Linux-libre 4.6.2-gnu

4 files changed, 271 insertions, 103 deletions

diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index 0dc927540..d42c98e1f 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -9,6 +9,7 @@ if MTD_SPI_NOR
 
 config MTD_MT81xx_NOR
 	tristate "Mediatek MT81xx SPI NOR flash controller"
+	depends on HAS_IOMEM
 	help
 	  This enables access to SPI NOR flash, using MT81xx SPI NOR flash
 	  controller. This controller does not support generic SPI BUS, it only
@@ -30,7 +31,7 @@ config MTD_SPI_NOR_USE_4K_SECTORS
 
 config SPI_FSL_QUADSPI
 	tristate "Freescale Quad SPI controller"
-	depends on ARCH_MXC || COMPILE_TEST
+	depends on ARCH_MXC || SOC_LS1021A || ARCH_LAYERSCAPE || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
 	  This enables support for the Quad SPI controller in master mode.
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
index 54640f1eb..9ab2b51d5 100644
--- a/drivers/mtd/spi-nor/fsl-quadspi.c
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -213,6 +213,7 @@ enum fsl_qspi_devtype {
 	FSL_QUADSPI_IMX6SX,
 	FSL_QUADSPI_IMX7D,
 	FSL_QUADSPI_IMX6UL,
+	FSL_QUADSPI_LS1021A,
 };
 
 struct fsl_qspi_devtype_data {
@@ -258,6 +259,14 @@ static struct fsl_qspi_devtype_data imx6ul_data = {
 		       | QUADSPI_QUIRK_4X_INT_CLK,
 };
 
+static struct fsl_qspi_devtype_data ls1021a_data = {
+	.devtype = FSL_QUADSPI_LS1021A,
+	.rxfifo = 128,
+	.txfifo = 64,
+	.ahb_buf_size = 1024,
+	.driver_data = 0,
+};
+
 #define FSL_QSPI_MAX_CHIP	4
 struct fsl_qspi {
 	struct spi_nor nor[FSL_QSPI_MAX_CHIP];
@@ -275,6 +284,7 @@ struct fsl_qspi {
 	u32 clk_rate;
 	unsigned int chip_base_addr; /* We may support two chips. */
 	bool has_second_chip;
+	bool big_endian;
 	struct mutex lock;
 	struct pm_qos_request pm_qos_req;
 };
@@ -300,6 +310,28 @@ static inline int needs_wakeup_wait_mode(struct fsl_qspi *q)
 }
 
 /*
+ * R/W functions for big- or little-endian registers:
+ * The qSPI controller's endian is independent of the CPU core's endian.
+ * So far, although the CPU core is little-endian but the qSPI have two
+ * versions for big-endian and little-endian.
+ */
+static void qspi_writel(struct fsl_qspi *q, u32 val, void __iomem *addr)
+{
+	if (q->big_endian)
+		iowrite32be(val, addr);
+	else
+		iowrite32(val, addr);
+}
+
+static u32 qspi_readl(struct fsl_qspi *q, void __iomem *addr)
+{
+	if (q->big_endian)
+		return ioread32be(addr);
+	else
+		return ioread32(addr);
+}
+
+/*
  * An IC bug makes us to re-arrange the 32-bit data.
  * The following chips, such as IMX6SLX, have fixed this bug.
  */
@@ -310,14 +342,14 @@ static inline u32 fsl_qspi_endian_xchg(struct fsl_qspi *q, u32 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);
+	qspi_writel(q, QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
+	qspi_writel(q, 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);
+	qspi_writel(q, QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
+	qspi_writel(q, QUADSPI_LCKER_LOCK, q->iobase + QUADSPI_LCKCR);
 }
 
 static irqreturn_t fsl_qspi_irq_handler(int irq, void *dev_id)
@@ -326,8 +358,8 @@ static irqreturn_t fsl_qspi_irq_handler(int irq, void *dev_id)
 	u32 reg;
 
 	/* clear interrupt */
-	reg = readl(q->iobase + QUADSPI_FR);
-	writel(reg, q->iobase + QUADSPI_FR);
+	reg = qspi_readl(q, q->iobase + QUADSPI_FR);
+	qspi_writel(q, reg, q->iobase + QUADSPI_FR);
 
 	if (reg & QUADSPI_FR_TFF_MASK)
 		complete(&q->c);
@@ -348,7 +380,7 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 
 	/* Clear all the LUT table */
 	for (i = 0; i < QUADSPI_LUT_NUM; i++)
-		writel(0, base + QUADSPI_LUT_BASE + i * 4);
+		qspi_writel(q, 0, base + QUADSPI_LUT_BASE + i * 4);
 
 	/* Quad Read */
 	lut_base = SEQID_QUAD_READ * 4;
@@ -364,14 +396,15 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 		dummy = 8;
 	}
 
