Merge tag 'spi-nor/for-4.15' of git://git.infradead.org/l2-mtd

This pull-request contains the following notable changes:

From Cyrille:
"
Core changes:
* Introduce system power management support.
* New mechanism to select the proper .quad_enable() hook by JEDEC ID,
  when needed, instead of only by manufacturer ID.
* Add support to new memory parts from Gigadevice, Winbond, Macronix and
  Everspin.

Driver changes:
* Maintainance for Cadence, Intel, Mediatek and STM32 drivers.
"

8 files changed, 378 insertions, 106 deletions

diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 00eea6fd379c..dbe6a1de2bb8 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -359,6 +359,7 @@ static const struct spi_device_id m25p_ids[] = {
 	{"m25p32-nonjedec"},	{"m25p64-nonjedec"},	{"m25p128-nonjedec"},
 
 	/* Everspin MRAMs (non-JEDEC) */
+	{ "mr25h128" }, /* 128 Kib, 40 MHz */
 	{ "mr25h256" }, /* 256 Kib, 40 MHz */
 	{ "mr25h10" },  /*   1 Mib, 40 MHz */
 	{ "mr25h40" },  /*   4 Mib, 40 MHz */
diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index 69c638dd0484..89da88e59121 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -50,7 +50,7 @@ config SPI_ATMEL_QUADSPI
 
 config SPI_CADENCE_QUADSPI
 	tristate "Cadence Quad SPI controller"
-	depends on OF && (ARM || COMPILE_TEST)
+	depends on OF && (ARM || ARM64 || COMPILE_TEST)
 	help
 	  Enable support for the Cadence Quad SPI Flash controller.
 
@@ -90,7 +90,7 @@ config SPI_INTEL_SPI
 	tristate
 
 config SPI_INTEL_SPI_PCI
-	tristate "Intel PCH/PCU SPI flash PCI driver" if EXPERT
+	tristate "Intel PCH/PCU SPI flash PCI driver"
 	depends on X86 && PCI
 	select SPI_INTEL_SPI
 	help
@@ -106,7 +106,7 @@ config SPI_INTEL_SPI_PCI
 	  will be called intel-spi-pci.
 
 config SPI_INTEL_SPI_PLATFORM
-	tristate "Intel PCH/PCU SPI flash platform driver" if EXPERT
+	tristate "Intel PCH/PCU SPI flash platform driver"
 	depends on X86
 	select SPI_INTEL_SPI
 	help
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index 53c7d8e0327a..75a2bc447a99 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -31,6 +31,7 @@
 #include <linux/of_device.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/sched.h>
 #include <linux/spi/spi.h>
 #include <linux/timer.h>
@@ -38,6 +39,9 @@
 #define CQSPI_NAME			"cadence-qspi"
 #define CQSPI_MAX_CHIPSELECT		16
 
+/* Quirks */
+#define CQSPI_NEEDS_WR_DELAY		BIT(0)
+
 struct cqspi_st;
 
 struct cqspi_flash_pdata {
@@ -75,7 +79,9 @@ struct cqspi_st {
 	bool			is_decoded_cs;
 	u32			fifo_depth;
 	u32			fifo_width;
+	bool			rclk_en;
 	u32			trigger_address;
+	u32			wr_delay;
 	struct cqspi_flash_pdata f_pdata[CQSPI_MAX_CHIPSELECT];
 };
 
@@ -608,6 +614,15 @@ static int cqspi_indirect_write_execute(struct spi_nor *nor,
 	reinit_completion(&cqspi->transfer_complete);
 	writel(CQSPI_REG_INDIRECTWR_START_MASK,
 	       reg_base + CQSPI_REG_INDIRECTWR);
+	/*
+	 * As per 66AK2G02 TRM SPRUHY8F section 11.15.5.3 Indirect Access
+	 * Controller programming sequence, couple of cycles of
+	 * QSPI_REF_CLK delay is required for the above bit to
+	 * be internally synchronized by the QSPI module. Provide 5
+	 * cycles of delay.
+	 */
+	if (cqspi->wr_delay)
+		ndelay(cqspi->wr_delay);
 
 	while (remaining > 0) {
 		write_bytes = remaining > page_size ? page_size : remaining;
@@ -775,7 +790,7 @@ static void cqspi_config_baudrate_div(struct cqspi_st *cqspi)
 }
 
 static void cqspi_readdata_capture(struct cqspi_st *cqspi,
-				   const unsigned int bypass,
+				   const bool bypass,
 				   const unsigned int delay)
 {
 	void __iomem *reg_base = cqspi->iobase;
@@ -839,7 +854,8 @@ static void cqspi_configure(struct spi_nor *nor)
 		cqspi->sclk = sclk;
 		cqspi_config_baudrate_div(cqspi);
 		cqspi_delay(nor);
-		cqspi_readdata_capture(cqspi, 1, f_pdata->read_delay);
+		cqspi_readdata_capture(cqspi, !cqspi->rclk_en,
+				       f_pdata->read_delay);
 	}
 
 	if (switch_cs || switch_ck)
@@ -1036,6 +1052,8 @@ static int cqspi_of_get_pdata(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
+	cqspi->rclk_en = of_property_read_bool(np, "cdns,rclk-en");
+
 	return 0;
 }
 
