spi: spi-nxp-fspi: add DTR mode support

Merge series from Haibo Chen <haibo.chen@nxp.com>:

this patch set add DTR mode support for flexspi.
For DTR mode, flexspi only support 8D-8D-8D mode.

Patch 1~2 extract nxp_fspi_dll_override(), prepare for adding the DTR mode.
        in nor suspend, it will disable DTR mode, and enable DTR mode back
	in nor resume. this require the flexspi driver has the ability to
	set back to dll override mode in STR mode when clock rate < 100MHz.
Patch 3 Add the DDR LUT command support. flexspi use LUT command to handle
	the dtr/str mode.
Patch 4 add the logic of sample clock source selection for STR/DTR mode
	STR use the default mode 0, sample based on the internal dummy pad.
	DTR use the mode 3, sample based on the external DQS pad, so this
	board and device connect the DQS pad.
	adjust the clock rate for DTR mode, when detect the DDR LUT command,
	flexspi will automatically div 2 of the root clock and output to device.
Patch 5 finally add the DTR support in default after the upper 4 patches's
	prepareation. Since lx2160a do not implement DQS pad, so can't support
	this DTR mode.

1 files changed, 98 insertions, 17 deletions

diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c
index 848fa9319e36..f9371f98a65b 100644
--- a/drivers/spi/spi-nxp-fspi.c
+++ b/drivers/spi/spi-nxp-fspi.c
@@ -330,6 +330,8 @@
 
 /* Access flash memory using IP bus only */
 #define FSPI_QUIRK_USE_IP_ONLY	BIT(0)
+/* Disable DTR */
+#define FSPI_QUIRK_DISABLE_DTR	BIT(1)
 
 struct nxp_fspi_devtype_data {
 	unsigned int rxfifo;
@@ -344,7 +346,7 @@ static struct nxp_fspi_devtype_data lx2160a_data = {
 	.rxfifo = SZ_512,       /* (64  * 64 bits)  */
 	.txfifo = SZ_1K,        /* (128 * 64 bits)  */
 	.ahb_buf_size = SZ_2K,  /* (256 * 64 bits)  */
-	.quirks = 0,
+	.quirks = FSPI_QUIRK_DISABLE_DTR,
 	.lut_num = 32,
 	.little_endian = true,  /* little-endian    */
 };
@@ -399,7 +401,8 @@ struct nxp_fspi {
 	struct mutex lock;
 	struct pm_qos_request pm_qos_req;
 	int selected;
-#define FSPI_NEED_INIT		(1 << 0)
+#define FSPI_NEED_INIT		BIT(0)
+#define FSPI_DTR_MODE		BIT(1)
 	int flags;
 };
 
@@ -559,12 +562,21 @@ static void nxp_fspi_prepare_lut(struct nxp_fspi *f,
 	u32 target_lut_reg;
 
 	/* cmd */
-	lutval[0] |= LUT_DEF(0, LUT_CMD, LUT_PAD(op->cmd.buswidth),
-			     op->cmd.opcode);
+	if (op->cmd.dtr) {
+		lutval[0] |= LUT_DEF(0, LUT_CMD_DDR, LUT_PAD(op->cmd.buswidth),
+				     op->cmd.opcode >> 8);
+		lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_CMD_DDR,
+					      LUT_PAD(op->cmd.buswidth),
+					      op->cmd.opcode & 0xFF);
+		lutidx++;
+	} else {
+		lutval[0] |= LUT_DEF(0, LUT_CMD, LUT_PAD(op->cmd.buswidth),
+				     op->cmd.opcode);
+	}
 
 	/* addr bytes */
 	if (op->addr.nbytes) {
-		lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_ADDR,
+		lutval[lutidx / 2] |= LUT_DEF(lutidx, op->addr.dtr ? LUT_ADDR_DDR : LUT_ADDR,
 					      LUT_PAD(op->addr.buswidth),
 					      op->addr.nbytes * 8);
 		lutidx++;
@@ -572,7 +584,7 @@ static void nxp_fspi_prepare_lut(struct nxp_fspi *f,
 
