mtd: rawnand: mtk: Improve data sampling timing for read cycle

Currently, we expand RE# low level time by choosing the max value
between RE# pulse width and RE# access time, and sample data at the
rising edge of RE#.

Then, if RE# access time is bigger than RE# pulse width, the real
read cycle time may be more than NAND SPEC required. This makes
read performance be worse than that expected.

This patch improves data sampling timing by calculating RE# low level
time according to RE# pulse width. If RE# access time is bigger than
RE# pulse width, then delay sampling data timing.

The result of contrast test base on MT2712 evaluat board is as follow.

nand: Micron MT29F16G08ADBCAH4
nand: 2048 MiB, SLC, erase size: 256 KiB, page size: 4096, OOB size: 224
NFI 2x clock rate: 124800000 HZ.

Read speed without this patch:
mtd_speedtest: page read speed is 14012 KiB/s
mtd_speedtest: 2 page read speed is 14860 KiB/s

Read speed with this patch:
mtd_speedtest: page read speed is 18724 KiB/s
mtd_speedtest: 2 page read speed is 18713 KiB/s
Signed-off-by: Xiaolei Li <xiaolei.li@mediatek.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>

drivers/mtd/nand/raw/mtk_nand.c

@@ -79,6 +79,10 @@
 #define NFI_FDMM(x)		(0xA4 + (x) * sizeof(u32) * 2)
 #define NFI_FDM_MAX_SIZE	(8)
 #define NFI_FDM_MIN_SIZE	(1)
+#define NFI_DEBUG_CON1		(0x220)
+#define		STROBE_MASK		GENMASK(4, 3)
+#define		STROBE_SHIFT		(3)
+#define		MAX_STROBE_DLY		(3)
 #define NFI_MASTER_STA		(0x224)
 #define		MASTER_STA_MASK		(0x0FFF)
 #define NFI_EMPTY_THRESH	(0x23C)
@@ -501,7 +505,7 @@ static int mtk_nfc_setup_data_interface(struct nand_chip *chip, int csline,
 	struct mtk_nfc *nfc = nand_get_controller_data(chip);
 	const struct nand_sdr_timings *timings;
 	u32 rate, tpoecs, tprecs, tc2r, tw2r, twh, twst = 0, trlt = 0;
-	u32 thold;
+	u32 temp, tsel = 0;
 
 	timings = nand_get_sdr_timings(conf);
 	if (IS_ERR(timings))
@@ -538,30 +542,52 @@ static int mtk_nfc_setup_data_interface(struct nand_chip *chip, int csline,
 	twh &= 0xf;
 
 	/* Calculate real WE#/RE# hold time in nanosecond */
-	thold = (twh + 1) * 1000000 / rate;
+	temp = (twh + 1) * 1000000 / rate;
 	/* nanosecond to picosecond */
-	thold *= 1000;
+	temp *= 1000;
 
 	/*
 	 * WE# low level time should be expaned to meet WE# pulse time
 	 * and WE# cycle time at the same time.
 	 */
-	if (thold < timings->tWC_min)
-		twst = timings->tWC_min - thold;
+	if (temp < timings->tWC_min)
+		twst = timings->tWC_min - temp;
 	twst = max(timings->tWP_min, twst) / 1000;
 	twst = DIV_ROUND_UP(twst * rate, 1000000) - 1;
 	twst &= 0xf;
 
 	/*
-	 * RE# low level time should be expaned to meet RE# pulse time,
-	 * RE# access time and RE# cycle time at the same time.
+	 * RE# low level time should be expaned to meet RE# pulse time
+	 * and RE# cycle time at the same time.
 	 */
-	if (thold < timings->tRC_min)
-		trlt = timings->tRC_min - thold;
-	trlt = max3(trlt, timings->tREA_max, timings->tRP_min) / 1000;
+	if (temp < timings->tRC_min)
+		trlt = timings->tRC_min - temp;
+	trlt = max(trlt, timings->tRP_min) / 1000;
 	trlt = DIV_ROUND_UP(trlt * rate, 1000000) - 1;
 	trlt &= 0xf;
 
+	/* Calculate RE# pulse time in nanosecond. */
+	temp = (trlt + 1) * 1000000 / rate;
+	/* nanosecond to picosecond */
+	temp *= 1000;
+	/*
+	 * If RE# access time is bigger than RE# pulse time,
+	 * delay sampling data timing.
+	 */
+	if (temp < timings->tREA_max) {
+		tsel = timings->tREA_max / 1000;
+		tsel = DIV_ROUND_UP(tsel * rate, 1000000);
+		tsel -= (trlt + 1);
+		if (tsel > MAX_STROBE_DLY) {
+			trlt += tsel - MAX_STROBE_DLY;
+			tsel = MAX_STROBE_DLY;
+		}
+	}
+	temp = nfi_readl(nfc, NFI_DEBUG_CON1);
+	temp &= ~STROBE_MASK;
+	temp |= tsel << STROBE_SHIFT;
+	nfi_writel(nfc, temp, NFI_DEBUG_CON1);
+
 	/*
 	 * ACCON: access timing control register
 	 * -------------------------------------