mmc: sdhci-of-dwcmshc: Implement SDHCI CQE support

For enabling CQE support just set 'supports-cqe' in your DevTree file
for appropriate mmc node.

Signed-off-by: Sergey Khimich <serghox@gmail.com>
Acked-by: Adrian Hunter <adrian.hunter@intel.com>
Link: https://lore.kernel.org/r/20240319115932.4108904-3-serghox@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>

Author: skhimich

drivers/mmc/host/Kconfig

@@ -233,6 +233,7 @@ config MMC_SDHCI_OF_DWCMSHC
 	depends on MMC_SDHCI_PLTFM
 	depends on OF
 	depends on COMMON_CLK
+	select MMC_CQHCI
 	help
 	  This selects Synopsys DesignWare Cores Mobile Storage Controller
 	  support.

drivers/mmc/host/sdhci-of-dwcmshc.c

@@ -21,6 +21,7 @@
 #include <linux/sizes.h>
 
 #include "sdhci-pltfm.h"
+#include "cqhci.h"
 
 #define SDHCI_DWCMSHC_ARG2_STUFF	GENMASK(31, 16)
 
@@ -52,6 +53,9 @@
 #define AT_CTRL_SWIN_TH_VAL_MASK	GENMASK(31, 24) /* bits [31:24] */
 #define AT_CTRL_SWIN_TH_VAL		0x9  /* sampling window threshold */
 
+/* DWC IP vendor area 2 pointer */
+#define DWCMSHC_P_VENDOR_AREA2		0xea
+
 /* Sophgo CV18XX specific Registers */
 #define CV18XX_SDHCI_MSHC_CTRL			0x00
 #define  CV18XX_EMMC_FUNC_EN			BIT(0)
@@ -181,6 +185,10 @@
 #define BOUNDARY_OK(addr, len) \
 	((addr | (SZ_128M - 1)) == ((addr + len - 1) | (SZ_128M - 1)))
 
+#define DWCMSHC_SDHCI_CQE_TRNS_MODE	(SDHCI_TRNS_MULTI | \
+					 SDHCI_TRNS_BLK_CNT_EN | \
+					 SDHCI_TRNS_DMA)
+
 enum dwcmshc_rk_type {
 	DWCMSHC_RK3568,
 	DWCMSHC_RK3588,
@@ -196,7 +204,9 @@ struct rk35xx_priv {
 
 struct dwcmshc_priv {
 	struct clk	*bus_clk;
-	int vendor_specific_area1; /* P_VENDOR_SPECIFIC_AREA reg */
+	int vendor_specific_area1; /* P_VENDOR_SPECIFIC_AREA1 reg */
+	int vendor_specific_area2; /* P_VENDOR_SPECIFIC_AREA2 reg */
+
 	void *priv; /* pointer to SoC private stuff */
 	u16 delay_line;
 	u16 flags;
@@ -455,6 +465,90 @@ static void dwcmshc_hs400_enhanced_strobe(struct mmc_host *mmc,
 	sdhci_writel(host, vendor, reg);
 }
 
