mmc: sdhci-msm: Add platform_execute_tuning implementation

This patch adds implementation for platform specific tuning in order
to support HS200 bus speed mode on Qualcomm SDHCI controller.
Signed-off-by: Asutosh Das <asutoshd@codeaurora.org>
Signed-off-by: Venkat Gopalakrishnan <venkatg@codeaurora.org>
Signed-off-by: Georgi Djakov <gdjakov@mm-sol.com>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Chris Ball <chris@printf.net>

drivers/mmc/host/sdhci-msm.c

@@ -18,6 +18,8 @@
 #include <linux/of_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/delay.h>
+#include <linux/mmc/mmc.h>
+#include <linux/slab.h>
 
 #include "sdhci-pltfm.h"
 
@@ -26,6 +28,42 @@
 #define CORE_POWER		0x0
 #define CORE_SW_RST		BIT(7)
 
+#define MAX_PHASES		16
+#define CORE_DLL_LOCK		BIT(7)
+#define CORE_DLL_EN		BIT(16)
+#define CORE_CDR_EN		BIT(17)
+#define CORE_CK_OUT_EN		BIT(18)
+#define CORE_CDR_EXT_EN		BIT(19)
+#define CORE_DLL_PDN		BIT(29)
+#define CORE_DLL_RST		BIT(30)
+#define CORE_DLL_CONFIG		0x100
+#define CORE_DLL_STATUS		0x108
+
+#define CORE_VENDOR_SPEC	0x10c
+#define CORE_CLK_PWRSAVE	BIT(1)
+
+#define CDR_SELEXT_SHIFT	20
+#define CDR_SELEXT_MASK		(0xf << CDR_SELEXT_SHIFT)
+#define CMUX_SHIFT_PHASE_SHIFT	24
+#define CMUX_SHIFT_PHASE_MASK	(7 << CMUX_SHIFT_PHASE_SHIFT)
+
+static const u32 tuning_block_64[] = {
+	0x00ff0fff, 0xccc3ccff, 0xffcc3cc3, 0xeffefffe,
+	0xddffdfff, 0xfbfffbff, 0xff7fffbf, 0xefbdf777,
+	0xf0fff0ff, 0x3cccfc0f, 0xcfcc33cc, 0xeeffefff,
+	0xfdfffdff, 0xffbfffdf, 0xfff7ffbb, 0xde7b7ff7
+};
+
+static const u32 tuning_block_128[] = {
+	0xff00ffff, 0x0000ffff, 0xccccffff, 0xcccc33cc,
+	0xcc3333cc, 0xffffcccc, 0xffffeeff, 0xffeeeeff,
+	0xffddffff, 0xddddffff, 0xbbffffff, 0xbbffffff,
+	0xffffffbb, 0xffffff77, 0x77ff7777, 0xffeeddbb,
+	0x00ffffff, 0x00ffffff, 0xccffff00, 0xcc33cccc,
+	0x3333cccc, 0xffcccccc, 0xffeeffff, 0xeeeeffff,
+	0xddffffff, 0xddffffff, 0xffffffdd, 0xffffffbb,
+	0xffffbbbb, 0xffff77ff, 0xff7777ff, 0xeeddbb77
+};
 
 struct sdhci_msm_host {
 	struct platform_device *pdev;
@@ -38,17 +76,389 @@ struct sdhci_msm_host {
 };
 
