Merge series "MTD: spinand: Add spi_mem_poll_status() support" from <patrice.chotard@foss.st.com>

Patrice Chotard <patrice.chotard@foss.st.com>:

From: Patrice Chotard <patrice.chotard@foss.st.com>

This series adds support for the spi_mem_poll_status() spinand
interface.
Some QSPI controllers allows to poll automatically memory
status during operations (erase, read or write). This allows to
offload the CPU for this task.
STM32 QSPI is supporting this feature, driver update are also
part of this series.

Changes in v5:
  - Update spi_mem_read_status() description.
  - Update poll_status() description API by indicating that data buffer is
    filled with last status value.
  - Update timeout parameter by timeout_ms in spi_mem_poll_status() prototype.
  - Remove parenthesys arount -EINVAL in spi_mem_poll_status().
  - Add missing spi_mem_supports_op() call in stm32_qspi_poll_status().
  - Add Boris Reviewed-by for patch 1 and 2.

Changes in v4:
  - Remove init_completion() from spi_mem_probe() added in v2.
  - Add missing static for spi_mem_read_status().
  - Check if operation in spi_mem_poll_status() is a READ.
  - Update patch 2 commit message.
  - Add comment which explains how delays has been calculated.
  - Rename SPINAND_STATUS_TIMEOUT_MS to SPINAND_WAITRDY_TIMEOUT_MS.

Chnages in v3:
  - Add spi_mem_read_status() which allows to read 8 or 16 bits status.
  - Add initial_delay_us and polling_delay_us parameters to spi_mem_poll_status().
    and also to poll_status() callback.
  - Move spi_mem_supports_op() in SW-based polling case.
  - Add delay before invoquing read_poll_timeout().
  - Remove the reinit/wait_for_completion() added in v2.
  - Add initial_delay_us and polling_delay_us parameters to spinand_wait().
  - Add SPINAND_READ/WRITE/ERASE/RESET_INITIAL_DELAY_US and
    SPINAND_READ/WRITE/ERASE/RESET_POLL_DELAY_US defines.
  - Remove spi_mem_finalize_op() API added in v2.

Changes in v2:
  - Indicates the spi_mem_poll_status() timeout unit
  - Use 2-byte wide status register
  - Add spi_mem_supports_op() call in spi_mem_poll_status()
  - Add completion management in spi_mem_poll_status()
  - Add offload/non-offload case management in spi_mem_poll_status()
  - Optimize the non-offload case by using read_poll_timeout()
  - mask and match stm32_qspi_poll_status()'s parameters are 2-byte wide
  - Make usage of new spi_mem_finalize_op() API in
    stm32_qspi_wait_poll_status()

Patrice Chotard (3):
  spi: spi-mem: add automatic poll status functions
  mtd: spinand: use the spi-mem poll status APIs
  spi: stm32-qspi: add automatic poll status feature

 drivers/mtd/nand/spi/core.c  | 45 +++++++++++++------
 drivers/spi/spi-mem.c        | 86 ++++++++++++++++++++++++++++++++++++
 drivers/spi/spi-stm32-qspi.c | 86 ++++++++++++++++++++++++++++++++----
 include/linux/mtd/spinand.h  | 22 +++++++++
 include/linux/spi/spi-mem.h  | 16 +++++++
 5 files changed, 234 insertions(+), 21 deletions(-)

base-commit: 6efb943b8616ec53a5e444193dccf1af9ad627b5

--
2.17.1

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

5 files changed, 234 insertions, 21 deletions

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 17f63f95f4a2..3131fae0c715 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -473,20 +473,26 @@ static int spinand_erase_op(struct spinand_device *spinand,
 	return spi_mem_exec_op(spinand->spimem, &op);
 }
 
-static int spinand_wait(struct spinand_device *spinand, u8 *s)
+static int spinand_wait(struct spinand_device *spinand,
+			unsigned long initial_delay_us,
+			unsigned long poll_delay_us,
+			u8 *s)
 {
-	unsigned long timeo =  jiffies + msecs_to_jiffies(400);
+	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(REG_STATUS,
+						      spinand->scratchbuf);
 	u8 status;
 	int ret;
 
-	do {
-		ret = spinand_read_status(spinand, &status);
-		if (ret)
-			return ret;
+	ret = spi_mem_poll_status(spinand->spimem, &op, STATUS_BUSY, 0,
+				  initial_delay_us,
+				  poll_delay_us,
+				  SPINAND_WAITRDY_TIMEOUT_MS);
+	if (ret)
+		return ret;
 
-		if (!(status & STATUS_BUSY))
-			goto out;
-	} while (time_before(jiffies, timeo));
+	status = *spinand->scratchbuf;
+	if (!(status & STATUS_BUSY))
+		goto out;
 
 	/*
 	 * Extra read, just in case the STATUS_READY bit has changed
@@ -526,7 +532,10 @@ static int spinand_reset_op(struct spinand_device *spinand)
 	if (ret)
 		return ret;
 