-	writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
 			base + QUADSPI_LUT(lut_base));
-	writel(LUT0(DUMMY, PAD1, dummy) | LUT1(FSL_READ, PAD4, rxfifo),
+	qspi_writel(q, LUT0(DUMMY, PAD1, dummy) | LUT1(FSL_READ, PAD4, rxfifo),
 			base + QUADSPI_LUT(lut_base + 1));
 
 	/* Write enable */
 	lut_base = SEQID_WREN * 4;
-	writel(LUT0(CMD, PAD1, SPINOR_OP_WREN), base + QUADSPI_LUT(lut_base));
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_WREN),
+			base + QUADSPI_LUT(lut_base));
 
 	/* Page Program */
 	lut_base = SEQID_PP * 4;
@@ -385,13 +418,15 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 		addrlen = ADDR32BIT;
 	}
 
-	writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
 			base + QUADSPI_LUT(lut_base));
-	writel(LUT0(FSL_WRITE, PAD1, 0), base + QUADSPI_LUT(lut_base + 1));
+	qspi_writel(q, LUT0(FSL_WRITE, PAD1, 0),
+			base + QUADSPI_LUT(lut_base + 1));
 
 	/* Read Status */
 	lut_base = SEQID_RDSR * 4;
-	writel(LUT0(CMD, PAD1, SPINOR_OP_RDSR) | LUT1(FSL_READ, PAD1, 0x1),
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_RDSR) |
+			LUT1(FSL_READ, PAD1, 0x1),
 			base + QUADSPI_LUT(lut_base));
 
 	/* Erase a sector */
@@ -400,40 +435,46 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 	cmd = q->nor[0].erase_opcode;
 	addrlen = q->nor_size <= SZ_16M ? ADDR24BIT : ADDR32BIT;
 
-	writel(LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, 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, SPINOR_OP_CHIP_ERASE),
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_CHIP_ERASE),
 			base + QUADSPI_LUT(lut_base));
 
 	/* READ ID */
 	lut_base = SEQID_RDID * 4;
-	writel(LUT0(CMD, PAD1, SPINOR_OP_RDID) | LUT1(FSL_READ, PAD1, 0x8),
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_RDID) |
+			LUT1(FSL_READ, PAD1, 0x8),
 			base + QUADSPI_LUT(lut_base));
 
 	/* Write Register */
 	lut_base = SEQID_WRSR * 4;
-	writel(LUT0(CMD, PAD1, SPINOR_OP_WRSR) | LUT1(FSL_WRITE, PAD1, 0x2),
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_WRSR) |
+			LUT1(FSL_WRITE, PAD1, 0x2),
 			base + QUADSPI_LUT(lut_base));
 
 	/* Read Configuration Register */
 	lut_base = SEQID_RDCR * 4;
-	writel(LUT0(CMD, PAD1, SPINOR_OP_RDCR) | LUT1(FSL_READ, PAD1, 0x1),
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_RDCR) |
+			LUT1(FSL_READ, PAD1, 0x1),
 			base + QUADSPI_LUT(lut_base));
 
 	/* Write disable */
 	lut_base = SEQID_WRDI * 4;
-	writel(LUT0(CMD, PAD1, SPINOR_OP_WRDI), base + QUADSPI_LUT(lut_base));
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_WRDI),
+			base + QUADSPI_LUT(lut_base));
 
 	/* Enter 4 Byte Mode (Micron) */
 	lut_base = SEQID_EN4B * 4;
-	writel(LUT0(CMD, PAD1, SPINOR_OP_EN4B), base + QUADSPI_LUT(lut_base));
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_EN4B),
+			base + QUADSPI_LUT(lut_base));
 
 	/* Enter 4 Byte Mode (Spansion) */
 	lut_base = SEQID_BRWR * 4;
-	writel(LUT0(CMD, PAD1, SPINOR_OP_BRWR), base + QUADSPI_LUT(lut_base));
+	qspi_writel(q, LUT0(CMD, PAD1, SPINOR_OP_BRWR),
+			base + QUADSPI_LUT(lut_base));
 
 	fsl_qspi_lock_lut(q);
 }
@@ -488,15 +529,16 @@ fsl_qspi_runcmd(struct fsl_qspi *q, u8 cmd, unsigned int addr, int len)
 			q->chip_base_addr, addr, len, cmd);
 
 	/* save the reg */
-	reg = readl(base + QUADSPI_MCR);
+	reg = qspi_readl(q, base + QUADSPI_MCR);
 