@@ -1156,6 +1174,7 @@ static int cqspi_probe(struct platform_device *pdev)
 	struct cqspi_st *cqspi;
 	struct resource *res;
 	struct resource *res_ahb;
+	unsigned long data;
 	int ret;
 	int irq;
 
@@ -1206,13 +1225,24 @@ static int cqspi_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(dev);
+		return ret;
+	}
+
 	ret = clk_prepare_enable(cqspi->clk);
 	if (ret) {
 		dev_err(dev, "Cannot enable QSPI clock.\n");
-		return ret;
+		goto probe_clk_failed;
 	}
 
 	cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk);
+	data  = (unsigned long)of_device_get_match_data(dev);
+	if (data & CQSPI_NEEDS_WR_DELAY)
+		cqspi->wr_delay = 5 * DIV_ROUND_UP(NSEC_PER_SEC,
+						   cqspi->master_ref_clk_hz);
 
 	ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0,
 			       pdev->name, cqspi);
@@ -1233,10 +1263,13 @@ static int cqspi_probe(struct platform_device *pdev)
 	}
 
 	return ret;
-probe_irq_failed:
-	cqspi_controller_enable(cqspi, 0);
 probe_setup_failed:
+	cqspi_controller_enable(cqspi, 0);
+probe_irq_failed:
 	clk_disable_unprepare(cqspi->clk);
+probe_clk_failed:
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
 	return ret;
 }
 
@@ -1253,6 +1286,9 @@ static int cqspi_remove(struct platform_device *pdev)
 
 	clk_disable_unprepare(cqspi->clk);
 
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
 	return 0;
 }
 
@@ -1284,7 +1320,14 @@ static const struct dev_pm_ops cqspi__dev_pm_ops = {
 #endif
 
 static const struct of_device_id cqspi_dt_ids[] = {
-	{.compatible = "cdns,qspi-nor",},
+	{
+		.compatible = "cdns,qspi-nor",
+		.data = (void *)0,
+	},
+	{
+		.compatible = "ti,k2g-qspi",
+		.data = (void *)CQSPI_NEEDS_WR_DELAY,
+	},
 	{ /* end of table */ }
 };
 
diff --git a/drivers/mtd/spi-nor/intel-spi-pci.c b/drivers/mtd/spi-nor/intel-spi-pci.c
index e82652335ede..c0976f2e3dd1 100644
--- a/drivers/mtd/spi-nor/intel-spi-pci.c
+++ b/drivers/mtd/spi-nor/intel-spi-pci.c
@@ -63,7 +63,10 @@ static void intel_spi_pci_remove(struct pci_dev *pdev)
 }
 
 static const struct pci_device_id intel_spi_pci_ids[] = {
+	{ PCI_VDEVICE(INTEL, 0x18e0), (unsigned long)&bxt_info },
 	{ PCI_VDEVICE(INTEL, 0x19e0), (unsigned long)&bxt_info },
+	{ PCI_VDEVICE(INTEL, 0xa1a4), (unsigned long)&bxt_info },
+	{ PCI_VDEVICE(INTEL, 0xa224), (unsigned long)&bxt_info },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, intel_spi_pci_ids);
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index 8a596bfeddff..ef034d898a23 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -67,8 +67,6 @@
 #define PR_LIMIT_MASK			(0x3fff << PR_LIMIT_SHIFT)
 #define PR_RPE				BIT(15)
 #define PR_BASE_MASK			0x3fff
-/* Last PR is GPR0 */
-#define PR_NUM				(5 + 1)
 
 /* Offsets are from @ispi->sregs */
 #define SSFSTS_CTL			0x00
@@ -90,20 +88,35 @@
 #define OPMENU0				0x08
 #define OPMENU1				0x0c
 
+#define OPTYPE_READ_NO_ADDR		0
+#define OPTYPE_WRITE_NO_ADDR		1
+#define OPTYPE_READ_WITH_ADDR		2
+#define OPTYPE_WRITE_WITH_ADDR		3
+
 /* CPU specifics */
 #define BYT_PR				0x74
 #define BYT_SSFSTS_CTL			0x90
 #define BYT_BCR				0xfc
 #define BYT_BCR_WPD			BIT(0)
 #define BYT_FREG_NUM			5
+#define BYT_PR_NUM			5
 
 #define LPT_PR				0x74
 #define LPT_SSFSTS_CTL			0x90
 #define LPT_FREG_NUM			5
+#define LPT_PR_NUM			5
 
 #define BXT_PR				0x84
 #define BXT_SSFSTS_CTL			0xa0
 #define BXT_FREG_NUM			12
+#define BXT_PR_NUM			6
+
+#define LVSCC				0xc4
+#define UVSCC				0xc8
+#define ERASE_OPCODE_SHIFT		8
+#define ERASE_OPCODE_MASK		(0xff << ERASE_OPCODE_SHIFT)
+#define ERASE_64K_OPCODE_SHIFT		16
+#define ERASE_64K_OPCODE_MASK		(0xff << ERASE_OPCODE_SHIFT)
 
 #define INTEL_SPI_TIMEOUT		5000 /* ms */
 #define INTEL_SPI_FIFO_SZ		64
@@ -117,8 +130,11 @@
  * @pregs: Start of protection registers
  * @sregs: Start of software sequencer registers
  * @nregions: Maximum number of regions
+ * @pr_num: Maximum number of protected range registers
  * @writeable: Is the chip writeable
- * @swseq: Use SW sequencer in register reads/writes
+ * @locked: Is SPI setting locked
+ * @swseq_reg: Use SW sequencer in register reads/writes
+ * @swseq_erase: Use SW sequencer in erase operation
  * @erase_64k: 64k erase supported
  * @opcodes: Opcodes which are supported. This are programmed by BIOS
  *           before it locks down the controller.
@@ -132,8 +148,11 @@ struct intel_spi {
 	void __iomem *pregs;
 	void __iomem *sregs;
 	size_t nregions;
+	size_t pr_num;
 	bool writeable;
-	bool swseq;
+	bool locked;
+	bool swseq_reg;
+	bool swseq_erase;
 	bool erase_64k;
 	u8 opcodes[8];
 	u8 preopcodes[2];
@@ -167,7 +186,7 @@ static void intel_spi_dump_regs(struct intel_spi *ispi)
 	for (i = 0; i < ispi->nregions; i++)
 		dev_dbg(ispi->dev, "FREG(%d)=0x%08x\n", i,
 			readl(ispi->base + FREG(i)));
-	for (i = 0; i < PR_NUM; i++)
+	for (i = 0; i < ispi->pr_num; i++)
 		dev_dbg(ispi->dev, "PR(%d)=0x%08x\n", i,
 			readl(ispi->pregs + PR(i)));
 
@@ -181,8 +200,11 @@ static void intel_spi_dump_regs(struct intel_spi *ispi)
 	if (ispi->info->type == INTEL_SPI_BYT)
 		dev_dbg(ispi->dev, "BCR=0x%08x\n", readl(ispi->base + BYT_BCR));
 
+	dev_dbg(ispi->dev, "LVSCC=0x%08x\n", readl(ispi->base + LVSCC));
+	dev_dbg(ispi->dev, "UVSCC=0x%08x\n", readl(ispi->base + UVSCC));
+
 	dev_dbg(ispi->dev, "Protected regions:\n");
-	for (i = 0; i < PR_NUM; i++) {
+	for (i = 0; i < ispi->pr_num; i++) {
 		u32 base, limit;
 
 		value = readl(ispi->pregs + PR(i));
@@ -214,7 +236,9 @@ static void intel_spi_dump_regs(struct intel_spi *ispi)
 	}
 
 	dev_dbg(ispi->dev, "Using %cW sequencer for register access\n",
-		ispi->swseq ? 'S' : 'H');
+		ispi->swseq_reg ? 'S' : 'H');
+	dev_dbg(ispi->dev, "Using %cW sequencer for erase operation\n",
+		ispi->swseq_erase ? 'S' : 'H');
 }
 
 /* Reads max INTEL_SPI_FIFO_SZ bytes from the device fifo */
@@ -278,7 +302,7 @@ static int intel_spi_wait_sw_busy(struct intel_spi *ispi)
 
 static int intel_spi_init(struct intel_spi *ispi)
 {
-	u32 opmenu0, opmenu1, val;
+	u32 opmenu0, opmenu1, lvscc, uvscc, val;
 	int i;
 
 	switch (ispi->info->type) {
@@ -286,6 +310,8 @@ static int intel_spi_init(struct intel_spi *ispi)
 		ispi->sregs = ispi->base + BYT_SSFSTS_CTL;
 		ispi->pregs = ispi->base + BYT_PR;
 		ispi->nregions = BYT_FREG_NUM;
+		ispi->pr_num = BYT_PR_NUM;
+		ispi->swseq_reg = true;
 
 		if (writeable) {
 			/* Disable write protection */
@@ -305,12 +331,15 @@ static int intel_spi_init(struct intel_spi *ispi)
 		ispi->sregs = ispi->base + LPT_SSFSTS_CTL;
 		ispi->pregs = ispi->base + LPT_PR;
 		ispi->nregions = LPT_FREG_NUM;
+		ispi->pr_num = LPT_PR_NUM;
+		ispi->swseq_reg = true;
 		break;
 
 	case INTEL_SPI_BXT:
 		ispi->sregs = ispi->base + BXT_SSFSTS_CTL;
 		ispi->pregs = ispi->base + BXT_PR;
 		ispi->nregions = BXT_FREG_NUM;
+		ispi->pr_num = BXT_PR_NUM;
 		ispi->erase_64k = true;
 		break;
 
@@ -318,42 +347,64 @@ static int intel_spi_init(struct intel_spi *ispi)
 		return -EINVAL;
 	}
 
-	/* Disable #SMI generation */
+	/* Disable #SMI generation from HW sequencer */
 	val = readl(ispi->base + HSFSTS_CTL);
 	val &= ~HSFSTS_CTL_FSMIE;
 	writel(val, ispi->base + HSFSTS_CTL);
 
 	/*
-	 * BIOS programs allowed opcodes and then locks down the register.
-	 * So read back what opcodes it decided to support. That's the set
-	 * we are going to support as well.
+	 * Determine whether erase operation should use HW or SW sequencer.
+	 *
+	 * The HW sequencer has a predefined list of opcodes, with only the
+	 * erase opcode being programmable in LVSCC and UVSCC registers.
+	 * If these registers don't contain a valid erase opcode, erase
+	 * cannot be done using HW sequencer.
 	 */
-	opmenu0 = readl(ispi->sregs + OPMENU0);
-	opmenu1 = readl(ispi->sregs + OPMENU1);
+	lvscc = readl(ispi->base + LVSCC);
+	uvscc = readl(ispi->base + UVSCC);
+	if (!(lvscc & ERASE_OPCODE_MASK) || !(uvscc & ERASE_OPCODE_MASK))
+		ispi->swseq_erase = true;
+	/* SPI controller on Intel BXT supports 64K erase opcode */
+	if (ispi->info->type == INTEL_SPI_BXT && !ispi->swseq_erase)
+		if (!(lvscc & ERASE_64K_OPCODE_MASK) ||
+		    !(uvscc & ERASE_64K_OPCODE_MASK))
+			ispi->erase_64k = false;
 
 	/*
 	 * Some controllers can only do basic operations using hardware
 	 * sequencer. All other operations are supposed to be carried out
-	 * using software sequencer. If we find that BIOS has programmed
-	 * opcodes for the software sequencer we use that over the hardware
-	 * sequencer.
+	 * using software sequencer.
 	 */
-	if (opmenu0 && opmenu1) {
-		for (i = 0; i < ARRAY_SIZE(ispi->opcodes) / 2; i++) {
-			ispi->opcodes[i] = opmenu0 >> i * 8;
-			ispi->opcodes[i + 4] = opmenu1 >> i * 8;
-		}
-
-		val = readl(ispi->sregs + PREOP_OPTYPE);
-		ispi->preopcodes[0] = val;
-		ispi->preopcodes[1] = val >> 8;
-
+	if (ispi->swseq_reg) {
 		/* Disable #SMI generation from SW sequencer */
 		val = readl(ispi->sregs + SSFSTS_CTL);
 		val &= ~SSFSTS_CTL_FSMIE;
 		writel(val, ispi->sregs + SSFSTS_CTL);
+	}
+
+	/* Check controller's lock status */
+	val = readl(ispi->base + HSFSTS_CTL);
+	ispi->locked = !!(val & HSFSTS_CTL_FLOCKDN);
+
+	if (ispi->locked) {
+		/*
+		 * BIOS programs allowed opcodes and then locks down the
+		 * register. So read back what opcodes it decided to support.
+		 * That's the set we are going to support as well.
+		 */
+		opmenu0 = readl(ispi->sregs + OPMENU0);
+		opmenu1 = readl(ispi->sregs + OPMENU1);
 
-		ispi->swseq = true;
+		if (opmenu0 && opmenu1) {
+			for (i = 0; i < ARRAY_SIZE(ispi->opcodes) / 2; i++) {
+				ispi->opcodes[i] = opmenu0 >> i * 8;
+				ispi->opcodes[i + 4] = opmenu1 >> i * 8;
+			}
+
+			val = readl(ispi->sregs + PREOP_OPTYPE);
+			ispi->preopcodes[0] = val;
+			ispi->preopcodes[1] = val >> 8;
+		}
 	}
 
 	intel_spi_dump_regs(ispi);
@@ -361,18 +412,28 @@ static int intel_spi_init(struct intel_spi *ispi)
 	return 0;
 }
 
-static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode)
+static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode, int optype)
 {
 	int i;
+	int preop;
 
-	for (i = 0; i < ARRAY_SIZE(ispi->opcodes); i++)
-		if (ispi->opcodes[i] == opcode)
-			return i;
-	return -EINVAL;
+	if (ispi->locked) {
+		for (i = 0; i < ARRAY_SIZE(ispi->opcodes); i++)
+			if (ispi->opcodes[i] == opcode)
+				return i;
+
+		return -EINVAL;
+	}
+
+	/* The lock is off, so just use index 0 */
+	writel(opcode, ispi->sregs + OPMENU0);
+	preop = readw(ispi->sregs + PREOP_OPTYPE);
+	writel(optype << 16 | preop, ispi->sregs + PREOP_OPTYPE);
+
+	return 0;
 }
 
-static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
-			      int len)
+static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, int len)
 {
 	u32 val, status;
 	int ret;
@@ -394,6 +455,9 @@ static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
 		return -EINVAL;
 	}
 
+	if (len > INTEL_SPI_FIFO_SZ)
+		return -EINVAL;
+
 	val |= (len - 1) << HSFSTS_CTL_FDBC_SHIFT;
 	val |= HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
 	val |= HSFSTS_CTL_FGO;
@@ -412,27 +476,39 @@ static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
 	return 0;
 }
 
-static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
-			      int len)
+static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, int len,
+			      int optype)
 {
-	u32 val, status;
+	u32 val = 0, status;
+	u16 preop;
 	int ret;
 
-	ret = intel_spi_opcode_index(ispi, opcode);
+	ret = intel_spi_opcode_index(ispi, opcode, optype);
 	if (ret < 0)
 		return ret;
 
-	val = (len << SSFSTS_CTL_DBC_SHIFT) | SSFSTS_CTL_DS;
+	if (len > INTEL_SPI_FIFO_SZ)
+		return -EINVAL;
+
+	/* Only mark 'Data Cycle' bit when there is data to be transferred */
+	if (len > 0)
+		val = ((len - 1) << SSFSTS_CTL_DBC_SHIFT) | SSFSTS_CTL_DS;
 	val |= ret << SSFSTS_CTL_COP_SHIFT;
 	val |= SSFSTS_CTL_FCERR | SSFSTS_CTL_FDONE;
 	val |= SSFSTS_CTL_SCGO;
+	preop = readw(ispi->sregs + PREOP_OPTYPE);
+	if (preop) {
+		val |= SSFSTS_CTL_ACS;
+		if (preop >> 8)
+			val |= SSFSTS_CTL_SPOP;
+	}
 	writel(val, ispi->sregs + SSFSTS_CTL);
 
 	ret = intel_spi_wait_sw_busy(ispi);
 	if (ret)
 		return ret;
 
-	status = readl(ispi->base + SSFSTS_CTL);
+	status = readl(ispi->sregs + SSFSTS_CTL);
 	if (status & SSFSTS_CTL_FCERR)
 		return -EIO;
 	else if (status & SSFSTS_CTL_AEL)
@@ -449,10 +525,11 @@ static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	/* Address of the first chip */
 	writel(0, ispi->base + FADDR);
 
-	if (ispi->swseq)
-		ret = intel_spi_sw_cycle(ispi, opcode, buf, len);
+	if (ispi->swseq_reg)
+		ret = intel_spi_sw_cycle(ispi, opcode, len,
+					 OPTYPE_READ_NO_ADDR);
 	else
-		ret = intel_spi_hw_cycle(ispi, opcode, buf, len);
+		ret = intel_spi_hw_cycle(ispi, opcode, len);
 
 	if (ret)
 		return ret;
@@ -467,10 +544,15 @@ static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 
 	/*
 	 * This is handled with atomic operation and preop code in Intel
-	 * controller so skip it here now.
+	 * controller so skip it here now. If the controller is not locked,
+	 * program the opcode to the PREOP register for later use.
 	 */
-	if (opcode == SPINOR_OP_WREN)
+	if (opcode == SPINOR_OP_WREN) {
+		if (!ispi->locked)
+			writel(opcode, ispi->sregs + PREOP_OPTYPE);
+
 		return 0;
+	}
 
 	writel(0, ispi->base + FADDR);
 
@@ -479,9 +561,10 @@ static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
 	if (ret)
 		return ret;
 
-	if (ispi->swseq)
-		return intel_spi_sw_cycle(ispi, opcode, buf, len);
-	return intel_spi_hw_cycle(ispi, opcode, buf, len);
+	if (ispi->swseq_reg)
+		return intel_spi_sw_cycle(ispi, opcode, len,
+					  OPTYPE_WRITE_NO_ADDR);
+	return intel_spi_hw_cycle(ispi, opcode, len);
 }
 
 static ssize_t intel_spi_read(struct spi_nor *nor, loff_t from, size_t len,
@@ -561,12 +644,6 @@ static ssize_t intel_spi_write(struct spi_nor *nor, loff_t to, size_t len,
 		val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT;
 		val |= HSFSTS_CTL_FCYCLE_WRITE;
 
-		/* Write enable */
-		if (ispi->preopcodes[1] == SPINOR_OP_WREN)
-			val |= SSFSTS_CTL_SPOP;
-		val |= SSFSTS_CTL_ACS;
-		writel(val, ispi->base + HSFSTS_CTL);
-
 		ret = intel_spi_write_block(ispi, write_buf, block_size);
 		if (ret) {
 			dev_err(ispi->dev, "failed to write block\n");
@@ -574,8 +651,8 @@ static ssize_t intel_spi_write(struct spi_nor *nor, loff_t to, size_t len,
 		}
 
 		/* Start the write now */
-		val = readl(ispi->base + HSFSTS_CTL);
-		writel(val | HSFSTS_CTL_FGO, ispi->base + HSFSTS_CTL);
+		val |= HSFSTS_CTL_FGO;
+		writel(val, ispi->base + HSFSTS_CTL);
 
 		ret = intel_spi_wait_hw_busy(ispi);
 		if (ret) {
@@ -620,6 +697,22 @@ static int intel_spi_erase(struct spi_nor *nor, loff_t offs)
 		erase_size = SZ_4K;
 	}
 
+	if (ispi->swseq_erase) {
+		while (len > 0) {
+			writel(offs, ispi->base + FADDR);
+
+			ret = intel_spi_sw_cycle(ispi, nor->erase_opcode,
+						 0, OPTYPE_WRITE_WITH_ADDR);
+			if (ret)
+				return ret;
+
+			offs += erase_size;
+			len -= erase_size;
+		}
+
+		return 0;
+	}
+
 	while (len > 0) {
 		writel(offs, ispi->base + FADDR);
 
@@ -652,7 +745,7 @@ static bool intel_spi_is_protected(const struct intel_spi *ispi,
 {
 	int i;
 
-	for (i = 0; i < PR_NUM; i++) {
+	for (i = 0; i < ispi->pr_num; i++) {
 		u32 pr_base, pr_limit, pr_value;
 
 		pr_value = readl(ispi->pregs + PR(i));
diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c
index c258c7adf1c5..abe455ccd68b 100644
--- a/drivers/mtd/spi-nor/mtk-quadspi.c
+++ b/drivers/mtd/spi-nor/mtk-quadspi.c
@@ -404,6 +404,29 @@ static int mt8173_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
 	return ret;
 }
 
+static void mt8173_nor_disable_clk(struct mt8173_nor *mt8173_nor)
+{
+	clk_disable_unprepare(mt8173_nor->spi_clk);
+	clk_disable_unprepare(mt8173_nor->nor_clk);
+}
+
+static int mt8173_nor_enable_clk(struct mt8173_nor *mt8173_nor)
+{
+	int ret;
+
+	ret = clk_prepare_enable(mt8173_nor->spi_clk);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(mt8173_nor->nor_clk);
+	if (ret) {
+		clk_disable_unprepare(mt8173_nor->spi_clk);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int mtk_nor_init(struct mt8173_nor *mt8173_nor,
 			struct device_node *flash_node)
 {
@@ -468,15 +491,11 @@ static int mtk_nor_drv_probe(struct platform_device *pdev)
 		return PTR_ERR(mt8173_nor->nor_clk);
 
 	mt8173_nor->dev = &pdev->dev;
-	ret = clk_prepare_enable(mt8173_nor->spi_clk);
+
+	ret = mt8173_nor_enable_clk(mt8173_nor);
 	if (ret)
 		return ret;
 
-	ret = clk_prepare_enable(mt8173_nor->nor_clk);
-	if (ret) {
-		clk_disable_unprepare(mt8173_nor->spi_clk);
-		return ret;
-	}
 	/* only support one attached flash */
 	flash_np = of_get_next_available_child(pdev->dev.of_node, NULL);
 	if (!flash_np) {
@@ -487,10 +506,9 @@ static int mtk_nor_drv_probe(struct platform_device *pdev)
 	ret = mtk_nor_init(mt8173_nor, flash_np);
 
 nor_free:
-	if (ret) {
-		clk_disable_unprepare(mt8173_nor->spi_clk);
-		clk_disable_unprepare(mt8173_nor->nor_clk);
-	}
+	if (ret)
+		mt8173_nor_disable_clk(mt8173_nor);
+
 	return ret;
 }
 
@@ -498,11 +516,38 @@ static int mtk_nor_drv_remove(struct platform_device *pdev)
 {
 	struct mt8173_nor *mt8173_nor = platform_get_drvdata(pdev);
 
-	clk_disable_unprepare(mt8173_nor->spi_clk);
-	clk_disable_unprepare(mt8173_nor->nor_clk);
+	mt8173_nor_disable_clk(mt8173_nor);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mtk_nor_suspend(struct device *dev)
+{
+	struct mt8173_nor *mt8173_nor = dev_get_drvdata(dev);
+
+	mt8173_nor_disable_clk(mt8173_nor);
+
 	return 0;
 }
 
+static int mtk_nor_resume(struct device *dev)
+{
+	struct mt8173_nor *mt8173_nor = dev_get_drvdata(dev);
+
+	return mt8173_nor_enable_clk(mt8173_nor);
+}
+
+static const struct dev_pm_ops mtk_nor_dev_pm_ops = {
+	.suspend = mtk_nor_suspend,
+	.resume = mtk_nor_resume,
+};
+
+#define MTK_NOR_DEV_PM_OPS	(&mtk_nor_dev_pm_ops)
+#else
+#define MTK_NOR_DEV_PM_OPS	NULL
+#endif
+
 static const struct of_device_id mtk_nor_of_ids[] = {
 	{ .compatible = "mediatek,mt8173-nor"},
 	{ /* sentinel */ }
@@ -514,6 +559,7 @@ static struct platform_driver mtk_nor_driver = {
 	.remove = mtk_nor_drv_remove,
 	.driver = {
 		.name = "mtk-nor",
+		.pm = MTK_NOR_DEV_PM_OPS,
 		.of_match_table = mtk_nor_of_ids,
 	},
 };
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index 19c000722cbc..bc266f70a15b 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -89,6 +89,8 @@ struct flash_info {
 #define NO_CHIP_ERASE		BIT(12) /* Chip does not support chip erase */
 #define SPI_NOR_SKIP_SFDP	BIT(13)	/* Skip parsing of SFDP tables */
 #define USE_CLSR		BIT(14)	/* use CLSR command */
+
+	int	(*quad_enable)(struct spi_nor *nor);
 };
 
 #define JEDEC_MFR(info)	((info)->id[0])
@@ -870,6 +872,8 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 	return ret;
 }
 
+static int macronix_quad_enable(struct spi_nor *nor);
+
 /* Used when the "_ext_id" is two bytes at most */
 #define INFO(_jedec_id, _ext_id, _sector_size, _n_sectors, _flags)	\
 		.id = {							\
@@ -964,6 +968,7 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "f25l64qa", INFO(0x8c4117, 0, 64 * 1024, 128, SECT_4K | SPI_NOR_HAS_LOCK) },
 
 	/* Everspin */
+	{ "mr25h128", CAT25_INFO( 16 * 1024, 1, 256, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
 	{ "mr25h256", CAT25_INFO( 32 * 1024, 1, 256, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
 	{ "mr25h10",  CAT25_INFO(128 * 1024, 1, 256, 3, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
 	{ "mr25h40",  CAT25_INFO(512 * 1024, 1, 256, 3, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
@@ -983,6 +988,11 @@ static const struct flash_info spi_nor_ids[] = {
 			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
 	},
 	{
+		"gd25lq32", INFO(0xc86016, 0, 64 * 1024, 64,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
+	{
 		"gd25q64", INFO(0xc84017, 0, 64 * 1024, 128,
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
 			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
@@ -997,6 +1007,12 @@ static const struct flash_info spi_nor_ids[] = {
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
 			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
 	},
+	{
+		"gd25q256", INFO(0xc84019, 0, 64 * 1024, 512,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_4B_OPCODES | SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+			.quad_enable = macronix_quad_enable,
+	},
 
 	/* Intel/Numonyx -- xxxs33b */
 	{ "160s33b",  INFO(0x898911, 0, 64 * 1024,  32, 0) },
@@ -1024,7 +1040,7 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "mx25u25635f", INFO(0xc22539, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_4B_OPCODES) },
 	{ "mx25l25655e", INFO(0xc22619, 0, 64 * 1024, 512, 0) },
-	{ "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) },
 	{ "mx66u51235f", INFO(0xc2253a, 0, 64 * 1024, 1024, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) },
 	{ "mx66l1g45g",  INFO(0xc2201b, 0, 64 * 1024, 2048, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "mx66l1g55g",  INFO(0xc2261b, 0, 64 * 1024, 2048, SPI_NOR_QUAD_READ) },
@@ -1137,6 +1153,11 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "w25x40", INFO(0xef3013, 0, 64 * 1024,  8,  SECT_4K) },
 	{ "w25x80", INFO(0xef3014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25x16", INFO(0xef3015, 0, 64 * 1024,  32, SECT_4K) },
+	{
+		"w25q16dw", INFO(0xef6015, 0, 64 * 1024,  32,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
 	{ "w25x32", INFO(0xef3016, 0, 64 * 1024,  64, SECT_4K) },
 	{ "w25q20cl", INFO(0xef4012, 0, 64 * 1024,  4, SECT_4K) },
 	{ "w25q20bw", INFO(0xef5012, 0, 64 * 1024,  4, SECT_4K) },
@@ -2288,8 +2309,7 @@ static int spi_nor_parse_sfdp(struct spi_nor *nor,
 
 	/* Check the SFDP header version. */
 	if (le32_to_cpu(header.signature) != SFDP_SIGNATURE ||
-	    header.major != SFDP_JESD216_MAJOR ||
-	    header.minor < SFDP_JESD216_MINOR)
+	    header.major != SFDP_JESD216_MAJOR)
 		return -EINVAL;
 
 	/*
@@ -2427,6 +2447,15 @@ static int spi_nor_init_params(struct spi_nor *nor,
 			params->quad_enable = spansion_quad_enable;
 			break;
 		}
+
+		/*
+		 * Some manufacturer like GigaDevice may use different
+		 * bit to set QE on different memories, so the MFR can't
+		 * indicate the quad_enable method for this case, we need
+		 * set it in flash info list.
+		 */
+		if (info->quad_enable)
+			params->quad_enable = info->quad_enable;
 	}
 
 	/* Override the parameters with data read from SFDP tables. */
@@ -2630,17 +2659,60 @@ static int spi_nor_setup(struct spi_nor *nor, const struct flash_info *info,
 	/* Enable Quad I/O if needed. */
 	enable_quad_io = (spi_nor_get_protocol_width(nor->read_proto) == 4 ||
 			  spi_nor_get_protocol_width(nor->write_proto) == 4);
-	if (enable_quad_io && params->quad_enable) {
-		err = params->quad_enable(nor);
+	if (enable_quad_io && params->quad_enable)
+		nor->quad_enable = params->quad_enable;
+	else
+		nor->quad_enable = NULL;
+
+	return 0;
+}
+
+static int spi_nor_init(struct spi_nor *nor)
+{
+	int err;
+
+	/*
+	 * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
+	 * with the software protection bits set
+	 */
+	if (JEDEC_MFR(nor->info) == SNOR_MFR_ATMEL ||
+	    JEDEC_MFR(nor->info) == SNOR_MFR_INTEL ||
+	    JEDEC_MFR(nor->info) == SNOR_MFR_SST ||
+	    nor->info->flags & SPI_NOR_HAS_LOCK) {
+		write_enable(nor);
+		write_sr(nor, 0);
+		spi_nor_wait_till_ready(nor);
+	}
+
+	if (nor->quad_enable) {
+		err = nor->quad_enable(nor);
 		if (err) {
 			dev_err(nor->dev, "quad mode not supported\n");
 			return err;
 		}
 	}
 
+	if ((nor->addr_width == 4) &&
+	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+		set_4byte(nor, nor->info, 1);
+
 	return 0;
 }
 
+/* mtd resume handler */
+static void spi_nor_resume(struct mtd_info *mtd)
+{
+	struct spi_nor *nor = mtd_to_spi_nor(mtd);
+	struct device *dev = nor->dev;
+	int ret;
+
+	/* re-initialize the nor chip */
+	ret = spi_nor_init(nor);
+	if (ret)
+		dev_err(dev, "resume() failed\n");
+}
+
 int spi_nor_scan(struct spi_nor *nor, const char *name,
 		 const struct spi_nor_hwcaps *hwcaps)
 {
@@ -2708,20 +2780,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 	if (ret)
 		return ret;
 
