(host);
 }
 
 /*
@@ -1168,10 +1106,8 @@ void mmc_set_bus_mode(struct mmc_host *host, unsigned int mode)
  */
 void mmc_set_bus_width(struct mmc_host *host, unsigned int width)
 {
-	mmc_host_clk_hold(host);
 	host->ios.bus_width = width;
 	mmc_set_ios(host);
-	mmc_host_clk_release(host);
 }
 
 /*
@@ -1341,6 +1277,40 @@ struct device_node *mmc_of_find_child_device(struct mmc_host *host,
 #ifdef CONFIG_REGULATOR
 
 /**
+ * mmc_ocrbitnum_to_vdd - Convert a OCR bit number to its voltage
+ * @vdd_bit:	OCR bit number
+ * @min_uV:	minimum voltage value (mV)
+ * @max_uV:	maximum voltage value (mV)
+ *
+ * This function returns the voltage range according to the provided OCR
+ * bit number. If conversion is not possible a negative errno value returned.
+ */
+static int mmc_ocrbitnum_to_vdd(int vdd_bit, int *min_uV, int *max_uV)
+{
+	int		tmp;
+
+	if (!vdd_bit)
+		return -EINVAL;
+
+	/*
+	 * REVISIT mmc_vddrange_to_ocrmask() may have set some
+	 * bits this regulator doesn't quite support ... don't
+	 * be too picky, most cards and regulators are OK with
+	 * a 0.1V range goof (it's a small error percentage).
+	 */
+	tmp = vdd_bit - ilog2(MMC_VDD_165_195);
+	if (tmp == 0) {
+		*min_uV = 1650 * 1000;
+		*max_uV = 1950 * 1000;
+	} else {
+		*min_uV = 1900 * 1000 + tmp * 100 * 1000;
+		*max_uV = *min_uV + 100 * 1000;
+	}
+
+	return 0;
+}
+
+/**
  * mmc_regulator_get_ocrmask - return mask of supported voltages
  * @supply: regulator to use
  *
@@ -1403,22 +1373,7 @@ int mmc_regulator_set_ocr(struct mmc_host *mmc,
 	int			min_uV, max_uV;
 
 	if (vdd_bit) {
-		int		tmp;
-
-		/*
-		 * REVISIT mmc_vddrange_to_ocrmask() may have set some
-		 * bits this regulator doesn't quite support ... don't
-		 * be too picky, most cards and regulators are OK with
-		 * a 0.1V range goof (it's a small error percentage).
-		 */
-		tmp = vdd_bit - ilog2(MMC_VDD_165_195);
-		if (tmp == 0) {
-			min_uV = 1650 * 1000;
-			max_uV = 1950 * 1000;
-		} else {
-			min_uV = 1900 * 1000 + tmp * 100 * 1000;
-			max_uV = min_uV + 100 * 1000;
-		}
+		mmc_ocrbitnum_to_vdd(vdd_bit, &min_uV, &max_uV);
 
 		result = regulator_set_voltage(supply, min_uV, max_uV);
 		if (result == 0 && !mmc->regulator_enabled) {
@@ -1439,6 +1394,84 @@ int mmc_regulator_set_ocr(struct mmc_host *mmc,
 }
 EXPORT_SYMBOL_GPL(mmc_regulator_set_ocr);
 
+static int mmc_regulator_set_voltage_if_supported(struct regulator *regulator,
+						  int min_uV, int target_uV,
+						  int max_uV)
+{
+	/*
+	 * Check if supported first to avoid errors since we may try several
+	 * signal levels during power up and don't want to show errors.
+	 */
+	if (!regulator_is_supported_voltage(regulator, min_uV, max_uV))
+		return -EINVAL;
+
+	return regulator_set_voltage_triplet(regulator, min_uV, target_uV,
+					     max_uV);
+}
+
+/**
+ * mmc_regulator_set_vqmmc - Set VQMMC as per the ios
+ *
+ * For 3.3V signaling, we try to match VQMMC to VMMC as closely as possible.
+ * That will match the behavior of old boards where VQMMC and VMMC were supplied
+ * by the same supply.  The Bus Operating conditions for 3.3V signaling in the
+ * SD card spec also define VQMMC in terms of VMMC.
+ * If this is not possible we'll try the full 2.7-3.6V of the spec.
+ *
+ * For 1.2V and 1.8V signaling we'll try to get as close as possible to the
+ * requested voltage.  This is definitely a good idea for UHS where there's a
+ * separate regulator on the card that's trying to make 1.8V and it's best if
+ * we match.
+ *
+ * This function is expected to be used by a controller's
+ * start_signal_voltage_switch() function.
+ */
+int mmc_regulator_set_vqmmc(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct device *dev = mmc_dev(mmc);
+	int ret, volt, min_uV, max_uV;
+
+	/* If no vqmmc supply then we can't change the voltage */
+	if (IS_ERR(mmc->supply.vqmmc))
+		return -EINVAL;
+
+	switch (ios->signal_voltage) {
+	case MMC_SIGNAL_VOLTAGE_120:
+		return mmc_regulator_set_voltage_if_supported(mmc->supply.vqmmc,
+						1100000, 1200000, 1300000);
+	case MMC_SIGNAL_VOLTAGE_180:
+		return mmc_regulator_set_voltage_if_supported(mmc->supply.vqmmc,
+						1700000, 1800000, 1950000);
+	case MMC_SIGNAL_VOLTAGE_330:
+		ret = mmc_ocrbitnum_to_vdd(mmc->ios.vdd, &volt, &max_uV);
+		if (ret < 0)
+			return ret;
+
+		dev_dbg(dev, "%s: found vmmc voltage range of %d-%duV\n",
+			__func__, volt, max_uV);
+
+		min_uV = max(volt - 300000, 2700000);
+		max_uV = min(max_uV + 200000, 3600000);
+
+		/*
+		 * Due to a limitation in the current implementation of
+		 * regulator_set_voltage_triplet() which is taking the lowest
+		 * voltage possible if below the target, search for a suitable
+		 * voltage in two steps and try to stay close to vmmc
+		 * with a 0.3V tolerance at first.
+		 */
+		if (!mmc_regulator_set_voltage_if_supported(mmc->supply.vqmmc,
+						min_uV, volt, max_uV))
+			return 0;
+
+		return mmc_regulator_set_voltage_if_supported(mmc->supply.vqmmc,
+						2700000, volt, 3600000);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL_GPL(mmc_regulator_set_vqmmc);
+
 #endif /* CONFIG_REGULATOR */
 
 int mmc_regulator_get_supply(struct mmc_host *mmc)
@@ -1515,11 +1548,8 @@ int __mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage)
 	int old_signal_voltage = host->ios.signal_voltage;
 
 	host->ios.signal_voltage = signal_voltage;
-	if (host->ops->start_signal_voltage_switch) {
-		mmc_host_clk_hold(host);
+	if (host->ops->start_signal_voltage_switch)
 		err = host->ops->start_signal_voltage_switch(host, &host->ios);
-		mmc_host_clk_release(host);
-	}
 
 	if (err)
 		host->ios.signal_voltage = old_signal_voltage;
@@ -1553,20 +1583,17 @@ int mmc_set_signal_voltage(struct mmc_host *host, int signal_voltage, u32 ocr)
 		pr_warn("%s: cannot verify signal voltage switch\n",
 			mmc_hostname(host));
 
-	mmc_host_clk_hold(host);
-
 	cmd.opcode = SD_SWITCH_VOLTAGE;
 	cmd.arg = 0;
 	cmd.flags = MMC_RSP_R1 | MMC_CMD_AC;
 
 	err = mmc_wait_for_cmd(host, &cmd, 0);
 	if (err)
-		goto err_command;
+		return err;
+
+	if (!mmc_host_is_spi(host) && (cmd.resp[0] & R1_ERROR))
+		return -EIO;
 
-	if (!mmc_host_is_spi(host) && (cmd.resp[0] & R1_ERROR)) {
-		err = -EIO;
-		goto err_command;
-	}
 	/*
 	 * The card should drive cmd and dat[0:3] low immediately
 	 * after the response of cmd11, but wait 1 ms to be sure
@@ -1615,9 +1642,6 @@ power_cycle:
 		mmc_power_cycle(host, ocr);
 	}
 
-err_command:
-	mmc_host_clk_release(host);
-
 	return err;
 }
 
@@ -1626,10 +1650,8 @@ err_command:
  */
 void mmc_set_timing(struct mmc_host *host, unsigned int timing)
 {
-	mmc_host_clk_hold(host);
 	host->ios.timing = timing;
 	mmc_set_ios(host);
-	mmc_host_clk_release(host);
 }
 
 /*
@@ -1637,10 +1659,8 @@ void mmc_set_timing(struct mmc_host *host, unsigned int timing)
  */
 void mmc_set_driver_type(struct mmc_host *host, unsigned int drv_type)
 {
-	mmc_host_clk_hold(host);
 	host->ios.drv_type = drv_type;
 	mmc_set_ios(host);
-	mmc_host_clk_release(host);
 }
 
 int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
@@ -1648,7 +1668,6 @@ int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
 {
 	struct mmc_host *host = card->host;
 	int host_drv_type = SD_DRIVER_TYPE_B;
-	int drive_strength;
 
 	*drv_type = 0;
 
@@ -1671,14 +1690,10 @@ int mmc_select_drive_strength(struct mmc_card *card, unsigned int max_dtr,
 	 * information and let the hardware specific code
 	 * return what is possible given the options
 	 */
-	mmc_host_clk_hold(host);
-	drive_strength = host->ops->select_drive_strength(card, max_dtr,
-							  host_drv_type,
-							  card_drv_type,
-							  drv_type);
-	mmc_host_clk_release(host);
-
-	return drive_strength;
+	return host->ops->select_drive_strength(card, max_dtr,
+						host_drv_type,
+						card_drv_type,
+						drv_type);
 }
 
 /*
@@ -1697,8 +1712,6 @@ void mmc_power_up(struct mmc_host *host, u32 ocr)
 	if (host->ios.power_mode == MMC_POWER_ON)
 		return;
 
-	mmc_host_clk_hold(host);
-
 	mmc_pwrseq_pre_power_on(host);
 
 	host->ios.vdd = fls(ocr) - 1;
@@ -1732,8 +1745,6 @@ void mmc_power_up(struct mmc_host *host, u32 ocr)
 	 * time required to reach a stable voltage.
 	 */
 	mmc_delay(10);
-
-	mmc_host_clk_release(host);
 }
 
 void mmc_power_off(struct mmc_host *host)
@@ -1741,8 +1752,6 @@ void mmc_power_off(struct mmc_host *host)
 	if (host->ios.power_mode == MMC_POWER_OFF)
 		return;
 
-	mmc_host_clk_hold(host);
-
 	mmc_pwrseq_power_off(host);
 
 	host->ios.clock = 0;
@@ -1758,8 +1767,6 @@ void mmc_power_off(struct mmc_host *host)
 	 * can be successfully turned on again.
 	 */
 	mmc_delay(1);
-
-	mmc_host_clk_release(host);
 }
 
 void mmc_power_cycle(struct mmc_host *host, u32 ocr)
@@ -1975,7 +1982,7 @@ static unsigned int mmc_mmc_erase_timeout(struct mmc_card *card,
 		 */
 		timeout_clks <<= 1;
 		timeout_us += (timeout_clks * 1000) /
-			      (mmc_host_clk_rate(card->host) / 1000);
+			      (card->host->ios.clock / 1000);
 
 		erase_timeout = timeout_us / 1000;
 
@@ -2423,9 +2430,7 @@ static void mmc_hw_reset_for_init(struct mmc_host *host)
 {
 	if (!(host->caps & MMC_CAP_HW_RESET) || !host->ops->hw_reset)
 		return;
-	mmc_host_clk_hold(host);
 	host->ops->hw_reset(host);
-	mmc_host_clk_release(host);
 }
 
 int mmc_hw_reset(struct mmc_host *host)
@@ -2633,10 +2638,14 @@ void mmc_start_host(struct mmc_host *host)
 	host->f_init = max(freqs[0], host->f_min);
 	host->rescan_disable = 0;
 	host->ios.power_mode = MMC_POWER_UNDEFINED;
+
+	mmc_claim_host(host);
 	if (host->caps2 & MMC_CAP2_NO_PRESCAN_POWERUP)
 		mmc_power_off(host);
 	else
 		mmc_power_up(host, host->ocr_avail);
+	mmc_release_host(host);
+
 	mmc_gpiod_request_cd_irq(host);
 	_mmc_detect_change(host, 0, false);
 }
@@ -2674,7 +2683,9 @@ void mmc_stop_host(struct mmc_host *host)
 
 	BUG_ON(host->card);
 
+	mmc_claim_host(host);
 	mmc_power_off(host);
+	mmc_release_host(host);
 }
 
 int mmc_power_save_host(struct mmc_host *host)
diff --git a/drivers/mmc/core/core.h b/drivers/mmc/core/core.h
index 1a22a82209b2..09241e56d628 100644
--- a/drivers/mmc/core/core.h
+++ b/drivers/mmc/core/core.h
@@ -40,9 +40,6 @@ void mmc_init_erase(struct mmc_card *card);
 
 void mmc_set_chip_select(struct mmc_host *host, int mode);
 void mmc_set_clock(struct mmc_host *host, unsigned int hz);
-void mmc_gate_clock(struct mmc_host *host);
-void mmc_ungate_clock(struct mmc_host *host);
-void mmc_set_ungated(struct mmc_host *host);
 void mmc_set_bus_mode(struct mmc_host *host, unsigned int mode);
 void mmc_set_bus_width(struct mmc_host *host, unsigned int width);
 u32 mmc_select_voltage(struct mmc_host *host, u32 ocr);
diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c
index e9142108a6c6..154aced0b91b 100644
--- a/drivers/mmc/core/debugfs.c
+++ b/drivers/mmc/core/debugfs.c
@@ -126,6 +126,12 @@ static int mmc_ios_show(struct seq_file *s, void *data)
 	case MMC_TIMING_SD_HS:
 		str = "sd high-speed";
 		break;
+	case MMC_TIMING_UHS_SDR12:
+		str = "sd uhs SDR12";
+		break;
+	case MMC_TIMING_UHS_SDR25:
+		str = "sd uhs SDR25";
+		break;
 	case MMC_TIMING_UHS_SDR50:
 		str = "sd uhs SDR50";
 		break;
@@ -166,6 +172,25 @@ static int mmc_ios_show(struct seq_file *s, void *data)
 	}
 	seq_printf(s, "signal voltage:\t%u (%s)\n", ios->chip_select, str);
 
+	switch (ios->drv_type) {
+	case MMC_SET_DRIVER_TYPE_A:
+		str = "driver type A";
+		break;
+	case MMC_SET_DRIVER_TYPE_B:
+		str = "driver type B";
+		break;
+	case MMC_SET_DRIVER_TYPE_C:
+		str = "driver type C";
+		break;
+	case MMC_SET_DRIVER_TYPE_D:
+		str = "driver type D";
+		break;
+	default:
+		str = "invalid";
+		break;
+	}
+	seq_printf(s, "driver type:\t%u (%s)\n", ios->drv_type, str);
+
 	return 0;
 }
 
@@ -230,11 +255,6 @@ void mmc_add_host_debugfs(struct mmc_host *host)
 			&mmc_clock_fops))
 		goto err_node;
 
-#ifdef CONFIG_MMC_CLKGATE
-	if (!debugfs_create_u32("clk_delay", (S_IRUSR | S_IWUSR),
-				root, &host->clk_delay))
-		goto err_node;
-#endif
 #ifdef CONFIG_FAIL_MMC_REQUEST
 	if (fail_request)
 		setup_fault_attr(&fail_default_attr, fail_request);
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 5466f25f0281..da950c44204d 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -61,246 +61,6 @@ void mmc_unregister_host_class(void)
 	class_unregister(&mmc_host_class);
 }
 