-	writel(q->memmap_phy + q->chip_base_addr + addr, base + QUADSPI_SFAR);
-	writel(QUADSPI_RBCT_WMRK_MASK | QUADSPI_RBCT_RXBRD_USEIPS,
+	qspi_writel(q, q->memmap_phy + q->chip_base_addr + addr,
+			base + QUADSPI_SFAR);
+	qspi_writel(q, QUADSPI_RBCT_WMRK_MASK | QUADSPI_RBCT_RXBRD_USEIPS,
 			base + QUADSPI_RBCT);
-	writel(reg | QUADSPI_MCR_CLR_RXF_MASK, base + QUADSPI_MCR);
+	qspi_writel(q, reg | QUADSPI_MCR_CLR_RXF_MASK, base + QUADSPI_MCR);
 
 	do {
-		reg2 = readl(base + QUADSPI_SR);
+		reg2 = qspi_readl(q, base + QUADSPI_SR);
 		if (reg2 & (QUADSPI_SR_IP_ACC_MASK | QUADSPI_SR_AHB_ACC_MASK)) {
 			udelay(1);
 			dev_dbg(q->dev, "The controller is busy, 0x%x\n", reg2);
@@ -507,21 +549,22 @@ fsl_qspi_runcmd(struct fsl_qspi *q, u8 cmd, unsigned int addr, int len)
 
 	/* trigger the LUT now */
 	seqid = fsl_qspi_get_seqid(q, cmd);
-	writel((seqid << QUADSPI_IPCR_SEQID_SHIFT) | len, base + QUADSPI_IPCR);
+	qspi_writel(q, (seqid << QUADSPI_IPCR_SEQID_SHIFT) | len,
+			base + QUADSPI_IPCR);
 
 	/* Wait for the interrupt. */
 	if (!wait_for_completion_timeout(&q->c, msecs_to_jiffies(1000))) {
 		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));
+			cmd, addr, qspi_readl(q, base + QUADSPI_FR),
+			qspi_readl(q, base + QUADSPI_SR));
 		err = -ETIMEDOUT;
 	} else {
 		err = 0;
 	}
 
 	/* restore the MCR */
-	writel(reg, base + QUADSPI_MCR);
+	qspi_writel(q, reg, base + QUADSPI_MCR);
 
 	return err;
 }
@@ -533,7 +576,7 @@ static void fsl_qspi_read_data(struct fsl_qspi *q, int len, u8 *rxbuf)
 	int i = 0;
 
 	while (len > 0) {
-		tmp = readl(q->iobase + QUADSPI_RBDR + i * 4);
+		tmp = qspi_readl(q, q->iobase + QUADSPI_RBDR + i * 4);
 		tmp = fsl_qspi_endian_xchg(q, tmp);
 		dev_dbg(q->dev, "chip addr:0x%.8x, rcv:0x%.8x\n",
 				q->chip_base_addr, tmp);
@@ -561,9 +604,9 @@ static inline void fsl_qspi_invalid(struct fsl_qspi *q)
 {
 	u32 reg;
 
-	reg = readl(q->iobase + QUADSPI_MCR);
+	reg = qspi_readl(q, q->iobase + QUADSPI_MCR);
 	reg |= QUADSPI_MCR_SWRSTHD_MASK | QUADSPI_MCR_SWRSTSD_MASK;
-	writel(reg, q->iobase + QUADSPI_MCR);
+	qspi_writel(q, reg, q->iobase + QUADSPI_MCR);
 
 	/*
 	 * The minimum delay : 1 AHB + 2 SFCK clocks.
@@ -572,7 +615,7 @@ static inline void fsl_qspi_invalid(struct fsl_qspi *q)
 	udelay(1);
 
 	reg &= ~(QUADSPI_MCR_SWRSTHD_MASK | QUADSPI_MCR_SWRSTSD_MASK);
-	writel(reg, q->iobase + QUADSPI_MCR);
+	qspi_writel(q, reg, q->iobase + QUADSPI_MCR);
 }
 
 static int fsl_qspi_nor_write(struct fsl_qspi *q, struct spi_nor *nor,
@@ -586,20 +629,20 @@ static int fsl_qspi_nor_write(struct fsl_qspi *q, struct spi_nor *nor,
 		q->chip_base_addr, to, count);
 
 	/* clear the TX FIFO. */
-	tmp = readl(q->iobase + QUADSPI_MCR);
-	writel(tmp | QUADSPI_MCR_CLR_TXF_MASK, q->iobase + QUADSPI_MCR);
+	tmp = qspi_readl(q, q->iobase + QUADSPI_MCR);
+	qspi_writel(q, tmp | QUADSPI_MCR_CLR_TXF_MASK, q->iobase + QUADSPI_MCR);
 
 	/* fill the TX data to the FIFO */
 	for (j = 0, i = ((count + 3) / 4); j < i; j++) {
 		tmp = fsl_qspi_endian_xchg(q, *txbuf);
-		writel(tmp, q->iobase + QUADSPI_TBDR);
+		qspi_writel(q, tmp, q->iobase + QUADSPI_TBDR);
 		txbuf++;
 	}
 
