[PATCH v2 1/7] mmc: sdhci_am654: Add tuning algorithm for delay chain

[Judith Mendez <jm@ti.com>]

Currently the sdhci_am654 driver only supports one tuning
algorithm which should be used only when DLL is enabled. The
ITAPDLY is selected from the largest passing window and the
buffer is viewed as a circular buffer.

The new algorithm should be used when the delay chain
is enabled. The ITAPDLY is selected from the largest passing
window and the buffer is not viewed as a circular buffer.

This implementation is based off of the following paper: [1].

Also add support for multiple failing windows.

[1] https://www.ti.com/lit/an/spract9/spract9.pdf

Fixes: 13ebeae68ac9 ("mmc: sdhci_am654: Add support for software tuning")
Signed-off-by: Judith Mendez <jm@ti.com>
---
Changelog:
v1->v2:
- Remove unnecessary indentations and if/else in
 sdhci_am654_calculate_itap()
- Optimize sdhci_am654_calculate_itap()
---
 drivers/mmc/host/sdhci_am654.c | 111 +++++++++++++++++++++++++++------
 1 file changed, 91 insertions(+), 20 deletions(-)

diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c
index d659c59422e1..2c66a965c225 100644
--- a/drivers/mmc/host/sdhci_am654.c
+++ b/drivers/mmc/host/sdhci_am654.c
@@ -149,10 +149,17 @@ struct sdhci_am654_data {
 	int strb_sel;
 	u32 flags;
 	u32 quirks;
+	bool dll_enable;
 
 #define SDHCI_AM654_QUIRK_FORCE_CDTEST BIT(0)
 };
 
+struct window {
+	u8 start;
+	u8 end;
+	u8 length;
+};
+
 struct sdhci_am654_driver_data {
 	const struct sdhci_pltfm_data *pdata;
 	u32 flags;
@@ -290,10 +297,13 @@ static void sdhci_am654_set_clock(struct sdhci_host *host, unsigned int clock)
 
 	regmap_update_bits(sdhci_am654->base, PHY_CTRL4, mask, val);
 
-	if (timing > MMC_TIMING_UHS_SDR25 && clock >= CLOCK_TOO_SLOW_HZ)
+	if (timing > MMC_TIMING_UHS_SDR25 && clock >= CLOCK_TOO_SLOW_HZ) {
 		sdhci_am654_setup_dll(host, clock);
-	else
+		sdhci_am654->dll_enable = true;
+	} else {
 		sdhci_am654_setup_delay_chain(sdhci_am654, timing);
+		sdhci_am654->dll_enable = false;
+	}
 
 	regmap_update_bits(sdhci_am654->base, PHY_CTRL5, CLKBUFSEL_MASK,
 			   sdhci_am654->clkbuf_sel);
@@ -408,39 +418,100 @@ static u32 sdhci_am654_cqhci_irq(struct sdhci_host *host, u32 intmask)
 	return 0;
 }
 
-#define ITAP_MAX	32
+#define ITAPDLY_LENGTH 32
+#define ITAPDLY_LAST_INDEX 31
+static u32 sdhci_am654_calculate_itap(struct sdhci_host *host, struct window
+			  *fail_window, u8 num_fails, bool circular_buffer)
+{
+	struct device *dev = mmc_dev(host->mmc);
+	struct window pass_window = {0, 0, 0};
+	u8 first_fail_start = 0, last_fail_end = 0;
+	int prev_fail_end = -1;
+	u8 itap = 0, start_fail = 0, end_fail = 0, pass_length = 0;
+	u8 i;
+
+	if (!num_fails)
+		return ITAPDLY_LAST_INDEX >> 1;
+
+	if (fail_window->length == ITAPDLY_LENGTH) {
+		dev_err(dev, "No passing ITAPDLY, return 0\n");
+		return 0;
+	}
+
+	first_fail_start = fail_window->start;
+	last_fail_end = fail_window[num_fails - 1].end;
+
+	for (i = 0; i < num_fails; i++) {
+		start_fail = fail_window[i].start;
+		end_fail = fail_window[i].end;
+		pass_length = start_fail - (prev_fail_end + 1);
+
+		if (pass_length > pass_window.length) {
+			pass_window.start = prev_fail_end + 1;
+			pass_window.length = pass_length;
+		}
+		prev_fail_end = end_fail;
+	}
+
+	if (!circular_buffer)
+		pass_length = ITAPDLY_LAST_INDEX - last_fail_end;
+	else
+		pass_length = ITAPDLY_LAST_INDEX - last_fail_end + first_fail_start;
+
+	if (pass_length > pass_window.length) {
+		pass_window.start = last_fail_end + 1;
+		pass_window.length = pass_length;
+	}
+
+	if (!circular_buffer)
+		itap = pass_window.start + (pass_window.length >> 1);
+	else
+		itap = (pass_window.start + (pass_window.length >> 1)) % ITAPDLY_LENGTH;
+
+	return (itap < 0 || itap > ITAPDLY_LAST_INDEX ? 0 : itap);
+}
+
 static int sdhci_am654_platform_execute_tuning(struct sdhci_host *host,
 					       u32 opcode)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_am654_data *sdhci_am654 = sdhci_pltfm_priv(pltfm_host);
-	int cur_val, prev_val = 1, fail_len = 0, pass_window = 0, pass_len;
-	u32 itap;
+	struct window fail_window[ITAPDLY_LENGTH];
+	u8 prev_pass = 1;
+	u8 fail_index = 0;
+	u8 curr_pass, itap;
+
+	memset(fail_window, 0, sizeof(fail_window[0]) * ITAPDLY_LENGTH);
 
 	/* Enable ITAPDLY */
 	regmap_update_bits(sdhci_am654->base, PHY_CTRL4, ITAPDLYENA_MASK,
 			   1 << ITAPDLYENA_SHIFT);
 
-	for (itap = 0; itap < ITAP_MAX; itap++) {
+	for (itap = 0; itap < ITAPDLY_LENGTH; itap++) {
 		sdhci_am654_write_itapdly(sdhci_am654, itap);
 
-		cur_val = !mmc_send_tuning(host->mmc, opcode, NULL);
-		if (cur_val && !prev_val)
-			pass_window = itap;
+		curr_pass = !mmc_send_tuning(host->mmc, opcode, NULL);
 
-		if (!cur_val)
-			fail_len++;
+		if (!curr_pass && prev_pass)
+			fail_window[fail_index].start = itap;
 
-		prev_val = cur_val;
+		if (!curr_pass) {
+			fail_window[fail_index].end = itap;
+			fail_window[fail_index].length++;
+		}
+
+		if (curr_pass && !prev_pass)
+			fail_index++;
+
+		prev_pass = curr_pass;
 	}
-	/*
-	 * Having determined the length of the failing window and start of
-	 * the passing window calculate the length of the passing window and
-	 * set the final value halfway through it considering the range as a
-	 * circular buffer
-	 */
-	pass_len = ITAP_MAX - fail_len;
-	itap = (pass_window + (pass_len >> 1)) % ITAP_MAX;
+
+	if (fail_window[fail_index].length != 0)
+		fail_index++;
+
+	itap = sdhci_am654_calculate_itap(host, fail_window, fail_index,
+					  (sdhci_am654->dll_enable));
+
 	sdhci_am654_write_itapdly(sdhci_am654, itap);
 
 	return 0;
-- 
2.43.0