 	/* dummy bytes, if needed */
 	if (op->dummy.nbytes) {
-		lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_DUMMY,
+		lutval[lutidx / 2] |= LUT_DEF(lutidx, op->dummy.dtr ? LUT_DUMMY_DDR : LUT_DUMMY,
 		/*
 		 * Due to FlexSPI controller limitation number of PAD for dummy
 		 * buswidth needs to be programmed as equal to data buswidth.
@@ -587,7 +599,8 @@ static void nxp_fspi_prepare_lut(struct nxp_fspi *f,
 	if (op->data.nbytes) {
 		lutval[lutidx / 2] |= LUT_DEF(lutidx,
 					      op->data.dir == SPI_MEM_DATA_IN ?
-					      LUT_NXP_READ : LUT_NXP_WRITE,
+					      (op->data.dtr ? LUT_READ_DDR : LUT_NXP_READ) :
+					      (op->data.dtr ? LUT_WRITE_DDR : LUT_NXP_WRITE),
 					      LUT_PAD(op->data.buswidth),
 					      0);
 		lutidx++;
@@ -645,6 +658,40 @@ static void nxp_fspi_clk_disable_unprep(struct nxp_fspi *f)
 	return;
 }
 
+/*
+ * Sample Clock source selection for Flash Reading
+ * Four modes defined by fspi:
+ * mode 0: Dummy Read strobe generated by FlexSPI Controller
+ *         and loopback internally
+ * mode 1: Dummy Read strobe generated by FlexSPI Controller
+ *         and loopback from DQS pad
+ * mode 2: Reserved
+ * mode 3: Flash provided Read strobe and input from DQS pad
+ *
+ * fspi default use mode 0 after reset
+ */
+static void nxp_fspi_select_rx_sample_clk_source(struct nxp_fspi *f,
+						 bool op_is_dtr)
+{
+	u32 reg;
+
+	/*
+	 * For 8D-8D-8D mode, need to use mode 3 (Flash provided Read
+	 * strobe and input from DQS pad), otherwise read operaton may
+	 * meet issue.
+	 * This mode require flash device connect the DQS pad on board.
+	 * For other modes, still use mode 0, keep align with before.
+	 * spi_nor_suspend will disable 8D-8D-8D mode, also need to
+	 * change the mode back to mode 0.
+	 */
+	reg = fspi_readl(f, f->iobase + FSPI_MCR0);
+	if (op_is_dtr)
+		reg |= FSPI_MCR0_RXCLKSRC(3);
+	else	/*select mode 0 */
+		reg &= ~FSPI_MCR0_RXCLKSRC(3);
+	fspi_writel(f, reg, f->iobase + FSPI_MCR0);
+}
+
 static void nxp_fspi_dll_calibration(struct nxp_fspi *f)
 {
 	int ret;
@@ -675,6 +722,17 @@ static void nxp_fspi_dll_calibration(struct nxp_fspi *f)
 }
 
 /*
+ * Config the DLL register to default value, enable the target clock delay
+ * line delay cell override mode, and use 1 fixed delay cell in DLL delay
+ * chain, this is the suggested setting when clock rate < 100MHz.
+ */
+static void nxp_fspi_dll_override(struct nxp_fspi *f)
+{
+	fspi_writel(f, FSPI_DLLACR_OVRDEN, f->iobase + FSPI_DLLACR);
+	fspi_writel(f, FSPI_DLLBCR_OVRDEN, f->iobase + FSPI_DLLBCR);
+}
+
+/*
  * In FlexSPI controller, flash access is based on value of FSPI_FLSHXXCR0
  * register and start base address of the target device.
  *
@@ -715,15 +773,18 @@ static void nxp_fspi_dll_calibration(struct nxp_fspi *f)
 static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi,
 				const struct spi_mem_op *op)
 {
+	/* flexspi only support one DTR mode: 8D-8D-8D */
+	bool op_is_dtr = op->cmd.dtr && op->addr.dtr && op->dummy.dtr && op->data.dtr;
 	unsigned long rate = op->max_freq;
 	int ret;
 	uint64_t size_kb;
 
 	/*
 	 * Return, if previously selected target device is same as current
-	 * requested target device.
+	 * requested target device. Also the DTR or STR mode do not change.
 	 */
-	if (f->selected == spi_get_chipselect(spi, 0))
+	if ((f->selected == spi_get_chipselect(spi, 0)) &&
+	    (!!(f->flags & FSPI_DTR_MODE) == op_is_dtr))
 		return;
 
 	/* Reset FLSHxxCR0 registers */
@@ -740,6 +801,18 @@ static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi,
 
 	dev_dbg(f->dev, "Target device [CS:%x] selected\n", spi_get_chipselect(spi, 0));
 
+	nxp_fspi_select_rx_sample_clk_source(f, op_is_dtr);
+
+	if (op_is_dtr) {
+		f->flags |= FSPI_DTR_MODE;
+		/* For DTR mode, flexspi will default div 2 and output to device.
+		 * so here to config the root clock to 2 * device rate.
+		 */
+		rate = rate * 2;
+	} else {
+		f->flags &= ~FSPI_DTR_MODE;
+	}
+
 	nxp_fspi_clk_disable_unprep(f);
 
 	ret = clk_set_rate(f->clk, rate);
@@ -756,6 +829,8 @@ static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi,
 	 */
 	if (rate > 100000000)
 		nxp_fspi_dll_calibration(f);
+	else
+		nxp_fspi_dll_override(f);
 
 	f->selected = spi_get_chipselect(spi, 0);
 }
@@ -1071,13 +1146,7 @@ static int nxp_fspi_default_setup(struct nxp_fspi *f)
 	/* Disable the module */
 	fspi_writel(f, FSPI_MCR0_MDIS, base + FSPI_MCR0);
 
-	/*
-	 * Config the DLL register to default value, enable the target clock delay
-	 * line delay cell override mode, and use 1 fixed delay cell in DLL delay
-	 * chain, this is the suggested setting when clock rate < 100MHz.
-	 */
-	fspi_writel(f, FSPI_DLLACR_OVRDEN, base + FSPI_DLLACR);
-	fspi_writel(f, FSPI_DLLBCR_OVRDEN, base + FSPI_DLLBCR);
+	nxp_fspi_dll_override(f);
 
 	/* enable module */
 	fspi_writel(f, FSPI_MCR0_AHB_TIMEOUT(0xFF) |
@@ -1164,6 +1233,13 @@ static const struct spi_controller_mem_ops nxp_fspi_mem_ops = {
 };
 
 static const struct spi_controller_mem_caps nxp_fspi_mem_caps = {
+	.dtr = true,
+	.swap16 = false,
+	.per_op_freq = true,
+};
+
+static const struct spi_controller_mem_caps nxp_fspi_mem_caps_disable_dtr = {
+	.dtr = false,
 	.per_op_freq = true,
 };
 
@@ -1279,7 +1355,12 @@ static int nxp_fspi_probe(struct platform_device *pdev)
 	ctlr->bus_num = -1;
 	ctlr->num_chipselect = NXP_FSPI_MAX_CHIPSELECT;
 	ctlr->mem_ops = &nxp_fspi_mem_ops;
-	ctlr->mem_caps = &nxp_fspi_mem_caps;
+
+	if (f->devtype_data->quirks & FSPI_QUIRK_DISABLE_DTR)
+		ctlr->mem_caps = &nxp_fspi_mem_caps_disable_dtr;
+	else
+		ctlr->mem_caps = &nxp_fspi_mem_caps;
+
 	ctlr->dev.of_node = np;
 
 	ret = devm_add_action_or_reset(dev, nxp_fspi_cleanup, f);