 	/* fill the TXFIFO upto 16 bytes for i.MX7d */
 	if (needs_fill_txfifo(q))
 		for (; i < 4; i++)
-			writel(tmp, q->iobase + QUADSPI_TBDR);
+			qspi_writel(q, tmp, q->iobase + QUADSPI_TBDR);
 
 	/* Trigger it */
 	ret = fsl_qspi_runcmd(q, opcode, to, count);
@@ -615,10 +658,10 @@ static void fsl_qspi_set_map_addr(struct fsl_qspi *q)
 	int nor_size = q->nor_size;
 	void __iomem *base = q->iobase;
 
-	writel(nor_size + q->memmap_phy, base + QUADSPI_SFA1AD);
-	writel(nor_size * 2 + q->memmap_phy, base + QUADSPI_SFA2AD);
-	writel(nor_size * 3 + q->memmap_phy, base + QUADSPI_SFB1AD);
-	writel(nor_size * 4 + q->memmap_phy, base + QUADSPI_SFB2AD);
+	qspi_writel(q, nor_size + q->memmap_phy, base + QUADSPI_SFA1AD);
+	qspi_writel(q, nor_size * 2 + q->memmap_phy, base + QUADSPI_SFA2AD);
+	qspi_writel(q, nor_size * 3 + q->memmap_phy, base + QUADSPI_SFB1AD);
+	qspi_writel(q, nor_size * 4 + q->memmap_phy, base + QUADSPI_SFB2AD);
 }
 
 /*
@@ -640,24 +683,26 @@ static void fsl_qspi_init_abh_read(struct fsl_qspi *q)
 	int seqid;
 
 	/* 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);
+	qspi_writel(q, QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF0CR);
+	qspi_writel(q, QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF1CR);
+	qspi_writel(q, QUADSPI_BUFXCR_INVALID_MSTRID, base + QUADSPI_BUF2CR);
 	/*
 	 * Set ADATSZ with the maximum AHB buffer size to improve the
 	 * read performance.
 	 */
-	writel(QUADSPI_BUF3CR_ALLMST_MASK | ((q->devtype_data->ahb_buf_size / 8)
-			<< QUADSPI_BUF3CR_ADATSZ_SHIFT), base + QUADSPI_BUF3CR);
+	qspi_writel(q, QUADSPI_BUF3CR_ALLMST_MASK |
+			((q->devtype_data->ahb_buf_size / 8)
+			<< QUADSPI_BUF3CR_ADATSZ_SHIFT),
+			base + QUADSPI_BUF3CR);
 
 	/* We only use the buffer3 */
-	writel(0, base + QUADSPI_BUF0IND);
-	writel(0, base + QUADSPI_BUF1IND);
-	writel(0, base + QUADSPI_BUF2IND);
+	qspi_writel(q, 0, base + QUADSPI_BUF0IND);
+	qspi_writel(q, 0, base + QUADSPI_BUF1IND);
+	qspi_writel(q, 0, base + QUADSPI_BUF2IND);
 
 	/* Set the default lut sequence for AHB Read. */
 	seqid = fsl_qspi_get_seqid(q, q->nor[0].read_opcode);
-	writel(seqid << QUADSPI_BFGENCR_SEQID_SHIFT,
+	qspi_writel(q, seqid << QUADSPI_BFGENCR_SEQID_SHIFT,
 		q->iobase + QUADSPI_BFGENCR);
 }
 
@@ -713,7 +758,7 @@ static int fsl_qspi_nor_setup(struct fsl_qspi *q)
 		return ret;
 
 	/* Reset the module */
-	writel(QUADSPI_MCR_SWRSTSD_MASK | QUADSPI_MCR_SWRSTHD_MASK,
+	qspi_writel(q, QUADSPI_MCR_SWRSTSD_MASK | QUADSPI_MCR_SWRSTHD_MASK,
 		base + QUADSPI_MCR);
 	udelay(1);
 
@@ -721,24 +766,24 @@ static int fsl_qspi_nor_setup(struct fsl_qspi *q)
 	fsl_qspi_init_lut(q);
 
 	/* Disable the module */
-	writel(QUADSPI_MCR_MDIS_MASK | QUADSPI_MCR_RESERVED_MASK,
+	qspi_writel(q, QUADSPI_MCR_MDIS_MASK | QUADSPI_MCR_RESERVED_MASK,
 			base + QUADSPI_MCR);
 
-	reg = readl(base + QUADSPI_SMPR);
-	writel(reg & ~(QUADSPI_SMPR_FSDLY_MASK
+	reg = qspi_readl(q, base + QUADSPI_SMPR);
+	qspi_writel(q, 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 | QUADSPI_MCR_END_CFG_MASK,
+	qspi_writel(q, QUADSPI_MCR_RESERVED_MASK | QUADSPI_MCR_END_CFG_MASK,
 			base + QUADSPI_MCR);
 