-#ifdef CONFIG_MMC_CLKGATE
-static ssize_t clkgate_delay_show(struct device *dev,
-		struct device_attribute *attr, char *buf)
-{
-	struct mmc_host *host = cls_dev_to_mmc_host(dev);
-	return snprintf(buf, PAGE_SIZE, "%lu\n", host->clkgate_delay);
-}
-
-static ssize_t clkgate_delay_store(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
-{
-	struct mmc_host *host = cls_dev_to_mmc_host(dev);
-	unsigned long flags, value;
-
-	if (kstrtoul(buf, 0, &value))
-		return -EINVAL;
-
-	spin_lock_irqsave(&host->clk_lock, flags);
-	host->clkgate_delay = value;
-	spin_unlock_irqrestore(&host->clk_lock, flags);
-	return count;
-}
-
-/*
- * Enabling clock gating will make the core call out to the host
- * once up and once down when it performs a request or card operation
- * intermingled in any fashion. The driver will see this through
- * set_ios() operations with ios.clock field set to 0 to gate (disable)
- * the block clock, and to the old frequency to enable it again.
- */
-static void mmc_host_clk_gate_delayed(struct mmc_host *host)
-{
-	unsigned long tick_ns;
-	unsigned long freq = host->ios.clock;
-	unsigned long flags;
-
-	if (!freq) {
-		pr_debug("%s: frequency set to 0 in disable function, "
-			 "this means the clock is already disabled.\n",
-			 mmc_hostname(host));
-		return;
-	}
-	/*
-	 * New requests may have appeared while we were scheduling,
-	 * then there is no reason to delay the check before
-	 * clk_disable().
-	 */
-	spin_lock_irqsave(&host->clk_lock, flags);
-
-	/*
-	 * Delay n bus cycles (at least 8 from MMC spec) before attempting
-	 * to disable the MCI block clock. The reference count may have
-	 * gone up again after this delay due to rescheduling!
-	 */
-	if (!host->clk_requests) {
-		spin_unlock_irqrestore(&host->clk_lock, flags);
-		tick_ns = DIV_ROUND_UP(1000000000, freq);
-		ndelay(host->clk_delay * tick_ns);
-	} else {
-		/* New users appeared while waiting for this work */
-		spin_unlock_irqrestore(&host->clk_lock, flags);
-		return;
-	}
-	mutex_lock(&host->clk_gate_mutex);
-	spin_lock_irqsave(&host->clk_lock, flags);
-	if (!host->clk_requests) {
-		spin_unlock_irqrestore(&host->clk_lock, flags);
-		/* This will set host->ios.clock to 0 */
-		mmc_gate_clock(host);
-		spin_lock_irqsave(&host->clk_lock, flags);
-		pr_debug("%s: gated MCI clock\n", mmc_hostname(host));
-	}
-	spin_unlock_irqrestore(&host->clk_lock, flags);
-	mutex_unlock(&host->clk_gate_mutex);
-}
-
-/*
- * Internal work. Work to disable the clock at some later point.
- */
-static void mmc_host_clk_gate_work(struct work_struct *work)
-{
-	struct mmc_host *host = container_of(work, struct mmc_host,
-					      clk_gate_work.work);
-
-	mmc_host_clk_gate_delayed(host);
-}
-
-/**
- *	mmc_host_clk_hold - ungate hardware MCI clocks
- *	@host: host to ungate.
- *
- *	Makes sure the host ios.clock is restored to a non-zero value
- *	past this call.	Increase clock reference count and ungate clock
- *	if we're the first user.
- */
-void mmc_host_clk_hold(struct mmc_host *host)
-{
-	unsigned long flags;
-
-	/* cancel any clock gating work scheduled by mmc_host_clk_release() */
-	cancel_delayed_work_sync(&host->clk_gate_work);
-	mutex_lock(&host->clk_gate_mutex);
-	spin_lock_irqsave(&host->clk_lock, flags);
-	if (host->clk_gated) {
-		spin_unlock_irqrestore(&host->clk_lock, flags);
-		mmc_ungate_clock(host);
-		spin_lock_irqsave(&host->clk_lock, flags);
-		pr_debug("%s: ungated MCI clock\n", mmc_hostname(host));
-	}
-	host->clk_requests++;
-	spin_unlock_irqrestore(&host->clk_lock, flags);
-	mutex_unlock(&host->clk_gate_mutex);
-}
-
-/**
- *	mmc_host_may_gate_card - check if this card may be gated
- *	@card: card to check.
- */
-static bool mmc_host_may_gate_card(struct mmc_card *card)
-{
-	/* If there is no card we may gate it */
-	if (!card)
-		return true;
-	/*
-	 * Don't gate SDIO cards! These need to be clocked at all times
-	 * since they may be independent systems generating interrupts
-	 * and other events. The clock requests counter from the core will
-	 * go down to zero since the core does not need it, but we will not
-	 * gate the clock, because there is somebody out there that may still
-	 * be using it.
-	 */
-	return !(card->quirks & MMC_QUIRK_BROKEN_CLK_GATING);
-}
-
-/**
- *	mmc_host_clk_release - gate off hardware MCI clocks
- *	@host: host to gate.
- *
- *	Calls the host driver with ios.clock set to zero as often as possible
- *	in order to gate off hardware MCI clocks. Decrease clock reference
- *	count and schedule disabling of clock.
- */
-void mmc_host_clk_release(struct mmc_host *host)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&host->clk_lock, flags);
-	host->clk_requests--;
-	if (mmc_host_may_gate_card(host->card) &&
-	    !host->clk_requests)
-		schedule_delayed_work(&host->clk_gate_work,
-				      msecs_to_jiffies(host->clkgate_delay));
-	spin_unlock_irqrestore(&host->clk_lock, flags);
-}
-
-/**
- *	mmc_host_clk_rate - get current clock frequency setting
- *	@host: host to get the clock frequency for.
- *
- *	Returns current clock frequency regardless of gating.
- */
-unsigned int mmc_host_clk_rate(struct mmc_host *host)
-{
-	unsigned long freq;
-	unsigned long flags;
-
-	spin_lock_irqsave(&host->clk_lock, flags);
-	if (host->clk_gated)
-		freq = host->clk_old;
-	else
-		freq = host->ios.clock;
-	spin_unlock_irqrestore(&host->clk_lock, flags);
-	return freq;
-}
-
-/**
- *	mmc_host_clk_init - set up clock gating code
- *	@host: host with potential clock to control
- */
-static inline void mmc_host_clk_init(struct mmc_host *host)
-{
-	host->clk_requests = 0;
-	/* Hold MCI clock for 8 cycles by default */
-	host->clk_delay = 8;
-	/*
-	 * Default clock gating delay is 0ms to avoid wasting power.
-	 * This value can be tuned by writing into sysfs entry.
-	 */
-	host->clkgate_delay = 0;
-	host->clk_gated = false;
-	INIT_DELAYED_WORK(&host->clk_gate_work, mmc_host_clk_gate_work);
-	spin_lock_init(&host->clk_lock);
-	mutex_init(&host->clk_gate_mutex);
-}
-
-/**
- *	mmc_host_clk_exit - shut down clock gating code
- *	@host: host with potential clock to control
- */
-static inline void mmc_host_clk_exit(struct mmc_host *host)
-{
-	/*
-	 * Wait for any outstanding gate and then make sure we're
-	 * ungated before exiting.
-	 */
-	if (cancel_delayed_work_sync(&host->clk_gate_work))
-		mmc_host_clk_gate_delayed(host);
-	if (host->clk_gated)
-		mmc_host_clk_hold(host);
-	/* There should be only one user now */
-	WARN_ON(host->clk_requests > 1);
-}
-
-static inline void mmc_host_clk_sysfs_init(struct mmc_host *host)
-{
-	host->clkgate_delay_attr.show = clkgate_delay_show;
-	host->clkgate_delay_attr.store = clkgate_delay_store;
-	sysfs_attr_init(&host->clkgate_delay_attr.attr);
-	host->clkgate_delay_attr.attr.name = "clkgate_delay";
-	host->clkgate_delay_attr.attr.mode = S_IRUGO | S_IWUSR;
-	if (device_create_file(&host->class_dev, &host->clkgate_delay_attr))
-		pr_err("%s: Failed to create clkgate_delay sysfs entry\n",
-				mmc_hostname(host));
-}
-#else
-
-static inline void mmc_host_clk_init(struct mmc_host *host)
-{
-}
-
-static inline void mmc_host_clk_exit(struct mmc_host *host)
-{
-}
-
-static inline void mmc_host_clk_sysfs_init(struct mmc_host *host)
-{
-}
-
-#endif
-
 void mmc_retune_enable(struct mmc_host *host)
 {
 	host->can_retune = 1;
@@ -507,6 +267,8 @@ int mmc_of_parse(struct mmc_host *host)
 		host->caps |= MMC_CAP_UHS_DDR50;
 	if (of_property_read_bool(np, "cap-power-off-card"))
 		host->caps |= MMC_CAP_POWER_OFF_CARD;
+	if (of_property_read_bool(np, "cap-mmc-hw-reset"))
+		host->caps |= MMC_CAP_HW_RESET;
 	if (of_property_read_bool(np, "cap-sdio-irq"))
 		host->caps |= MMC_CAP_SDIO_IRQ;
 	if (of_property_read_bool(np, "full-pwr-cycle"))
@@ -583,8 +345,6 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
 		return NULL;
 	}
 
-	mmc_host_clk_init(host);
-
 	spin_lock_init(&host->lock);
 	init_waitqueue_head(&host->wq);
 	INIT_DELAYED_WORK(&host->detect, mmc_rescan);
@@ -633,7 +393,6 @@ int mmc_add_host(struct mmc_host *host)
 #ifdef CONFIG_DEBUG_FS
 	mmc_add_host_debugfs(host);
 #endif
-	mmc_host_clk_sysfs_init(host);
 
 	mmc_start_host(host);
 	register_pm_notifier(&host->pm_notify);
@@ -663,8 +422,6 @@ void mmc_remove_host(struct mmc_host *host)
 	device_del(&host->class_dev);
 
 	led_trigger_unregister_simple(host->led);
-
-	mmc_host_clk_exit(host);
 }
 
 EXPORT_SYMBOL(mmc_remove_host);
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index f6cd995dbe92..c793fda27321 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1931,14 +1931,12 @@ static int mmc_reset(struct mmc_host *host)
 	if (!mmc_can_reset(card))
 		return -EOPNOTSUPP;
 
-	mmc_host_clk_hold(host);
 	mmc_set_clock(host, host->f_init);
 
 	host->ops->hw_reset(host);
 
 	/* Set initial state and call mmc_set_ios */
 	mmc_set_initial_state(host);
-	mmc_host_clk_release(host);
 
 	return mmc_init_card(host, card->ocr, card);
 }
@@ -2006,14 +2004,13 @@ int mmc_attach_mmc(struct mmc_host *host)
 
 	mmc_release_host(host);
 	err = mmc_add_card(host->card);
-	mmc_claim_host(host);
 	if (err)
 		goto remove_card;
 
+	mmc_claim_host(host);
 	return 0;
 
 remove_card:
-	mmc_release_host(host);
 	mmc_remove_card(host->card);
 	mmc_claim_host(host);
 	host->card = NULL;
diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c
index 0e9ae1c276c8..1f444269ebbe 100644
--- a/drivers/mmc/core/mmc_ops.c
+++ b/drivers/mmc/core/mmc_ops.c
@@ -579,7 +579,6 @@ out:
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(__mmc_switch);
 
 int mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 		unsigned int timeout_ms)
@@ -589,7 +588,7 @@ int mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
 }
 EXPORT_SYMBOL_GPL(mmc_switch);
 
-int mmc_send_tuning(struct mmc_host *host)
+int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error)
 {
 	struct mmc_request mrq = {NULL};
 	struct mmc_command cmd = {0};
@@ -599,16 +598,13 @@ int mmc_send_tuning(struct mmc_host *host)
 	const u8 *tuning_block_pattern;
 	int size, err = 0;
 	u8 *data_buf;
-	u32 opcode;
 
 	if (ios->bus_width == MMC_BUS_WIDTH_8) {
 		tuning_block_pattern = tuning_blk_pattern_8bit;
 		size = sizeof(tuning_blk_pattern_8bit);
-		opcode = MMC_SEND_TUNING_BLOCK_HS200;
 	} else if (ios->bus_width == MMC_BUS_WIDTH_4) {
 		tuning_block_pattern = tuning_blk_pattern_4bit;
 		size = sizeof(tuning_blk_pattern_4bit);
-		opcode = MMC_SEND_TUNING_BLOCK;
 	} else
 		return -EINVAL;
 
@@ -639,6 +635,9 @@ int mmc_send_tuning(struct mmc_host *host)
 
 	mmc_wait_for_req(host, &mrq);
 
+	if (cmd_error)
+		*cmd_error = cmd.error;
+
 	if (cmd.error) {
 		err = cmd.error;
 		goto out;
diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h
index f498f9ae21f0..f1b8e81aaa28 100644
--- a/drivers/mmc/core/mmc_ops.h
+++ b/drivers/mmc/core/mmc_ops.h
@@ -28,6 +28,9 @@ int mmc_bus_test(struct mmc_card *card, u8 bus_width);
 int mmc_send_hpi_cmd(struct mmc_card *card, u32 *status);
 int mmc_can_ext_csd(struct mmc_card *card);
 int mmc_switch_status_error(struct mmc_host *host, u32 status);
+int __mmc_switch(struct mmc_card *card, u8 set, u8 index, u8 value,
+		unsigned int timeout_ms, bool use_busy_signal, bool send_status,
+		bool ignore_crc);
 
 #endif
 
diff --git a/drivers/mmc/core/pwrseq_emmc.c b/drivers/mmc/core/pwrseq_emmc.c
index 9d6d2fb21796..ad4f94ec7e8d 100644
--- a/drivers/mmc/core/pwrseq_emmc.c
+++ b/drivers/mmc/core/pwrseq_emmc.c
@@ -76,7 +76,7 @@ struct mmc_pwrseq *mmc_pwrseq_emmc_alloc(struct mmc_host *host,
 	if (!pwrseq)
 		return ERR_PTR(-ENOMEM);
 
-	pwrseq->reset_gpio = gpiod_get_index(dev, "reset", 0, GPIOD_OUT_LOW);
+	pwrseq->reset_gpio = gpiod_get(dev, "reset", GPIOD_OUT_LOW);
 	if (IS_ERR(pwrseq->reset_gpio)) {
 		ret = PTR_ERR(pwrseq->reset_gpio);
 		goto free;
@@ -84,11 +84,11 @@ struct mmc_pwrseq *mmc_pwrseq_emmc_alloc(struct mmc_host *host,
 
 	/*
 	 * register reset handler to ensure emmc reset also from
-	 * emergency_reboot(), priority 129 schedules it just before
-	 * system reboot
+	 * emergency_reboot(), priority 255 is the highest priority
+	 * so it will be executed before any system reboot handler.
 	 */
 	pwrseq->reset_nb.notifier_call = mmc_pwrseq_emmc_reset_nb;
-	pwrseq->reset_nb.priority = 129;
+	pwrseq->reset_nb.priority = 255;
 	register_restart_handler(&pwrseq->reset_nb);
 
 	pwrseq->pwrseq.ops = &mmc_pwrseq_emmc_ops;
diff --git a/drivers/mmc/core/pwrseq_simple.c b/drivers/mmc/core/pwrseq_simple.c
index 0b14b83a53d6..d10538bb5e07 100644
--- a/drivers/mmc/core/pwrseq_simple.c
+++ b/drivers/mmc/core/pwrseq_simple.c
@@ -23,18 +23,21 @@ struct mmc_pwrseq_simple {
 	struct mmc_pwrseq pwrseq;
 	bool clk_enabled;
 	struct clk *ext_clk;
-	int nr_gpios;
-	struct gpio_desc *reset_gpios[0];
+	struct gpio_descs *reset_gpios;
 };
 
 static void mmc_pwrseq_simple_set_gpios_value(struct mmc_pwrseq_simple *pwrseq,
 					      int value)
 {
 	int i;
+	struct gpio_descs *reset_gpios = pwrseq->reset_gpios;
+	int values[reset_gpios->ndescs];
 
-	for (i = 0; i < pwrseq->nr_gpios; i++)
-		if (!IS_ERR(pwrseq->reset_gpios[i]))
-			gpiod_set_value_cansleep(pwrseq->reset_gpios[i], value);
+	for (i = 0; i < reset_gpios->ndescs; i++)
+		values[i] = value;
+
+	gpiod_set_array_value_cansleep(reset_gpios->ndescs, reset_gpios->desc,
+				       values);
 }
 
 static void mmc_pwrseq_simple_pre_power_on(struct mmc_host *host)
@@ -75,11 +78,8 @@ static void mmc_pwrseq_simple_free(struct mmc_host *host)
 {
 	struct mmc_pwrseq_simple *pwrseq = container_of(host->pwrseq,
 					struct mmc_pwrseq_simple, pwrseq);
-	int i;
 
-	for (i = 0; i < pwrseq->nr_gpios; i++)
-		if (!IS_ERR(pwrseq->reset_gpios[i]))
-			gpiod_put(pwrseq->reset_gpios[i]);
+	gpiod_put_array(pwrseq->reset_gpios);
 
 	if (!IS_ERR(pwrseq->ext_clk))
 		clk_put(pwrseq->ext_clk);
@@ -98,14 +98,9 @@ struct mmc_pwrseq *mmc_pwrseq_simple_alloc(struct mmc_host *host,
 					   struct device *dev)
 {
 	struct mmc_pwrseq_simple *pwrseq;
-	int i, nr_gpios, ret = 0;
-
-	nr_gpios = of_gpio_named_count(dev->of_node, "reset-gpios");
-	if (nr_gpios < 0)
-		nr_gpios = 0;
+	int ret = 0;
 
-	pwrseq = kzalloc(sizeof(struct mmc_pwrseq_simple) + nr_gpios *
-			 sizeof(struct gpio_desc *), GFP_KERNEL);
+	pwrseq = kzalloc(sizeof(*pwrseq), GFP_KERNEL);
 	if (!pwrseq)
 		return ERR_PTR(-ENOMEM);
 
@@ -116,22 +111,12 @@ struct mmc_pwrseq *mmc_pwrseq_simple_alloc(struct mmc_host *host,
 		goto free;
 	}
 
-	for (i = 0; i < nr_gpios; i++) {
-		pwrseq->reset_gpios[i] = gpiod_get_index(dev, "reset", i,
-							 GPIOD_OUT_HIGH);
-		if (IS_ERR(pwrseq->reset_gpios[i]) &&
-		    PTR_ERR(pwrseq->reset_gpios[i]) != -ENOENT &&
-		    PTR_ERR(pwrseq->reset_gpios[i]) != -ENOSYS) {
-			ret = PTR_ERR(pwrseq->reset_gpios[i]);
-
-			while (i--)
-				gpiod_put(pwrseq->reset_gpios[i]);
-
-			goto clk_put;
-		}
+	pwrseq->reset_gpios = gpiod_get_array(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(pwrseq->reset_gpios)) {
+		ret = PTR_ERR(pwrseq->reset_gpios);
+		goto clk_put;
 	}
 
-	pwrseq->nr_gpios = nr_gpios;
 	pwrseq->pwrseq.ops = &mmc_pwrseq_simple_ops;
 
 	return &pwrseq->pwrseq;
diff --git a/drivers/mmc/core/quirks.c b/drivers/mmc/core/quirks.c
index dd1d1e0fe322..fad660b95809 100644
--- a/drivers/mmc/core/quirks.c
+++ b/drivers/mmc/core/quirks.c
@@ -35,25 +35,7 @@
 #define SDIO_DEVICE_ID_MARVELL_8797_F0	0x9128
 #endif
 
-/*
- * This hook just adds a quirk for all sdio devices
- */
-static void add_quirk_for_sdio_devices(struct mmc_card *card, int data)
-{
-	if (mmc_card_sdio(card))
-		card->quirks |= data;
-}
-
 static const struct mmc_fixup mmc_fixup_methods[] = {
-	/* by default sdio devices are considered CLK_GATING broken */
-	/* good cards will be whitelisted as they are tested */
-	SDIO_FIXUP(SDIO_ANY_ID, SDIO_ANY_ID,
-		   add_quirk_for_sdio_devices,
-		   MMC_QUIRK_BROKEN_CLK_GATING),
-
-	SDIO_FIXUP(SDIO_VENDOR_ID_TI, SDIO_DEVICE_ID_TI_WL1271,
-		   remove_quirk, MMC_QUIRK_BROKEN_CLK_GATING),
-
 	SDIO_FIXUP(SDIO_VENDOR_ID_TI, SDIO_DEVICE_ID_TI_WL1271,
 		   add_quirk, MMC_QUIRK_NONSTD_FUNC_IF),
 
diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
index 4e7366ab187f..141eaa923e18 100644
--- a/drivers/mmc/core/sd.c
+++ b/drivers/mmc/core/sd.c
@@ -357,8 +357,6 @@ int mmc_sd_switch_hs(struct mmc_card *card)
 	if (card->sw_caps.hs_max_dtr == 0)
 		return 0;
 
-	err = -EIO;
-
 	status = kmalloc(64, GFP_KERNEL);
 	if (!status) {
 		pr_err("%s: could not allocate a buffer for "
@@ -628,9 +626,25 @@ static int mmc_sd_init_uhs_card(struct mmc_card *card)
 	 * SDR104 mode SD-cards. Note that tuning is mandatory for SDR104.
 	 */
 	if (!mmc_host_is_spi(card->host) &&
-	    (card->sd_bus_speed == UHS_SDR50_BUS_SPEED ||
-	     card->sd_bus_speed == UHS_SDR104_BUS_SPEED))
+		(card->sd_bus_speed == UHS_SDR50_BUS_SPEED ||
+		 card->sd_bus_speed == UHS_DDR50_BUS_SPEED ||
+		 card->sd_bus_speed == UHS_SDR104_BUS_SPEED)) {
 		err = mmc_execute_tuning(card);
+
+		/*
+		 * As SD Specifications Part1 Physical Layer Specification
+		 * Version 3.01 says, CMD19 tuning is available for unlocked
+		 * cards in transfer state of 1.8V signaling mode. The small
+		 * difference between v3.00 and 3.01 spec means that CMD19
+		 * tuning is also available for DDR50 mode.
+		 */
+		if (err && card->sd_bus_speed == UHS_DDR50_BUS_SPEED) {
+			pr_warn("%s: ddr50 tuning failed\n",
+				mmc_hostname(card->host));
+			err = 0;
+		}
+	}
+
 out:
 	kfree(status);
 
@@ -786,9 +800,7 @@ static int mmc_sd_get_ro(struct mmc_host *host)
 	if (!host->ops->get_ro)
 		return -1;
 
-	mmc_host_clk_hold(host);
 	ro = host->ops->get_ro(host);
-	mmc_host_clk_release(host);
 
 	return ro;
 }
@@ -1231,14 +1243,13 @@ int mmc_attach_sd(struct mmc_host *host)
 
 	mmc_release_host(host);
 	err = mmc_add_card(host->card);
-	mmc_claim_host(host);
 	if (err)
 		goto remove_card;
 
+	mmc_claim_host(host);
 	return 0;
 
 remove_card:
-	mmc_release_host(host);
 	mmc_remove_card(host->card);
 	host->card = NULL;
 	mmc_claim_host(host);
diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c
index b91abedcfdca..16d838e6d623 100644
--- a/drivers/mmc/core/sdio.c
+++ b/drivers/mmc/core/sdio.c
@@ -897,11 +897,10 @@ static int mmc_sdio_pre_suspend(struct mmc_host *host)
  */
 static int mmc_sdio_suspend(struct mmc_host *host)
 {
-	if (mmc_card_keep_power(host) && mmc_card_wake_sdio_irq(host)) {
-		mmc_claim_host(host);
+	mmc_claim_host(host);
+
+	if (mmc_card_keep_power(host) && mmc_card_wake_sdio_irq(host))
 		sdio_disable_wide(host->card);
-		mmc_release_host(host);
-	}
 
 	if (!mmc_card_keep_power(host)) {
 		mmc_power_off(host);
@@ -910,6 +909,8 @@ static int mmc_sdio_suspend(struct mmc_host *host)
 		mmc_retune_needed(host);
 	}
 
