(0) What is the Quadspi controller?
The Quadspi(Quad Serial Peripheral Interface) acts as an interface to
one single or two external serial flash devices, each with up to 4
bidirectional data lines.
(1) The Quadspi controller is driven by the LUT(Look-up Table) registers.
The LUT registers are a look-up-table for sequences of instructions.
A valid sequence consists of four LUT registers.
(2) The definition of the LUT register shows below:
---------------------------------------------------
| INSTR1 | PAD1 | OPRND1 | INSTR0 | PAD0 | OPRND0 |
---------------------------------------------------
There are several types of INSTRx, such as:
CMD : the SPI NOR command.
ADDR : the address for the SPI NOR command.
DUMMY : the dummy cycles needed by the SPI NOR command.
....
There are several types of PADx, such as:
PAD1 : use a singe I/O line.
PAD2 : use two I/O lines.
PAD4 : use quad I/O lines.
....
(3) We connect the NOR the QuadSPI now. I am not sure, but i think the
QuadSPI will be only used for the NOR. We may connect other devices
to it. But, for the reason of (2), we have to parse out the SPI NOR
command for the QuadSPI.
(4) Test this driver with the JFFS2 and UBIFS:
For jffs2:
-------------
#flash_eraseall /dev/mtd0
#mount -t jffs2 /dev/mtdblock0 tmp
#bonnie++ -d tmp -u 0 -s 10 -r 5
For ubifs:
-------------
#flash_eraseall /dev/mtd0
#ubiattach /dev/ubi_ctrl -m 0
#ubimkvol /dev/ubi0 -N test -m
#mount -t ubifs ubi0:test tmp
#bonnie++ -d tmp -u 0 -s 10 -r 5
(5) The test result of the DDR QUAD Read (66MHz) performance:
#insmod mtd_speedtest.ko dev=0
[ 194.831313] =================================================
[ 194.825453] mtd_speedtest: MTD device: 0
[ 194.818670] mtd_speedtest: not NAND flash, assume page size is 512 bytes.
[ 194.811705] mtd_speedtest: MTD device size 16777216, eraseblock size 65536,
page size 512, count of eraseblocks 256, pages per eraseblock 128, OOB size 0
[ 228.482355] mtd_speedtest: testing eraseblock write speed
[ 213.024166] mtd_speedtest: eraseblock write speed is 203 KiB/s
[ 213.018306] mtd_speedtest: testing eraseblock read speed
[ 212.660856] mtd_speedtest: eraseblock read speed is 46545 KiB/s
[ 181.728267] mtd_speedtest: testing page write speed
[ 231.434842] mtd_speedtest: page write speed is 203 KiB/s
[ 231.429515] mtd_speedtest: testing page read speed
[ 228.957422] mtd_speedtest: page read speed is 6641 KiB/s
[ 197.778872] mtd_speedtest: testing 2 page write speed
[ 247.338069] mtd_speedtest: 2 page write speed is 203 KiB/s
[ 247.332514] mtd_speedtest: testing 2 page read speed
[ 245.925048] mtd_speedtest: 2 page read speed is 11686 KiB/s
[ 245.919460] mtd_speedtest: Testing erase speed
[ 214.612341] mtd_speedtest: erase speed is 523 KiB/s
[ 214.607410] mtd_speedtest: Testing 2x multi-block erase speed
[ 245.545971] mtd_speedtest: 2x multi-block erase speed is 480 KiB/s
[ 245.539744] mtd_speedtest: Testing 4x multi-block erase speed
[ 211.141696] mtd_speedtest: 4x multi-block erase speed is 476 KiB/s
[ 211.135496] mtd_speedtest: Testing 8x multi-block erase speed
[ 241.761502] mtd_speedtest: 8x multi-block erase speed is 475 KiB/s
[ 241.755269] mtd_speedtest: Testing 16x multi-block erase speed
[ 272.307979] mtd_speedtest: 16x multi-block erase speed is 474 KiB/s
[ 272.301660] mtd_speedtest: Testing 32x multi-block erase speed
[ 237.637902] mtd_speedtest: 32x multi-block erase speed is 472 KiB/s
[ 237.631581] mtd_speedtest: Testing 64x multi-block erase speed
[ 267.954341] mtd_speedtest: 64x multi-block erase speed is 471 KiB/s
[ 267.948005] mtd_speedtest: finished
[ 267.944478] =================================================
* Conclusion *:
--------------------------------------------------------------------
We can get the 46.5 MiB/s read speed when the DDR Quad Read is enabled.
(From S25FL128S's spec, the maximum read rate of DDR Quad Read is
66MiB/s)
--------------------------------------------------------------------
Signed-off-by: Huang Shijie<b32955@xxxxxxxxxxxxx>
---
drivers/spi/Kconfig | 7 +
drivers/spi/Makefile | 1 +
drivers/spi/spi-fsl-quadspi.c | 1034 +++++++++++++++++++++++++++++++++++++++++
3 files changed, 1042 insertions(+), 0 deletions(-)
create mode 100644 drivers/spi/spi-fsl-quadspi.c
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 92b2373..dc38063 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -187,6 +187,13 @@ config SPI_FALCON
has only been tested with m25p80 type chips. The hardware has no
support for other types of SPI peripherals.
+config SPI_FSL_QUADSPI
+ tristate "Freescale Quad SPI controller"
+ depends on ARCH_MXC
+ help
+ This enables support for the Quad SPI controller in master mode.
+ We only connect the NOR to this controller now.