 	/* clear all interrupt status */
-	writel(0xffffffff, q->iobase + QUADSPI_FR);
+	qspi_writel(q, 0xffffffff, q->iobase + QUADSPI_FR);
 
 	/* enable the interrupt */
-	writel(QUADSPI_RSER_TFIE, q->iobase + QUADSPI_RSER);
+	qspi_writel(q, QUADSPI_RSER_TFIE, q->iobase + QUADSPI_RSER);
 
 	return 0;
 }
@@ -776,6 +821,7 @@ static const struct of_device_id fsl_qspi_dt_ids[] = {
 	{ .compatible = "fsl,imx6sx-qspi", .data = (void *)&imx6sx_data, },
 	{ .compatible = "fsl,imx7d-qspi", .data = (void *)&imx7d_data, },
 	{ .compatible = "fsl,imx6ul-qspi", .data = (void *)&imx6ul_data, },
+	{ .compatible = "fsl,ls1021a-qspi", .data = (void *)&ls1021a_data, },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_qspi_dt_ids);
@@ -954,6 +1000,7 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 	if (IS_ERR(q->iobase))
 		return PTR_ERR(q->iobase);
 
+	q->big_endian = of_property_read_bool(np, "big-endian");
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 					"QuadSPI-memory");
 	if (!devm_request_mem_region(dev, res->start, resource_size(res),
@@ -1101,8 +1148,8 @@ static int fsl_qspi_remove(struct platform_device *pdev)
 	}
 
 	/* disable the hardware */
-	writel(QUADSPI_MCR_MDIS_MASK, q->iobase + QUADSPI_MCR);
-	writel(0x0, q->iobase + QUADSPI_RSER);
+	qspi_writel(q, QUADSPI_MCR_MDIS_MASK, q->iobase + QUADSPI_MCR);
+	qspi_writel(q, 0x0, q->iobase + QUADSPI_RSER);
 
 	mutex_destroy(&q->lock);
 
diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c
index d5f850d03..8bed1a4cb 100644
--- a/drivers/mtd/spi-nor/mtk-quadspi.c
+++ b/drivers/mtd/spi-nor/mtk-quadspi.c
@@ -371,8 +371,8 @@ static int mt8173_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
 	return ret;
 }
 
-static int __init mtk_nor_init(struct mt8173_nor *mt8173_nor,
-			       struct device_node *flash_node)
+static int mtk_nor_init(struct mt8173_nor *mt8173_nor,
+			struct device_node *flash_node)
 {
 	int ret;
 	struct spi_nor *nor;
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 3028c0654..157841dc3 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -61,14 +61,20 @@ struct flash_info {
 	u16		addr_width;
 
 	u16		flags;
-#define	SECT_4K			0x01	/* SPINOR_OP_BE_4K works uniformly */
-#define	SPI_NOR_NO_ERASE	0x02	/* No erase command needed */
-#define	SST_WRITE		0x04	/* use SST byte programming */
-#define	SPI_NOR_NO_FR		0x08	/* Can't do fastread */
-#define	SECT_4K_PMC		0x10	/* SPINOR_OP_BE_4K_PMC works uniformly */
-#define	SPI_NOR_DUAL_READ	0x20    /* Flash supports Dual Read */
-#define	SPI_NOR_QUAD_READ	0x40    /* Flash supports Quad Read */
-#define	USE_FSR			0x80	/* use flag status register */
+#define SECT_4K			BIT(0)	/* SPINOR_OP_BE_4K works uniformly */
+#define SPI_NOR_NO_ERASE	BIT(1)	/* No erase command needed */
+#define SST_WRITE		BIT(2)	/* use SST byte programming */
+#define SPI_NOR_NO_FR		BIT(3)	/* Can't do fastread */
+#define SECT_4K_PMC		BIT(4)	/* SPINOR_OP_BE_4K_PMC works uniformly */
+#define SPI_NOR_DUAL_READ	BIT(5)	/* Flash supports Dual Read */
+#define SPI_NOR_QUAD_READ	BIT(6)	/* Flash supports Quad Read */
+#define USE_FSR			BIT(7)	/* use flag status register */
+#define SPI_NOR_HAS_LOCK	BIT(8)	/* Flash supports lock/unlock via SR */
+#define SPI_NOR_HAS_TB		BIT(9)	/*
+					 * Flash SR has Top/Bottom (TB) protect
+					 * bit. Must be used with
+					 * SPI_NOR_HAS_LOCK.
+					 */
 };
 