+	mmc_release_host(host);
+
 	return 0;
 }
 
@@ -955,13 +956,10 @@ static int mmc_sdio_resume(struct mmc_host *host)
 	}
 
 	if (!err && host->sdio_irqs) {
-		if (!(host->caps2 & MMC_CAP2_SDIO_IRQ_NOTHREAD)) {
+		if (!(host->caps2 & MMC_CAP2_SDIO_IRQ_NOTHREAD))
 			wake_up_process(host->sdio_irq_thread);
-		} else if (host->caps & MMC_CAP_SDIO_IRQ) {
-			mmc_host_clk_hold(host);
+		else if (host->caps & MMC_CAP_SDIO_IRQ)
 			host->ops->enable_sdio_irq(host, 1);
-			mmc_host_clk_release(host);
-		}
 	}
 
 	mmc_release_host(host);
@@ -1018,15 +1016,24 @@ out:
 static int mmc_sdio_runtime_suspend(struct mmc_host *host)
 {
 	/* No references to the card, cut the power to it. */
+	mmc_claim_host(host);
 	mmc_power_off(host);
+	mmc_release_host(host);
+
 	return 0;
 }
 
 static int mmc_sdio_runtime_resume(struct mmc_host *host)
 {
+	int ret;
+
 	/* Restore power and re-initialize. */
+	mmc_claim_host(host);
 	mmc_power_up(host, host->card->ocr);
-	return mmc_sdio_power_restore(host);
+	ret = mmc_sdio_power_restore(host);
+	mmc_release_host(host);
+
+	return ret;
 }
 
 static int mmc_sdio_reset(struct mmc_host *host)
diff --git a/drivers/mmc/core/sdio_irq.c b/drivers/mmc/core/sdio_irq.c
index 09cc67d028f0..91bbbfb29f3f 100644
--- a/drivers/mmc/core/sdio_irq.c
+++ b/drivers/mmc/core/sdio_irq.c
@@ -168,21 +168,15 @@ static int sdio_irq_thread(void *_host)
 		}
 
 		set_current_state(TASK_INTERRUPTIBLE);
-		if (host->caps & MMC_CAP_SDIO_IRQ) {
-			mmc_host_clk_hold(host);
+		if (host->caps & MMC_CAP_SDIO_IRQ)
 			host->ops->enable_sdio_irq(host, 1);
-			mmc_host_clk_release(host);
-		}
 		if (!kthread_should_stop())
 			schedule_timeout(period);
 		set_current_state(TASK_RUNNING);
 	} while (!kthread_should_stop());
 
-	if (host->caps & MMC_CAP_SDIO_IRQ) {
-		mmc_host_clk_hold(host);
+	if (host->caps & MMC_CAP_SDIO_IRQ)
 		host->ops->enable_sdio_irq(host, 0);
-		mmc_host_clk_release(host);
-	}
 
 	pr_debug("%s: IRQ thread exiting with code %d\n",
 		 mmc_hostname(host), ret);
@@ -208,9 +202,7 @@ static int sdio_card_irq_get(struct mmc_card *card)
 				return err;
 			}
 		} else if (host->caps & MMC_CAP_SDIO_IRQ) {
-			mmc_host_clk_hold(host);
 			host->ops->enable_sdio_irq(host, 1);
-			mmc_host_clk_release(host);
 		}
 	}
 
@@ -229,9 +221,7 @@ static int sdio_card_irq_put(struct mmc_card *card)
 			atomic_set(&host->sdio_irq_thread_abort, 1);
 			kthread_stop(host->sdio_irq_thread);
 		} else if (host->caps & MMC_CAP_SDIO_IRQ) {
-			mmc_host_clk_hold(host);
 			host->ops->enable_sdio_irq(host, 0);
-			mmc_host_clk_release(host);
 		}
 	}
 
diff --git a/drivers/mmc/core/sdio_ops.h b/drivers/mmc/core/sdio_ops.h
index 12a4d3ab174c..5660c7f459e9 100644
--- a/drivers/mmc/core/sdio_ops.h
+++ b/drivers/mmc/core/sdio_ops.h
@@ -12,6 +12,8 @@
 #ifndef _MMC_SDIO_OPS_H
 #define _MMC_SDIO_OPS_H
 
+#include <linux/mmc/sdio.h>
+
 int mmc_send_io_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr);
 int mmc_io_rw_direct(struct mmc_card *card, int write, unsigned fn,
 	unsigned addr, u8 in, u8* out);
@@ -19,5 +21,10 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 	unsigned addr, int incr_addr, u8 *buf, unsigned blocks, unsigned blksz);
 int sdio_reset(struct mmc_host *host);
 
+static inline bool mmc_is_io_op(u32 opcode)
+{
+	return opcode == SD_IO_RW_DIRECT || opcode == SD_IO_RW_EXTENDED;
+}
+
 #endif
 
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 8a1e3498261e..af71de5fda3b 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -67,7 +67,7 @@ config MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER
 	  has the effect of scrambling the addresses and formats of data
 	  accessed in sizes other than the datum size.
 
-	  This is the case for the Freescale eSDHC and Nintendo Wii SDHCI.
+	  This is the case for the Nintendo Wii SDHCI.
 
 config MMC_SDHCI_PCI
 	tristate "SDHCI support on PCI bus"
@@ -140,8 +140,8 @@ config MMC_SDHCI_OF_AT91
 config MMC_SDHCI_OF_ESDHC
 	tristate "SDHCI OF support for the Freescale eSDHC controller"
 	depends on MMC_SDHCI_PLTFM
-	depends on PPC
-	select MMC_SDHCI_BIG_ENDIAN_32BIT_BYTE_SWAPPER
+	depends on PPC || ARCH_MXC || ARCH_LAYERSCAPE
+	select MMC_SDHCI_IO_ACCESSORS
 	help
 	  This selects the Freescale eSDHC controller support.
 
@@ -366,7 +366,7 @@ config MMC_OMAP
 config MMC_OMAP_HS
 	tristate "TI OMAP High Speed Multimedia Card Interface support"
 	depends on HAS_DMA
-	depends on ARCH_OMAP2PLUS || COMPILE_TEST
+	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
 	help
 	  This selects the TI OMAP High Speed Multimedia card Interface.
 	  If you have an omap2plus board with a Multimedia Card slot,
@@ -473,7 +473,7 @@ config MMC_DAVINCI
 
 config MMC_GOLDFISH
 	tristate "goldfish qemu Multimedia Card Interface support"
-	depends on GOLDFISH
+	depends on GOLDFISH || COMPILE_TEST
 	help
 	  This selects the Goldfish Multimedia card Interface emulation
 	  found on the Goldfish Android virtual device emulation.
@@ -615,15 +615,7 @@ config MMC_DW
 	help
 	  This selects support for the Synopsys DesignWare Mobile Storage IP
 	  block, this provides host support for SD and MMC interfaces, in both
-	  PIO and external DMA modes.
-
-config MMC_DW_IDMAC
-	bool "Internal DMAC interface"
-	depends on MMC_DW
-	help
-	  This selects support for the internal DMAC block within the Synopsys
-	  Designware Mobile Storage IP block. This disables the external DMA
-	  interface.
+	  PIO, internal DMA mode and external DMA mode.
 
 config MMC_DW_PLTFM
 	tristate "Synopsys Designware MCI Support as platform device"
@@ -652,7 +644,6 @@ config MMC_DW_K3
 	tristate "K3 specific extensions for Synopsys DW Memory Card Interface"
 	depends on MMC_DW
 	select MMC_DW_PLTFM
-	select MMC_DW_IDMAC
 	help
 	  This selects support for Hisilicon K3 SoC specific extensions to the
 	  Synopsys DesignWare Memory Card Interface driver. Select this option
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index 4f3452afa6ca..3595f83e89dd 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -9,8 +9,8 @@ obj-$(CONFIG_MMC_MXC)		+= mxcmmc.o
 obj-$(CONFIG_MMC_MXS)		+= mxs-mmc.o
 obj-$(CONFIG_MMC_SDHCI)		+= sdhci.o
 obj-$(CONFIG_MMC_SDHCI_PCI)	+= sdhci-pci.o
+sdhci-pci-y			+= sdhci-pci-core.o sdhci-pci-o2micro.o
 obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI))	+= sdhci-pci-data.o
-obj-$(subst m,y,$(CONFIG_MMC_SDHCI_PCI))	+= sdhci-pci-o2micro.o
 obj-$(CONFIG_MMC_SDHCI_ACPI)	+= sdhci-acpi.o
 obj-$(CONFIG_MMC_SDHCI_PXAV3)	+= sdhci-pxav3.o
 obj-$(CONFIG_MMC_SDHCI_PXAV2)	+= sdhci-pxav2.o
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index 1e75309898b7..3a7e835a0033 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -446,7 +446,7 @@ out:
 	return loc;
 }
 
-static int dw_mci_exynos_execute_tuning(struct dw_mci_slot *slot)
+static int dw_mci_exynos_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
 {
 	struct dw_mci *host = slot->host;
 	struct dw_mci_exynos_priv_data *priv = host->priv;
@@ -461,7 +461,7 @@ static int dw_mci_exynos_execute_tuning(struct dw_mci_slot *slot)
 		mci_writel(host, TMOUT, ~0);
 		smpl = dw_mci_exynos_move_next_clksmpl(host);
 
-		if (!mmc_send_tuning(mmc))
+		if (!mmc_send_tuning(mmc, opcode, NULL))
 			candiates |= (1 << smpl);
 
 	} while (start_smpl != smpl);
diff --git a/drivers/mmc/host/dw_mmc-pltfm.c b/drivers/mmc/host/dw_mmc-pltfm.c
index ec6dbcdec693..7e1d13b68b06 100644
--- a/drivers/mmc/host/dw_mmc-pltfm.c
+++ b/drivers/mmc/host/dw_mmc-pltfm.c
@@ -59,6 +59,8 @@ int dw_mci_pltfm_register(struct platform_device *pdev,
 	host->pdata = pdev->dev.platform_data;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	/* Get registers' physical base address */
+	host->phy_regs = (void *)(regs->start);
 	host->regs = devm_ioremap_resource(&pdev->dev, regs);
 	if (IS_ERR(host->regs))
 		return PTR_ERR(host->regs);
diff --git a/drivers/mmc/host/dw_mmc-rockchip.c b/drivers/mmc/host/dw_mmc-rockchip.c
index bc76aa22473e..9becebeeccd1 100644
--- a/drivers/mmc/host/dw_mmc-rockchip.c
+++ b/drivers/mmc/host/dw_mmc-rockchip.c
@@ -13,12 +13,19 @@
 #include <linux/mmc/host.h>
 #include <linux/mmc/dw_mmc.h>
 #include <linux/of_address.h>
+#include <linux/slab.h>
 
 #include "dw_mmc.h"
 #include "dw_mmc-pltfm.h"
 
 #define RK3288_CLKGEN_DIV       2
 
+struct dw_mci_rockchip_priv_data {
+	struct clk		*drv_clk;
+	struct clk		*sample_clk;
+	int			default_sample_phase;
+};
+
 static void dw_mci_rockchip_prepare_command(struct dw_mci *host, u32 *cmdr)
 {
 	*cmdr |= SDMMC_CMD_USE_HOLD_REG;
@@ -33,6 +40,7 @@ static int dw_mci_rk3288_setup_clock(struct dw_mci *host)
 
 static void dw_mci_rk3288_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 {
+	struct dw_mci_rockchip_priv_data *priv = host->priv;
 	int ret;
 	unsigned int cclkin;
 	u32 bus_hz;
@@ -66,6 +74,158 @@ static void dw_mci_rk3288_set_ios(struct dw_mci *host, struct mmc_ios *ios)
 		/* force dw_mci_setup_bus() */
 		host->current_speed = 0;
 	}
+
+	/* Make sure we use phases which we can enumerate with */
+	if (!IS_ERR(priv->sample_clk))
+		clk_set_phase(priv->sample_clk, priv->default_sample_phase);
+}
+
+#define NUM_PHASES			360
+#define TUNING_ITERATION_TO_PHASE(i)	(DIV_ROUND_UP((i) * 360, NUM_PHASES))
+
+static int dw_mci_rk3288_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
+{
+	struct dw_mci *host = slot->host;
+	struct dw_mci_rockchip_priv_data *priv = host->priv;
+	struct mmc_host *mmc = slot->mmc;
+	int ret = 0;
+	int i;
+	bool v, prev_v = 0, first_v;
+	struct range_t {
+		int start;
+		int end; /* inclusive */
+	};
+	struct range_t *ranges;
+	unsigned int range_count = 0;
+	int longest_range_len = -1;
+	int longest_range = -1;
+	int middle_phase;
+
+	if (IS_ERR(priv->sample_clk)) {
+		dev_err(host->dev, "Tuning clock (sample_clk) not defined.\n");
+		return -EIO;
+	}
+
+	ranges = kmalloc_array(NUM_PHASES / 2 + 1, sizeof(*ranges), GFP_KERNEL);
+	if (!ranges)
+		return -ENOMEM;
+
+	/* Try each phase and extract good ranges */
+	for (i = 0; i < NUM_PHASES; ) {
+		clk_set_phase(priv->sample_clk, TUNING_ITERATION_TO_PHASE(i));
+
+		v = !mmc_send_tuning(mmc, opcode, NULL);
+
+		if (i == 0)
+			first_v = v;
+
+		if ((!prev_v) && v) {
+			range_count++;
+			ranges[range_count-1].start = i;
+		}
+		if (v) {
+			ranges[range_count-1].end = i;
+			i++;
+		} else if (i == NUM_PHASES - 1) {
+			/* No extra skipping rules if we're at the end */
+			i++;
+		} else {
+			/*
+			 * No need to check too close to an invalid
+			 * one since testing bad phases is slow.  Skip
+			 * 20 degrees.
+			 */
+			i += DIV_ROUND_UP(20 * NUM_PHASES, 360);
+
+			/* Always test the last one */
+			if (i >= NUM_PHASES)
+				i = NUM_PHASES - 1;
+		}
+
+		prev_v = v;
+	}
+
+	if (range_count == 0) {
+		dev_warn(host->dev, "All phases bad!");
+		ret = -EIO;
+		goto free;
+	}
+
+	/* wrap around case, merge the end points */
+	if ((range_count > 1) && first_v && v) {
+		ranges[0].start = ranges[range_count-1].start;
+		range_count--;
+	}
+
+	if (ranges[0].start == 0 && ranges[0].end == NUM_PHASES - 1) {
+		clk_set_phase(priv->sample_clk, priv->default_sample_phase);
+		dev_info(host->dev, "All phases work, using default phase %d.",
+			 priv->default_sample_phase);
+		goto free;
+	}
+
+	/* Find the longest range */
+	for (i = 0; i < range_count; i++) {
+		int len = (ranges[i].end - ranges[i].start + 1);
+
+		if (len < 0)
+			len += NUM_PHASES;
+
+		if (longest_range_len < len) {
+			longest_range_len = len;
+			longest_range = i;
+		}
+
+		dev_dbg(host->dev, "Good phase range %d-%d (%d len)\n",
+			TUNING_ITERATION_TO_PHASE(ranges[i].start),
+			TUNING_ITERATION_TO_PHASE(ranges[i].end),
+			len
+		);
+	}
+
+	dev_dbg(host->dev, "Best phase range %d-%d (%d len)\n",
+		TUNING_ITERATION_TO_PHASE(ranges[longest_range].start),
+		TUNING_ITERATION_TO_PHASE(ranges[longest_range].end),
+		longest_range_len
+	);
+
+	middle_phase = ranges[longest_range].start + longest_range_len / 2;
+	middle_phase %= NUM_PHASES;
+	dev_info(host->dev, "Successfully tuned phase to %d\n",
+		 TUNING_ITERATION_TO_PHASE(middle_phase));
+
+	clk_set_phase(priv->sample_clk,
+		      TUNING_ITERATION_TO_PHASE(middle_phase));
+
+free:
+	kfree(ranges);
+	return ret;
+}
+
+static int dw_mci_rk3288_parse_dt(struct dw_mci *host)
+{
+	struct device_node *np = host->dev->of_node;
+	struct dw_mci_rockchip_priv_data *priv;
+
+	priv = devm_kzalloc(host->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	if (of_property_read_u32(np, "rockchip,default-sample-phase",
+					&priv->default_sample_phase))
+		priv->default_sample_phase = 0;
+
+	priv->drv_clk = devm_clk_get(host->dev, "ciu-drive");
+	if (IS_ERR(priv->drv_clk))
+		dev_dbg(host->dev, "ciu_drv not available\n");
+
+	priv->sample_clk = devm_clk_get(host->dev, "ciu-sample");
+	if (IS_ERR(priv->sample_clk))
+		dev_dbg(host->dev, "ciu_sample not available\n");
+
+	host->priv = priv;
+
+	return 0;
 }
 
 static int dw_mci_rockchip_init(struct dw_mci *host)
@@ -95,6 +255,8 @@ static const struct dw_mci_drv_data rk3288_drv_data = {
 	.caps			= dw_mci_rk3288_dwmmc_caps,
 	.prepare_command        = dw_mci_rockchip_prepare_command,
 	.set_ios		= dw_mci_rk3288_set_ios,
+	.execute_tuning		= dw_mci_rk3288_execute_tuning,
+	.parse_dt		= dw_mci_rk3288_parse_dt,
 	.setup_clock    = dw_mci_rk3288_setup_clock,
 	.init			= dw_mci_rockchip_init,
 };
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index fcbf5524fd31..7a6cedbe48a8 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -56,7 +56,6 @@
 #define DW_MCI_FREQ_MAX	200000000	/* unit: HZ */
 #define DW_MCI_FREQ_MIN	400000		/* unit: HZ */
 
-#ifdef CONFIG_MMC_DW_IDMAC
 #define IDMAC_INT_CLR		(SDMMC_IDMAC_INT_AI | SDMMC_IDMAC_INT_NI | \
 				 SDMMC_IDMAC_INT_CES | SDMMC_IDMAC_INT_DU | \
 				 SDMMC_IDMAC_INT_FBE | SDMMC_IDMAC_INT_RI | \
@@ -102,7 +101,6 @@ struct idmac_desc {
 
 /* Each descriptor can transfer up to 4KB of data in chained mode */
 #define DW_MCI_DESC_DATA_LENGTH	0x1000
-#endif /* CONFIG_MMC_DW_IDMAC */
 
 static bool dw_mci_reset(struct dw_mci *host);
 static bool dw_mci_ctrl_reset(struct dw_mci *host, u32 reset);
@@ -407,7 +405,6 @@ static int dw_mci_get_dma_dir(struct mmc_data *data)
 		return DMA_FROM_DEVICE;
 }
 
-#ifdef CONFIG_MMC_DW_IDMAC
 static void dw_mci_dma_cleanup(struct dw_mci *host)
 {
 	struct mmc_data *data = host->data;
@@ -445,12 +442,21 @@ static void dw_mci_idmac_stop_dma(struct dw_mci *host)
 	mci_writel(host, BMOD, temp);
 }
 
-static void dw_mci_idmac_complete_dma(struct dw_mci *host)
+static void dw_mci_dmac_complete_dma(void *arg)
 {
+	struct dw_mci *host = arg;
 	struct mmc_data *data = host->data;
 
 	dev_vdbg(host->dev, "DMA complete\n");
 
+	if ((host->use_dma == TRANS_MODE_EDMAC) &&
+	    data && (data->flags & MMC_DATA_READ))
+		/* Invalidate cache after read */
+		dma_sync_sg_for_cpu(mmc_dev(host->cur_slot->mmc),
+				    data->sg,
+				    data->sg_len,
+				    DMA_FROM_DEVICE);
+
 	host->dma_ops->cleanup(host);
 
