[PATCH V5 0/3] HW Command Queue support for Tegra SDMMC

[PATCH V5 0/3] HW Command Queue support for Tegra SDMMC

[Sowjanya Komatineni]

This patch series is for HW Command Queue support for Tegra SDMMC.

Patch[3] adds HW Command Queue support for Tegra SDMMC and has
dependencies on other patches in this series as explained below.

Patch[2] SDMMC address range:
This patch defines exact register space for all the SDMMC
Controllers. Controllers supporting command queue are having
CQHCI register space from offset 0xF000.
Patch[3] uses address range of sdmmc controllers to identify command
queue supported controllers

Patch[1] Fix V4 Mode enable:
V4 Mode need to be enabled to select Host Version 4.0 mode for HW Command
queue support with Tegra SDHCI.

Sowjanya Komatineni (3):
  mmc: sdhci: Fix sdhci_do_enable_v4_mode
  arm64: dtsi: Fix SDMMC address range
  mmc: tegra: HW Command Queue Support for Tegra SDMMC

 arch/arm64/boot/dts/nvidia/tegra186.dtsi |   6 +-
 arch/arm64/boot/dts/nvidia/tegra194.dtsi |   4 +-
 drivers/mmc/host/Kconfig                 |   1 +
 drivers/mmc/host/sdhci-tegra.c           | 138 ++++++++++++++++++++++++++++++-
 drivers/mmc/host/sdhci.c                 |   4 +-
 5 files changed, 145 insertions(+), 8 deletions(-)

-- 
2.7.4

[PATCH V5 1/3] mmc: sdhci: Fix sdhci_do_enable_v4_mode

[Sowjanya Komatineni]

V4_MODE is Bit-15 of SDHCI_HOST_CONTROL2 register.
Need to perform word access to this register.

Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>
---
 drivers/mmc/host/sdhci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 99bdae53fa2e..fde984d10619 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -127,12 +127,12 @@ static void sdhci_do_enable_v4_mode(struct sdhci_host *host)
 {
 	u16 ctrl2;
 
-	ctrl2 = sdhci_readb(host, SDHCI_HOST_CONTROL2);
+	ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
 	if (ctrl2 & SDHCI_CTRL_V4_MODE)
 		return;
 
 	ctrl2 |= SDHCI_CTRL_V4_MODE;
-	sdhci_writeb(host, ctrl2, SDHCI_HOST_CONTROL);
+	sdhci_writew(host, ctrl2, SDHCI_HOST_CONTROL2);
 }
 
 /*
-- 
2.7.4

[PATCH V5 2/3] arm64: dtsi: Fix SDMMC address range

[Sowjanya Komatineni]

This patch fixes the SDMMC Controllers address space to be exact
defined register address range as per the design.

SDMMC Controller supporting Command Queue has CQHCI registers at
offset 0xF000.

This fix helps to identify the Tegra SDMMC Controllers supporting
Command Queue based on the size of address space.

Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>
---
 arch/arm64/boot/dts/nvidia/tegra186.dtsi | 6 +++---
 arch/arm64/boot/dts/nvidia/tegra194.dtsi | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
index 2f3c8e29520d..6fda3d6a7f3d 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
@@ -231,7 +231,7 @@
 
 	sdmmc1: sdhci@3400000 {
 		compatible = "nvidia,tegra186-sdhci";
-		reg = <0x0 0x03400000 0x0 0x10000>;
+		reg = <0x0 0x03400000 0x0 0x220>;
 		interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&bpmp TEGRA186_CLK_SDMMC1>;
 		clock-names = "sdhci";
@@ -256,7 +256,7 @@
 
 	sdmmc2: sdhci@3420000 {
 		compatible = "nvidia,tegra186-sdhci";
-		reg = <0x0 0x03420000 0x0 0x10000>;
+		reg = <0x0 0x03420000 0x0 0x220>;
 		interrupts = <GIC_SPI 63 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&bpmp TEGRA186_CLK_SDMMC2>;
 		clock-names = "sdhci";
@@ -276,7 +276,7 @@
 
 	sdmmc3: sdhci@3440000 {
 		compatible = "nvidia,tegra186-sdhci";
-		reg = <0x0 0x03440000 0x0 0x10000>;
+		reg = <0x0 0x03440000 0x0 0x220>;
 		interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
 		clocks = <&bpmp TEGRA186_CLK_SDMMC3>;
 		clock-names = "sdhci";
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index c2091bb16546..6510ef6492b1 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -295,7 +295,7 @@
 