 #define JEDEC_MFR(info)	((info)->id[0])
@@ -434,32 +440,58 @@ static void stm_get_locked_range(struct spi_nor *nor, u8 sr, loff_t *ofs,
 	} else {
 		pow = ((sr & mask) ^ mask) >> shift;
 		*len = mtd->size >> pow;
-		*ofs = mtd->size - *len;
+		if (nor->flags & SNOR_F_HAS_SR_TB && sr & SR_TB)
+			*ofs = 0;
+		else
+			*ofs = mtd->size - *len;
 	}
 }
 
 /*
- * Return 1 if the entire region is locked, 0 otherwise
+ * Return 1 if the entire region is locked (if @locked is true) or unlocked (if
+ * @locked is false); 0 otherwise
  */
-static int stm_is_locked_sr(struct spi_nor *nor, loff_t ofs, uint64_t len,
-			    u8 sr)
+static int stm_check_lock_status_sr(struct spi_nor *nor, loff_t ofs, uint64_t len,
+				    u8 sr, bool locked)
 {
 	loff_t lock_offs;
 	uint64_t lock_len;
 
+	if (!len)
+		return 1;
+
 	stm_get_locked_range(nor, sr, &lock_offs, &lock_len);
 
-	return (ofs + len <= lock_offs + lock_len) && (ofs >= lock_offs);
+	if (locked)
+		/* Requested range is a sub-range of locked range */
+		return (ofs + len <= lock_offs + lock_len) && (ofs >= lock_offs);
+	else
+		/* Requested range does not overlap with locked range */
+		return (ofs >= lock_offs + lock_len) || (ofs + len <= lock_offs);
+}
+
+static int stm_is_locked_sr(struct spi_nor *nor, loff_t ofs, uint64_t len,
+			    u8 sr)
+{
+	return stm_check_lock_status_sr(nor, ofs, len, sr, true);
+}
+
+static int stm_is_unlocked_sr(struct spi_nor *nor, loff_t ofs, uint64_t len,
+			      u8 sr)
+{
+	return stm_check_lock_status_sr(nor, ofs, len, sr, false);
 }
 
 /*
  * Lock a region of the flash. Compatible with ST Micro and similar flash.
- * Supports only the block protection bits BP{0,1,2} in the status register
+ * Supports the block protection bits BP{0,1,2} in the status register
  * (SR). Does not support these features found in newer SR bitfields:
- *   - TB: top/bottom protect - only handle TB=0 (top protect)
  *   - SEC: sector/block protect - only handle SEC=0 (block protect)
  *   - CMP: complement protect - only support CMP=0 (range is not complemented)
  *
+ * Support for the following is provided conditionally for some flash:
+ *   - TB: top/bottom protect
+ *
  * Sample table portion for 8MB flash (Winbond w25q64fw):
  *
  *   SEC  |  TB   |  BP2  |  BP1  |  BP0  |  Prot Length  | Protected Portion
@@ -472,6 +504,13 @@ static int stm_is_locked_sr(struct spi_nor *nor, loff_t ofs, uint64_t len,
  *    0   |   0   |   1   |   0   |   1   |  2 MB         | Upper 1/4
  *    0   |   0   |   1   |   1   |   0   |  4 MB         | Upper 1/2
  *    X   |   X   |   1   |   1   |   1   |  8 MB         | ALL
+ *  ------|-------|-------|-------|-------|---------------|-------------------
+ *    0   |   1   |   0   |   0   |   1   |  128 KB       | Lower 1/64
+ *    0   |   1   |   0   |   1   |   0   |  256 KB       | Lower 1/32
+ *    0   |   1   |   0   |   1   |   1   |  512 KB       | Lower 1/16
+ *    0   |   1   |   1   |   0   |   0   |  1 MB         | Lower 1/8
+ *    0   |   1   |   1   |   0   |   1   |  2 MB         | Lower 1/4
+ *    0   |   1   |   1   |   1   |   0   |  4 MB         | Lower 1/2
  *
  * Returns negative on errors, 0 on success.
  */
@@ -481,20 +520,39 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	int status_old, status_new;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
 	u8 shift = ffs(mask) - 1, pow, val;
+	loff_t lock_len;
+	bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB;
+	bool use_top;
 	int ret;
 
 	status_old = read_sr(nor);
 	if (status_old < 0)
 		return status_old;
 