+
config SPI_GPIO
tristate "GPIO-based bitbanging SPI Master"
depends on GPIOLIB
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index b25f385..7fe505c 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_SPI_FSL_ESPI) += spi-fsl-espi.o
obj-$(CONFIG_SPI_FSL_SPI) += spi-fsl-spi.o
obj-$(CONFIG_SPI_GPIO) += spi-gpio.o
obj-$(CONFIG_SPI_IMX) += spi-imx.o
+obj-$(CONFIG_SPI_FSL_QUADSPI) += spi-fsl-quadspi.o
obj-$(CONFIG_SPI_LM70_LLP) += spi-lm70llp.o
obj-$(CONFIG_SPI_MPC512x_PSC) += spi-mpc512x-psc.o
obj-$(CONFIG_SPI_MPC52xx_PSC) += spi-mpc52xx-psc.o
diff --git a/drivers/spi/spi-fsl-quadspi.c b/drivers/spi/spi-fsl-quadspi.c
new file mode 100644
index 0000000..fa0718f
--- /dev/null
+++ b/drivers/spi/spi-fsl-quadspi.c
@@ -0,0 +1,1034 @@
+/*
+ * Freescale Quad SPI driver.
+ *
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#include<linux/kernel.h>
+#include<linux/module.h>
+#include<linux/interrupt.h>
+#include<linux/errno.h>
+#include<linux/platform_device.h>
+#include<linux/sched.h>
+#include<linux/delay.h>
+#include<linux/io.h>
+#include<linux/clk.h>
+#include<linux/err.h>
+#include<linux/spi/spi.h>
+#include<linux/of.h>
+#include<linux/of_device.h>
+#include<linux/timer.h>
+#include<linux/jiffies.h>
+#include<linux/completion.h>
+#include<linux/mtd/spi-nor.h>
+
+/* The registers */
+#define QUADSPI_MCR 0x00
+#define QUADSPI_MCR_RESERVED_SHIFT 16
+#define QUADSPI_MCR_RESERVED_MASK (0xF<< QUADSPI_MCR_RESERVED_SHIFT)
+#define QUADSPI_MCR_MDIS_SHIFT 14
+#define QUADSPI_MCR_MDIS_MASK (1<< QUADSPI_MCR_MDIS_SHIFT)
+#define QUADSPI_MCR_CLR_TXF_SHIFT 11
+#define QUADSPI_MCR_CLR_TXF_MASK (1<< QUADSPI_MCR_CLR_TXF_SHIFT)
+#define QUADSPI_MCR_CLR_RXF_SHIFT 10
+#define QUADSPI_MCR_CLR_RXF_MASK (1<< QUADSPI_MCR_CLR_RXF_SHIFT)
+#define QUADSPI_MCR_DDR_EN_SHIFT 7
+#define QUADSPI_MCR_DDR_EN_MASK (1<< QUADSPI_MCR_DDR_EN_SHIFT)
+#define QUADSPI_MCR_SWRSTHD_SHIFT 1
+#define QUADSPI_MCR_SWRSTHD_MASK (1<< QUADSPI_MCR_SWRSTHD_SHIFT)
+#define QUADSPI_MCR_SWRSTSD_SHIFT 0
+#define QUADSPI_MCR_SWRSTSD_MASK (1<< QUADSPI_MCR_SWRSTSD_SHIFT)
+
+#define QUADSPI_IPCR 0x08
+#define QUADSPI_IPCR_SEQID_SHIFT 24
+#define QUADSPI_IPCR_SEQID_MASK (0xF<< QUADSPI_IPCR_SEQID_SHIFT)
+
+#define QUADSPI_BUF0CR 0x10
+#define QUADSPI_BUF1CR 0x14
+#define QUADSPI_BUF2CR 0x18
+#define QUADSPI_BUFXCR_INVALID_MSTRID 0xe
+
+#define QUADSPI_BUF3CR 0x1c
+#define QUADSPI_BUF3CR_ALLMST_SHIFT 31
+#define QUADSPI_BUF3CR_ALLMST (1<< QUADSPI_BUF3CR_ALLMST_SHIFT)
+
+#define QUADSPI_BFGENCR 0x20
+#define QUADSPI_BFGENCR_PAR_EN_SHIFT 16
+#define QUADSPI_BFGENCR_PAR_EN_MASK (1<< (QUADSPI_BFGENCR_PAR_EN_SHIFT))
+#define QUADSPI_BFGENCR_SEQID_SHIFT 12
+#define QUADSPI_BFGENCR_SEQID_MASK (0xF<< QUADSPI_BFGENCR_SEQID_SHIFT)
+
+#define QUADSPI_BUF0IND 0x30
+#define QUADSPI_BUF1IND 0x34
+#define QUADSPI_BUF2IND 0x38
+#define QUADSPI_SFAR 0x100
+
+#define QUADSPI_SMPR 0x108
+#define QUADSPI_SMPR_DDRSMP_SHIFT 16
+#define QUADSPI_SMPR_DDRSMP_MASK (7<< QUADSPI_SMPR_DDRSMP_SHIFT)
+#define QUADSPI_SMPR_FSDLY_SHIFT 6
+#define QUADSPI_SMPR_FSDLY_MASK (1<< QUADSPI_SMPR_FSDLY_SHIFT)
+#define QUADSPI_SMPR_FSPHS_SHIFT 5
+#define QUADSPI_SMPR_FSPHS_MASK (1<< QUADSPI_SMPR_FSPHS_SHIFT)
+#define QUADSPI_SMPR_HSENA_SHIFT 0
+#define QUADSPI_SMPR_HSENA_MASK (1<< QUADSPI_SMPR_HSENA_SHIFT)
+
+#define QUADSPI_RBSR 0x10c
+#define QUADSPI_RBSR_RDBFL_SHIFT 8
+#define QUADSPI_RBSR_RDBFL_MASK (0x3F<< QUADSPI_RBSR_RDBFL_SHIFT)
+
+#define QUADSPI_RBCT 0x110
+#define QUADSPI_RBCT_WMRK_MASK 0x1F
+#define QUADSPI_RBCT_RXBRD_SHIFT 8