 		sdmmc1: sdhci@3400000 {
 			compatible = "nvidia,tegra194-sdhci", "nvidia,tegra186-sdhci";
-			reg = <0x03400000 0x10000>;
+			reg = <0x03400000 0x220>;
 			interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&bpmp TEGRA194_CLK_SDMMC1>;
 			clock-names = "sdhci";
@@ -306,7 +306,7 @@
 
 		sdmmc3: sdhci@3440000 {
 			compatible = "nvidia,tegra194-sdhci", "nvidia,tegra186-sdhci";
-			reg = <0x03440000 0x10000>;
+			reg = <0x03440000 0x220>;
 			interrupts = <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&bpmp TEGRA194_CLK_SDMMC3>;
 			clock-names = "sdhci";
-- 
2.7.4

[PATCH V5 3/3] mmc: tegra: HW Command Queue Support for Tegra SDMMC

[Sowjanya Komatineni]

This patch adds HW Command Queue for supported Tegra SDMMC
controllers.

Tegra SDHCI with Quirk SDHCI_QUIRK2_BROKEN_64_BIT_DMA disables the
use of 64_BIT DMA to disable 64-bit addressing mode access to the
system memory and sdhci_cqe_enable using flag SDHCI_USE_64_BIT_DMA
for ADMA32/ADMA2 Vs ADMA64/ADMA3 DMA selection.

CQE need to use ADMA3 as it need to fetch task descriptor along
with transfer descriptor, so this patch forces DMA Select to be
ADMA3 for CQE.

Tegra SDMMC Host design prevents write access to BLOCK_COUNT
register when CQE is enabled to prevent SW from updating block
size during Command Queue mode. As per eMMC5.1 device spec, block
size of 512 B need to be set prior to enabling Command Queue.

Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>
---
 drivers/mmc/host/Kconfig       |   1 +
 drivers/mmc/host/sdhci-tegra.c | 138 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 138 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 1b58739d9744..5aa2de2c7609 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -250,6 +250,7 @@ config MMC_SDHCI_TEGRA
 	depends on ARCH_TEGRA
 	depends on MMC_SDHCI_PLTFM
 	select MMC_SDHCI_IO_ACCESSORS
+	select MMC_CQHCI
 	help
 	  This selects the Tegra SD/MMC controller. If you have a Tegra
 	  platform with SD or MMC devices, say Y or M here.
diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
index 7b95d088fdef..68b328df05ed 100644
--- a/drivers/mmc/host/sdhci-tegra.c
+++ b/drivers/mmc/host/sdhci-tegra.c
@@ -33,6 +33,7 @@
 #include <linux/ktime.h>
 
 #include "sdhci-pltfm.h"
+#include "cqhci.h"
 
 /* Tegra SDHOST controller vendor register definitions */
 #define SDHCI_TEGRA_VENDOR_CLOCK_CTRL			0x100
@@ -89,6 +90,9 @@
 #define NVQUIRK_NEEDS_PAD_CONTROL			BIT(7)
 #define NVQUIRK_DIS_CARD_CLK_CONFIG_TAP			BIT(8)
 
+/* SDMMC CQE Base Address for Tegra Host Ver 4.1 and Higher */
+#define SDHCI_TEGRA_CQE_BASE_ADDR			0xF000
+
 struct sdhci_tegra_soc_data {
 	const struct sdhci_pltfm_data *pdata;
 	u32 nvquirks;
@@ -128,6 +132,7 @@ struct sdhci_tegra {
 	u32 default_tap;
 	u32 default_trim;
 	u32 dqs_trim;
+	bool enable_hwcq;
 };
 
 static u16 tegra_sdhci_readw(struct sdhci_host *host, int reg)
@@ -836,6 +841,80 @@ static void tegra_sdhci_voltage_switch(struct sdhci_host *host)
 		tegra_host->pad_calib_required = true;
 }
 