 	/*
@@ -564,7 +570,7 @@ static void dw_mci_translate_sglist(struct dw_mci *host, struct mmc_data *data,
 	wmb(); /* drain writebuffer */
 }
 
-static void dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
+static int dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
 {
 	u32 temp;
 
@@ -589,6 +595,8 @@ static void dw_mci_idmac_start_dma(struct dw_mci *host, unsigned int sg_len)
 
 	/* Start it running */
 	mci_writel(host, PLDMND, 1);
+
+	return 0;
 }
 
 static int dw_mci_idmac_init(struct dw_mci *host)
@@ -669,10 +677,110 @@ static const struct dw_mci_dma_ops dw_mci_idmac_ops = {
 	.init = dw_mci_idmac_init,
 	.start = dw_mci_idmac_start_dma,
 	.stop = dw_mci_idmac_stop_dma,
-	.complete = dw_mci_idmac_complete_dma,
+	.complete = dw_mci_dmac_complete_dma,
+	.cleanup = dw_mci_dma_cleanup,
+};
+
+static void dw_mci_edmac_stop_dma(struct dw_mci *host)
+{
+	dmaengine_terminate_all(host->dms->ch);
+}
+
+static int dw_mci_edmac_start_dma(struct dw_mci *host,
+					    unsigned int sg_len)
+{
+	struct dma_slave_config cfg;
+	struct dma_async_tx_descriptor *desc = NULL;
+	struct scatterlist *sgl = host->data->sg;
+	const u32 mszs[] = {1, 4, 8, 16, 32, 64, 128, 256};
+	u32 sg_elems = host->data->sg_len;
+	u32 fifoth_val;
+	u32 fifo_offset = host->fifo_reg - host->regs;
+	int ret = 0;
+
+	/* Set external dma config: burst size, burst width */
+	cfg.dst_addr = (dma_addr_t)(host->phy_regs + fifo_offset);
+	cfg.src_addr = cfg.dst_addr;
+	cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+
+	/* Match burst msize with external dma config */
+	fifoth_val = mci_readl(host, FIFOTH);
+	cfg.dst_maxburst = mszs[(fifoth_val >> 28) & 0x7];
+	cfg.src_maxburst = cfg.dst_maxburst;
+
+	if (host->data->flags & MMC_DATA_WRITE)
+		cfg.direction = DMA_MEM_TO_DEV;
+	else
+		cfg.direction = DMA_DEV_TO_MEM;
+
+	ret = dmaengine_slave_config(host->dms->ch, &cfg);
+	if (ret) {
+		dev_err(host->dev, "Failed to config edmac.\n");
+		return -EBUSY;
+	}
+
+	desc = dmaengine_prep_slave_sg(host->dms->ch, sgl,
+				       sg_len, cfg.direction,
+				       DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc) {
+		dev_err(host->dev, "Can't prepare slave sg.\n");
+		return -EBUSY;
+	}
+
+	/* Set dw_mci_dmac_complete_dma as callback */
+	desc->callback = dw_mci_dmac_complete_dma;
+	desc->callback_param = (void *)host;
+	dmaengine_submit(desc);
+
+	/* Flush cache before write */
+	if (host->data->flags & MMC_DATA_WRITE)
+		dma_sync_sg_for_device(mmc_dev(host->cur_slot->mmc), sgl,
+				       sg_elems, DMA_TO_DEVICE);
+
+	dma_async_issue_pending(host->dms->ch);
+
+	return 0;
+}
+
+static int dw_mci_edmac_init(struct dw_mci *host)
+{
+	/* Request external dma channel */
+	host->dms = kzalloc(sizeof(struct dw_mci_dma_slave), GFP_KERNEL);
+	if (!host->dms)
+		return -ENOMEM;
+
+	host->dms->ch = dma_request_slave_channel(host->dev, "rx-tx");
+	if (!host->dms->ch) {
+		dev_err(host->dev, "Failed to get external DMA channel.\n");
+		kfree(host->dms);
+		host->dms = NULL;
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static void dw_mci_edmac_exit(struct dw_mci *host)
+{
+	if (host->dms) {
+		if (host->dms->ch) {
+			dma_release_channel(host->dms->ch);
+			host->dms->ch = NULL;
+		}
+		kfree(host->dms);
+		host->dms = NULL;
+	}
+}
+
+static const struct dw_mci_dma_ops dw_mci_edmac_ops = {
+	.init = dw_mci_edmac_init,
+	.exit = dw_mci_edmac_exit,
+	.start = dw_mci_edmac_start_dma,
+	.stop = dw_mci_edmac_stop_dma,
+	.complete = dw_mci_dmac_complete_dma,
 	.cleanup = dw_mci_dma_cleanup,
 };
-#endif /* CONFIG_MMC_DW_IDMAC */
 
 static int dw_mci_pre_dma_transfer(struct dw_mci *host,
 				   struct mmc_data *data,
@@ -752,7 +860,6 @@ static void dw_mci_post_req(struct mmc_host *mmc,
 
 static void dw_mci_adjust_fifoth(struct dw_mci *host, struct mmc_data *data)
 {
-#ifdef CONFIG_MMC_DW_IDMAC
 	unsigned int blksz = data->blksz;
 	const u32 mszs[] = {1, 4, 8, 16, 32, 64, 128, 256};
 	u32 fifo_width = 1 << host->data_shift;
@@ -760,6 +867,10 @@ static void dw_mci_adjust_fifoth(struct dw_mci *host, struct mmc_data *data)
 	u32 msize = 0, rx_wmark = 1, tx_wmark, tx_wmark_invers;
 	int idx = ARRAY_SIZE(mszs) - 1;
 
+	/* pio should ship this scenario */
+	if (!host->use_dma)
+		return;
+
 	tx_wmark = (host->fifo_depth) / 2;
 	tx_wmark_invers = host->fifo_depth - tx_wmark;
 
@@ -788,7 +899,6 @@ static void dw_mci_adjust_fifoth(struct dw_mci *host, struct mmc_data *data)
 done:
 	fifoth_val = SDMMC_SET_FIFOTH(msize, rx_wmark, tx_wmark);
 	mci_writel(host, FIFOTH, fifoth_val);
-#endif
 }
 
 static void dw_mci_ctrl_rd_thld(struct dw_mci *host, struct mmc_data *data)
@@ -850,10 +960,12 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 
 	host->using_dma = 1;
 
-	dev_vdbg(host->dev,
-		 "sd sg_cpu: %#lx sg_dma: %#lx sg_len: %d\n",
-		 (unsigned long)host->sg_cpu, (unsigned long)host->sg_dma,
-		 sg_len);
+	if (host->use_dma == TRANS_MODE_IDMAC)
+		dev_vdbg(host->dev,
+			 "sd sg_cpu: %#lx sg_dma: %#lx sg_len: %d\n",
+			 (unsigned long)host->sg_cpu,
+			 (unsigned long)host->sg_dma,
+			 sg_len);
 
 	/*
 	 * Decide the MSIZE and RX/TX Watermark.
@@ -875,7 +987,11 @@ static int dw_mci_submit_data_dma(struct dw_mci *host, struct mmc_data *data)
 	mci_writel(host, INTMASK, temp);
 	spin_unlock_irqrestore(&host->irq_lock, irqflags);
 
-	host->dma_ops->start(host, sg_len);
+	if (host->dma_ops->start(host, sg_len)) {
+		/* We can't do DMA */
+		dev_err(host->dev, "%s: failed to start DMA.\n", __func__);
+		return -ENODEV;
+	}
 
 	return 0;
 }
@@ -1177,6 +1293,7 @@ static void dw_mci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 
 	/* DDR mode set */
 	if (ios->timing == MMC_TIMING_MMC_DDR52 ||
+	    ios->timing == MMC_TIMING_UHS_DDR50 ||
 	    ios->timing == MMC_TIMING_MMC_HS400)
 		regs |= ((0x1 << slot->id) << 16);
 	else
@@ -1279,7 +1396,6 @@ static int dw_mci_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
 	const struct dw_mci_drv_data *drv_data = host->drv_data;
 	u32 uhs;
 	u32 v18 = SDMMC_UHS_18V << slot->id;
-	int min_uv, max_uv;
 	int ret;
 
 	if (drv_data && drv_data->switch_voltage)
@@ -1291,22 +1407,18 @@ static int dw_mci_switch_voltage(struct mmc_host *mmc, struct mmc_ios *ios)
 	 * does no harm but you need to set the regulator directly.  Try both.
 	 */
 	uhs = mci_readl(host, UHS_REG);
-	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330) {
-		min_uv = 2700000;
-		max_uv = 3600000;
+	if (ios->signal_voltage == MMC_SIGNAL_VOLTAGE_330)
 		uhs &= ~v18;
-	} else {
-		min_uv = 1700000;
-		max_uv = 1950000;
+	else
 		uhs |= v18;
-	}
+
 	if (!IS_ERR(mmc->supply.vqmmc)) {
-		ret = regulator_set_voltage(mmc->supply.vqmmc, min_uv, max_uv);
+		ret = mmc_regulator_set_vqmmc(mmc, ios);
 
 		if (ret) {
 			dev_dbg(&mmc->class_dev,
-					 "Regulator set error %d: %d - %d\n",
-					 ret, min_uv, max_uv);
+					 "Regulator set error %d - %s V\n",
+					 ret, uhs & v18 ? "1.8" : "3.3");
 			return ret;
 		}
 	}
@@ -1427,7 +1539,7 @@ static int dw_mci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	int err = -EINVAL;
 
 	if (drv_data && drv_data->execute_tuning)
-		err = drv_data->execute_tuning(slot);
+		err = drv_data->execute_tuning(slot, opcode);
 	return err;
 }
 
@@ -2343,15 +2455,17 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 
 	}
 
-#ifdef CONFIG_MMC_DW_IDMAC
-	/* Handle DMA interrupts */
+	if (host->use_dma != TRANS_MODE_IDMAC)
+		return IRQ_HANDLED;
+
+	/* Handle IDMA interrupts */
 	if (host->dma_64bit_address == 1) {
 		pending = mci_readl(host, IDSTS64);
 		if (pending & (SDMMC_IDMAC_INT_TI | SDMMC_IDMAC_INT_RI)) {
 			mci_writel(host, IDSTS64, SDMMC_IDMAC_INT_TI |
 							SDMMC_IDMAC_INT_RI);
 			mci_writel(host, IDSTS64, SDMMC_IDMAC_INT_NI);
-			host->dma_ops->complete(host);
+			host->dma_ops->complete((void *)host);
 		}
 	} else {
 		pending = mci_readl(host, IDSTS);
@@ -2359,10 +2473,9 @@ static irqreturn_t dw_mci_interrupt(int irq, void *dev_id)
 			mci_writel(host, IDSTS, SDMMC_IDMAC_INT_TI |
 							SDMMC_IDMAC_INT_RI);
 			mci_writel(host, IDSTS, SDMMC_IDMAC_INT_NI);
-			host->dma_ops->complete(host);
+			host->dma_ops->complete((void *)host);
 		}
 	}
-#endif
 
 	return IRQ_HANDLED;
 }
@@ -2471,13 +2584,21 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 		goto err_host_allocated;
 
 	/* Useful defaults if platform data is unset. */
-	if (host->use_dma) {
+	if (host->use_dma == TRANS_MODE_IDMAC) {
 		mmc->max_segs = host->ring_size;
 		mmc->max_blk_size = 65536;
 		mmc->max_seg_size = 0x1000;
 		mmc->max_req_size = mmc->max_seg_size * host->ring_size;
 		mmc->max_blk_count = mmc->max_req_size / 512;
+	} else if (host->use_dma == TRANS_MODE_EDMAC) {
+		mmc->max_segs = 64;
+		mmc->max_blk_size = 65536;
+		mmc->max_blk_count = 65535;
+		mmc->max_req_size =
+				mmc->max_blk_size * mmc->max_blk_count;
+		mmc->max_seg_size = mmc->max_req_size;
 	} else {
+		/* TRANS_MODE_PIO */
 		mmc->max_segs = 64;
 		mmc->max_blk_size = 65536; /* BLKSIZ is 16 bits */
 		mmc->max_blk_count = 512;
@@ -2517,38 +2638,74 @@ static void dw_mci_cleanup_slot(struct dw_mci_slot *slot, unsigned int id)
 static void dw_mci_init_dma(struct dw_mci *host)
 {
 	int addr_config;
-	/* Check ADDR_CONFIG bit in HCON to find IDMAC address bus width */
-	addr_config = (mci_readl(host, HCON) >> 27) & 0x01;
-
-	if (addr_config == 1) {
-		/* host supports IDMAC in 64-bit address mode */
-		host->dma_64bit_address = 1;
-		dev_info(host->dev, "IDMAC supports 64-bit address mode.\n");
-		if (!dma_set_mask(host->dev, DMA_BIT_MASK(64)))
-			dma_set_coherent_mask(host->dev, DMA_BIT_MASK(64));
-	} else {
-		/* host supports IDMAC in 32-bit address mode */
-		host->dma_64bit_address = 0;
-		dev_info(host->dev, "IDMAC supports 32-bit address mode.\n");
-	}
+	struct device *dev = host->dev;
+	struct device_node *np = dev->of_node;
 
-	/* Alloc memory for sg translation */
-	host->sg_cpu = dmam_alloc_coherent(host->dev, PAGE_SIZE,
-					  &host->sg_dma, GFP_KERNEL);
-	if (!host->sg_cpu) {
-		dev_err(host->dev, "%s: could not alloc DMA memory\n",
-			__func__);
+	/*
+	* Check tansfer mode from HCON[17:16]
+	* Clear the ambiguous description of dw_mmc databook:
+	* 2b'00: No DMA Interface -> Actually means using Internal DMA block
+	* 2b'01: DesignWare DMA Interface -> Synopsys DW-DMA block
+	* 2b'10: Generic DMA Interface -> non-Synopsys generic DMA block
+	* 2b'11: Non DW DMA Interface -> pio only
+	* Compared to DesignWare DMA Interface, Generic DMA Interface has a
+	* simpler request/acknowledge handshake mechanism and both of them
+	* are regarded as external dma master for dw_mmc.
+	*/
+	host->use_dma = SDMMC_GET_TRANS_MODE(mci_readl(host, HCON));
+	if (host->use_dma == DMA_INTERFACE_IDMA) {
+		host->use_dma = TRANS_MODE_IDMAC;
+	} else if (host->use_dma == DMA_INTERFACE_DWDMA ||
+		   host->use_dma == DMA_INTERFACE_GDMA) {
+		host->use_dma = TRANS_MODE_EDMAC;
+	} else {
 		goto no_dma;
 	}
 
 	/* Determine which DMA interface to use */
-#ifdef CONFIG_MMC_DW_IDMAC
-	host->dma_ops = &dw_mci_idmac_ops;
-	dev_info(host->dev, "Using internal DMA controller.\n");
-#endif
+	if (host->use_dma == TRANS_MODE_IDMAC) {
+		/*
+		* Check ADDR_CONFIG bit in HCON to find
+		* IDMAC address bus width
+		*/
+		addr_config = SDMMC_GET_ADDR_CONFIG(mci_readl(host, HCON));
+
+		if (addr_config == 1) {
+			/* host supports IDMAC in 64-bit address mode */
+			host->dma_64bit_address = 1;
+			dev_info(host->dev,
+				 "IDMAC supports 64-bit address mode.\n");
+			if (!dma_set_mask(host->dev, DMA_BIT_MASK(64)))
+				dma_set_coherent_mask(host->dev,
+						      DMA_BIT_MASK(64));
+		} else {
+			/* host supports IDMAC in 32-bit address mode */
+			host->dma_64bit_address = 0;
+			dev_info(host->dev,
+				 "IDMAC supports 32-bit address mode.\n");
+		}
 
-	if (!host->dma_ops)
-		goto no_dma;
+		/* Alloc memory for sg translation */
+		host->sg_cpu = dmam_alloc_coherent(host->dev, PAGE_SIZE,
+						   &host->sg_dma, GFP_KERNEL);
+		if (!host->sg_cpu) {
+			dev_err(host->dev,
+				"%s: could not alloc DMA memory\n",
+				__func__);
+			goto no_dma;
+		}
+
+		host->dma_ops = &dw_mci_idmac_ops;
+		dev_info(host->dev, "Using internal DMA controller.\n");
+	} else {
+		/* TRANS_MODE_EDMAC: check dma bindings again */
+		if ((of_property_count_strings(np, "dma-names") < 0) ||
+		    (!of_find_property(np, "dmas", NULL))) {
+			goto no_dma;
+		}
+		host->dma_ops = &dw_mci_edmac_ops;
+		dev_info(host->dev, "Using external DMA controller.\n");
+	}
 
 	if (host->dma_ops->init && host->dma_ops->start &&
 	    host->dma_ops->stop && host->dma_ops->cleanup) {
@@ -2562,12 +2719,11 @@ static void dw_mci_init_dma(struct dw_mci *host)
 		goto no_dma;
 	}
 
-	host->use_dma = 1;
 	return;
 
 no_dma:
 	dev_info(host->dev, "Using PIO mode.\n");
-	host->use_dma = 0;
+	host->use_dma = TRANS_MODE_PIO;
 }
 
 static bool dw_mci_ctrl_reset(struct dw_mci *host, u32 reset)
@@ -2650,10 +2806,9 @@ static bool dw_mci_reset(struct dw_mci *host)
 		}
 	}
 
-#if IS_ENABLED(CONFIG_MMC_DW_IDMAC)
-	/* It is also recommended that we reset and reprogram idmac */
-	dw_mci_idmac_reset(host);
-#endif
+	if (host->use_dma == TRANS_MODE_IDMAC)
+		/* It is also recommended that we reset and reprogram idmac */
+		dw_mci_idmac_reset(host);
 
 	ret = true;
 
@@ -2890,7 +3045,7 @@ int dw_mci_probe(struct dw_mci *host)
 	 * Get the host data width - this assumes that HCON has been set with
 	 * the correct values.
 	 */
-	i = (mci_readl(host, HCON) >> 7) & 0x7;
+	i = SDMMC_GET_HDATA_WIDTH(mci_readl(host, HCON));
 	if (!i) {
 		host->push_data = dw_mci_push_data16;
 		host->pull_data = dw_mci_pull_data16;
@@ -2972,7 +3127,7 @@ int dw_mci_probe(struct dw_mci *host)
 	if (host->pdata->num_slots)
 		host->num_slots = host->pdata->num_slots;
 	else
-		host->num_slots = ((mci_readl(host, HCON) >> 1) & 0x1F) + 1;
+		host->num_slots = SDMMC_GET_SLOT_NUM(mci_readl(host, HCON));
 
 	/*
 	 * Enable interrupts for command done, data over, data empty,
@@ -3067,6 +3222,9 @@ EXPORT_SYMBOL(dw_mci_remove);
  */
 int dw_mci_suspend(struct dw_mci *host)
 {
+	if (host->use_dma && host->dma_ops->exit)
+		host->dma_ops->exit(host);
+
 	return 0;
 }
 EXPORT_SYMBOL(dw_mci_suspend);
diff --git a/drivers/mmc/host/dw_mmc.h b/drivers/mmc/host/dw_mmc.h
index 8ce4674730a6..f695b58f0613 100644
--- a/drivers/mmc/host/dw_mmc.h
+++ b/drivers/mmc/host/dw_mmc.h
@@ -148,6 +148,15 @@
 #define SDMMC_SET_FIFOTH(m, r, t)	(((m) & 0x7) << 28 | \
 					 ((r) & 0xFFF) << 16 | \
 					 ((t) & 0xFFF))
+/* HCON register defines */
+#define DMA_INTERFACE_IDMA		(0x0)
+#define DMA_INTERFACE_DWDMA		(0x1)
+#define DMA_INTERFACE_GDMA		(0x2)
+#define DMA_INTERFACE_NODMA		(0x3)
+#define SDMMC_GET_TRANS_MODE(x)		(((x)>>16) & 0x3)
+#define SDMMC_GET_SLOT_NUM(x)		((((x)>>1) & 0x1F) + 1)
+#define SDMMC_GET_HDATA_WIDTH(x)	(((x)>>7) & 0x7)
+#define SDMMC_GET_ADDR_CONFIG(x)	(((x)>>27) & 0x1)
 /* Internal DMAC interrupt defines */
 #define SDMMC_IDMAC_INT_AI		BIT(9)
 #define SDMMC_IDMAC_INT_NI		BIT(8)
@@ -163,7 +172,7 @@
 /* Version ID register define */
 #define SDMMC_GET_VERID(x)		((x) & 0xFFFF)
 /* Card read threshold */
-#define SDMMC_SET_RD_THLD(v, x)		(((v) & 0x1FFF) << 16 | (x))
+#define SDMMC_SET_RD_THLD(v, x)		(((v) & 0xFFF) << 16 | (x))
 #define SDMMC_UHS_18V			BIT(0)
 /* All ctrl reset bits */
 #define SDMMC_CTRL_ALL_RESET_FLAGS \
@@ -281,7 +290,7 @@ struct dw_mci_drv_data {
 	void		(*prepare_command)(struct dw_mci *host, u32 *cmdr);
 	void		(*set_ios)(struct dw_mci *host, struct mmc_ios *ios);
 	int		(*parse_dt)(struct dw_mci *host);
-	int		(*execute_tuning)(struct dw_mci_slot *slot);
+	int		(*execute_tuning)(struct dw_mci_slot *slot, u32 opcode);
 	int		(*prepare_hs400_tuning)(struct dw_mci *host,
 						struct mmc_ios *ios);
 	int		(*switch_voltage)(struct mmc_host *mmc,
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index ae19d83bb9de..8ee11f4120fc 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1511,6 +1511,7 @@ static const struct of_device_id mmc_spi_of_match_table[] = {
 	{ .compatible = "mmc-spi-slot", },
 	{},
 };
+MODULE_DEVICE_TABLE(of, mmc_spi_of_match_table);
 
 static struct spi_driver mmc_spi_driver = {
 	.driver = {
diff --git a/drivers/mmc/host/moxart-mmc.c b/drivers/mmc/host/moxart-mmc.c
index 006f1862444b..79905ce895ad 100644
--- a/drivers/mmc/host/moxart-mmc.c
+++ b/drivers/mmc/host/moxart-mmc.c
@@ -711,6 +711,7 @@ static const struct of_device_id moxart_mmc_match[] = {
 	{ .compatible = "faraday,ftsdc010" },
 	{ }
 };
+MODULE_DEVICE_TABLE(of, moxart_mmc_match);
 
 static struct platform_driver moxart_mmc_driver = {
 	.probe      = moxart_probe,
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 7153500dd007..39568cc29a2a 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -26,6 +26,7 @@
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 #include <linux/mmc/card.h>
@@ -64,6 +65,7 @@
 #define SDC_RESP2        0x48
 #define SDC_RESP3        0x4c
 #define SDC_BLK_NUM      0x50
+#define EMMC_IOCON       0x7c
 #define SDC_ACMD_RESP    0x80
 #define MSDC_DMA_SA      0x90
 #define MSDC_DMA_CTRL    0x98
@@ -71,6 +73,8 @@
 #define MSDC_PATCH_BIT   0xb0
 #define MSDC_PATCH_BIT1  0xb4
 #define MSDC_PAD_TUNE    0xec
+#define PAD_DS_TUNE      0x188
+#define EMMC50_CFG0      0x208
 
 /*--------------------------------------------------------------------------*/
 /* Register Mask                                                            */
@@ -87,6 +91,7 @@
 #define MSDC_CFG_CKSTB          (0x1 << 7)	/* R  */
 #define MSDC_CFG_CKDIV          (0xff << 8)	/* RW */
 #define MSDC_CFG_CKMOD          (0x3 << 16)	/* RW */
+#define MSDC_CFG_HS400_CK_MODE  (0x1 << 18)	/* RW */
 
 /* MSDC_IOCON mask */
 #define MSDC_IOCON_SDR104CKS    (0x1 << 0)	/* RW */
@@ -204,6 +209,17 @@
 #define MSDC_PATCH_BIT_SPCPUSH    (0x1 << 29)	/* RW */
 #define MSDC_PATCH_BIT_DECRCTMO   (0x1 << 30)	/* RW */
 
+#define MSDC_PAD_TUNE_DATRRDLY	  (0x1f <<  8)	/* RW */
+#define MSDC_PAD_TUNE_CMDRDLY	  (0x1f << 16)  /* RW */
+
+#define PAD_DS_TUNE_DLY1	  (0x1f << 2)   /* RW */
+#define PAD_DS_TUNE_DLY2	  (0x1f << 7)   /* RW */
+#define PAD_DS_TUNE_DLY3	  (0x1f << 12)  /* RW */
+
+#define EMMC50_CFG_PADCMD_LATCHCK (0x1 << 0)   /* RW */
+#define EMMC50_CFG_CRCSTS_EDGE    (0x1 << 3)   /* RW */
+#define EMMC50_CFG_CFCSTS_SEL     (0x1 << 4)   /* RW */
+
 #define REQ_CMD_EIO  (0x1 << 0)
 #define REQ_CMD_TMO  (0x1 << 1)
 #define REQ_DAT_ERR  (0x1 << 2)
@@ -219,6 +235,7 @@
 #define CMD_TIMEOUT         (HZ/10 * 5)	/* 100ms x5 */
 #define DAT_TIMEOUT         (HZ    * 5)	/* 1000ms x5 */
 
+#define PAD_DELAY_MAX	32 /* PAD delay cells */
 /*--------------------------------------------------------------------------*/
 /* Descriptor Structure                                                     */
 /*--------------------------------------------------------------------------*/
@@ -265,6 +282,14 @@ struct msdc_save_para {
 	u32 pad_tune;
 	u32 patch_bit0;
 	u32 patch_bit1;
+	u32 pad_ds_tune;
+	u32 emmc50_cfg0;
+};
+
+struct msdc_delay_phase {
+	u8 maxlen;
+	u8 start;
+	u8 final_phase;
 };
 
 struct msdc_host {
@@ -297,8 +322,9 @@ struct msdc_host {
 	u32 mclk;		/* mmc subsystem clock frequency */
 	u32 src_clk_freq;	/* source clock frequency */
 	u32 sclk;		/* SD/MS bus clock frequency */
-	bool ddr;
+	unsigned char timing;
 	bool vqmmc_enabled;
+	u32 hs400_ds_delay;
 	struct msdc_save_para save_para; /* used when gate HCLK */
 };
 
@@ -353,7 +379,10 @@ static void msdc_reset_hw(struct msdc_host *host)
 static void msdc_cmd_next(struct msdc_host *host,
 		struct mmc_request *mrq, struct mmc_command *cmd);
 
-static u32 data_ints_mask = MSDC_INTEN_XFER_COMPL | MSDC_INTEN_DATTMO |
+static const u32 cmd_ints_mask = MSDC_INTEN_CMDRDY | MSDC_INTEN_RSPCRCERR |
+			MSDC_INTEN_CMDTMO | MSDC_INTEN_ACMDRDY |
+			MSDC_INTEN_ACMDCRCERR | MSDC_INTEN_ACMDTMO;
+static const u32 data_ints_mask = MSDC_INTEN_XFER_COMPL | MSDC_INTEN_DATTMO |
 			MSDC_INTEN_DATCRCERR | MSDC_INTEN_DMA_BDCSERR |
 			MSDC_INTEN_DMA_GPDCSERR | MSDC_INTEN_DMA_PROTECT;
 
@@ -485,7 +514,7 @@ static void msdc_ungate_clock(struct msdc_host *host)
 		cpu_relax();
 }
 
-static void msdc_set_mclk(struct msdc_host *host, int ddr, u32 hz)
+static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz)
 {
 	u32 mode;
 	u32 flags;
@@ -501,8 +530,15 @@ static void msdc_set_mclk(struct msdc_host *host, int ddr, u32 hz)
 
 	flags = readl(host->base + MSDC_INTEN);
 	sdr_clr_bits(host->base + MSDC_INTEN, flags);
-	if (ddr) { /* may need to modify later */
-		mode = 0x2; /* ddr mode and use divisor */
+	sdr_clr_bits(host->base + MSDC_CFG, MSDC_CFG_HS400_CK_MODE);
+	if (timing == MMC_TIMING_UHS_DDR50 ||
+	    timing == MMC_TIMING_MMC_DDR52 ||
+	    timing == MMC_TIMING_MMC_HS400) {
+		if (timing == MMC_TIMING_MMC_HS400)
+			mode = 0x3;
+		else
+			mode = 0x2; /* ddr mode and use divisor */
+
 		if (hz >= (host->src_clk_freq >> 2)) {
 			div = 0; /* mean div = 1/4 */
 			sclk = host->src_clk_freq >> 2; /* sclk = clk / 4 */
@@ -511,6 +547,14 @@ static void msdc_set_mclk(struct msdc_host *host, int ddr, u32 hz)
 			sclk = (host->src_clk_freq >> 2) / div;
 			div = (div >> 1);
 		}
+
+		if (timing == MMC_TIMING_MMC_HS400 &&
+		    hz >= (host->src_clk_freq >> 1)) {
+			sdr_set_bits(host->base + MSDC_CFG,
+				     MSDC_CFG_HS400_CK_MODE);
+			sclk = host->src_clk_freq >> 1;
+			div = 0; /* div is ignore when bit18 is set */
+		}
 	} else if (hz >= host->src_clk_freq) {
 		mode = 0x1; /* no divisor */
 		div = 0;
@@ -532,12 +576,12 @@ static void msdc_set_mclk(struct msdc_host *host, int ddr, u32 hz)
 		cpu_relax();
 	host->sclk = sclk;
 	host->mclk = hz;
-	host->ddr = ddr;
+	host->timing = timing;
 	/* need because clk changed. */
 	msdc_set_timeout(host, host->timeout_ns, host->timeout_clks);
 	sdr_set_bits(host->base + MSDC_INTEN, flags);
 
-	dev_dbg(host->dev, "sclk: %d, ddr: %d\n", host->sclk, ddr);
+	dev_dbg(host->dev, "sclk: %d, timing: %d\n", host->sclk, timing);
 }
 
 static inline u32 msdc_cmd_find_resp(struct msdc_host *host,
@@ -725,11 +769,7 @@ static bool msdc_cmd_done(struct msdc_host *host, int events,
 	if (done)
 		return true;
 
-	sdr_clr_bits(host->base + MSDC_INTEN, MSDC_INTEN_CMDRDY |
-			MSDC_INTEN_RSPCRCERR | MSDC_INTEN_CMDTMO |
-			MSDC_INTEN_ACMDRDY | MSDC_INTEN_ACMDCRCERR |
-			MSDC_INTEN_ACMDTMO);
-	writel(cmd->arg, host->base + SDC_ARG);
+	sdr_clr_bits(host->base + MSDC_INTEN, cmd_ints_mask);
 
 	if (cmd->flags & MMC_RSP_PRESENT) {
 		if (cmd->flags & MMC_RSP_136) {
@@ -819,10 +859,7 @@ static void msdc_start_command(struct msdc_host *host,
 	rawcmd = msdc_cmd_prepare_raw_cmd(host, mrq, cmd);
 	mod_delayed_work(system_wq, &host->req_timeout, DAT_TIMEOUT);
 
-	sdr_set_bits(host->base + MSDC_INTEN, MSDC_INTEN_CMDRDY |
-			MSDC_INTEN_RSPCRCERR | MSDC_INTEN_CMDTMO |
-			MSDC_INTEN_ACMDRDY | MSDC_INTEN_ACMDCRCERR |
-			MSDC_INTEN_ACMDTMO);
+	sdr_set_bits(host->base + MSDC_INTEN, cmd_ints_mask);
 	writel(cmd->arg, host->base + SDC_ARG);
 	writel(rawcmd, host->base + SDC_CMD);
 }
@@ -896,7 +933,7 @@ static void msdc_data_xfer_next(struct msdc_host *host,
 				struct mmc_request *mrq, struct mmc_data *data)
 {
 	if (mmc_op_multi(mrq->cmd->opcode) && mrq->stop && !mrq->stop->error &&
-	    (!data->bytes_xfered || !mrq->sbc))
+	    !mrq->sbc)
 		msdc_start_command(host, mrq, mrq->stop);
 	else
 		msdc_request_done(host, mrq);
@@ -942,6 +979,8 @@ static bool msdc_data_xfer_done(struct msdc_host *host, u32 events,
 
 			if (events & MSDC_INT_DATTMO)
 				data->error = -ETIMEDOUT;
+			else if (events & MSDC_INT_DATCRCERR)
+				data->error = -EILSEQ;
 
 			dev_err(host->dev, "%s: cmd=%d; blocks=%d",
 				__func__, mrq->cmd->opcode, data->blocks);
@@ -1113,10 +1152,12 @@ static void msdc_init_hw(struct msdc_host *host)
 
 	writel(0, host->base + MSDC_PAD_TUNE);
 	writel(0, host->base + MSDC_IOCON);
-	sdr_set_field(host->base + MSDC_IOCON, MSDC_IOCON_DDLSEL, 1);
-	writel(0x403c004f, host->base + MSDC_PATCH_BIT);
+	sdr_set_field(host->base + MSDC_IOCON, MSDC_IOCON_DDLSEL, 0);
+	writel(0x403c0046, host->base + MSDC_PATCH_BIT);
 	sdr_set_field(host->base + MSDC_PATCH_BIT, MSDC_CKGEN_MSDC_DLY_SEL, 1);
 	writel(0xffff0089, host->base + MSDC_PATCH_BIT1);
+	sdr_set_bits(host->base + EMMC50_CFG0, EMMC50_CFG_CFCSTS_SEL);
+
 	/* Configure to enable SDIO mode.
 	 * it's must otherwise sdio cmd5 failed
 	 */
@@ -1148,11 +1189,14 @@ static void msdc_init_gpd_bd(struct msdc_host *host, struct msdc_dma *dma)
 	struct mt_bdma_desc *bd = dma->bd;
 	int i;
 
-	memset(gpd, 0, sizeof(struct mt_gpdma_desc));
+	memset(gpd, 0, sizeof(struct mt_gpdma_desc) * 2);
 
 	gpd->gpd_info = GPDMA_DESC_BDP; /* hwo, cs, bd pointer */
 	gpd->ptr = (u32)dma->bd_addr; /* physical address */
-
+	/* gpd->next is must set for desc DMA
+	 * That's why must alloc 2 gpd structure.
+	 */
+	gpd->next = (u32)dma->gpd_addr + sizeof(struct mt_gpdma_desc);
 	memset(bd, 0, sizeof(struct mt_bdma_desc) * MAX_BD_NUM);
 	for (i = 0; i < (MAX_BD_NUM - 1); i++)
 		bd[i].next = (u32)dma->bd_addr + sizeof(*bd) * (i + 1);
@@ -1162,20 +1206,16 @@ static void msdc_ops_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 {
 	struct msdc_host *host = mmc_priv(mmc);
 	int ret;
-	u32 ddr = 0;
 
 	pm_runtime_get_sync(host->dev);
 
-	if (ios->timing == MMC_TIMING_UHS_DDR50 ||
-	    ios->timing == MMC_TIMING_MMC_DDR52)
-		ddr = 1;
-
 	msdc_set_buswidth(host, ios->bus_width);
 
 	/* Suspend/Resume will do power off/on */
 	switch (ios->power_mode) {
 	case MMC_POWER_UP:
 		if (!IS_ERR(mmc->supply.vmmc)) {
+			msdc_init_hw(host);
 			ret = mmc_regulator_set_ocr(mmc, mmc->supply.vmmc,
 					ios->vdd);
 			if (ret) {
@@ -1206,14 +1246,207 @@ static void msdc_ops_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		break;
 	}
 
-	if (host->mclk != ios->clock || host->ddr != ddr)
-		msdc_set_mclk(host, ddr, ios->clock);
+	if (host->mclk != ios->clock || host->timing != ios->timing)
+		msdc_set_mclk(host, ios->timing, ios->clock);
 
 end:
 	pm_runtime_mark_last_busy(host->dev);
 	pm_runtime_put_autosuspend(host->dev);
 }
 
+static u32 test_delay_bit(u32 delay, u32 bit)
+{
+	bit %= PAD_DELAY_MAX;
+	return delay & (1 << bit);
+}
+
+static int get_delay_len(u32 delay, u32 start_bit)
+{
+	int i;
+
+	for (i = 0; i < (PAD_DELAY_MAX - start_bit); i++) {
+		if (test_delay_bit(delay, start_bit + i) == 0)
+			return i;
+	}
+	return PAD_DELAY_MAX - start_bit;
+}
+
+static struct msdc_delay_phase get_best_delay(struct msdc_host *host, u32 delay)
+{
+	int start = 0, len = 0;
+	int start_final = 0, len_final = 0;
+	u8 final_phase = 0xff;
+	struct msdc_delay_phase delay_phase;
+
+	if (delay == 0) {
+		dev_err(host->dev, "phase error: [map:%x]\n", delay);
+		delay_phase.final_phase = final_phase;
+		return delay_phase;
+	}
+
+	while (start < PAD_DELAY_MAX) {
+		len = get_delay_len(delay, start);
+		if (len_final < len) {
+			start_final = start;
+			len_final = len;
+		}
+		start += len ? len : 1;
+		if (len >= 8 && start_final < 4)
+			break;
+	}
+
+	/* The rule is that to find the smallest delay cell */
+	if (start_final == 0)
+		final_phase = (start_final + len_final / 3) % PAD_DELAY_MAX;
+	else
+		final_phase = (start_final + len_final / 2) % PAD_DELAY_MAX;
+	dev_info(host->dev, "phase: [map:%x] [maxlen:%d] [final:%d]\n",
+		 delay, len_final, final_phase);
+
+	delay_phase.maxlen = len_final;
+	delay_phase.start = start_final;
+	delay_phase.final_phase = final_phase;
+	return delay_phase;
+}
+
+static int msdc_tune_response(struct mmc_host *mmc, u32 opcode)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	u32 rise_delay = 0, fall_delay = 0;
+	struct msdc_delay_phase final_rise_delay, final_fall_delay;
+	u8 final_delay, final_maxlen;
+	int cmd_err;
+	int i;
+
+	sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
+	for (i = 0 ; i < PAD_DELAY_MAX; i++) {
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_CMDRDLY, i);
+		mmc_send_tuning(mmc, opcode, &cmd_err);
+		if (!cmd_err)
+			rise_delay |= (1 << i);
+	}
+
+	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
+	for (i = 0; i < PAD_DELAY_MAX; i++) {
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_CMDRDLY, i);
+		mmc_send_tuning(mmc, opcode, &cmd_err);
+		if (!cmd_err)
+			fall_delay |= (1 << i);
+	}
+
+	final_rise_delay = get_best_delay(host, rise_delay);
+	final_fall_delay = get_best_delay(host, fall_delay);
+
+	final_maxlen = max(final_rise_delay.maxlen, final_fall_delay.maxlen);
+	if (final_maxlen == final_rise_delay.maxlen) {
+		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
+		sdr_set_field(host->base + MSDC_PAD_TUNE, MSDC_PAD_TUNE_CMDRDLY,
+			      final_rise_delay.final_phase);
+		final_delay = final_rise_delay.final_phase;
+	} else {
+		sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_RSPL);
+		sdr_set_field(host->base + MSDC_PAD_TUNE, MSDC_PAD_TUNE_CMDRDLY,
+			      final_fall_delay.final_phase);
+		final_delay = final_fall_delay.final_phase;
+	}
+
+	return final_delay == 0xff ? -EIO : 0;
+}
+
+static int msdc_tune_data(struct mmc_host *mmc, u32 opcode)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	u32 rise_delay = 0, fall_delay = 0;
+	struct msdc_delay_phase final_rise_delay, final_fall_delay;
+	u8 final_delay, final_maxlen;
+	int i, ret;
+
+	sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_DSPL);
+	sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_W_DSPL);
+	for (i = 0 ; i < PAD_DELAY_MAX; i++) {
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_DATRRDLY, i);
+		ret = mmc_send_tuning(mmc, opcode, NULL);
+		if (!ret)
+			rise_delay |= (1 << i);
+	}
+
+	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_DSPL);
+	sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_W_DSPL);
+	for (i = 0; i < PAD_DELAY_MAX; i++) {
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_DATRRDLY, i);
+		ret = mmc_send_tuning(mmc, opcode, NULL);
+		if (!ret)
+			fall_delay |= (1 << i);
+	}
+
+	final_rise_delay = get_best_delay(host, rise_delay);
+	final_fall_delay = get_best_delay(host, fall_delay);
+
+	final_maxlen = max(final_rise_delay.maxlen, final_fall_delay.maxlen);
+	/* Rising edge is more stable, prefer to use it */
+	if (final_rise_delay.maxlen >= 10)
+		final_maxlen = final_rise_delay.maxlen;
+	if (final_maxlen == final_rise_delay.maxlen) {
+		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_DSPL);
+		sdr_clr_bits(host->base + MSDC_IOCON, MSDC_IOCON_W_DSPL);
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_DATRRDLY,
+			      final_rise_delay.final_phase);
+		final_delay = final_rise_delay.final_phase;
+	} else {
+		sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_DSPL);
+		sdr_set_bits(host->base + MSDC_IOCON, MSDC_IOCON_W_DSPL);
+		sdr_set_field(host->base + MSDC_PAD_TUNE,
+			      MSDC_PAD_TUNE_DATRRDLY,
+			      final_fall_delay.final_phase);
+		final_delay = final_fall_delay.final_phase;
+	}
+
+	return final_delay == 0xff ? -EIO : 0;
+}
+
+static int msdc_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+	int ret;
+
+	pm_runtime_get_sync(host->dev);
+	ret = msdc_tune_response(mmc, opcode);
+	if (ret == -EIO) {
+		dev_err(host->dev, "Tune response fail!\n");
+		goto out;
+	}
+	ret = msdc_tune_data(mmc, opcode);
+	if (ret == -EIO)
+		dev_err(host->dev, "Tune data fail!\n");
+
+out:
+	pm_runtime_mark_last_busy(host->dev);
+	pm_runtime_put_autosuspend(host->dev);
+	return ret;
+}
+
+static int msdc_prepare_hs400_tuning(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+
+	writel(host->hs400_ds_delay, host->base + PAD_DS_TUNE);
+	return 0;
+}
+
+static void msdc_hw_reset(struct mmc_host *mmc)
+{
+	struct msdc_host *host = mmc_priv(mmc);
+
+	sdr_set_bits(host->base + EMMC_IOCON, 1);
+	udelay(10); /* 10us is enough */
+	sdr_clr_bits(host->base + EMMC_IOCON, 1);
+}
+
 static struct mmc_host_ops mt_msdc_ops = {
 	.post_req = msdc_post_req,
 	.pre_req = msdc_pre_req,
@@ -1221,6 +1454,9 @@ static struct mmc_host_ops mt_msdc_ops = {
 	.set_ios = msdc_ops_set_ios,
 	.start_signal_voltage_switch = msdc_ops_switch_volt,
 	.card_busy = msdc_card_busy,
+	.execute_tuning = msdc_execute_tuning,
+	.prepare_hs400_tuning = msdc_prepare_hs400_tuning,
+	.hw_reset = msdc_hw_reset,
 };
 
 static int msdc_drv_probe(struct platform_device *pdev)
@@ -1294,6 +1530,11 @@ static int msdc_drv_probe(struct platform_device *pdev)
 		goto host_free;
 	}
 
+	if (!of_property_read_u32(pdev->dev.of_node, "hs400-ds-delay",
+				  &host->hs400_ds_delay))
+		dev_dbg(&pdev->dev, "hs400-ds-delay: %x\n",
+			host->hs400_ds_delay);
+
 	host->dev = &pdev->dev;
 	host->mmc = mmc;
 	host->src_clk_freq = clk_get_rate(host->src_clk);
@@ -1302,6 +1543,7 @@ static int msdc_drv_probe(struct platform_device *pdev)
 	mmc->f_min = host->src_clk_freq / (4 * 255);
 
 	mmc->caps |= MMC_CAP_ERASE | MMC_CAP_CMD23;
+	mmc->caps |= MMC_CAP_RUNTIME_RESUME;
 	/* MMC core transfer sizes tunable parameters */
 	mmc->max_segs = MAX_BD_NUM;
 	mmc->max_seg_size = BDMA_DESC_BUFLEN;
@@ -1313,7 +1555,7 @@ static int msdc_drv_probe(struct platform_device *pdev)
 
 	host->timeout_clks = 3 * 1048576;
 	host->dma.gpd = dma_alloc_coherent(&pdev->dev,
-				sizeof(struct mt_gpdma_desc),
+				2 * sizeof(struct mt_gpdma_desc),
 				&host->dma.gpd_addr, GFP_KERNEL);
 	host->dma.bd = dma_alloc_coherent(&pdev->dev,
 				MAX_BD_NUM * sizeof(struct mt_bdma_desc),
@@ -1354,7 +1596,7 @@ release:
 release_mem:
 	if (host->dma.gpd)
 		dma_free_coherent(&pdev->dev,
-			sizeof(struct mt_gpdma_desc),
+			2 * sizeof(struct mt_gpdma_desc),
 			host->dma.gpd, host->dma.gpd_addr);
 	if (host->dma.bd)
 		dma_free_coherent(&pdev->dev,
@@ -1403,6 +1645,8 @@ static void msdc_save_reg(struct msdc_host *host)
 	host->save_para.pad_tune = readl(host->base + MSDC_PAD_TUNE);
 	host->save_para.patch_bit0 = readl(host->base + MSDC_PATCH_BIT);
 	host->save_para.patch_bit1 = readl(host->base + MSDC_PATCH_BIT1);
+	host->save_para.pad_ds_tune = readl(host->base + PAD_DS_TUNE);
+	host->save_para.emmc50_cfg0 = readl(host->base + EMMC50_CFG0);
 }
 
 static void msdc_restore_reg(struct msdc_host *host)
@@ -1413,6 +1657,8 @@ static void msdc_restore_reg(struct msdc_host *host)
 	writel(host->save_para.pad_tune, host->base + MSDC_PAD_TUNE);
 	writel(host->save_para.patch_bit0, host->base + MSDC_PATCH_BIT);
 	writel(host->save_para.patch_bit1, host->base + MSDC_PATCH_BIT1);
+	writel(host->save_para.pad_ds_tune, host->base + PAD_DS_TUNE);
+	writel(host->save_para.emmc50_cfg0, host->base + EMMC50_CFG0);
 }
 
 static int msdc_runtime_suspend(struct device *dev)
diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c
index b763b11ed9e1..b9958a123594 100644
--- a/drivers/mmc/host/omap.c
+++ b/drivers/mmc/host/omap.c
@@ -1490,6 +1490,7 @@ static const struct of_device_id mmc_omap_match[] = {
 	{ .compatible = "ti,omap2420-mmc", },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, mmc_omap_match);
 #endif
 
 static struct platform_driver mmc_omap_driver = {
diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c
index 22d929fa3371..f6047fc94062 100644
--- a/drivers/mmc/host/sdhci-acpi.c
+++ b/drivers/mmc/host/sdhci-acpi.c
@@ -207,7 +207,9 @@ static const struct sdhci_acpi_slot sdhci_acpi_slot_int_emmc = {
 	.caps2   = MMC_CAP2_HC_ERASE_SZ,
 	.flags   = SDHCI_ACPI_RUNTIME_PM,
 	.quirks  = SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
-	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN | SDHCI_QUIRK2_STOP_WITH_TC,
+	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN |
+		   SDHCI_QUIRK2_STOP_WITH_TC |
+		   SDHCI_QUIRK2_CAPS_BIT63_FOR_HS400,
 	.probe_slot	= sdhci_acpi_emmc_probe_slot,
 };
 
@@ -239,6 +241,9 @@ struct sdhci_acpi_uid_slot {
 };
 
 static const struct sdhci_acpi_uid_slot sdhci_acpi_uids[] = {
+	{ "80865ACA", NULL, &sdhci_acpi_slot_int_sd },
+	{ "80865ACC", NULL, &sdhci_acpi_slot_int_emmc },
+	{ "80865AD0", NULL, &sdhci_acpi_slot_int_sdio },
 	{ "80860F14" , "1" , &sdhci_acpi_slot_int_emmc },
 	{ "80860F14" , "3" , &sdhci_acpi_slot_int_sd   },
 	{ "80860F16" , NULL, &sdhci_acpi_slot_int_sd   },
@@ -247,11 +252,15 @@ static const struct sdhci_acpi_uid_slot sdhci_acpi_uids[] = {
 	{ "INT33C6"  , NULL, &sdhci_acpi_slot_int_sdio },
 	{ "INT3436"  , NULL, &sdhci_acpi_slot_int_sdio },
 	{ "INT344D"  , NULL, &sdhci_acpi_slot_int_sdio },
+	{ "PNP0FFF"  , "3" , &sdhci_acpi_slot_int_sd   },
 	{ "PNP0D40"  },
 	{ },
 };
 
 static const struct acpi_device_id sdhci_acpi_ids[] = {
+	{ "80865ACA" },
+	{ "80865ACC" },
+	{ "80865AD0" },
 	{ "80860F14" },
 	{ "80860F16" },
 	{ "INT33BB"  },
diff --git a/drivers/mmc/host/sdhci-bcm-kona.c b/drivers/mmc/host/sdhci-bcm-kona.c
index 2bd90fb35c75..00a8a40a3729 100644
--- a/drivers/mmc/host/sdhci-bcm-kona.c
+++ b/drivers/mmc/host/sdhci-bcm-kona.c
@@ -273,7 +273,7 @@ static int sdhci_bcm_kona_probe(struct platform_device *pdev)
 		host->quirks |= SDHCI_QUIRK_BROKEN_CARD_DETECTION;
 
 	dev_dbg(dev, "is_8bit=%c\n",
-		(host->mmc->caps | MMC_CAP_8_BIT_DATA) ? 'Y' : 'N');
+		(host->mmc->caps & MMC_CAP_8_BIT_DATA) ? 'Y' : 'N');
 
 	ret = sdhci_bcm_kona_sd_reset(host);
 	if (ret)
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 886d230f41d0..1f1582f6cccb 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -759,7 +759,7 @@ static int esdhc_executing_tuning(struct sdhci_host *host, u32 opcode)
 	min = ESDHC_TUNE_CTRL_MIN;
 	while (min < ESDHC_TUNE_CTRL_MAX) {
 		esdhc_prepare_tuning(host, min);
-		if (!mmc_send_tuning(host->mmc))
+		if (!mmc_send_tuning(host->mmc, opcode, NULL))
 			break;
 		min += ESDHC_TUNE_CTRL_STEP;
 	}
@@ -768,7 +768,7 @@ static int esdhc_executing_tuning(struct sdhci_host *host, u32 opcode)
 	max = min + ESDHC_TUNE_CTRL_STEP;
 	while (max < ESDHC_TUNE_CTRL_MAX) {
 		esdhc_prepare_tuning(host, max);
-		if (mmc_send_tuning(host->mmc)) {
+		if (mmc_send_tuning(host->mmc, opcode, NULL)) {
 			max -= ESDHC_TUNE_CTRL_STEP;
 			break;
 		}
@@ -778,7 +778,7 @@ static int esdhc_executing_tuning(struct sdhci_host *host, u32 opcode)
 	/* use average delay to get the best timing */
 	avg = (min + max) / 2;
 	esdhc_prepare_tuning(host, avg);
-	ret = mmc_send_tuning(host->mmc);
+	ret = mmc_send_tuning(host->mmc, opcode, NULL);
 	esdhc_post_tuning(host);
 
 	dev_dbg(mmc_dev(host->mmc), "tunning %s at 0x%x ret %d\n",
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index 163ac9974d91..de132e281753 100644
--- a/drivers/mmc/host/sdhci-esdhc.h
+++ b/drivers/mmc/host/sdhci-esdhc.h
@@ -24,6 +24,8 @@
 				SDHCI_QUIRK_PIO_NEEDS_DELAY | \
 				SDHCI_QUIRK_NO_HISPD_BIT)
 
+#define ESDHC_PROCTL		0x28
+
 #define ESDHC_SYSTEM_CONTROL	0x2c
 #define ESDHC_CLOCK_MASK	0x0000fff0
 #define ESDHC_PREDIV_SHIFT	8
diff --git a/drivers/mmc/host/sdhci-msm.c b/drivers/mmc/host/sdhci-msm.c
index 4bcee033feda..4695bee203ea 100644
--- a/drivers/mmc/host/sdhci-msm.c
+++ b/drivers/mmc/host/sdhci-msm.c
@@ -373,7 +373,7 @@ retry:
 		if (rc)
 			return rc;
 
-		rc = mmc_send_tuning(mmc);
+		rc = mmc_send_tuning(mmc, opcode, NULL);
 		if (!rc) {
 			/* Tuning is successful at this tuning point */
 			tuned_phases[tuned_phase_cnt++] = phase;
diff --git a/drivers/mmc/host/sdhci-of-at91.c b/drivers/mmc/host/sdhci-of-at91.c
index a0f05de5409f..06d0b50dfe71 100644
--- a/drivers/mmc/host/sdhci-of-at91.c
+++ b/drivers/mmc/host/sdhci-of-at91.c
@@ -111,7 +111,6 @@ static int sdhci_at91_probe(struct platform_device *pdev)
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to set gck");
 		goto hclock_disable_unprepare;
-		return -EINVAL;
 	}
 	/*
 	 * We need to check if we have the requested rate for gck because in
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c
index 653f335bef15..90e94a028a49 100644
--- a/drivers/mmc/host/sdhci-of-esdhc.c
+++ b/drivers/mmc/host/sdhci-of-esdhc.c
@@ -24,122 +24,324 @@
 
 #define VENDOR_V_22	0x12
 #define VENDOR_V_23	0x13
-static u32 esdhc_readl(struct sdhci_host *host, int reg)
+
+struct sdhci_esdhc {
+	u8 vendor_ver;
+	u8 spec_ver;
+};
+
+/**
+ * esdhc_read*_fixup - Fixup the value read from incompatible eSDHC register
+ *		       to make it compatible with SD spec.
+ *
+ * @host: pointer to sdhci_host
+ * @spec_reg: SD spec register address
+ * @value: 32bit eSDHC register value on spec_reg address
+ *
+ * In SD spec, there are 8/16/32/64 bits registers, while all of eSDHC
+ * registers are 32 bits. There are differences in register size, register
+ * address, register function, bit position and function between eSDHC spec
+ * and SD spec.
+ *
+ * Return a fixed up register value
+ */
+static u32 esdhc_readl_fixup(struct sdhci_host *host,
+				     int spec_reg, u32 value)
 {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_esdhc *esdhc = pltfm_host->priv;
 	u32 ret;
 
-	ret = in_be32(host->ioaddr + reg);
 	/*
 	 * The bit of ADMA flag in eSDHC is not compatible with standard
 	 * SDHC register, so set fake flag SDHCI_CAN_DO_ADMA2 when ADMA is
 	 * supported by eSDHC.
 	 * And for many FSL eSDHC controller, the reset value of field
-	 * SDHCI_CAN_DO_ADMA1 is one, but some of them can't support ADMA,
+	 * SDHCI_CAN_DO_ADMA1 is 1, but some of them can't support ADMA,
 	 * only these vendor version is greater than 2.2/0x12 support ADMA.
-	 * For FSL eSDHC, must aligned 4-byte, so use 0xFC to read the
-	 * the verdor version number, oxFE is SDHCI_HOST_VERSION.
 	 */
-	if ((reg == SDHCI_CAPABILITIES) && (ret & SDHCI_CAN_DO_ADMA1)) {
-		u32 tmp = in_be32(host->ioaddr + SDHCI_SLOT_INT_STATUS);
-		tmp = (tmp & SDHCI_VENDOR_VER_MASK) >> SDHCI_VENDOR_VER_SHIFT;
-		if (tmp > VENDOR_V_22)
-			ret |= SDHCI_CAN_DO_ADMA2;
+	if ((spec_reg == SDHCI_CAPABILITIES) && (value & SDHCI_CAN_DO_ADMA1)) {
+		if (esdhc->vendor_ver > VENDOR_V_22) {
+			ret = value | SDHCI_CAN_DO_ADMA2;
+			return ret;
+		}
 	}
-
+	ret = value;
 	return ret;
 }
 
-static u16 esdhc_readw(struct sdhci_host *host, int reg)
+static u16 esdhc_readw_fixup(struct sdhci_host *host,
+				     int spec_reg, u32 value)
 {
 	u16 ret;
-	int base = reg & ~0x3;
-	int shift = (reg & 0x2) * 8;
+	int shift = (spec_reg & 0x2) * 8;
 
-	if (unlikely(reg == SDHCI_HOST_VERSION))
-		ret = in_be32(host->ioaddr + base) & 0xffff;
+	if (spec_reg == SDHCI_HOST_VERSION)
+		ret = value & 0xffff;
 	else
-		ret = (in_be32(host->ioaddr + base) >> shift) & 0xffff;
+		ret = (value >> shift) & 0xffff;
 	return ret;
 }
 
-static u8 esdhc_readb(struct sdhci_host *host, int reg)
+static u8 esdhc_readb_fixup(struct sdhci_host *host,
+				     int spec_reg, u32 value)
 {
-	int base = reg & ~0x3;
-	int shift = (reg & 0x3) * 8;
-	u8 ret = (in_be32(host->ioaddr + base) >> shift) & 0xff;
+	u8 ret;
+	u8 dma_bits;
+	int shift = (spec_reg & 0x3) * 8;
+
+	ret = (value >> shift) & 0xff;
 
 	/*
 	 * "DMA select" locates at offset 0x28 in SD specification, but on
 	 * P5020 or P3041, it locates at 0x29.
 	 */
-	if (reg == SDHCI_HOST_CONTROL) {
-		u32 dma_bits;
-
-		dma_bits = in_be32(host->ioaddr + reg);
+	if (spec_reg == SDHCI_HOST_CONTROL) {
 		/* DMA select is 22,23 bits in Protocol Control Register */
-		dma_bits = (dma_bits >> 5) & SDHCI_CTRL_DMA_MASK;
-
+		dma_bits = (value >> 5) & SDHCI_CTRL_DMA_MASK;
 		/* fixup the result */
 		ret &= ~SDHCI_CTRL_DMA_MASK;
 		ret |= dma_bits;
 	}
-
 	return ret;
 }
 
-static void esdhc_writel(struct sdhci_host *host, u32 val, int reg)
+/**
+ * esdhc_write*_fixup - Fixup the SD spec register value so that it could be
+ *			written into eSDHC register.
+ *
+ * @host: pointer to sdhci_host
+ * @spec_reg: SD spec register address
+ * @value: 8/16/32bit SD spec register value that would be written
+ * @old_value: 32bit eSDHC register value on spec_reg address
+ *
+ * In SD spec, there are 8/16/32/64 bits registers, while all of eSDHC
+ * registers are 32 bits. There are differences in register size, register
+ * address, register function, bit position and function between eSDHC spec
+ * and SD spec.
+ *
+ * Return a fixed up register value
+ */
+static u32 esdhc_writel_fixup(struct sdhci_host *host,
+				     int spec_reg, u32 value, u32 old_value)
 {
+	u32 ret;
+
 	/*
-	 * Enable IRQSTATEN[BGESEN] is just to set IRQSTAT[BGE]
-	 * when SYSCTL[RSTD]) is set for some special operations.
-	 * No any impact other operation.
+	 * Enabling IRQSTATEN[BGESEN] is just to set IRQSTAT[BGE]
+	 * when SYSCTL[RSTD] is set for some special operations.
+	 * No any impact on other operation.
 	 */
-	if (reg == SDHCI_INT_ENABLE)
-		val |= SDHCI_INT_BLK_GAP;
-	sdhci_be32bs_writel(host, val, reg);
+	if (spec_reg == SDHCI_INT_ENABLE)
+		ret = value | SDHCI_INT_BLK_GAP;
+	else
+		ret = value;
+
+	return ret;
 }
 
-static void esdhc_writew(struct sdhci_host *host, u16 val, int reg)
+static u32 esdhc_writew_fixup(struct sdhci_host *host,
+				     int spec_reg, u16 value, u32 old_value)
 {
-	if (reg == SDHCI_BLOCK_SIZE) {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	int shift = (spec_reg & 0x2) * 8;
+	u32 ret;
+
+	switch (spec_reg) {
+	case SDHCI_TRANSFER_MODE:
+		/*
+		 * Postpone this write, we must do it together with a
+		 * command write that is down below. Return old value.
+		 */
+		pltfm_host->xfer_mode_shadow = value;
+		return old_value;
+	case SDHCI_COMMAND:
+		ret = (value << 16) | pltfm_host->xfer_mode_shadow;
+		return ret;
+	}
+
+	ret = old_value & (~(0xffff << shift));
+	ret |= (value << shift);
+
+	if (spec_reg == SDHCI_BLOCK_SIZE) {
 		/*
 		 * Two last DMA bits are reserved, and first one is used for
 		 * non-standard blksz of 4096 bytes that we don't support
 		 * yet. So clear the DMA boundary bits.
 		 */
-		val &= ~SDHCI_MAKE_BLKSZ(0x7, 0);
+		ret &= (~SDHCI_MAKE_BLKSZ(0x7, 0));
 	}
-	sdhci_be32bs_writew(host, val, reg);
+	return ret;
 }
 
-static void esdhc_writeb(struct sdhci_host *host, u8 val, int reg)
+static u32 esdhc_writeb_fixup(struct sdhci_host *host,
+				     int spec_reg, u8 value, u32 old_value)
 {
+	u32 ret;
+	u32 dma_bits;
+	u8 tmp;
+	int shift = (spec_reg & 0x3) * 8;
+
+	/*
+	 * eSDHC doesn't have a standard power control register, so we do
+	 * nothing here to avoid incorrect operation.
+	 */
+	if (spec_reg == SDHCI_POWER_CONTROL)
+		return old_value;
 	/*
 	 * "DMA select" location is offset 0x28 in SD specification, but on
 	 * P5020 or P3041, it's located at 0x29.
 	 */
-	if (reg == SDHCI_HOST_CONTROL) {
-		u32 dma_bits;
-
+	if (spec_reg == SDHCI_HOST_CONTROL) {
 		/*
 		 * If host control register is not standard, exit
 		 * this function
 		 */
 		if (host->quirks2 & SDHCI_QUIRK2_BROKEN_HOST_CONTROL)
-			return;
+			return old_value;
 
 		/* DMA select is 22,23 bits in Protocol Control Register */
-		dma_bits = (val & SDHCI_CTRL_DMA_MASK) << 5;
-		clrsetbits_be32(host->ioaddr + reg , SDHCI_CTRL_DMA_MASK << 5,
-			dma_bits);
-		val &= ~SDHCI_CTRL_DMA_MASK;
-		val |= in_be32(host->ioaddr + reg) & SDHCI_CTRL_DMA_MASK;
+		dma_bits = (value & SDHCI_CTRL_DMA_MASK) << 5;
+		ret = (old_value & (~(SDHCI_CTRL_DMA_MASK << 5))) | dma_bits;
+		tmp = (value & (~SDHCI_CTRL_DMA_MASK)) |
+		      (old_value & SDHCI_CTRL_DMA_MASK);
+		ret = (ret & (~0xff)) | tmp;
+
+		/* Prevent SDHCI core from writing reserved bits (e.g. HISPD) */
+		ret &= ~ESDHC_HOST_CONTROL_RES;
+		return ret;
 	}
 
-	/* Prevent SDHCI core from writing reserved bits (e.g. HISPD). */
-	if (reg == SDHCI_HOST_CONTROL)
-		val &= ~ESDHC_HOST_CONTROL_RES;
-	sdhci_be32bs_writeb(host, val, reg);
+	ret = (old_value & (~(0xff << shift))) | (value << shift);
+	return ret;
+}
+
+static u32 esdhc_be_readl(struct sdhci_host *host, int reg)
+{
+	u32 ret;
+	u32 value;
+
+	value = ioread32be(host->ioaddr + reg);
+	ret = esdhc_readl_fixup(host, reg, value);
+
+	return ret;
+}
+
+static u32 esdhc_le_readl(struct sdhci_host *host, int reg)
+{
+	u32 ret;
+	u32 value;
+
+	value = ioread32(host->ioaddr + reg);
+	ret = esdhc_readl_fixup(host, reg, value);
+
+	return ret;
+}
+
+static u16 esdhc_be_readw(struct sdhci_host *host, int reg)
+{
+	u16 ret;
+	u32 value;
+	int base = reg & ~0x3;
+
+	value = ioread32be(host->ioaddr + base);
+	ret = esdhc_readw_fixup(host, reg, value);
+	return ret;
+}
+
+static u16 esdhc_le_readw(struct sdhci_host *host, int reg)
+{
+	u16 ret;
+	u32 value;
+	int base = reg & ~0x3;
+
+	value = ioread32(host->ioaddr + base);
+	ret = esdhc_readw_fixup(host, reg, value);
+	return ret;
+}
+
+static u8 esdhc_be_readb(struct sdhci_host *host, int reg)
+{
+	u8 ret;
+	u32 value;
+	int base = reg & ~0x3;
+
+	value = ioread32be(host->ioaddr + base);
+	ret = esdhc_readb_fixup(host, reg, value);
+	return ret;
+}
+
+static u8 esdhc_le_readb(struct sdhci_host *host, int reg)
+{
+	u8 ret;
+	u32 value;
+	int base = reg & ~0x3;
+
+	value = ioread32(host->ioaddr + base);
+	ret = esdhc_readb_fixup(host, reg, value);
+	return ret;
+}
+
+static void esdhc_be_writel(struct sdhci_host *host, u32 val, int reg)
+{
+	u32 value;
+
+	value = esdhc_writel_fixup(host, reg, val, 0);
+	iowrite32be(value, host->ioaddr + reg);
+}
+
+static void esdhc_le_writel(struct sdhci_host *host, u32 val, int reg)
+{
+	u32 value;
+
+	value = esdhc_writel_fixup(host, reg, val, 0);
+	iowrite32(value, host->ioaddr + reg);
+}
+
+static void esdhc_be_writew(struct sdhci_host *host, u16 val, int reg)
+{
+	int base = reg & ~0x3;
+	u32 value;
+	u32 ret;
+
+	value = ioread32be(host->ioaddr + base);
+	ret = esdhc_writew_fixup(host, reg, val, value);
+	if (reg != SDHCI_TRANSFER_MODE)
+		iowrite32be(ret, host->ioaddr + base);
+}
+
+static void esdhc_le_writew(struct sdhci_host *host, u16 val, int reg)
+{
+	int base = reg & ~0x3;
+	u32 value;
+	u32 ret;
+
+	value = ioread32(host->ioaddr + base);
+	ret = esdhc_writew_fixup(host, reg, val, value);
+	if (reg != SDHCI_TRANSFER_MODE)
+		iowrite32(ret, host->ioaddr + base);
+}
+
+static void esdhc_be_writeb(struct sdhci_host *host, u8 val, int reg)
+{
+	int base = reg & ~0x3;
+	u32 value;
+	u32 ret;
+
+	value = ioread32be(host->ioaddr + base);
+	ret = esdhc_writeb_fixup(host, reg, val, value);
+	iowrite32be(ret, host->ioaddr + base);
+}
+
+static void esdhc_le_writeb(struct sdhci_host *host, u8 val, int reg)
+{
+	int base = reg & ~0x3;
+	u32 value;
+	u32 ret;
+
+	value = ioread32(host->ioaddr + base);
+	ret = esdhc_writeb_fixup(host, reg, val, value);
+	iowrite32(ret, host->ioaddr + base);
 }
 
 /*
@@ -149,19 +351,17 @@ static void esdhc_writeb(struct sdhci_host *host, u8 val, int reg)
  * For Continue, apply soft reset for data(SYSCTL[RSTD]);
  * and re-issue the entire read transaction from beginning.
  */
-static void esdhci_of_adma_workaround(struct sdhci_host *host, u32 intmask)
+static void esdhc_of_adma_workaround(struct sdhci_host *host, u32 intmask)
 {
-	u32 tmp;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_esdhc *esdhc = pltfm_host->priv;
 	bool applicable;
 	dma_addr_t dmastart;
 	dma_addr_t dmanow;
 
-	tmp = in_be32(host->ioaddr + SDHCI_SLOT_INT_STATUS);
-	tmp = (tmp & SDHCI_VENDOR_VER_MASK) >> SDHCI_VENDOR_VER_SHIFT;
-
 	applicable = (intmask & SDHCI_INT_DATA_END) &&
-		(intmask & SDHCI_INT_BLK_GAP) &&
-		(tmp == VENDOR_V_23);
+		     (intmask & SDHCI_INT_BLK_GAP) &&
+		     (esdhc->vendor_ver == VENDOR_V_23);
 	if (!applicable)
 		return;
 
@@ -179,7 +379,11 @@ static void esdhci_of_adma_workaround(struct sdhci_host *host, u32 intmask)
 
 static int esdhc_of_enable_dma(struct sdhci_host *host)
 {
-	setbits32(host->ioaddr + ESDHC_DMA_SYSCTL, ESDHC_DMA_SNOOP);
+	u32 value;
+
+	value = sdhci_readl(host, ESDHC_DMA_SYSCTL);
+	value |= ESDHC_DMA_SNOOP;
+	sdhci_writel(host, value, ESDHC_DMA_SYSCTL);
 	return 0;
 }
 
@@ -199,6 +403,8 @@ static unsigned int esdhc_of_get_min_clock(struct sdhci_host *host)
 
 static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 {
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_esdhc *esdhc = pltfm_host->priv;
 	int pre_div = 1;
 	int div = 1;
 	u32 temp;
@@ -209,9 +415,7 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 		return;
 
 	/* Workaround to start pre_div at 2 for VNN < VENDOR_V_23 */
-	temp = esdhc_readw(host, SDHCI_HOST_VERSION);
-	temp = (temp & SDHCI_VENDOR_VER_MASK) >> SDHCI_VENDOR_VER_SHIFT;
-	if (temp < VENDOR_V_23)
+	if (esdhc->vendor_ver < VENDOR_V_23)
 		pre_div = 2;
 
 	/* Workaround to reduce the clock frequency for p1010 esdhc */
@@ -247,39 +451,26 @@ static void esdhc_of_set_clock(struct sdhci_host *host, unsigned int clock)
 	mdelay(1);
 }
 
-static void esdhc_of_platform_init(struct sdhci_host *host)
-{
-	u32 vvn;
-
-	vvn = in_be32(host->ioaddr + SDHCI_SLOT_INT_STATUS);
-	vvn = (vvn & SDHCI_VENDOR_VER_MASK) >> SDHCI_VENDOR_VER_SHIFT;
-	if (vvn == VENDOR_V_22)
-		host->quirks2 |= SDHCI_QUIRK2_HOST_NO_CMD23;
-
-	if (vvn > VENDOR_V_22)
-		host->quirks &= ~SDHCI_QUIRK_NO_BUSY_IRQ;
-}
-
 static void esdhc_pltfm_set_bus_width(struct sdhci_host *host, int width)
 {
 	u32 ctrl;
 
+	ctrl = sdhci_readl(host, ESDHC_PROCTL);
+	ctrl &= (~ESDHC_CTRL_BUSWIDTH_MASK);
 	switch (width) {
 	case MMC_BUS_WIDTH_8:
-		ctrl = ESDHC_CTRL_8BITBUS;
+		ctrl |= ESDHC_CTRL_8BITBUS;
 		break;
 
 	case MMC_BUS_WIDTH_4:
-		ctrl = ESDHC_CTRL_4BITBUS;
+		ctrl |= ESDHC_CTRL_4BITBUS;
 		break;
 
 	default:
-		ctrl = 0;
 		break;
 	}
 
-	clrsetbits_be32(host->ioaddr + SDHCI_HOST_CONTROL,
-			ESDHC_CTRL_BUSWIDTH_MASK, ctrl);
+	sdhci_writel(host, ctrl, ESDHC_PROCTL);
 }
 
 static void esdhc_reset(struct sdhci_host *host, u8 mask)
@@ -290,32 +481,13 @@ static void esdhc_reset(struct sdhci_host *host, u8 mask)
 	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
 }
 
-static const struct sdhci_ops sdhci_esdhc_ops = {
-	.read_l = esdhc_readl,
-	.read_w = esdhc_readw,
-	.read_b = esdhc_readb,
-	.write_l = esdhc_writel,
-	.write_w = esdhc_writew,
-	.write_b = esdhc_writeb,
-	.set_clock = esdhc_of_set_clock,
-	.enable_dma = esdhc_of_enable_dma,
-	.get_max_clock = esdhc_of_get_max_clock,
-	.get_min_clock = esdhc_of_get_min_clock,
-	.platform_init = esdhc_of_platform_init,
-	.adma_workaround = esdhci_of_adma_workaround,
-	.set_bus_width = esdhc_pltfm_set_bus_width,
-	.reset = esdhc_reset,
-	.set_uhs_signaling = sdhci_set_uhs_signaling,
-};
-
 #ifdef CONFIG_PM
-
 static u32 esdhc_proctl;
 static int esdhc_of_suspend(struct device *dev)
 {
 	struct sdhci_host *host = dev_get_drvdata(dev);
 
-	esdhc_proctl = sdhci_be32bs_readl(host, SDHCI_HOST_CONTROL);
+	esdhc_proctl = sdhci_readl(host, SDHCI_HOST_CONTROL);
 
 	return sdhci_suspend_host(host);
 }
@@ -328,9 +500,8 @@ static int esdhc_of_resume(struct device *dev)
 	if (ret == 0) {
 		/* Isn't this already done by sdhci_resume_host() ? --rmk */
 		esdhc_of_enable_dma(host);
-		sdhci_be32bs_writel(host, esdhc_proctl, SDHCI_HOST_CONTROL);
+		sdhci_writel(host, esdhc_proctl, SDHCI_HOST_CONTROL);
 	}
-
 	return ret;
 }
 
@@ -343,37 +514,103 @@ static const struct dev_pm_ops esdhc_pmops = {
 #define ESDHC_PMOPS NULL
 #endif
 
-static const struct sdhci_pltfm_data sdhci_esdhc_pdata = {
-	/*
-	 * card detection could be handled via GPIO
-	 * eSDHC cannot support End Attribute in NOP ADMA descriptor
-	 */
+static const struct sdhci_ops sdhci_esdhc_be_ops = {
+	.read_l = esdhc_be_readl,
+	.read_w = esdhc_be_readw,
+	.read_b = esdhc_be_readb,
+	.write_l = esdhc_be_writel,
+	.write_w = esdhc_be_writew,
+	.write_b = esdhc_be_writeb,
+	.set_clock = esdhc_of_set_clock,
+	.enable_dma = esdhc_of_enable_dma,
+	.get_max_clock = esdhc_of_get_max_clock,
+	.get_min_clock = esdhc_of_get_min_clock,
+	.adma_workaround = esdhc_of_adma_workaround,
+	.set_bus_width = esdhc_pltfm_set_bus_width,
+	.reset = esdhc_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
+};
+
+static const struct sdhci_ops sdhci_esdhc_le_ops = {
+	.read_l = esdhc_le_readl,
+	.read_w = esdhc_le_readw,
+	.read_b = esdhc_le_readb,
+	.write_l = esdhc_le_writel,
+	.write_w = esdhc_le_writew,
+	.write_b = esdhc_le_writeb,
+	.set_clock = esdhc_of_set_clock,
+	.enable_dma = esdhc_of_enable_dma,
+	.get_max_clock = esdhc_of_get_max_clock,
+	.get_min_clock = esdhc_of_get_min_clock,
+	.adma_workaround = esdhc_of_adma_workaround,
+	.set_bus_width = esdhc_pltfm_set_bus_width,
+	.reset = esdhc_reset,
+	.set_uhs_signaling = sdhci_set_uhs_signaling,
+};
+
+static const struct sdhci_pltfm_data sdhci_esdhc_be_pdata = {
 	.quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_CARD_DETECTION
 		| SDHCI_QUIRK_NO_CARD_NO_RESET
 		| SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
-	.ops = &sdhci_esdhc_ops,
+	.ops = &sdhci_esdhc_be_ops,
 };
 
+static const struct sdhci_pltfm_data sdhci_esdhc_le_pdata = {
+	.quirks = ESDHC_DEFAULT_QUIRKS | SDHCI_QUIRK_BROKEN_CARD_DETECTION
+		| SDHCI_QUIRK_NO_CARD_NO_RESET
+		| SDHCI_QUIRK_NO_ENDATTR_IN_NOPDESC,
+	.ops = &sdhci_esdhc_le_ops,
+};
+
+static void esdhc_init(struct platform_device *pdev, struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host;
+	struct sdhci_esdhc *esdhc;
+	u16 host_ver;
+
+	pltfm_host = sdhci_priv(host);
+	esdhc = devm_kzalloc(&pdev->dev, sizeof(struct sdhci_esdhc),
+			     GFP_KERNEL);
+
+	host_ver = sdhci_readw(host, SDHCI_HOST_VERSION);
+	esdhc->vendor_ver = (host_ver & SDHCI_VENDOR_VER_MASK) >>
+			     SDHCI_VENDOR_VER_SHIFT;
+	esdhc->spec_ver = host_ver & SDHCI_SPEC_VER_MASK;
+
+	pltfm_host->priv = esdhc;
+}
+
 static int sdhci_esdhc_probe(struct platform_device *pdev)
 {
 	struct sdhci_host *host;
 	struct device_node *np;
 	int ret;
 
-	host = sdhci_pltfm_init(pdev, &sdhci_esdhc_pdata, 0);
+	np = pdev->dev.of_node;
+
+	if (of_get_property(np, "little-endian", NULL))
+		host = sdhci_pltfm_init(pdev, &sdhci_esdhc_le_pdata, 0);
+	else
+		host = sdhci_pltfm_init(pdev, &sdhci_esdhc_be_pdata, 0);
+
 	if (IS_ERR(host))
 		return PTR_ERR(host);
 
+	esdhc_init(pdev, host);
+
 	sdhci_get_of_property(pdev);
 
-	np = pdev->dev.of_node;
 	if (of_device_is_compatible(np, "fsl,p5040-esdhc") ||
 	    of_device_is_compatible(np, "fsl,p5020-esdhc") ||
 	    of_device_is_compatible(np, "fsl,p4080-esdhc") ||
 	    of_device_is_compatible(np, "fsl,p1020-esdhc") ||
-	    of_device_is_compatible(np, "fsl,t1040-esdhc"))
+	    of_device_is_compatible(np, "fsl,t1040-esdhc") ||
+	    of_device_is_compatible(np, "fsl,ls1021a-esdhc"))
 		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
 
+	if (of_device_is_compatible(np, "fsl,ls1021a-esdhc"))
+		host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL;
+
 	if (of_device_is_compatible(np, "fsl,p2020-esdhc")) {
 		/*
 		 * Freescale messed up with P2020 as it has a non-standard
diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci-core.c
index b3b0a3e4fca1..cf7ad458b4f4 100644
--- a/drivers/mmc/host/sdhci-pci.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -444,11 +444,7 @@ static int jmicron_pmos(struct sdhci_pci_chip *chip, int on)
 	else
 		scratch &= ~0x47;
 
-	ret = pci_write_config_byte(chip->pdev, 0xAE, scratch);
-	if (ret)
-		return ret;
-
-	return 0;
+	return pci_write_config_byte(chip->pdev, 0xAE, scratch);
 }
 
 static int jmicron_probe(struct sdhci_pci_chip *chip)
@@ -1113,6 +1109,62 @@ static const struct pci_device_id pci_ids[] = {
 	},
 
 	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_DNV_EMMC,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_emmc,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BXT_EMMC,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_emmc,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BXT_SDIO,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sdio,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_BXT_SD,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sd,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_APL_EMMC,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_emmc,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_APL_SDIO,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sdio,
+	},
+
+	{
+		.vendor		= PCI_VENDOR_ID_INTEL,
+		.device		= PCI_DEVICE_ID_INTEL_APL_SD,
+		.subvendor	= PCI_ANY_ID,
+		.subdevice	= PCI_ANY_ID,
+		.driver_data	= (kernel_ulong_t)&sdhci_intel_byt_sd,
+	},
+
+	{
 		.vendor		= PCI_VENDOR_ID_O2,
 		.device		= PCI_DEVICE_ID_O2_8120,
 		.subvendor	= PCI_ANY_ID,
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.c b/drivers/mmc/host/sdhci-pci-o2micro.c
index e2ec108dba0e..d48f03104b5b 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.c
+++ b/drivers/mmc/host/sdhci-pci-o2micro.c
@@ -60,7 +60,7 @@ static void o2_pci_led_enable(struct sdhci_pci_chip *chip)
 
 }
 
-void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip)
+static void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip)
 {
 	u32 scratch_32;
 	int ret;
@@ -145,7 +145,6 @@ void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip)
 	scratch_32 |= 0x00080000;
 	pci_write_config_dword(chip->pdev, O2_SD_MISC_CTRL4, scratch_32);
 }
-EXPORT_SYMBOL_GPL(sdhci_pci_o2_fujin2_pci_init);
 
 int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot)
 {
@@ -179,7 +178,6 @@ int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sdhci_pci_o2_probe_slot);
 
 int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip)
 {
@@ -385,11 +383,9 @@ int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sdhci_pci_o2_probe);
 
 int sdhci_pci_o2_resume(struct sdhci_pci_chip *chip)
 {
 	sdhci_pci_o2_probe(chip);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(sdhci_pci_o2_resume);
diff --git a/drivers/mmc/host/sdhci-pci-o2micro.h b/drivers/mmc/host/sdhci-pci-o2micro.h
index f7ffc908d9a0..770f53857211 100644
--- a/drivers/mmc/host/sdhci-pci-o2micro.h
+++ b/drivers/mmc/host/sdhci-pci-o2micro.h
@@ -64,8 +64,6 @@
 #define O2_SD_VENDOR_SETTING	0x110
 #define O2_SD_VENDOR_SETTING2	0x1C8
 
-extern void sdhci_pci_o2_fujin2_pci_init(struct sdhci_pci_chip *chip);
-
 extern int sdhci_pci_o2_probe_slot(struct sdhci_pci_slot *slot);
 
 extern int sdhci_pci_o2_probe(struct sdhci_pci_chip *chip);
diff --git a/drivers/mmc/host/sdhci-pci.h b/drivers/mmc/host/sdhci-pci.h
index 541f1cad5247..d1a0b4db60db 100644
--- a/drivers/mmc/host/sdhci-pci.h
+++ b/drivers/mmc/host/sdhci-pci.h
@@ -24,6 +24,13 @@
 #define PCI_DEVICE_ID_INTEL_SPT_EMMC	0x9d2b
 #define PCI_DEVICE_ID_INTEL_SPT_SDIO	0x9d2c
 #define PCI_DEVICE_ID_INTEL_SPT_SD	0x9d2d
+#define PCI_DEVICE_ID_INTEL_DNV_EMMC	0x19db
+#define PCI_DEVICE_ID_INTEL_BXT_SD	0x0aca
+#define PCI_DEVICE_ID_INTEL_BXT_EMMC	0x0acc
+#define PCI_DEVICE_ID_INTEL_BXT_SDIO	0x0ad0
+#define PCI_DEVICE_ID_INTEL_APL_SD	0x5aca
+#define PCI_DEVICE_ID_INTEL_APL_EMMC	0x5acc
+#define PCI_DEVICE_ID_INTEL_APL_SDIO	0x5ad0
 
 /*
  * PCI registers
diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c
index a207f5aaf62f..87fb5ea8ebe7 100644
--- a/drivers/mmc/host/sdhci-pltfm.c
+++ b/drivers/mmc/host/sdhci-pltfm.c
@@ -71,9 +71,7 @@ void sdhci_get_of_property(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	struct sdhci_host *host = platform_get_drvdata(pdev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	const __be32 *clk;
 	u32 bus_width;
-	int size;
 
 	if (of_get_property(np, "sdhci,auto-cmd12", NULL))
 		host->quirks |= SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12;
@@ -101,9 +99,7 @@ void sdhci_get_of_property(struct platform_device *pdev)
 	    of_device_is_compatible(np, "fsl,mpc8536-esdhc"))
 		host->quirks |= SDHCI_QUIRK_BROKEN_TIMEOUT_VAL;
 
-	clk = of_get_property(np, "clock-frequency", &size);
-	if (clk && size == sizeof(*clk) && *clk)
-		pltfm_host->clock = be32_to_cpup(clk);
+	of_property_read_u32(np, "clock-frequency", &pltfm_host->clock);
 
 	if (of_find_property(np, "keep-power-in-suspend", NULL))
 		host->mmc->pm_caps |= MMC_PM_KEEP_POWER;
diff --git a/drivers/mmc/host/sdhci-sirf.c b/drivers/mmc/host/sdhci-sirf.c
index 884294576356..34866f668dd7 100644
--- a/drivers/mmc/host/sdhci-sirf.c
+++ b/drivers/mmc/host/sdhci-sirf.c
@@ -50,7 +50,8 @@ static u32 sdhci_sirf_readl_le(struct sdhci_host *host, int reg)
 	if (unlikely((reg == SDHCI_CAPABILITIES_1) &&
 			(host->mmc->caps & MMC_CAP_UHS_SDR50))) {
 		/* fake CAP_1 register */
-		val = SDHCI_SUPPORT_SDR50 | SDHCI_USE_SDR50_TUNING;
+		val = SDHCI_SUPPORT_DDR50 |
+			SDHCI_SUPPORT_SDR50 | SDHCI_USE_SDR50_TUNING;
 	}
 
 	if (unlikely(reg == SDHCI_SLOT_INT_STATUS)) {
@@ -97,7 +98,7 @@ retry:
 			clock_setting | phase,
 			SDHCI_CLK_DELAY_SETTING);
 
-		if (!mmc_send_tuning(mmc)) {
+		if (!mmc_send_tuning(mmc, opcode, NULL)) {
 			/* Tuning is successful at this tuning point */
 			tuned_phase_cnt++;
 			dev_dbg(mmc_dev(mmc), "%s: Found good phase = %d\n",
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index fbc7efdddcb5..b48565ed5616 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1895,9 +1895,9 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		tuning_count = host->tuning_count;
 
 	/*
-	 * The Host Controller needs tuning only in case of SDR104 mode
-	 * and for SDR50 mode when Use Tuning for SDR50 is set in the
-	 * Capabilities register.
+	 * The Host Controller needs tuning in case of SDR104 and DDR50
+	 * mode, and for SDR50 mode when Use Tuning for SDR50 is set in
+	 * the Capabilities register.
 	 * If the Host Controller supports the HS200 mode then the
 	 * tuning function has to be executed.
 	 */
@@ -1917,6 +1917,7 @@ static int sdhci_execute_tuning(struct mmc_host *mmc, u32 opcode)
 		break;
 
 	case MMC_TIMING_UHS_SDR104:
+	case MMC_TIMING_UHS_DDR50:
 		break;
 
 	case MMC_TIMING_UHS_SDR50:
@@ -2716,17 +2717,6 @@ int sdhci_resume_host(struct sdhci_host *host)
 			host->ops->enable_dma(host);
 	}
 
-	if (!device_may_wakeup(mmc_dev(host->mmc))) {
-		ret = request_threaded_irq(host->irq, sdhci_irq,
-					   sdhci_thread_irq, IRQF_SHARED,
-					   mmc_hostname(host->mmc), host);
-		if (ret)
-			return ret;
-	} else {
-		sdhci_disable_irq_wakeups(host);
-		disable_irq_wake(host->irq);
-	}
-
 	if ((host->mmc->pm_flags & MMC_PM_KEEP_POWER) &&
 	    (host->quirks2 & SDHCI_QUIRK2_HOST_OFF_CARD_ON)) {
 		/* Card keeps power but host controller does not */
@@ -2739,6 +2729,17 @@ int sdhci_resume_host(struct sdhci_host *host)
 		mmiowb();
 	}
 
+	if (!device_may_wakeup(mmc_dev(host->mmc))) {
+		ret = request_threaded_irq(host->irq, sdhci_irq,
+					   sdhci_thread_irq, IRQF_SHARED,
+					   mmc_hostname(host->mmc), host);
+		if (ret)
+			return ret;
+	} else {
+		sdhci_disable_irq_wakeups(host);
+		disable_irq_wake(host->irq);
+	}
+
 	sdhci_enable_card_detection(host);
 
 	return ret;
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index b981b8552e43..83de82bceafc 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -873,6 +873,13 @@ static void sunxi_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	spin_unlock_irqrestore(&host->lock, iflags);
 }
 
+static int sunxi_mmc_card_busy(struct mmc_host *mmc)
+{
+	struct sunxi_mmc_host *host = mmc_priv(mmc);
+
+	return !!(mmc_readl(host, REG_STAS) & SDXC_CARD_DATA_BUSY);
+}
+
 static const struct of_device_id sunxi_mmc_of_match[] = {
 	{ .compatible = "allwinner,sun4i-a10-mmc", },
 	{ .compatible = "allwinner,sun5i-a13-mmc", },
@@ -888,6 +895,7 @@ static struct mmc_host_ops sunxi_mmc_ops = {
 	.get_cd		 = mmc_gpio_get_cd,
 	.enable_sdio_irq = sunxi_mmc_enable_sdio_irq,
 	.hw_reset	 = sunxi_mmc_hw_reset,
+	.card_busy	 = sunxi_mmc_card_busy,
 };
 
 static const struct sunxi_mmc_clk_delay sunxi_mmc_clk_delays[] = {
diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c
index fbabbb82b354..1e819f98b94f 100644
--- a/drivers/mmc/host/vub300.c
+++ b/drivers/mmc/host/vub300.c
@@ -563,7 +563,7 @@ static void add_offloaded_reg(struct vub300_mmc_host *vub300,
 			i += 1;
 			continue;
 		}
-	};
+	}
 	__add_offloaded_reg_to_fifo(vub300, register_access, func);
 }
 
@@ -1372,7 +1372,7 @@ static void download_offload_pseudocode(struct vub300_mmc_host *vub300)
 		l += snprintf(vub300->vub_name + l,
 			      sizeof(vub300->vub_name) - l, "_%04X%04X",
 			      sf->vendor, sf->device);
-	};
+	}
 	snprintf(vub300->vub_name + l, sizeof(vub300->vub_name) - l, ".bin");
 	dev_info(&vub300->udev->dev, "requesting offload firmware %s\n",
 		 vub300->vub_name);
@@ -1893,7 +1893,7 @@ static int satisfy_request_from_offloaded_data(struct vub300_mmc_host *vub300,
 			i += 1;
 			continue;
 		}
-	};
+	}
 	if (vub300->total_offload_count == 0)
 		return 0;
 	else if (vub300->fn[func].offload_count == 0)
diff --git a/drivers/mmc/host/wbsd.c b/drivers/mmc/host/wbsd.c
index ca183ea767b3..c3fd16d997ca 100644
--- a/drivers/mmc/host/wbsd.c
+++ b/drivers/mmc/host/wbsd.c
@@ -809,7 +809,7 @@ static void wbsd_request(struct mmc_host *mmc, struct mmc_request *mrq)
 			cmd->error = -EINVAL;
 
 			goto done;
-		};
+		}
 	}
 
 	/*
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index fdd0779ccdfa..eb0151bac50c 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -269,7 +269,6 @@ struct mmc_card {
 						/* for byte mode */
 #define MMC_QUIRK_NONSTD_SDIO	(1<<2)		/* non-standard SDIO card attached */
 						/* (missing CIA registers) */
-#define MMC_QUIRK_BROKEN_CLK_GATING (1<<3)	/* clock gating the sdio bus will make card fail */
 #define MMC_QUIRK_NONSTD_FUNC_IF (1<<4)		/* SDIO card has nonstd function interfaces */
 #define MMC_QUIRK_DISABLE_CD	(1<<5)		/* disconnect CD/DAT[3] resistor */
 #define MMC_QUIRK_INAND_CMD38	(1<<6)		/* iNAND devices have broken CMD38 */
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 258daf914c6d..37967b6da03c 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -152,10 +152,8 @@ extern int mmc_app_cmd(struct mmc_host *, struct mmc_card *);
 extern int mmc_wait_for_app_cmd(struct mmc_host *, struct mmc_card *,
 	struct mmc_command *, int);
 extern void mmc_start_bkops(struct mmc_card *card, bool from_exception);
-extern int __mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int, bool,
-			bool, bool);
 extern int mmc_switch(struct mmc_card *, u8, u8, u8, unsigned int);
-extern int mmc_send_tuning(struct mmc_host *host);
+extern int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error);
 extern int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd);
 
 #define MMC_ERASE_ARG		0x00000000
diff --git a/include/linux/mmc/dw_mmc.h b/include/linux/mmc/dw_mmc.h
index 134c57422740..f67b2ec18e6d 100644
--- a/include/linux/mmc/dw_mmc.h
+++ b/include/linux/mmc/dw_mmc.h
@@ -16,6 +16,7 @@
 
 #include <linux/scatterlist.h>
 #include <linux/mmc/core.h>
+#include <linux/dmaengine.h>
 
 #define MAX_MCI_SLOTS	2
 
@@ -40,6 +41,17 @@ enum {
 
 struct mmc_data;
 
+enum {
+	TRANS_MODE_PIO = 0,
+	TRANS_MODE_IDMAC,
+	TRANS_MODE_EDMAC
+};
+
+struct dw_mci_dma_slave {
+	struct dma_chan *ch;
+	enum dma_transfer_direction direction;
+};
+
 /**
  * struct dw_mci - MMC controller state shared between all slots
  * @lock: Spinlock protecting the queue and associated data.
@@ -154,7 +166,14 @@ struct dw_mci {
 	dma_addr_t		sg_dma;
 	void			*sg_cpu;
 	const struct dw_mci_dma_ops	*dma_ops;
+	/* For idmac */
 	unsigned int		ring_size;
+
+	/* For edmac */
+	struct dw_mci_dma_slave *dms;
+	/* Registers's physical base address */
+	void                    *phy_regs;
+
 	u32			cmd_status;
 	u32			data_status;
 	u32			stop_cmdr;
@@ -208,8 +227,8 @@ struct dw_mci {
 struct dw_mci_dma_ops {
 	/* DMA Ops */
 	int (*init)(struct dw_mci *host);
-	void (*start)(struct dw_mci *host, unsigned int sg_len);
-	void (*complete)(struct dw_mci *host);
+	int (*start)(struct dw_mci *host, unsigned int sg_len);
+	void (*complete)(void *host);
 	void (*stop)(struct dw_mci *host);
 	void (*cleanup)(struct dw_mci *host);
 	void (*exit)(struct dw_mci *host);
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 83b81fd865f3..8673ffe3d86e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -292,18 +292,6 @@ struct mmc_host {
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 
-#ifdef CONFIG_MMC_CLKGATE
-	int			clk_requests;	/* internal reference counter */
-	unsigned int		clk_delay;	/* number of MCI clk hold cycles */
-	bool			clk_gated;	/* clock gated */
-	struct delayed_work	clk_gate_work; /* delayed clock gate */
-	unsigned int		clk_old;	/* old clock value cache */
-	spinlock_t		clk_lock;	/* lock for clk fields */
-	struct mutex		clk_gate_mutex;	/* mutex for clock gating */
-	struct device_attribute clkgate_delay_attr;
-	unsigned long           clkgate_delay;
-#endif
-
 	/* host specific block data */
 	unsigned int		max_seg_size;	/* see blk_queue_max_segment_size */
 	unsigned short		max_segs;	/* see blk_queue_max_segments */
@@ -423,6 +411,7 @@ int mmc_regulator_get_ocrmask(struct regulator *supply);
 int mmc_regulator_set_ocr(struct mmc_host *mmc,
 			struct regulator *supply,
 			unsigned short vdd_bit);
+int mmc_regulator_set_vqmmc(struct mmc_host *mmc, struct mmc_ios *ios);
 #else
 static inline int mmc_regulator_get_ocrmask(struct regulator *supply)
 {
@@ -435,6 +424,12 @@ static inline int mmc_regulator_set_ocr(struct mmc_host *mmc,
 {
 	return 0;
 }
+
+static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc,
+					  struct mmc_ios *ios)
+{
+	return -EINVAL;
+}
 #endif
 
 int mmc_regulator_get_supply(struct mmc_host *mmc);
@@ -479,26 +474,6 @@ static inline int mmc_host_packed_wr(struct mmc_host *host)
 	return host->caps2 & MMC_CAP2_PACKED_WR;
 }
 
-#ifdef CONFIG_MMC_CLKGATE
-void mmc_host_clk_hold(struct mmc_host *host);
-void mmc_host_clk_release(struct mmc_host *host);
-unsigned int mmc_host_clk_rate(struct mmc_host *host);
-
-#else
-static inline void mmc_host_clk_hold(struct mmc_host *host)
-{
-}
-
-static inline void mmc_host_clk_release(struct mmc_host *host)
-{
-}
-
-static inline unsigned int mmc_host_clk_rate(struct mmc_host *host)
-{
-	return host->ios.clock;
-}
-#endif
-
 static inline int mmc_card_hs(struct mmc_card *card)
 {
 	return card->host->ios.timing == MMC_TIMING_SD_HS ||
diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h
index 1f5e68923929..7e385b83b9d8 100644
--- a/include/uapi/linux/mmc/ioctl.h
+++ b/include/uapi/linux/mmc/ioctl.h
@@ -45,8 +45,24 @@ struct mmc_ioc_cmd {
 };
 #define mmc_ioc_cmd_set_data(ic, ptr) ic.data_ptr = (__u64)(unsigned long) ptr
 
-#define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd)
+/**
+ * struct mmc_ioc_multi_cmd - multi command information
+ * @num_of_cmds: Number of commands to send. Must be equal to or less than
+ *	MMC_IOC_MAX_CMDS.
+ * @cmds: Array of commands with length equal to 'num_of_cmds'
+ */
+struct mmc_ioc_multi_cmd {
+	__u64 num_of_cmds;
+	struct mmc_ioc_cmd cmds[0];
+};
 
+#define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd)
+/*
+ * MMC_IOC_MULTI_CMD: Used to send an array of MMC commands described by
+ *	the structure mmc_ioc_multi_cmd. The MMC driver will issue all
+ *	commands in array in sequence to card.
+ */
+#define MMC_IOC_MULTI_CMD _IOWR(MMC_BLOCK_MAJOR, 1, struct mmc_ioc_multi_cmd)
 /*
  * Since this ioctl is only meant to enhance (and not replace) normal access
  * to the mmc bus device, an upper data transfer limit of MMC_IOC_MAX_BYTES
@@ -54,4 +70,5 @@ struct mmc_ioc_cmd {
  * block device operations.
  */
 #define MMC_IOC_MAX_BYTES  (512L * 256)
+#define MMC_IOC_MAX_CMDS    255
 #endif /* LINUX_MMC_IOCTL_H */