 /* Platform specific tuning */
-static int sdhci_msm_execute_tuning(struct sdhci_host *host, u32 opcode)
+static inline int msm_dll_poll_ck_out_en(struct sdhci_host *host, u8 poll)
+{
+	u32 wait_cnt = 50;
+	u8 ck_out_en;
+	struct mmc_host *mmc = host->mmc;
+
+	/* Poll for CK_OUT_EN bit.  max. poll time = 50us */
+	ck_out_en = !!(readl_relaxed(host->ioaddr + CORE_DLL_CONFIG) &
+			CORE_CK_OUT_EN);
+
+	while (ck_out_en != poll) {
+		if (--wait_cnt == 0) {
+			dev_err(mmc_dev(mmc), "%s: CK_OUT_EN bit is not %d\n",
+			       mmc_hostname(mmc), poll);
+			return -ETIMEDOUT;
+		}
+		udelay(1);
+
+		ck_out_en = !!(readl_relaxed(host->ioaddr + CORE_DLL_CONFIG) &
+				CORE_CK_OUT_EN);
+	}
+
+	return 0;
+}
+
+static int msm_config_cm_dll_phase(struct sdhci_host *host, u8 phase)
+{
+	int rc;
+	static const u8 grey_coded_phase_table[] = {
+		0x0, 0x1, 0x3, 0x2, 0x6, 0x7, 0x5, 0x4,
+		0xc, 0xd, 0xf, 0xe, 0xa, 0xb, 0x9, 0x8
+	};
+	unsigned long flags;
+	u32 config;
+	struct mmc_host *mmc = host->mmc;
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	config = readl_relaxed(host->ioaddr + CORE_DLL_CONFIG);
+	config &= ~(CORE_CDR_EN | CORE_CK_OUT_EN);
+	config |= (CORE_CDR_EXT_EN | CORE_DLL_EN);
+	writel_relaxed(config, host->ioaddr + CORE_DLL_CONFIG);
+
+	/* Wait until CK_OUT_EN bit of DLL_CONFIG register becomes '0' */
+	rc = msm_dll_poll_ck_out_en(host, 0);
+	if (rc)
+		goto err_out;
+
+	/*
+	 * Write the selected DLL clock output phase (0 ... 15)
+	 * to CDR_SELEXT bit field of DLL_CONFIG register.
+	 */
+	config = readl_relaxed(host->ioaddr + CORE_DLL_CONFIG);
+	config &= ~CDR_SELEXT_MASK;
+	config |= grey_coded_phase_table[phase] << CDR_SELEXT_SHIFT;
+	writel_relaxed(config, host->ioaddr + CORE_DLL_CONFIG);
+
+	/* Set CK_OUT_EN bit of DLL_CONFIG register to 1. */
+	writel_relaxed((readl_relaxed(host->ioaddr + CORE_DLL_CONFIG)
+			| CORE_CK_OUT_EN), host->ioaddr + CORE_DLL_CONFIG);
+
+	/* Wait until CK_OUT_EN bit of DLL_CONFIG register becomes '1' */
+	rc = msm_dll_poll_ck_out_en(host, 1);
+	if (rc)
+		goto err_out;
+
+	config = readl_relaxed(host->ioaddr + CORE_DLL_CONFIG);
+	config |= CORE_CDR_EN;
+	config &= ~CORE_CDR_EXT_EN;
+	writel_relaxed(config, host->ioaddr + CORE_DLL_CONFIG);
+	goto out;
+
+err_out:
+	dev_err(mmc_dev(mmc), "%s: Failed to set DLL phase: %d\n",
+	       mmc_hostname(mmc), phase);
+out:
+	spin_unlock_irqrestore(&host->lock, flags);
+	return rc;
+}
+
+/*
+ * Find out the greatest range of consecuitive selected
+ * DLL clock output phases that can be used as sampling
+ * setting for SD3.0 UHS-I card read operation (in SDR104
+ * timing mode) or for eMMC4.5 card read operation (in HS200
+ * timing mode).
+ * Select the 3/4 of the range and configure the DLL with the
+ * selected DLL clock output phase.
+ */
+
+static int msm_find_most_appropriate_phase(struct sdhci_host *host,
+					   u8 *phase_table, u8 total_phases)