-	return spinand_wait(spinand, NULL);
+	return spinand_wait(spinand,
+			    SPINAND_RESET_INITIAL_DELAY_US,
+			    SPINAND_RESET_POLL_DELAY_US,
+			    NULL);
 }
 
 static int spinand_lock_block(struct spinand_device *spinand, u8 lock)
@@ -549,7 +558,10 @@ static int spinand_read_page(struct spinand_device *spinand,
 	if (ret)
 		return ret;
 
-	ret = spinand_wait(spinand, &status);
+	ret = spinand_wait(spinand,
+			   SPINAND_READ_INITIAL_DELAY_US,
+			   SPINAND_READ_POLL_DELAY_US,
+			   &status);
 	if (ret < 0)
 		return ret;
 
@@ -585,7 +597,10 @@ static int spinand_write_page(struct spinand_device *spinand,
 	if (ret)
 		return ret;
 
-	ret = spinand_wait(spinand, &status);
+	ret = spinand_wait(spinand,
+			   SPINAND_WRITE_INITIAL_DELAY_US,
+			   SPINAND_WRITE_POLL_DELAY_US,
+			   &status);
 	if (!ret && (status & STATUS_PROG_FAILED))
 		return -EIO;
 
@@ -768,7 +783,11 @@ static int spinand_erase(struct nand_device *nand, const struct nand_pos *pos)
 	if (ret)
 		return ret;
 
-	ret = spinand_wait(spinand, &status);
+	ret = spinand_wait(spinand,
+			   SPINAND_ERASE_INITIAL_DELAY_US,
+			   SPINAND_ERASE_POLL_DELAY_US,
+			   &status);
+
 	if (!ret && (status & STATUS_ERASE_FAILED))
 		ret = -EIO;
 
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 1513553e4080..177b3e21febf 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -6,6 +6,7 @@
  * Author: Boris Brezillon <boris.brezillon@bootlin.com>
  */
 #include <linux/dmaengine.h>
+#include <linux/iopoll.h>
 #include <linux/pm_runtime.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi-mem.h>
@@ -743,6 +744,91 @@ static inline struct spi_mem_driver *to_spi_mem_drv(struct device_driver *drv)
 	return container_of(drv, struct spi_mem_driver, spidrv.driver);
 }
 
+static int spi_mem_read_status(struct spi_mem *mem,
+			       const struct spi_mem_op *op,
+			       u16 *status)
+{
+	const u8 *bytes = (u8 *)op->data.buf.in;
+	int ret;
+
+	ret = spi_mem_exec_op(mem, op);
+	if (ret)
+		return ret;
+
+	if (op->data.nbytes > 1)
+		*status = ((u16)bytes[0] << 8) | bytes[1];
+	else
+		*status = bytes[0];
+
+	return 0;
+}
+
+/**
+ * spi_mem_poll_status() - Poll memory device status
+ * @mem: SPI memory device
+ * @op: the memory operation to execute
+ * @mask: status bitmask to ckeck
+ * @match: (status & mask) expected value
+ * @initial_delay_us: delay in us before starting to poll
+ * @polling_delay_us: time to sleep between reads in us
+ * @timeout_ms: timeout in milliseconds
+ *
+ * This function polls a status register and returns when
+ * (status & mask) == match or when the timeout has expired.
+ *
+ * Return: 0 in case of success, -ETIMEDOUT in case of error,
+ *         -EOPNOTSUPP if not supported.
+ */
+int spi_mem_poll_status(struct spi_mem *mem,
+			const struct spi_mem_op *op,
+			u16 mask, u16 match,
+			unsigned long initial_delay_us,
+			unsigned long polling_delay_us,
+			u16 timeout_ms)
+{
+	struct spi_controller *ctlr = mem->spi->controller;
+	int ret = -EOPNOTSUPP;
+	int read_status_ret;
+	u16 status;
+
+	if (op->data.nbytes < 1 || op->data.nbytes > 2 ||
+	    op->data.dir != SPI_MEM_DATA_IN)
+		return -EINVAL;
+
+	if (ctlr->mem_ops && ctlr->mem_ops->poll_status) {
+		ret = spi_mem_access_start(mem);
+		if (ret)
+			return ret;
+
+		ret = ctlr->mem_ops->poll_status(mem, op, mask, match,
+						 initial_delay_us, polling_delay_us,
+						 timeout_ms);
+
+		spi_mem_access_end(mem);
+	}
+
+	if (ret == -EOPNOTSUPP) {
+		if (!spi_mem_supports_op(mem, op))
+			return ret;
+
+		if (initial_delay_us < 10)
+			udelay(initial_delay_us);
+		else
+			usleep_range((initial_delay_us >> 2) + 1,
+				     initial_delay_us);
+
+		ret = read_poll_timeout(spi_mem_read_status, read_status_ret,
+					(read_status_ret || ((status) & mask) == match),
+					polling_delay_us, timeout_ms * 1000, false, mem,
+					op, &status);
+		if (read_status_ret)
+			return read_status_ret;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(spi_mem_poll_status);
+
 static int spi_mem_probe(struct spi_device *spi)
 {
 	struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c
index 7e640ccc7e77..69fd220a2894 100644
--- a/drivers/spi/spi-stm32-qspi.c
+++ b/drivers/spi/spi-stm32-qspi.c
@@ -36,6 +36,7 @@
 #define CR_FTIE			BIT(18)
 #define CR_SMIE			BIT(19)
 #define CR_TOIE			BIT(20)
+#define CR_APMS			BIT(22)
 #define CR_PRESC_MASK		GENMASK(31, 24)
 