+static void sdhci_tegra_cqe_enable(struct mmc_host *mmc)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	struct cqhci_host *cq_host = mmc->cqe_private;
+	unsigned long flags;
+	u8 ctrl;
+	u32 cqcfg = 0;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
+	ctrl &= ~SDHCI_CTRL_DMA_MASK;
+	if ((host->flags & SDHCI_USE_64_BIT_DMA) ||
+			(host->quirks2 & SDHCI_QUIRK2_BROKEN_64_BIT_DMA))
+		ctrl |= SDHCI_CTRL_ADMA64;
+	else
+		ctrl |= SDHCI_CTRL_ADMA32;
+	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
+
+	/* Tegra SDMMC Controller design prevents write access to BLOCK_COUNT
+	 * registers when CQE is enabled.
+	 */
+	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
+	if (cqcfg & CQHCI_ENABLE)
+		cqhci_writel(cq_host, (cqcfg & ~CQHCI_ENABLE), CQHCI_CFG);
+
+	sdhci_writew(host, SDHCI_MAKE_BLKSZ(host->sdma_boundary, 512),
+		     SDHCI_BLOCK_SIZE);
+
+	if (cqcfg & CQHCI_ENABLE)
+		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+	/* Set maximum timeout */
+	sdhci_writeb(host, 0xE, SDHCI_TIMEOUT_CONTROL);
+
+	host->ier = host->cqe_ier;
+
+	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
+
+	host->cqe_on = true;
+
+	pr_debug("%s: sdhci: CQE on, IRQ mask %#x, IRQ status %#x\n",
+		 mmc_hostname(mmc), host->ier,
+		 sdhci_readl(host, SDHCI_INT_STATUS));
+
+	mmiowb();
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
+static void sdhci_tegra_dumpregs(struct mmc_host *mmc)
+{
+	sdhci_dumpregs(mmc_priv(mmc));
+}
+
+static u32 sdhci_tegra_cqhci_irq(struct sdhci_host *host, u32 intmask)
+{
+	int cmd_error = 0;
+	int data_error = 0;
+
+	if (!sdhci_cqe_irq(host, intmask, &cmd_error, &data_error))
+		return intmask;
+
+	cqhci_irq(host->mmc, intmask, cmd_error, data_error);
+
+	return 0;
+}
+
+static const struct cqhci_host_ops sdhci_tegra_cqhci_ops = {
+	.enable	= sdhci_tegra_cqe_enable,
+	.disable = sdhci_cqe_disable,
+	.dumpregs = sdhci_tegra_dumpregs,
+};
+
 static const struct sdhci_ops tegra_sdhci_ops = {
 	.get_ro     = tegra_sdhci_get_ro,
 	.read_w     = tegra_sdhci_readw,
@@ -989,6 +1068,7 @@ static const struct sdhci_ops tegra186_sdhci_ops = {
 	.set_uhs_signaling = tegra_sdhci_set_uhs_signaling,
 	.voltage_switch = tegra_sdhci_voltage_switch,
 	.get_max_clock = tegra_sdhci_get_max_clock,
+	.irq = sdhci_tegra_cqhci_irq,
 };
 
 static const struct sdhci_pltfm_data sdhci_tegra186_pdata = {
@@ -1030,6 +1110,55 @@ static const struct of_device_id sdhci_tegra_dt_match[] = {
 };
 MODULE_DEVICE_TABLE(of, sdhci_tegra_dt_match);
 
+static int sdhci_tegra_add_host(struct sdhci_host *host)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_tegra *tegra_host = sdhci_pltfm_priv(pltfm_host);
+	struct cqhci_host *cq_host;
+	bool dma64;
+	int ret;
+
+	if (!tegra_host->enable_hwcq)
+		return sdhci_add_host(host);
+
+	host->v4_mode = true;
+
+	ret = sdhci_setup_host(host);
+	if (ret)
+		return ret;
+
+	host->mmc->caps2 |= MMC_CAP2_CQE | MMC_CAP2_CQE_DCMD;
+
+	cq_host = devm_kzalloc(host->mmc->parent,
+				sizeof(*cq_host), GFP_KERNEL);
+	if (!cq_host) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
+	cq_host->mmio = host->ioaddr + SDHCI_TEGRA_CQE_BASE_ADDR;
+	cq_host->ops = &sdhci_tegra_cqhci_ops;
+
+	dma64 = host->flags & SDHCI_USE_64_BIT_DMA;
+	if (dma64)
+		cq_host->caps |= CQHCI_TASK_DESC_SZ_128;
+
+	ret = cqhci_init(cq_host, host->mmc, dma64);
+	if (ret)
+		goto cleanup;
+
+	ret = __sdhci_add_host(host);
+	if (ret)
+		goto cleanup;
+
+	return 0;
+
+cleanup:
+	sdhci_cleanup_host(host);
+	return ret;
+
+}
+
 static int sdhci_tegra_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
@@ -1039,6 +1168,7 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 	struct sdhci_tegra *tegra_host;
 	struct clk *clk;
 	int rc;
+	struct resource *iomem;
 
 	match = of_match_device(sdhci_tegra_dt_match, &pdev->dev);
 	if (!match)
@@ -1056,6 +1186,12 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 	tegra_host->pad_control_available = false;
 	tegra_host->soc_data = soc_data;
 