+#define QUADSPI_RBCT_RXBRD_USEIPS (0x1<< QUADSPI_RBCT_RXBRD_SHIFT)
+
+#define QUADSPI_TBSR 0x150
+#define QUADSPI_TBDR 0x154
+#define QUADSPI_SR 0x15c
+
+#define QUADSPI_FR 0x160
+#define QUADSPI_FR_TFF_MASK 0x1
+
+#define QUADSPI_SFA1AD 0x180
+#define QUADSPI_SFA2AD 0x184
+#define QUADSPI_SFB1AD 0x188
+#define QUADSPI_SFB2AD 0x18c
+#define QUADSPI_RBDR 0x200
+
+#define QUADSPI_LUTKEY 0x300
+#define QUADSPI_LUTKEY_VALUE 0x5AF05AF0
+
+#define QUADSPI_LCKCR 0x304
+#define QUADSPI_LCKER_LOCK 0x1
+#define QUADSPI_LCKER_UNLOCK 0x2
+
+#define QUADSPI_RSER 0x164
+#define QUADSPI_RSER_TFIE (0x1<< 0)
+
+#define QUADSPI_LUT_BASE 0x310
+
+/*
+ * The definition of the LUT register shows below:
+ *
+ * ---------------------------------------------------
+ * | INSTR1 | PAD1 | OPRND1 | INSTR0 | PAD0 | OPRND0 |
+ * ---------------------------------------------------
+ */
+#define OPRND0_SHIFT 0
+#define PAD0_SHIFT 8
+#define INSTR0_SHIFT 10
+#define OPRND1_SHIFT 16
+
+/* Instruction set for the LUT register. */
+#define LUT_STOP 0
+#define LUT_CMD 1
+#define LUT_ADDR 2
+#define LUT_DUMMY 3
+#define LUT_MODE 4
+#define LUT_MODE2 5
+#define LUT_MODE4 6
+#define LUT_READ 7
+#define LUT_WRITE 8
+#define LUT_JMP_ON_CS 9
+#define LUT_ADDR_DDR 10
+#define LUT_MODE_DDR 11
+#define LUT_MODE2_DDR 12
+#define LUT_MODE4_DDR 13
+#define LUT_READ_DDR 14
+#define LUT_WRITE_DDR 15
+#define LUT_DATA_LEARN 16
+
+/*
+ * The PAD definitions for LUT register.
+ *
+ * The pad stands for the lines number of IO[0:3].
+ * For example, the Quad read need four IO lines, so you should
+ * set LUT_PAD4 which means we use four IO lines.
+ */
+#define LUT_PAD1 0
+#define LUT_PAD2 1
+#define LUT_PAD4 2
+
+/* Oprands for the LUT register. */
+#define ADDR24BIT 0x18
+#define ADDR32BIT 0x20
+
+/* Macros for constructing the LUT register. */
+#define LUT0(ins, pad, opr) \
+ (((opr)<< OPRND0_SHIFT) | ((LUT_##pad)<< PAD0_SHIFT) | \
+ ((LUT_##ins)<< INSTR0_SHIFT))
+
+#define LUT1(ins, pad, opr) (LUT0(ins, pad, opr)<< OPRND1_SHIFT)
+
+/* other macros for LUT register. */
+#define QUADSPI_LUT(x) (QUADSPI_LUT_BASE + (x) * 4)
+#define QUADSPI_LUT_NUM 64
+
+/* SEQID -- we can have 16 seqids at most. */
+#define SEQID_QUAD_READ 0
+#define SEQID_WREN 1
+#define SEQID_FAST_READ 2
+#define SEQID_RDSR 3
+#define SEQID_SE 4
+#define SEQID_CHIP_ERASE 5
+#define SEQID_PP 6
+#define SEQID_RDID 7
+#define SEQID_WRSR 8
+#define SEQID_RDCR 9
+#define SEQID_DDRQUAD_READ 10
+
+struct fsl_qspi_handler {
+ int (*setup)(struct spi_device *);
+ int (*do_one_msg)(struct spi_master *, struct spi_message *);
+};
+
+enum fsl_qspi_devtype {
+ FSL_QUADSPI_VYBRID,
+ FSL_QUADSPI_IMX6SLX
+};
+
+struct fsl_qspi_devtype_data {
+ enum fsl_qspi_devtype devtype;
+ u32 memmap_base;
+ int rxfifo;
+ int txfifo;
+};
+
+static struct fsl_qspi_devtype_data vybrid_data = {
+ .devtype = FSL_QUADSPI_VYBRID,
+ .memmap_base = 0x20000000,
+ .rxfifo = 128,
+ .txfifo = 64
+};
+
+struct fsl_qspi {
+ void __iomem *iobase;
+ struct clk *clk, *clk_en;
+ struct device *dev;
+ struct fsl_qspi_handler *h;
+ struct completion c;
+ struct fsl_qspi_devtype_data *devtype_data;
+ void __iomem *ahb_base; /* Used when read from AHB bus */
+ unsigned int chip_base_addr; /* We may support two chips. */
+ unsigned int addr;
+ u32 nor_size; /* for mapping */
+ u8 cmd;
+ unsigned int quad_read_enabled:1;
+ unsigned int has_inited:1;
+};
+
+static inline int is_vybrid_qspi(struct fsl_qspi *q)
+{
+ return q->devtype_data->devtype == FSL_QUADSPI_VYBRID;
+}
+
+/*
+ * An IC bug makes us to re-arrange the 32-bit data.