-	/* SPI NOR always locks to the end */
-	if (ofs + len != mtd->size) {
-		/* Does combined region extend to end? */
-		if (!stm_is_locked_sr(nor, ofs + len, mtd->size - ofs - len,
-				      status_old))
-			return -EINVAL;
-		len = mtd->size - ofs;
-	}
+	/* If nothing in our range is unlocked, we don't need to do anything */
+	if (stm_is_locked_sr(nor, ofs, len, status_old))
+		return 0;
+
+	/* If anything below us is unlocked, we can't use 'bottom' protection */
+	if (!stm_is_locked_sr(nor, 0, ofs, status_old))
+		can_be_bottom = false;
+
+	/* If anything above us is unlocked, we can't use 'top' protection */
+	if (!stm_is_locked_sr(nor, ofs + len, mtd->size - (ofs + len),
+				status_old))
+		can_be_top = false;
+
+	if (!can_be_bottom && !can_be_top)
+		return -EINVAL;
+
+	/* Prefer top, if both are valid */
+	use_top = can_be_top;
+
+	/* lock_len: length of region that should end up locked */
+	if (use_top)
+		lock_len = mtd->size - ofs;
+	else
+		lock_len = ofs + len;
 
 	/*
 	 * Need smallest pow such that:
@@ -505,7 +563,7 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	 *
 	 *   pow = ceil(log2(size / len)) = log2(size) - floor(log2(len))
 	 */
-	pow = ilog2(mtd->size) - ilog2(len);
+	pow = ilog2(mtd->size) - ilog2(lock_len);
 	val = mask - (pow << shift);
 	if (val & ~mask)
 		return -EINVAL;
@@ -513,10 +571,20 @@ static int stm_lock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	if (!(val & mask))
 		return -EINVAL;
 
-	status_new = (status_old & ~mask) | val;
+	status_new = (status_old & ~mask & ~SR_TB) | val;
+
+	/* Disallow further writes if WP pin is asserted */
+	status_new |= SR_SRWD;
+
+	if (!use_top)
+		status_new |= SR_TB;
+
+	/* Don't bother if they're the same */
+	if (status_new == status_old)
+		return 0;
 
 	/* Only modify protection if it will not unlock other areas */
-	if ((status_new & mask) <= (status_old & mask))
+	if ((status_new & mask) < (status_old & mask))
 		return -EINVAL;
 
 	write_enable(nor);
@@ -537,17 +605,40 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	int status_old, status_new;
 	u8 mask = SR_BP2 | SR_BP1 | SR_BP0;
 	u8 shift = ffs(mask) - 1, pow, val;
+	loff_t lock_len;
+	bool can_be_top = true, can_be_bottom = nor->flags & SNOR_F_HAS_SR_TB;
+	bool use_top;
 	int ret;
 
 	status_old = read_sr(nor);
 	if (status_old < 0)
 		return status_old;
 
-	/* Cannot unlock; would unlock larger region than requested */
-	if (stm_is_locked_sr(nor, ofs - mtd->erasesize, mtd->erasesize,
-			     status_old))
+	/* If nothing in our range is locked, we don't need to do anything */
+	if (stm_is_unlocked_sr(nor, ofs, len, status_old))
+		return 0;
+
+	/* If anything below us is locked, we can't use 'top' protection */
+	if (!stm_is_unlocked_sr(nor, 0, ofs, status_old))
+		can_be_top = false;
+
+	/* If anything above us is locked, we can't use 'bottom' protection */
+	if (!stm_is_unlocked_sr(nor, ofs + len, mtd->size - (ofs + len),
+				status_old))
+		can_be_bottom = false;
+
+	if (!can_be_bottom && !can_be_top)
 		return -EINVAL;
 
+	/* Prefer top, if both are valid */
+	use_top = can_be_top;
+
+	/* lock_len: length of region that should remain locked */
+	if (use_top)
+		lock_len = mtd->size - (ofs + len);
+	else
+		lock_len = ofs;
+
 	/*
 	 * Need largest pow such that:
 	 *
@@ -557,8 +648,8 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 	 *
 	 *   pow = floor(log2(size / len)) = log2(size) - ceil(log2(len))
 	 */
-	pow = ilog2(mtd->size) - order_base_2(mtd->size - (ofs + len));
-	if (ofs + len == mtd->size) {
+	pow = ilog2(mtd->size) - order_base_2(lock_len);
+	if (lock_len == 0) {
 		val = 0; /* fully unlocked */
 	} else {
 		val = mask - (pow << shift);
@@ -567,10 +658,21 @@ static int stm_unlock(struct spi_nor *nor, loff_t ofs, uint64_t len)
 			return -EINVAL;
 	}
 
-	status_new = (status_old & ~mask) | val;
+	status_new = (status_old & ~mask & ~SR_TB) | val;
+
+	/* Don't protect status register if we're fully unlocked */
+	if (lock_len == mtd->size)
+		status_new &= ~SR_SRWD;
+
+	if (!use_top)
+		status_new |= SR_TB;
+
+	/* Don't bother if they're the same */
+	if (status_new == status_old)
+		return 0;
 
 	/* Only modify protection if it will not lock other areas */
-	if ((status_new & mask) >= (status_old & mask))
+	if ((status_new & mask) > (status_old & mask))
 		return -EINVAL;
 
 	write_enable(nor);
@@ -762,8 +864,8 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "n25q032a",	 INFO(0x20bb16, 0, 64 * 1024,   64, SPI_NOR_QUAD_READ) },
 	{ "n25q064",     INFO(0x20ba17, 0, 64 * 1024,  128, SECT_4K | SPI_NOR_QUAD_READ) },
 	{ "n25q064a",    INFO(0x20bb17, 0, 64 * 1024,  128, SECT_4K | SPI_NOR_QUAD_READ) },
-	{ "n25q128a11",  INFO(0x20bb18, 0, 64 * 1024,  256, SPI_NOR_QUAD_READ) },
-	{ "n25q128a13",  INFO(0x20ba18, 0, 64 * 1024,  256, SPI_NOR_QUAD_READ) },
+	{ "n25q128a11",  INFO(0x20bb18, 0, 64 * 1024,  256, SECT_4K | SPI_NOR_QUAD_READ) },
+	{ "n25q128a13",  INFO(0x20ba18, 0, 64 * 1024,  256, SECT_4K | SPI_NOR_QUAD_READ) },
 	{ "n25q256a",    INFO(0x20ba19, 0, 64 * 1024,  512, SECT_4K | SPI_NOR_QUAD_READ) },
 	{ "n25q512a",    INFO(0x20bb20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
 	{ "n25q512ax3",  INFO(0x20ba20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
@@ -797,6 +899,7 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "s25fl008k",  INFO(0xef4014,      0,  64 * 1024,  16, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "s25fl016k",  INFO(0xef4015,      0,  64 * 1024,  32, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "s25fl064k",  INFO(0xef4017,      0,  64 * 1024, 128, SECT_4K) },
+	{ "s25fl116k",  INFO(0x014015,      0,  64 * 1024,  32, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "s25fl132k",  INFO(0x014016,      0,  64 * 1024,  64, SECT_4K) },
 	{ "s25fl164k",  INFO(0x014017,      0,  64 * 1024, 128, SECT_4K) },
 	{ "s25fl204k",  INFO(0x014013,      0,  64 * 1024,   8, SECT_4K | SPI_NOR_DUAL_READ) },
@@ -860,11 +963,23 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "w25x16", INFO(0xef3015, 0, 64 * 1024,  32, SECT_4K) },
 	{ "w25x32", INFO(0xef3016, 0, 64 * 1024,  64, SECT_4K) },
 	{ "w25q32", INFO(0xef4016, 0, 64 * 1024,  64, SECT_4K) },
-	{ "w25q32dw", INFO(0xef6016, 0, 64 * 1024,  64, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{
+		"w25q32dw", INFO(0xef6016, 0, 64 * 1024,  64,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
 	{ "w25x64", INFO(0xef3017, 0, 64 * 1024, 128, SECT_4K) },
 	{ "w25q64", INFO(0xef4017, 0, 64 * 1024, 128, SECT_4K) },
-	{ "w25q64dw", INFO(0xef6017, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
-	{ "w25q128fw", INFO(0xef6018, 0, 64 * 1024, 256, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{
+		"w25q64dw", INFO(0xef6017, 0, 64 * 1024, 128,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
+	{
+		"w25q128fw", INFO(0xef6018, 0, 64 * 1024, 256,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
 	{ "w25q80", INFO(0xef5014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25q80bl", INFO(0xef4014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
@@ -1189,9 +1304,11 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 
 	if (JEDEC_MFR(info) == SNOR_MFR_ATMEL ||
 	    JEDEC_MFR(info) == SNOR_MFR_INTEL ||
-	    JEDEC_MFR(info) == SNOR_MFR_SST) {
+	    JEDEC_MFR(info) == SNOR_MFR_SST ||
+	    info->flags & SPI_NOR_HAS_LOCK) {
 		write_enable(nor);
 		write_sr(nor, 0);
+		spi_nor_wait_till_ready(nor);
 	}
 
 	if (!mtd->name)
@@ -1205,7 +1322,8 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	mtd->_read = spi_nor_read;
 
 	/* NOR protection support for STmicro/Micron chips and similar */
-	if (JEDEC_MFR(info) == SNOR_MFR_MICRON) {
+	if (JEDEC_MFR(info) == SNOR_MFR_MICRON ||
+			info->flags & SPI_NOR_HAS_LOCK) {
 		nor->flash_lock = stm_lock;
 		nor->flash_unlock = stm_unlock;
 		nor->flash_is_locked = stm_is_locked;
@@ -1225,6 +1343,8 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 
 	if (info->flags & USE_FSR)
 		nor->flags |= SNOR_F_USE_FSR;
+	if (info->flags & SPI_NOR_HAS_TB)
+		nor->flags |= SNOR_F_HAS_SR_TB;
 
 #ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS
 	/* prefer "small sector" erase if possible */