+{
+	int ret;
+	u8 ranges[MAX_PHASES][MAX_PHASES] = { {0}, {0} };
+	u8 phases_per_row[MAX_PHASES] = { 0 };
+	int row_index = 0, col_index = 0, selected_row_index = 0, curr_max = 0;
+	int i, cnt, phase_0_raw_index = 0, phase_15_raw_index = 0;
+	bool phase_0_found = false, phase_15_found = false;
+	struct mmc_host *mmc = host->mmc;
+
+	if (!total_phases || (total_phases > MAX_PHASES)) {
+		dev_err(mmc_dev(mmc), "%s: Invalid argument: total_phases=%d\n",
+		       mmc_hostname(mmc), total_phases);
+		return -EINVAL;
+	}
+
+	for (cnt = 0; cnt < total_phases; cnt++) {
+		ranges[row_index][col_index] = phase_table[cnt];
+		phases_per_row[row_index] += 1;
+		col_index++;
+
+		if ((cnt + 1) == total_phases) {
+			continue;
+		/* check if next phase in phase_table is consecutive or not */
+		} else if ((phase_table[cnt] + 1) != phase_table[cnt + 1]) {
+			row_index++;
+			col_index = 0;
+		}
+	}
+
+	if (row_index >= MAX_PHASES)
+		return -EINVAL;
+
+	/* Check if phase-0 is present in first valid window? */
+	if (!ranges[0][0]) {
+		phase_0_found = true;
+		phase_0_raw_index = 0;
+		/* Check if cycle exist between 2 valid windows */
+		for (cnt = 1; cnt <= row_index; cnt++) {
+			if (phases_per_row[cnt]) {
+				for (i = 0; i < phases_per_row[cnt]; i++) {
+					if (ranges[cnt][i] == 15) {
+						phase_15_found = true;
+						phase_15_raw_index = cnt;
+						break;
+					}
+				}
+			}
+		}
+	}
+
+	/* If 2 valid windows form cycle then merge them as single window */
+	if (phase_0_found && phase_15_found) {
+		/* number of phases in raw where phase 0 is present */
+		u8 phases_0 = phases_per_row[phase_0_raw_index];
+		/* number of phases in raw where phase 15 is present */
+		u8 phases_15 = phases_per_row[phase_15_raw_index];
+
+		if (phases_0 + phases_15 >= MAX_PHASES)
+			/*
+			 * If there are more than 1 phase windows then total
+			 * number of phases in both the windows should not be
+			 * more than or equal to MAX_PHASES.
+			 */
+			return -EINVAL;
+
+		/* Merge 2 cyclic windows */
+		i = phases_15;
+		for (cnt = 0; cnt < phases_0; cnt++) {
+			ranges[phase_15_raw_index][i] =
+			    ranges[phase_0_raw_index][cnt];
+			if (++i >= MAX_PHASES)
+				break;
+		}
+
+		phases_per_row[phase_0_raw_index] = 0;
+		phases_per_row[phase_15_raw_index] = phases_15 + phases_0;
+	}
+
+	for (cnt = 0; cnt <= row_index; cnt++) {
+		if (phases_per_row[cnt] > curr_max) {
+			curr_max = phases_per_row[cnt];
+			selected_row_index = cnt;
+		}
+	}
+
+	i = (curr_max * 3) / 4;
+	if (i)
+		i--;
+
+	ret = ranges[selected_row_index][i];
+
+	if (ret >= MAX_PHASES) {
+		ret = -EINVAL;
+		dev_err(mmc_dev(mmc), "%s: Invalid phase selected=%d\n",
+		       mmc_hostname(mmc), ret);
+	}
+
+	return ret;
+}
+
+static inline void msm_cm_dll_set_freq(struct sdhci_host *host)
+{
+	u32 mclk_freq = 0, config;
+
+	/* Program the MCLK value to MCLK_FREQ bit field */