+static int dwcmshc_execute_tuning(struct mmc_host *mmc, u32 opcode)
+{
+	int err = sdhci_execute_tuning(mmc, opcode);
+	struct sdhci_host *host = mmc_priv(mmc);
+
+	if (err)
+		return err;
+
+	/*
+	 * Tuning can leave the IP in an active state (Buffer Read Enable bit
+	 * set) which prevents the entry to low power states (i.e. S0i3). Data
+	 * reset will clear it.
+	 */
+	sdhci_reset(host, SDHCI_RESET_DATA);
+
+	return 0;
+}
+
+static u32 dwcmshc_cqe_irq_handler(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 void dwcmshc_sdhci_cqe_enable(struct mmc_host *mmc)
+{
+	struct sdhci_host *host = mmc_priv(mmc);
+	u8 ctrl;
+
+	sdhci_writew(host, DWCMSHC_SDHCI_CQE_TRNS_MODE, SDHCI_TRANSFER_MODE);
+
+	sdhci_cqe_enable(mmc);
+
+	/*
+	 * The "DesignWare Cores Mobile Storage Host Controller
+	 * DWC_mshc / DWC_mshc_lite Databook" says:
+	 * when Host Version 4 Enable" is 1 in Host Control 2 register,
+	 * SDHCI_CTRL_ADMA32 bit means ADMA2 is selected.
+	 * Selection of 32-bit/64-bit System Addressing:
+	 * either 32-bit or 64-bit system addressing is selected by
+	 * 64-bit Addressing bit in Host Control 2 register.
+	 *
+	 * On the other hand the "DesignWare Cores Mobile Storage Host
+	 * Controller DWC_mshc / DWC_mshc_lite User Guide" says, that we have to
+	 * set DMA_SEL to ADMA2 _only_ mode in the Host Control 2 register.
+	 */
+	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
+	ctrl &= ~SDHCI_CTRL_DMA_MASK;
+	ctrl |= SDHCI_CTRL_ADMA32;
+	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
+}
+
+static void dwcmshc_set_tran_desc(struct cqhci_host *cq_host, u8 **desc,
+				  dma_addr_t addr, int len, bool end, bool dma64)
+{
+	int tmplen, offset;
+
+	if (likely(!len || BOUNDARY_OK(addr, len))) {
+		cqhci_set_tran_desc(*desc, addr, len, end, dma64);
+		return;
+	}
+
+	offset = addr & (SZ_128M - 1);
+	tmplen = SZ_128M - offset;
+	cqhci_set_tran_desc(*desc, addr, tmplen, false, dma64);
+
+	addr += tmplen;
+	len -= tmplen;
+	*desc += cq_host->trans_desc_len;
+	cqhci_set_tran_desc(*desc, addr, len, end, dma64);
+}
+
+static void dwcmshc_cqhci_dumpregs(struct mmc_host *mmc)
+{
+	sdhci_dumpregs(mmc_priv(mmc));
+}
+
 static void dwcmshc_rk3568_set_clock(struct sdhci_host *host, unsigned int clock)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
@@ -692,6 +786,7 @@ static const struct sdhci_ops sdhci_dwcmshc_ops = {
 	.get_max_clock		= dwcmshc_get_max_clock,
 	.reset			= sdhci_reset,
 	.adma_write_desc	= dwcmshc_adma_write_desc,
+	.irq			= dwcmshc_cqe_irq_handler,
 };
 
 static const struct sdhci_ops sdhci_dwcmshc_rk35xx_ops = {
@@ -758,6 +853,73 @@ static const struct sdhci_pltfm_data sdhci_dwcmshc_cv18xx_pdata = {
 	.quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN,
 };
 