-	/*
-	 * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
-	 * with the software protection bits set
-	 */
-
-	if (JEDEC_MFR(info) == SNOR_MFR_ATMEL ||
-	    JEDEC_MFR(info) == SNOR_MFR_INTEL ||
-	    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)
 		mtd->name = dev_name(dev);
 	mtd->priv = nor;
@@ -2731,6 +2789,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 	mtd->size = params.size;
 	mtd->_erase = spi_nor_erase;
 	mtd->_read = spi_nor_read;
+	mtd->_resume = spi_nor_resume;
 
 	/* NOR protection support for STmicro/Micron chips and similar */
 	if (JEDEC_MFR(info) == SNOR_MFR_MICRON ||
@@ -2804,8 +2863,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 		if (JEDEC_MFR(info) == SNOR_MFR_SPANSION ||
 		    info->flags & SPI_NOR_4B_OPCODES)
 			spi_nor_set_4byte_opcodes(nor, info);
-		else
-			set_4byte(nor, info, 1);
 	} else {
 		nor->addr_width = 3;
 	}
@@ -2822,6 +2879,12 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 			return ret;
 	}
 
+	/* Send all the required SPI flash commands to initialize device */
+	nor->info = info;
+	ret = spi_nor_init(nor);
+	if (ret)
+		return ret;
+
 	dev_info(dev, "%s (%lld Kbytes)\n", info->name,
 			(long long)mtd->size >> 10);
 
diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c
index 86c0931543c5..b3c7f6addba7 100644
--- a/drivers/mtd/spi-nor/stm32-quadspi.c
+++ b/drivers/mtd/spi-nor/stm32-quadspi.c
@@ -1,9 +1,22 @@
 /*
- * stm32_quadspi.c
+ * Driver for stm32 quadspi controller
  *
- * Copyright (C) 2017, Ludovic Barre
+ * Copyright (C) 2017, STMicroelectronics - All Rights Reserved
+ * Author(s): Ludovic Barre author <ludovic.barre@st.com>.
  *
- * License terms: GNU General Public License (GPL), version 2
+ * License terms: GPL V2.0.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * This program. If not, see <http://www.gnu.org/licenses/>.
  */
 #include <linux/clk.h>
 #include <linux/errno.h>
@@ -113,6 +126,7 @@
 #define STM32_MAX_MMAP_SZ	SZ_256M
 #define STM32_MAX_NORCHIP	2
 
+#define STM32_QSPI_FIFO_SZ	32
 #define STM32_QSPI_FIFO_TIMEOUT_US 30000
 #define STM32_QSPI_BUSY_TIMEOUT_US 100000
 
@@ -124,6 +138,7 @@ struct stm32_qspi_flash {
 	u32 presc;
 	u32 read_mode;
 	bool registered;
+	u32 prefetch_limit;
 };
 
 struct stm32_qspi {
@@ -240,12 +255,12 @@ static int stm32_qspi_tx_poll(struct stm32_qspi *qspi,
 						 STM32_QSPI_FIFO_TIMEOUT_US);
 		if (ret) {
 			dev_err(qspi->dev, "fifo timeout (stat:%#x)\n", sr);
-			break;
+			return ret;
 		}
 		tx_fifo(buf++, qspi->io_base + QUADSPI_DR);
 	}
 
-	return ret;
+	return 0;
 }
 
 static int stm32_qspi_tx_mm(struct stm32_qspi *qspi,
@@ -272,6 +287,7 @@ static int stm32_qspi_send(struct stm32_qspi_flash *flash,
 {
 	struct stm32_qspi *qspi = flash->qspi;
 	u32 ccr, dcr, cr;
+	u32 last_byte;
 	int err;
 
 	err = stm32_qspi_wait_nobusy(qspi);
@@ -314,6 +330,10 @@ static int stm32_qspi_send(struct stm32_qspi_flash *flash,
 		if (err)
 			goto abort;
 		writel_relaxed(FCR_CTCF, qspi->io_base + QUADSPI_FCR);
+	} else {
+		last_byte = cmd->addr + cmd->len;
+		if (last_byte > flash->prefetch_limit)
+			goto abort;
 	}
 
 	return err;
@@ -322,7 +342,9 @@ abort:
 	cr = readl_relaxed(qspi->io_base + QUADSPI_CR) | CR_ABORT;
 	writel_relaxed(cr, qspi->io_base + QUADSPI_CR);
 
-	dev_err(qspi->dev, "%s abort err:%d\n", __func__, err);
+	if (err)
+		dev_err(qspi->dev, "%s abort err:%d\n", __func__, err);
+
 	return err;
 }
 
@@ -550,6 +572,7 @@ static int stm32_qspi_flash_setup(struct stm32_qspi *qspi,
 	}
 
 	flash->fsize = FSIZE_VAL(mtd->size);
+	flash->prefetch_limit = mtd->size - STM32_QSPI_FIFO_SZ;
 
 	flash->read_mode = CCR_FMODE_MM;
 	if (mtd->size > qspi->mm_size)