+	if (host->clock <= 112000000)
+		mclk_freq = 0;
+	else if (host->clock <= 125000000)
+		mclk_freq = 1;
+	else if (host->clock <= 137000000)
+		mclk_freq = 2;
+	else if (host->clock <= 150000000)
+		mclk_freq = 3;
+	else if (host->clock <= 162000000)
+		mclk_freq = 4;
+	else if (host->clock <= 175000000)
+		mclk_freq = 5;
+	else if (host->clock <= 187000000)
+		mclk_freq = 6;
+	else if (host->clock <= 200000000)
+		mclk_freq = 7;
+
+	config = readl_relaxed(host->ioaddr + CORE_DLL_CONFIG);
+	config &= ~CMUX_SHIFT_PHASE_MASK;
+	config |= mclk_freq << CMUX_SHIFT_PHASE_SHIFT;
+	writel_relaxed(config, host->ioaddr + CORE_DLL_CONFIG);
+}
+
+/* Initialize the DLL (Programmable Delay Line) */
+static int msm_init_cm_dll(struct sdhci_host *host)
 {
+	struct mmc_host *mmc = host->mmc;
+	int wait_cnt = 50;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+
 	/*
-	 * Tuning is required for SDR104, HS200 and HS400 cards and if the clock
-	 * frequency greater than 100MHz in those modes. The standard tuning
-	 * procedure should not be executed, but a custom implementation will be
-	 * added here instead.
+	 * Make sure that clock is always enabled when DLL
+	 * tuning is in progress. Keeping PWRSAVE ON may
+	 * turn off the clock.
 	 */
+	writel_relaxed((readl_relaxed(host->ioaddr + CORE_VENDOR_SPEC)
+			& ~CORE_CLK_PWRSAVE), host->ioaddr + CORE_VENDOR_SPEC);
+
+	/* Write 1 to DLL_RST bit of DLL_CONFIG register */
+	writel_relaxed((readl_relaxed(host->ioaddr + CORE_DLL_CONFIG)
+			| CORE_DLL_RST), host->ioaddr + CORE_DLL_CONFIG);
+
+	/* Write 1 to DLL_PDN bit of DLL_CONFIG register */
+	writel_relaxed((readl_relaxed(host->ioaddr + CORE_DLL_CONFIG)
+			| CORE_DLL_PDN), host->ioaddr + CORE_DLL_CONFIG);
+	msm_cm_dll_set_freq(host);
+
+	/* Write 0 to DLL_RST bit of DLL_CONFIG register */
+	writel_relaxed((readl_relaxed(host->ioaddr + CORE_DLL_CONFIG)
+			& ~CORE_DLL_RST), host->ioaddr + CORE_DLL_CONFIG);
+
+	/* Write 0 to DLL_PDN bit of DLL_CONFIG register */
+	writel_relaxed((readl_relaxed(host->ioaddr + CORE_DLL_CONFIG)
+			& ~CORE_DLL_PDN), host->ioaddr + CORE_DLL_CONFIG);
+
+	/* Set DLL_EN bit to 1. */
+	writel_relaxed((readl_relaxed(host->ioaddr + CORE_DLL_CONFIG)
+			| CORE_DLL_EN), host->ioaddr + CORE_DLL_CONFIG);
+
+	/* Set CK_OUT_EN bit to 1. */
+	writel_relaxed((readl_relaxed(host->ioaddr + CORE_DLL_CONFIG)
+			| CORE_CK_OUT_EN), host->ioaddr + CORE_DLL_CONFIG);
+
+	/* Wait until DLL_LOCK bit of DLL_STATUS register becomes '1' */
+	while (!(readl_relaxed(host->ioaddr + CORE_DLL_STATUS) &
+		 CORE_DLL_LOCK)) {
+		/* max. wait for 50us sec for LOCK bit to be set */
+		if (--wait_cnt == 0) {
+			dev_err(mmc_dev(mmc), "%s: DLL failed to LOCK\n",
+			       mmc_hostname(mmc));
+			spin_unlock_irqrestore(&host->lock, flags);
+			return -ETIMEDOUT;
+		}
+		udelay(1);
+	}
+
+	spin_unlock_irqrestore(&host->lock, flags);
 	return 0;
 }
 
+static int sdhci_msm_execute_tuning(struct sdhci_host *host, u32 opcode)
+{
+	int tuning_seq_cnt = 3;
+	u8 phase, *data_buf, tuned_phases[16], tuned_phase_cnt = 0;
+	const u32 *tuning_block_pattern = tuning_block_64;
+	int size = sizeof(tuning_block_64);	/* Pattern size in bytes */
+	int rc;
+	struct mmc_host *mmc = host->mmc;
+	struct mmc_ios ios = host->mmc->ios;
+
+	/*
+	 * Tuning is required for SDR104, HS200 and HS400 cards and
+	 * if clock frequency is greater than 100MHz in these modes.
+	 */
+	if (host->clock <= 100 * 1000 * 1000 ||
+	    !((ios.timing == MMC_TIMING_MMC_HS200) ||
+	      (ios.timing == MMC_TIMING_UHS_SDR104)))
+		return 0;
+
+	if ((opcode == MMC_SEND_TUNING_BLOCK_HS200) &&
+	    (mmc->ios.bus_width == MMC_BUS_WIDTH_8)) {
+		tuning_block_pattern = tuning_block_128;
+		size = sizeof(tuning_block_128);
+	}
+
+	data_buf = kmalloc(size, GFP_KERNEL);
+	if (!data_buf)
+		return -ENOMEM;
+
+retry:
+	/* First of all reset the tuning block */
+	rc = msm_init_cm_dll(host);
+	if (rc)
+		goto out;
+
+	phase = 0;
+	do {
+		struct mmc_command cmd = { 0 };
+		struct mmc_data data = { 0 };
+		struct mmc_request mrq = {
+			.cmd = &cmd,
+			.data = &data
+		};
+		struct scatterlist sg;
+
+		/* Set the phase in delay line hw block */
+		rc = msm_config_cm_dll_phase(host, phase);
+		if (rc)
+			goto out;
+
+		cmd.opcode = opcode;
+		cmd.flags = MMC_RSP_R1 | MMC_CMD_ADTC;
+
+		data.blksz = size;
+		data.blocks = 1;
+		data.flags = MMC_DATA_READ;
+		data.timeout_ns = NSEC_PER_SEC;	/* 1 second */
+
+		data.sg = &sg;
+		data.sg_len = 1;
+		sg_init_one(&sg, data_buf, size);
+		memset(data_buf, 0, size);
+		mmc_wait_for_req(mmc, &mrq);
+
+		if (!cmd.error && !data.error &&
+		    !memcmp(data_buf, tuning_block_pattern, size)) {
+			/* Tuning is successful at this tuning point */
+			tuned_phases[tuned_phase_cnt++] = phase;
+			dev_dbg(mmc_dev(mmc), "%s: Found good phase = %d\n",
+				 mmc_hostname(mmc), phase);
+		}
+	} while (++phase < ARRAY_SIZE(tuned_phases));
+
+	if (tuned_phase_cnt) {
+		rc = msm_find_most_appropriate_phase(host, tuned_phases,
+						     tuned_phase_cnt);
+		if (rc < 0)
+			goto out;
+		else
+			phase = rc;
+
+		/*
+		 * Finally set the selected phase in delay
+		 * line hw block.
+		 */
+		rc = msm_config_cm_dll_phase(host, phase);
+		if (rc)
+			goto out;
+		dev_dbg(mmc_dev(mmc), "%s: Setting the tuning phase to %d\n",
+			 mmc_hostname(mmc), phase);
+	} else {
+		if (--tuning_seq_cnt)
+			goto retry;
+		/* Tuning failed */
+		dev_dbg(mmc_dev(mmc), "%s: No tuning point found\n",
+		       mmc_hostname(mmc));
+		rc = -EIO;
+	}
+
+out:
+	kfree(data_buf);
+	return rc;
+}
+
 static const struct of_device_id sdhci_msm_dt_match[] = {
 	{ .compatible = "qcom,sdhci-msm-v4" },
 	{},