+static const struct cqhci_host_ops dwcmshc_cqhci_ops = {
+	.enable		= dwcmshc_sdhci_cqe_enable,
+	.disable	= sdhci_cqe_disable,
+	.dumpregs	= dwcmshc_cqhci_dumpregs,
+	.set_tran_desc	= dwcmshc_set_tran_desc,
+};
+
+static void dwcmshc_cqhci_init(struct sdhci_host *host, struct platform_device *pdev)
+{
+	struct cqhci_host *cq_host;
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct dwcmshc_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	bool dma64 = false;
+	u16 clk;
+	int err;
+
+	host->mmc->caps2 |= MMC_CAP2_CQE | MMC_CAP2_CQE_DCMD;
+	cq_host = devm_kzalloc(&pdev->dev, sizeof(*cq_host), GFP_KERNEL);
+	if (!cq_host) {
+		dev_err(mmc_dev(host->mmc), "Unable to setup CQE: not enough memory\n");
+		goto dsbl_cqe_caps;
+	}
+
+	/*
+	 * For dwcmshc host controller we have to enable internal clock
+	 * before access to some registers from Vendor Specific Area 2.
+	 */
+	clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
+	clk |= SDHCI_CLOCK_INT_EN;
+	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
+	clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
+	if (!(clk & SDHCI_CLOCK_INT_EN)) {
+		dev_err(mmc_dev(host->mmc), "Unable to setup CQE: internal clock enable error\n");
+		goto free_cq_host;
+	}
+
+	cq_host->mmio = host->ioaddr + priv->vendor_specific_area2;
+	cq_host->ops = &dwcmshc_cqhci_ops;
+
+	/* Enable using of 128-bit task descriptors */
+	dma64 = host->flags & SDHCI_USE_64_BIT_DMA;
+	if (dma64) {
+		dev_dbg(mmc_dev(host->mmc), "128-bit task descriptors\n");
+		cq_host->caps |= CQHCI_TASK_DESC_SZ_128;
+	}
+	err = cqhci_init(cq_host, host->mmc, dma64);
+	if (err) {
+		dev_err(mmc_dev(host->mmc), "Unable to setup CQE: error %d\n", err);
+		goto int_clock_disable;
+	}
+
+	dev_dbg(mmc_dev(host->mmc), "CQE init done\n");
+
+	return;
+
+int_clock_disable:
+	clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL);
+	clk &= ~SDHCI_CLOCK_INT_EN;
+	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
+
+free_cq_host:
+	devm_kfree(&pdev->dev, cq_host);
+
+dsbl_cqe_caps:
+	host->mmc->caps2 &= ~(MMC_CAP2_CQE | MMC_CAP2_CQE_DCMD);
+}
+
 static int dwcmshc_rk35xx_init(struct sdhci_host *host, struct dwcmshc_priv *dwc_priv)
 {
 	int err;
@@ -862,7 +1024,7 @@ static int dwcmshc_probe(struct platform_device *pdev)
 	struct rk35xx_priv *rk_priv = NULL;
 	const struct sdhci_pltfm_data *pltfm_data;
 	int err;
-	u32 extra;
+	u32 extra, caps;
 
 	pltfm_data = device_get_match_data(&pdev->dev);
 	if (!pltfm_data) {
@@ -913,6 +1075,7 @@ static int dwcmshc_probe(struct platform_device *pdev)
 
 	host->mmc_host_ops.request = dwcmshc_request;
 	host->mmc_host_ops.hs400_enhanced_strobe = dwcmshc_hs400_enhanced_strobe;
+	host->mmc_host_ops.execute_tuning = dwcmshc_execute_tuning;
 
 	if (pltfm_data == &sdhci_dwcmshc_rk35xx_pdata) {
 		rk_priv = devm_kzalloc(&pdev->dev, sizeof(struct rk35xx_priv), GFP_KERNEL);
@@ -962,6 +1125,10 @@ static int dwcmshc_probe(struct platform_device *pdev)
 		sdhci_enable_v4_mode(host);
 #endif
 
+	caps = sdhci_readl(host, SDHCI_CAPABILITIES);
+	if (caps & SDHCI_CAN_64BIT_V4)
+		sdhci_enable_v4_mode(host);
+
 	host->mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
 
 	pm_runtime_get_noresume(dev);
@@ -972,6 +1139,14 @@ static int dwcmshc_probe(struct platform_device *pdev)
 	if (err)
 		goto err_rpm;
 
+	/* Setup Command Queue Engine if enabled */
+	if (device_property_read_bool(&pdev->dev, "supports-cqe")) {
+		priv->vendor_specific_area2 =
+			sdhci_readw(host, DWCMSHC_P_VENDOR_AREA2);
+
+		dwcmshc_cqhci_init(host, pdev);
+	}
+
 	if (rk_priv)
 		dwcmshc_rk35xx_postinit(host, priv);
 
@@ -1044,6 +1219,12 @@ static int dwcmshc_suspend(struct device *dev)
 
 	pm_runtime_resume(dev);
 
+	if (host->mmc->caps2 & MMC_CAP2_CQE) {
+		ret = cqhci_suspend(host->mmc);
+		if (ret)
+			return ret;
+	}
+
 	ret = sdhci_suspend_host(host);
 	if (ret)
 		return ret;
@@ -1088,6 +1269,12 @@ static int dwcmshc_resume(struct device *dev)
 	if (ret)
 		goto disable_rockchip_clks;
 
+	if (host->mmc->caps2 & MMC_CAP2_CQE) {
+		ret = cqhci_resume(host->mmc);
+		if (ret)
+			goto disable_rockchip_clks;
+	}
+
 	return 0;
 
 disable_rockchip_clks: