[PATCH V6 2/2] mmc: tegra: HW Command Queue Support for Tegra SDMMC

[Sowjanya Komatineni <skomatineni@nvidia.com>]

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
registers when CQE is enabled to prevent SW from updating block
size during Command Queue mode.

Signed-off-by: Sowjanya Komatineni <skomatineni@nvidia.com>
---
 drivers/mmc/host/Kconfig       |   1 +
 drivers/mmc/host/sdhci-tegra.c | 107 ++++++++++++++++++++++++++++++++++++++++-
 drivers/mmc/host/sdhci.c       |   6 ++-
 3 files changed, 112 insertions(+), 2 deletions(-)

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..7beecd1da94a 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 +841,49 @@ 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 cqhci_host *cq_host = mmc->cqe_private;
+	u32 cqcfg = 0;
+
+	/* 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_cqe_enable(mmc);
+
+	if (cqcfg & CQHCI_ENABLE)
+		cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+
+}
+
+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 +1037,7 @@ 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 +1079,55 @@ 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 +1137,7 @@ 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 +1155,12 @@ 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 +1222,7 @@ 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;
 
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index fde984d10619..25683a935b30 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -3308,7 +3308,11 @@ void sdhci_cqe_enable(struct mmc_host *mmc)
 
 	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
 	ctrl &= ~SDHCI_CTRL_DMA_MASK;
-	if (host->flags & SDHCI_USE_64_BIT_DMA)
+	/* CQE need to use ADMA3 as it need to fetch task descriptor along
+	 * with transfer descriptor, so force DMA Select to ADMA64 during CQE
+	 */
+	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;
-- 
2.7.4