+	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (resource_size(iomem) > SDHCI_TEGRA_CQE_BASE_ADDR)
+		tegra_host->enable_hwcq = true;
+	else
+		tegra_host->enable_hwcq = false;
+
 	if (soc_data->nvquirks & NVQUIRK_NEEDS_PAD_CONTROL) {
 		rc = tegra_sdhci_init_pinctrl_info(&pdev->dev, tegra_host);
 		if (rc == 0)
@@ -1117,7 +1253,7 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
 
 	usleep_range(2000, 4000);
 
-	rc = sdhci_add_host(host);
+	rc = sdhci_tegra_add_host(host);
 	if (rc)
 		goto err_add_host;
 
-- 
2.7.4

Re: [PATCH V5 1/3] mmc: sdhci: Fix sdhci_do_enable_v4_mode

[Adrian Hunter]

On 21/12/18 3:25 AM, Sowjanya Komatineni wrote:
> V4_MODE is Bit-15 of SDHCI_HOST_CONTROL2 register.
> Need to perform word access to this register.
> 
> Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>

This patch has already been applied.

> ---
>  drivers/mmc/host/sdhci.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
> index 99bdae53fa2e..fde984d10619 100644
> --- a/drivers/mmc/host/sdhci.c
> +++ b/drivers/mmc/host/sdhci.c
> @@ -127,12 +127,12 @@ static void sdhci_do_enable_v4_mode(struct sdhci_host *host)
>  {
>  	u16 ctrl2;
>  
> -	ctrl2 = sdhci_readb(host, SDHCI_HOST_CONTROL2);
> +	ctrl2 = sdhci_readw(host, SDHCI_HOST_CONTROL2);
>  	if (ctrl2 & SDHCI_CTRL_V4_MODE)
>  		return;
>  
>  	ctrl2 |= SDHCI_CTRL_V4_MODE;
> -	sdhci_writeb(host, ctrl2, SDHCI_HOST_CONTROL);
> +	sdhci_writew(host, ctrl2, SDHCI_HOST_CONTROL2);
>  }
>  
>  /*
> 

Re: [PATCH V5 3/3] mmc: tegra: HW Command Queue Support for Tegra SDMMC

[Adrian Hunter]

On 21/12/18 3:25 AM, Sowjanya Komatineni wrote:
> This patch adds HW Command Queue for supported Tegra SDMMC
> controllers.
> 
> Tegra SDHCI with Quirk SDHCI_QUIRK2_BROKEN_64_BIT_DMA disables the
> use of 64_BIT DMA to disable 64-bit addressing mode access to the
> system memory and sdhci_cqe_enable using flag SDHCI_USE_64_BIT_DMA
> for ADMA32/ADMA2 Vs ADMA64/ADMA3 DMA selection.
> 
> CQE need to use ADMA3 as it need to fetch task descriptor along
> with transfer descriptor, so this patch forces DMA Select to be
> ADMA3 for CQE.
> 
> Tegra SDMMC Host design prevents write access to BLOCK_COUNT
> register when CQE is enabled to prevent SW from updating block
> size during Command Queue mode. As per eMMC5.1 device spec, block
> size of 512 B need to be set prior to enabling Command Queue.
> 
> Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>

Just a couple of minor comments below.