+ * The following chips, such as IMX6SLX, have fixed this bug.
+ */
+static inline u32 fsl_qspi_endian_xchg(struct fsl_qspi *q, u32 a)
+{
+ return is_vybrid_qspi(q) ? __swab32(a) : a;
+}
+
+static inline void fsl_qspi_unlock_lut(struct fsl_qspi *q)
+{
+ writel(QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
+ writel(QUADSPI_LCKER_UNLOCK, q->iobase + QUADSPI_LCKCR);
+}
+
+static inline void fsl_qspi_lock_lut(struct fsl_qspi *q)
+{
+ writel(QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
+ writel(QUADSPI_LCKER_LOCK, q->iobase + QUADSPI_LCKCR);
+}
+
+static irqreturn_t fsl_qspi_irq_handler(int irq, void *dev_id)
+{
+ struct fsl_qspi *q = dev_id;
+ u32 reg;
+
+ /* clear interrupt */
+ reg = readl(q->iobase + QUADSPI_FR);
+ writel(reg, q->iobase + QUADSPI_FR);
+
+ if (reg& QUADSPI_FR_TFF_MASK)
+ complete(&q->c);
+
+ dev_dbg(q->dev, "QUADSPI_FR : 0x%.8x\n", reg);
+ return IRQ_HANDLED;
+}
+
+/* Init the LUT table. All the parameters are from the S25FL128S. */
+static void fsl_qspi_init_lut(struct fsl_qspi *q)
+{
+ void *__iomem base = q->iobase;
+ int rxfifo = q->devtype_data->rxfifo;
+ u32 lut_base;
+ u8 cmd, addrlen, dummy;
+ int i;
+
+ fsl_qspi_unlock_lut(q);
+
+ /* Clear all the LUT table */
+ for (i = 0; i< QUADSPI_LUT_NUM; i++)
+ writel(0, base + QUADSPI_LUT_BASE + i * 4);
+
+ /* Quad Read */
+ lut_base = SEQID_QUAD_READ * 4;
+
+ if (q->nor_size<= SZ_16M) {
+ cmd = OPCODE_QIOR;
+ addrlen = ADDR24BIT;
+ dummy = 4;
+ } else {
+ cmd = OPCODE_4QIOR;
+ addrlen = ADDR32BIT;
+ dummy = 4;
+ }
+
+ writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD4, addrlen),
+ base + QUADSPI_LUT(lut_base));
+ writel(LUT0(MODE, PAD4, 0xff) | LUT1(DUMMY, PAD4, dummy),
+ base + QUADSPI_LUT(lut_base + 1));
+ writel(LUT0(READ, PAD4, rxfifo), base + QUADSPI_LUT(lut_base + 2));
+
+ /* Write enable */
+ lut_base = SEQID_WREN * 4;
+ writel(LUT0(CMD, PAD1, OPCODE_WREN), base + QUADSPI_LUT(lut_base));
+
+ /* Fast Read */
+ lut_base = SEQID_FAST_READ * 4;
+
+ if (q->nor_size<= SZ_16M) {
+ cmd = OPCODE_FAST_READ;
+ addrlen = ADDR24BIT;
+ dummy = 8;
+ } else {
+ cmd = OPCODE_FAST_READ_4B;
+ addrlen = ADDR32BIT;
+ dummy = 8;
+ }
+ writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+ base + QUADSPI_LUT(lut_base));
+ writel(LUT0(DUMMY, PAD1, dummy) | LUT1(READ, PAD1, rxfifo),
+ base + QUADSPI_LUT(lut_base + 1));
+
+ /* Page Program */
+ lut_base = SEQID_PP * 4;
+
+ if (q->nor_size<= SZ_16M) {
+ cmd = OPCODE_PP;
+ addrlen = ADDR24BIT;
+ } else {
+ cmd = OPCODE_PP_4B;
+ addrlen = ADDR32BIT;
+ }
+
+ writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+ base + QUADSPI_LUT(lut_base));
+ writel(LUT0(WRITE, PAD1, 0), base + QUADSPI_LUT(lut_base + 1));
+
+ /* Read Status */
+ lut_base = SEQID_RDSR * 4;
+ writel(LUT0(CMD, PAD1, OPCODE_RDSR) | LUT1(READ, PAD1, 0x1),
+ base + QUADSPI_LUT(lut_base));
+
+ /* Erase a sector */
+ lut_base = SEQID_SE * 4;
+
+ if (q->nor_size<= SZ_16M) {
+ cmd = OPCODE_SE;
+ addrlen = ADDR24BIT;
+ } else {
+ cmd = OPCODE_SE_4B;
+ addrlen = ADDR32BIT;
+ }
+
+ writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+ base + QUADSPI_LUT(lut_base));
+
+ /* Erase the whole chip */
+ lut_base = SEQID_CHIP_ERASE * 4;
+ writel(LUT0(CMD, PAD1, OPCODE_CHIP_ERASE),
+ base + QUADSPI_LUT(lut_base));
+
+ /* READ ID */
+ lut_base = SEQID_RDID * 4;
+ writel(LUT0(CMD, PAD1, OPCODE_RDID) | LUT1(READ, PAD1, 0x8),
+ base + QUADSPI_LUT(lut_base));
+
+ /* Write Register */
+ lut_base = SEQID_WRSR * 4;
+ writel(LUT0(CMD, PAD1, OPCODE_WRSR) | LUT1(WRITE, PAD1, 0x2),
+ base + QUADSPI_LUT(lut_base));
+
+ /* Read Configuration Register */
+ lut_base = SEQID_RDCR * 4;
+ writel(LUT0(CMD, PAD1, OPCODE_RDCR) | LUT1(READ, PAD1, 0x1),
+ base + QUADSPI_LUT(lut_base));
+
+ /* DDR Quad Read */
+ lut_base = SEQID_DDRQUAD_READ * 4;
+
+ if (q->nor_size<= SZ_16M) {
+ cmd = OPCODE_DDRQIOR;
+ addrlen = ADDR24BIT;
+ dummy = 6;
+ } else {
+ cmd = OPCODE_4DDRQIOR;
+ addrlen = ADDR32BIT;
+ dummy = 6;
+ }
+
+ writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR_DDR, PAD4, addrlen),
+ base + QUADSPI_LUT(lut_base));
+ writel(LUT0(MODE_DDR, PAD4, 0xff) | LUT1(DUMMY, PAD1, dummy),
+ base + QUADSPI_LUT(lut_base + 1));
+ writel(LUT0(READ_DDR, PAD4, rxfifo),
+ base + QUADSPI_LUT(lut_base + 2));
+
+ fsl_qspi_lock_lut(q);
+}
+
+/* Get the SEQID for the command */
+static int fsl_qspi_get_seqid(struct fsl_qspi *q, u8 cmd)
+{
+ switch (cmd) {
+ case OPCODE_QIOR:
+ case OPCODE_4QIOR:
+ return SEQID_QUAD_READ;
+ case OPCODE_WREN:
+ return SEQID_WREN;
+ case OPCODE_RDSR:
+ return SEQID_RDSR;
+ case OPCODE_SE:
+ return SEQID_SE;
+ case OPCODE_CHIP_ERASE:
+ return SEQID_CHIP_ERASE;
+ case OPCODE_PP:
+ return SEQID_PP;
+ case OPCODE_RDID:
+ return SEQID_RDID;
+ case OPCODE_WRSR:
+ return SEQID_WRSR;
+ case OPCODE_RDCR:
+ return SEQID_RDCR;
+ case OPCODE_DDRQIOR:
+ case OPCODE_4DDRQIOR:
+ return SEQID_DDRQUAD_READ;
+ default:
+ dev_err(q->dev, "Unsupported cmd 0x%.2x\n", cmd);
+ break;
+ }
+ return -EINVAL;
+}
+
+static int
+fsl_qspi_runcmd(struct fsl_qspi *q, u8 cmd, unsigned int addr, int len)
+{
+ void *__iomem base = q->iobase;
+ int seqid;
+ u32 reg;
+ int err;
+
+ init_completion(&q->c);
+ dev_dbg(q->dev, "to 0x%.8x:0x%.8x, len:%d, cmd:%.2x\n",
+ q->chip_base_addr, addr, len, cmd);
+
+ /* save the reg */
+ reg = readl(base + QUADSPI_MCR);
+
+ writel(q->devtype_data->memmap_base + q->chip_base_addr + addr,
+ base + QUADSPI_SFAR);
+ writel(QUADSPI_RBCT_WMRK_MASK | QUADSPI_RBCT_RXBRD_USEIPS,
+ base + QUADSPI_RBCT);
+ writel(reg | QUADSPI_MCR_CLR_RXF_MASK, base + QUADSPI_MCR);
+
+ /* trigger the LUT now */
+ seqid = fsl_qspi_get_seqid(q, cmd);
+ writel((seqid<< QUADSPI_IPCR_SEQID_SHIFT) | len, base + QUADSPI_IPCR);
+
+ /* Wait for the interrupt. */
+ err = wait_for_completion_timeout(&q->c, msecs_to_jiffies(1000));
+ if (!err) {
+ dev_err(q->dev,
+ "cmd 0x%.2x timeout, addr@%.8x, FR:0x%.8x, SR:0x%.8x\n",
+ cmd, addr, readl(base + QUADSPI_FR),
+ readl(base + QUADSPI_SR));
+ err = -ETIMEDOUT;
+ } else {
+ err = 0;
+ }
+
+ /* restore the MCR */
+ writel(reg, base + QUADSPI_MCR);
+
+ return err;
+}
+
+static unsigned int fsl_qspi_get_addr(struct fsl_qspi *q,
+ struct spi_transfer *t)
+{
+ unsigned int addr;
+ u8 *buf = (u8 *)t->tx_buf;
+
+ /* 3-byte address */
+ if (q->nor_size<= SZ_16M)
+ addr = (buf[1]<< 16) | (buf[2]<< 8) | buf[3];
+ else /* 4-byte address */
+ addr = (buf[1]<< 24) | (buf[2]<< 16) | (buf[3]<< 8) | buf[4];
+
+ return addr;
+}
+
+/* Read out the data from the QUADSPI_RBDR buffer registers. */
+static void fsl_qspi_read_data(struct fsl_qspi *q, int len, u32 *rxbuf)
+{
+ u32 tmp;
+ int i = 0;
+
+ while (len> 0) {
+ tmp = readl(q->iobase + QUADSPI_RBDR + i * 4);
+ *rxbuf = fsl_qspi_endian_xchg(q, tmp);
+ dev_dbg(q->dev, "rcv: 0x%.8x, tmp : 0x%.8x\n", *rxbuf, tmp);
+
+ rxbuf++;
+ len -= 4;
+ i++;
+ }
+}
+
+/* Read out the data directly from the AHB buffer.*/
+static int fsl_qspi_read_data_ahb(struct fsl_qspi *q, struct spi_transfer *t)
+{
+ dev_dbg(q->dev, "cmd [%x],read from (0x%p, 0x%.8x, 0x%.8x),len:%d\n",
+ q->cmd, q->ahb_base, q->chip_base_addr, q->addr, t->len);
+ memcpy(t->rx_buf, q->ahb_base + q->chip_base_addr + q->addr, t->len);
+ return 0;
+}
+
+static u32 fsl_qspi_read_sr(struct fsl_qspi *q)
+{
+ u32 val = -EINVAL;
+ int ret;
+
+ ret = fsl_qspi_runcmd(q, OPCODE_RDSR, 0, 1);
+ if (!ret)
+ fsl_qspi_read_data(q, 1,&val);
+ else
+ return ret;
+ return val;
+}
+
+static int fsl_qspi_wait_till_ready(struct fsl_qspi *q)
+{
+ unsigned long deadline;
+ u32 sr;
+
+ deadline = jiffies + msecs_to_jiffies(40000);
+
+ do {
+ cond_resched();
+
+ if ((sr = fsl_qspi_read_sr(q))< 0)
+ break;
+ else if (!(sr& SR_WIP))
+ return 0;
+ } while (!time_after_eq(jiffies, deadline));
+
+ return (sr< 0) ? sr : -ETIMEDOUT;
+}
+
+/*
+ * If we have changed the content of the flash by writing or erasing,
+ * we need to invalidate the AHB buffer. If we do not do so, we may read out
+ * the wrong data. The spec tells us reset the AHB domain and Serial Flash
+ * domain at the same time.
+ */
+static inline void fsl_qspi_invalid(struct fsl_qspi *q)
+{
+ u32 reg;
+
+ reg = readl(q->iobase + QUADSPI_MCR);
+ reg |= QUADSPI_MCR_SWRSTHD_MASK | QUADSPI_MCR_SWRSTSD_MASK;
+ writel(reg, q->iobase + QUADSPI_MCR);
+
+ /*
+ * The minimum delay : 1 AHB + 2 SFCK clocks.
+ * Delay 1 us is enough.
+ */
+ udelay(1);
+
+ reg&= ~(QUADSPI_MCR_SWRSTHD_MASK | QUADSPI_MCR_SWRSTSD_MASK);
+ writel(reg, q->iobase + QUADSPI_MCR);
+}
+
+static int fsl_qspi_nor_write(struct fsl_qspi *q, u32 *txbuf, unsigned count)
+{
+ unsigned int addr = q->addr;
+ int txfifo_size = q->devtype_data->txfifo;
+ int ret = 0;
+ int tx_size;
+ u32 tmp;
+ int i, j;
+ u8 cmd = q->cmd;
+
+ q->cmd = -1; /* clear the cmd */
+ dev_dbg(q->dev, "to 0x%.8x:0x%.8x, len : %d\n",
+ q->chip_base_addr, addr, count);
+
+ while (count> 0) {
+ tx_size = (count> txfifo_size) ? txfifo_size : count;
+
+ /* clear the TX FIFO. */
+ tmp = readl(q->iobase + QUADSPI_MCR);
+ writel(tmp | QUADSPI_MCR_CLR_RXF_MASK, q->iobase + QUADSPI_MCR);
+
+ /* fill the TX data to the FIFO */
+ for (j = 0, i = ((tx_size + 3) / 4); j< i; j++) {
+ tmp = fsl_qspi_endian_xchg(q, *txbuf);
+ writel(tmp, q->iobase + QUADSPI_TBDR);
+ txbuf++;
+ }
+
+ /* Trigger it */
+ ret = fsl_qspi_runcmd(q, cmd, addr, tx_size);
+
+ addr += tx_size;
+ count -= tx_size;
+
+ /*
+ * If the TX FIFO is smaller then the size of Page Program,
+ * we have to wait until this Write is finished.
+ * For example, the TX FIFO is 64 bytes in the Vybrid,
+ * but the Page Program may writes 265 bytes per time.
+ * We are lucky that some chip(IMX6SLX) has increase the TX FIFO
+ * to 512 bytes.
+ *
+ * If we can change the @m25p->page_size, we can remove the
+ * following code.
+ */
+ if (count> 0) {
+ ret = fsl_qspi_wait_till_ready(q);
+ if (ret) {
+ dev_err(q->dev, "Reading SR, err:%d\n", ret);
+ break;
+ }
+
+ /* Write Enable again. */
+ ret = fsl_qspi_runcmd(q, OPCODE_WREN, 0, 0);
+ if (ret) {
+ dev_err(q->dev, "Write Enable, err:%d\n", ret);
+ break;
+ }
+ }
+ }
+ return ret;
+}
+
+/* Switch to Quad read or DDR Quad read now. */
+static inline void fsl_qspi_enable_quad_read(struct fsl_qspi *q, u8 cmd)
+{
+ int seqid;
+ u32 reg, reg2;
+
+ seqid = fsl_qspi_get_seqid(q, cmd);
+ writel(seqid<< QUADSPI_BFGENCR_SEQID_SHIFT,
+ q->iobase + QUADSPI_BFGENCR);
+
+ /* should we enable the DDR ? */
+ if (seqid == SEQID_DDRQUAD_READ) {
+ reg = readl(q->iobase + QUADSPI_MCR);
+
+ /* Firstly, disable the module */
+ writel(reg | QUADSPI_MCR_MDIS_MASK, q->iobase + QUADSPI_MCR);
+
+ /* Set the Sampling Register for DDR */
+ reg2 = readl(q->iobase + QUADSPI_SMPR);
+ reg2&= ~QUADSPI_SMPR_DDRSMP_MASK;
+ reg2 |= (1<< QUADSPI_SMPR_DDRSMP_SHIFT);
+ writel(reg2, q->iobase + QUADSPI_SMPR);
+
+ /* Enable the module again (enable the DDR too) */
+ writel(reg | QUADSPI_MCR_DDR_EN_MASK, q->iobase + QUADSPI_MCR);
+ }
+
+ q->quad_read_enabled = 1;
+}
+
+static int fsl_qspi_nor_tx(struct fsl_qspi *q, struct spi_transfer *t)
+{
+ unsigned int addr = 0;
+ bool need_invalid = false;
+ int ret = 0;
+ u8 cmd;
+
+ /* This is the second spi_transfer for Page Program. */
+ if (q->cmd == OPCODE_PP) {
+ ret = fsl_qspi_nor_write(q, (u32 *)t->tx_buf, t->len);
+ need_invalid = true;
+ goto qspi_tx_out;
+ }
+
+ cmd = *(u8 *)t->tx_buf;
+ dev_dbg(q->dev, "NOR cmd is [0x%.2x], len : %d.\n", cmd, t->len);
+
+ switch (cmd) {
+ case OPCODE_SE:
+ addr = fsl_qspi_get_addr(q, t);
+ /* fall through */
+ case OPCODE_CHIP_ERASE:
+ need_invalid = true;
+ /* fall through */
+ case OPCODE_WREN:
+ ret = fsl_qspi_runcmd(q, cmd, addr, 0);
+ q->cmd = -1;
+ break;
+
+ case OPCODE_4DDRQIOR:
+ case OPCODE_DDRQIOR:
+ case OPCODE_4QIOR:
+ case OPCODE_QIOR:
+ if (!q->quad_read_enabled)
+ fsl_qspi_enable_quad_read(q, cmd);
+ /* fall through */
+ case OPCODE_FAST_READ:
+ case OPCODE_PP:
+ q->cmd = cmd;
+ q->addr = fsl_qspi_get_addr(q, t);
+ break;
+
+ case OPCODE_WRSR:
+ q->addr = 0;
+ q->cmd = cmd;
+ ret = fsl_qspi_nor_write(q,
+ (u32*)(((u8 *)t->tx_buf) + 1),/* skip the cmd */
+ t->len - 1);
+ break;
+
+ default:
+ q->cmd = cmd;
+ break;
+ }
+
+qspi_tx_out:
+ if (need_invalid)
+ fsl_qspi_invalid(q);
+ return ret;
+}
+
+static int fsl_qspi_nor_rx(struct fsl_qspi *q, struct spi_transfer *t)
+{
+ int ret = 0;
+
+ switch (q->cmd) {
+ case OPCODE_RDSR:
+ case OPCODE_RDCR:
+ case OPCODE_RDID:
+ ret = fsl_qspi_runcmd(q, q->cmd, 0, t->len);
+ if (!ret)
+ fsl_qspi_read_data(q, t->len, t->rx_buf);
+ break;
+
+ case OPCODE_4DDRQIOR:
+ case OPCODE_DDRQIOR:
+ case OPCODE_4QIOR:
+ case OPCODE_QIOR:
+ case OPCODE_FAST_READ:
+ ret = fsl_qspi_read_data_ahb(q, t);
+ break;
+ default:
+ dev_err(q->dev, "Unsupported cmd : %x\n", q->cmd);
+ return -EINVAL;
+ }
+ return ret;
+}
+
+static int fsl_qspi_nor_do_one_msg(struct spi_master *master,
+ struct spi_message *m)
+{
+ struct fsl_qspi *q = spi_master_get_devdata(master);
+ struct spi_transfer *t;
+ int ret = 0;
+
+ /* The chip address we are working. */
+ q->chip_base_addr = q->nor_size * m->spi->chip_select;
+
+ list_for_each_entry(t,&m->transfers, transfer_list) {
+ if (t->tx_buf) {
+ ret = fsl_qspi_nor_tx(q, t);
+ if (!ret)
+ m->actual_length += t->len;
+ continue;
+ }
+
+ if (t->rx_buf) {
+ ret = fsl_qspi_nor_rx(q, t);
+ if (!ret)
+ m->actual_length += t->len;
+ }
+ }
+
+ m->status = ret;
+ spi_finalize_current_message(master);
+ return ret;
+}
+
+/*
+ * There are two different ways to read out the data from the flash:
+ * the "IP Command Read" and the "AHB Command Read".
+ *
+ * The IC guy suggests we use the "AHB Command Read" which is faster
+ * then the "IP Command Read". (What's more is that there is a bug in
+ * the "IP Command Read" in the Vybrid.)
+ *
+ * After we set up the registers for the "AHB Command Read", we can use
+ * the memcpy to read the data directly. A "missed" access to the buffer
+ * causes the controller to clear the buffer, and use the sequence pointed
+ * by the QUADSPI_BFGENCR[SEQID] to initiate a read from the flash.
+ */
+static int fsl_qspi_init_abh_read(struct fsl_qspi *q, struct spi_device *spi)
+{
+ void __iomem *base = q->iobase;
+ u32 memmap_base = q->devtype_data->memmap_base;
+ int nor_size = q->nor_size;
+ int nor_num = spi->master->num_chipselect;
+
+ /* We only can support two NOR flash at the most. */
+ if (nor_num> 2)
+ nor_num = 2;
+
+ /* Map the SPI NOR to accessiable address */
+ writel(nor_size | memmap_base, base + QUADSPI_SFA1AD);
+ writel(nor_size | memmap_base, base + QUADSPI_SFA2AD);
+ writel((nor_size * nor_num) | memmap_base, base + QUADSPI_SFB1AD);
+ writel((nor_size * nor_num) | memmap_base, base + QUADSPI_SFB2AD);
+
+ /* AHB configuration for access buffer 0/1/2 .*/
+ writel(QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF0CR);
+ writel(QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF1CR);
+ writel(QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF2CR);
+ writel(QUADSPI_BUF3CR_ALLMST, base + QUADSPI_BUF3CR);
+
+ /* We only use the buffer3 */
+ writel(0, base + QUADSPI_BUF0IND);
+ writel(0, base + QUADSPI_BUF1IND);
+ writel(0, base + QUADSPI_BUF2IND);
+
+ /* Set the default lut sequence for AHB Read. */
+ writel(SEQID_FAST_READ<< QUADSPI_BFGENCR_SEQID_SHIFT,
+ base + QUADSPI_BFGENCR);
+
+ /* Map the AHB address for read. */
+ q->ahb_base = devm_ioremap(q->dev, memmap_base, nor_size * nor_num);
+ if (!q->ahb_base)
+ return -ENOMEM;
+ return 0;
+}
+
+static int fsl_qspi_nor_setup(struct spi_device *spi)
+{
+ struct fsl_qspi *q = spi_master_get_devdata(spi->master);
+ void __iomem *base = q->iobase;
+ u32 reg;
+ int ret;
+
+ /* We may support two NOR chips, we only need to init one times. */
+ if (q->has_inited)
+ return 0;
+
+ /* The DDR Quad read can run at 66MHz for the S25FL128S. */
+ ret = clk_set_rate(q->clk, spi->max_speed_hz);
+ if (ret)
+ return ret;
+
+ fsl_qspi_init_lut(q);
+ ret = fsl_qspi_init_abh_read(q, spi);
+ if (ret< 0)
+ return ret;
+
+ /* Disable the module */
+ writel(QUADSPI_MCR_MDIS_MASK | QUADSPI_MCR_RESERVED_MASK,
+ base + QUADSPI_MCR);
+
+ reg = readl(base + QUADSPI_SMPR);
+ writel(reg& ~(QUADSPI_SMPR_FSDLY_MASK
+ | QUADSPI_SMPR_FSPHS_MASK
+ | QUADSPI_SMPR_HSENA_MASK
+ | QUADSPI_SMPR_DDRSMP_MASK), base + QUADSPI_SMPR);
+
+ /* Enable the module */
+ writel(QUADSPI_MCR_RESERVED_MASK, base + QUADSPI_MCR);
+
+ /* enable the interrupt */
+ writel(QUADSPI_RSER_TFIE, q->iobase + QUADSPI_RSER);
+
+ q->has_inited = 1;
+ return 0;
+}
+
+/* We only support the NOR now. */
+static struct fsl_qspi_handler fsl_qspi_nor_handler = {
+ .setup = fsl_qspi_nor_setup,
+ .do_one_msg = fsl_qspi_nor_do_one_msg,
+};
+
+static int fsl_qspi_setup(struct spi_device *spi)
+{
+ struct fsl_qspi *q = spi_master_get_devdata(spi->master);
+
+ if (q->h&& q->h->setup)
+ return q->h->setup(spi);
+ return 0;
+}
+
+static int fsl_qspi_do_one_msg(struct spi_master *master,
+ struct spi_message *m)
+{
+ struct fsl_qspi *q = spi_master_get_devdata(master);
+
+ if (q->h&& q->h->do_one_msg)
+ return q->h->do_one_msg(master, m);
+ return 0;
+}
+
+static struct of_device_id fsl_qspi_dt_ids[] = {
+ { .compatible = "fsl,vf610-qspi", .data = (void*)&vybrid_data, },
+ { /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, fsl_qspi_dt_ids);
+
+static int fsl_qspi_probe(struct platform_device *pdev)
+{
+ struct device_node *np = pdev->dev.of_node;
+ struct spi_master *master;
+ struct fsl_qspi *q;
+ struct resource *res;
+ int num_cs, ret;
+ const struct of_device_id *of_id =
+ of_match_device(fsl_qspi_dt_ids,&pdev->dev);
+
+ ret = of_property_read_u32(np, "fsl,spi-num-chipselects",&num_cs);