> ---
>  drivers/mmc/host/Kconfig       |   1 +
>  drivers/mmc/host/sdhci-tegra.c | 138 ++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 138 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
> index 1b58739d9744..5aa2de2c7609 100644
> --- a/drivers/mmc/host/Kconfig
> +++ b/drivers/mmc/host/Kconfig
> @@ -250,6 +250,7 @@ config MMC_SDHCI_TEGRA
>  	depends on ARCH_TEGRA
>  	depends on MMC_SDHCI_PLTFM
>  	select MMC_SDHCI_IO_ACCESSORS
> +	select MMC_CQHCI
>  	help
>  	  This selects the Tegra SD/MMC controller. If you have a Tegra
>  	  platform with SD or MMC devices, say Y or M here.
> diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c
> index 7b95d088fdef..68b328df05ed 100644
> --- a/drivers/mmc/host/sdhci-tegra.c
> +++ b/drivers/mmc/host/sdhci-tegra.c
> @@ -33,6 +33,7 @@
>  #include <linux/ktime.h>
>  
>  #include "sdhci-pltfm.h"
> +#include "cqhci.h"
>  
>  /* Tegra SDHOST controller vendor register definitions */
>  #define SDHCI_TEGRA_VENDOR_CLOCK_CTRL			0x100
> @@ -89,6 +90,9 @@
>  #define NVQUIRK_NEEDS_PAD_CONTROL			BIT(7)
>  #define NVQUIRK_DIS_CARD_CLK_CONFIG_TAP			BIT(8)
>  
> +/* SDMMC CQE Base Address for Tegra Host Ver 4.1 and Higher */
> +#define SDHCI_TEGRA_CQE_BASE_ADDR			0xF000
> +
>  struct sdhci_tegra_soc_data {
>  	const struct sdhci_pltfm_data *pdata;
>  	u32 nvquirks;
> @@ -128,6 +132,7 @@ struct sdhci_tegra {
>  	u32 default_tap;
>  	u32 default_trim;
>  	u32 dqs_trim;
> +	bool enable_hwcq;
>  };
>  
>  static u16 tegra_sdhci_readw(struct sdhci_host *host, int reg)
> @@ -836,6 +841,80 @@ static void tegra_sdhci_voltage_switch(struct sdhci_host *host)
>  		tegra_host->pad_calib_required = true;
>  }
>  
> +static void sdhci_tegra_cqe_enable(struct mmc_host *mmc)
> +{
> +	struct sdhci_host *host = mmc_priv(mmc);
> +	struct cqhci_host *cq_host = mmc->cqe_private;
> +	unsigned long flags;
> +	u8 ctrl;
> +	u32 cqcfg = 0;
> +
> +	spin_lock_irqsave(&host->lock, flags);
> +
> +	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
> +	ctrl &= ~SDHCI_CTRL_DMA_MASK;
> +	if ((host->flags & SDHCI_USE_64_BIT_DMA) ||
> +			(host->quirks2 & SDHCI_QUIRK2_BROKEN_64_BIT_DMA))

You are selecting 64-bit DMA if 64-bit DMA is broken.  Is that intended?
Maybe add a comment.

> +		ctrl |= SDHCI_CTRL_ADMA64;
> +	else
> +		ctrl |= SDHCI_CTRL_ADMA32;
> +	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
> +
> +	/* Tegra SDMMC Controller design prevents write access to BLOCK_COUNT
> +	 * registers when CQE is enabled.
> +	 */
> +	cqcfg = cqhci_readl(cq_host, CQHCI_CFG);
> +	if (cqcfg & CQHCI_ENABLE)
> +		cqhci_writel(cq_host, (cqcfg & ~CQHCI_ENABLE), CQHCI_CFG);
> +
> +	sdhci_writew(host, SDHCI_MAKE_BLKSZ(host->sdma_boundary, 512),
> +		     SDHCI_BLOCK_SIZE);
> +
> +	if (cqcfg & CQHCI_ENABLE)
> +		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
> +
> +	/* Set maximum timeout */
> +	sdhci_writeb(host, 0xE, SDHCI_TIMEOUT_CONTROL);
> +
> +	host->ier = host->cqe_ier;
> +
> +	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
> +	sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
> +
> +	host->cqe_on = true;
> +
> +	pr_debug("%s: sdhci: CQE on, IRQ mask %#x, IRQ status %#x\n",
> +		 mmc_hostname(mmc), host->ier,
> +		 sdhci_readl(host, SDHCI_INT_STATUS));
> +
> +	mmiowb();
> +	spin_unlock_irqrestore(&host->lock, flags);

Most of this is the same as sdhci_cqe_enable().  Did you consider
rearranging things and calling sdhci_cqe_enable()?

> +}
> +
> +static void sdhci_tegra_dumpregs(struct mmc_host *mmc)
> +{
> +	sdhci_dumpregs(mmc_priv(mmc));
> +}
> +
> +static u32 sdhci_tegra_cqhci_irq(struct sdhci_host *host, u32 intmask)
> +{
> +	int cmd_error = 0;
> +	int data_error = 0;
> +
> +	if (!sdhci_cqe_irq(host, intmask, &cmd_error, &data_error))
> +		return intmask;
> +
> +	cqhci_irq(host->mmc, intmask, cmd_error, data_error);
> +
> +	return 0;
> +}
> +
> +static const struct cqhci_host_ops sdhci_tegra_cqhci_ops = {
> +	.enable	= sdhci_tegra_cqe_enable,
> +	.disable = sdhci_cqe_disable,
> +	.dumpregs = sdhci_tegra_dumpregs,
> +};
> +
>  static const struct sdhci_ops tegra_sdhci_ops = {
>  	.get_ro     = tegra_sdhci_get_ro,
>  	.read_w     = tegra_sdhci_readw,
> @@ -989,6 +1068,7 @@ static const struct sdhci_ops tegra186_sdhci_ops = {
>  	.set_uhs_signaling = tegra_sdhci_set_uhs_signaling,
>  	.voltage_switch = tegra_sdhci_voltage_switch,
>  	.get_max_clock = tegra_sdhci_get_max_clock,
> +	.irq = sdhci_tegra_cqhci_irq,
>  };
>  
>  static const struct sdhci_pltfm_data sdhci_tegra186_pdata = {
> @@ -1030,6 +1110,55 @@ static const struct of_device_id sdhci_tegra_dt_match[] = {
>  };
>  MODULE_DEVICE_TABLE(of, sdhci_tegra_dt_match);
>  
> +static int sdhci_tegra_add_host(struct sdhci_host *host)
> +{
> +	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
> +	struct sdhci_tegra *tegra_host = sdhci_pltfm_priv(pltfm_host);
> +	struct cqhci_host *cq_host;
> +	bool dma64;
> +	int ret;
> +
> +	if (!tegra_host->enable_hwcq)
> +		return sdhci_add_host(host);
> +
> +	host->v4_mode = true;
> +
> +	ret = sdhci_setup_host(host);
> +	if (ret)
> +		return ret;
> +
> +	host->mmc->caps2 |= MMC_CAP2_CQE | MMC_CAP2_CQE_DCMD;
> +
> +	cq_host = devm_kzalloc(host->mmc->parent,
> +				sizeof(*cq_host), GFP_KERNEL);
> +	if (!cq_host) {
> +		ret = -ENOMEM;
> +		goto cleanup;
> +	}
> +
> +	cq_host->mmio = host->ioaddr + SDHCI_TEGRA_CQE_BASE_ADDR;
> +	cq_host->ops = &sdhci_tegra_cqhci_ops;
> +
> +	dma64 = host->flags & SDHCI_USE_64_BIT_DMA;
> +	if (dma64)
> +		cq_host->caps |= CQHCI_TASK_DESC_SZ_128;
> +
> +	ret = cqhci_init(cq_host, host->mmc, dma64);
> +	if (ret)
> +		goto cleanup;
> +
> +	ret = __sdhci_add_host(host);
> +	if (ret)
> +		goto cleanup;
> +
> +	return 0;
> +
> +cleanup:
> +	sdhci_cleanup_host(host);
> +	return ret;
> +
> +}
> +
>  static int sdhci_tegra_probe(struct platform_device *pdev)
>  {
>  	const struct of_device_id *match;
> @@ -1039,6 +1168,7 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
>  	struct sdhci_tegra *tegra_host;
>  	struct clk *clk;
>  	int rc;
> +	struct resource *iomem;
>  
>  	match = of_match_device(sdhci_tegra_dt_match, &pdev->dev);
>  	if (!match)
> @@ -1056,6 +1186,12 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
>  	tegra_host->pad_control_available = false;
>  	tegra_host->soc_data = soc_data;
>  
> +	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
> +	if (resource_size(iomem) > SDHCI_TEGRA_CQE_BASE_ADDR)
> +		tegra_host->enable_hwcq = true;
> +	else
> +		tegra_host->enable_hwcq = false;
> +
>  	if (soc_data->nvquirks & NVQUIRK_NEEDS_PAD_CONTROL) {
>  		rc = tegra_sdhci_init_pinctrl_info(&pdev->dev, tegra_host);
>  		if (rc == 0)
> @@ -1117,7 +1253,7 @@ static int sdhci_tegra_probe(struct platform_device *pdev)
>  
>  	usleep_range(2000, 4000);
>  
> -	rc = sdhci_add_host(host);
> +	rc = sdhci_tegra_add_host(host);
>  	if (rc)
>  		goto err_add_host;
>  
>