 #define QSPI_DCR		0x04
@@ -53,6 +54,7 @@
 #define QSPI_FCR		0x0c
 #define FCR_CTEF		BIT(0)
 #define FCR_CTCF		BIT(1)
+#define FCR_CSMF		BIT(3)
 
 #define QSPI_DLR		0x10
 
@@ -107,6 +109,7 @@ struct stm32_qspi {
 	u32 clk_rate;
 	struct stm32_qspi_flash flash[STM32_QSPI_MAX_NORCHIP];
 	struct completion data_completion;
+	struct completion match_completion;
 	u32 fmode;
 
 	struct dma_chan *dma_chtx;
@@ -115,6 +118,7 @@ struct stm32_qspi {
 
 	u32 cr_reg;
 	u32 dcr_reg;
+	unsigned long status_timeout;
 
 	/*
 	 * to protect device configuration, could be different between
@@ -128,11 +132,20 @@ static irqreturn_t stm32_qspi_irq(int irq, void *dev_id)
 	struct stm32_qspi *qspi = (struct stm32_qspi *)dev_id;
 	u32 cr, sr;
 
+	cr = readl_relaxed(qspi->io_base + QSPI_CR);
 	sr = readl_relaxed(qspi->io_base + QSPI_SR);
 
+	if (cr & CR_SMIE && sr & SR_SMF) {
+		/* disable irq */
+		cr &= ~CR_SMIE;
+		writel_relaxed(cr, qspi->io_base + QSPI_CR);
+		complete(&qspi->match_completion);
+
+		return IRQ_HANDLED;
+	}
+
 	if (sr & (SR_TEF | SR_TCF)) {
 		/* disable irq */
-		cr = readl_relaxed(qspi->io_base + QSPI_CR);
 		cr &= ~CR_TCIE & ~CR_TEIE;
 		writel_relaxed(cr, qspi->io_base + QSPI_CR);
 		complete(&qspi->data_completion);
@@ -319,6 +332,24 @@ out:
 	return err;
 }
 
+static int stm32_qspi_wait_poll_status(struct stm32_qspi *qspi,
+				       const struct spi_mem_op *op)
+{
+	u32 cr;
+
+	reinit_completion(&qspi->match_completion);
+	cr = readl_relaxed(qspi->io_base + QSPI_CR);
+	writel_relaxed(cr | CR_SMIE, qspi->io_base + QSPI_CR);
+
+	if (!wait_for_completion_timeout(&qspi->match_completion,
+				msecs_to_jiffies(qspi->status_timeout)))
+		return -ETIMEDOUT;
+
+	writel_relaxed(FCR_CSMF, qspi->io_base + QSPI_FCR);
+
+	return 0;
+}
+
 static int stm32_qspi_get_mode(struct stm32_qspi *qspi, u8 buswidth)
 {
 	if (buswidth == 4)
@@ -332,7 +363,7 @@ static int stm32_qspi_send(struct spi_mem *mem, const struct spi_mem_op *op)
 	struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->master);
 	struct stm32_qspi_flash *flash = &qspi->flash[mem->spi->chip_select];
 	u32 ccr, cr;
-	int timeout, err = 0;
+	int timeout, err = 0, err_poll_status = 0;
 
 	dev_dbg(qspi->dev, "cmd:%#x mode:%d.%d.%d.%d addr:%#llx len:%#x\n",
 		op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth,
@@ -378,6 +409,9 @@ static int stm32_qspi_send(struct spi_mem *mem, const struct spi_mem_op *op)
 	if (op->addr.nbytes && qspi->fmode != CCR_FMODE_MM)
 		writel_relaxed(op->addr.val, qspi->io_base + QSPI_AR);
 
+	if (qspi->fmode == CCR_FMODE_APM)
+		err_poll_status = stm32_qspi_wait_poll_status(qspi, op);
+
 	err = stm32_qspi_tx(qspi, op);
 
 	/*
@@ -387,7 +421,7 @@ static int stm32_qspi_send(struct spi_mem *mem, const struct spi_mem_op *op)
 	 *  byte of device (device size - fifo size). like device size is not
 	 *  knows, the prefetching is always stop.
 	 */
-	if (err || qspi->fmode == CCR_FMODE_MM)
+	if (err || err_poll_status || qspi->fmode == CCR_FMODE_MM)
 		goto abort;
 
 	/* wait end of tx in indirect mode */
@@ -406,15 +440,49 @@ abort:
 						    cr, !(cr & CR_ABORT), 1,
 						    STM32_ABT_TIMEOUT_US);
 
-	writel_relaxed(FCR_CTCF, qspi->io_base + QSPI_FCR);
+	writel_relaxed(FCR_CTCF | FCR_CSMF, qspi->io_base + QSPI_FCR);
 
-	if (err || timeout)
-		dev_err(qspi->dev, "%s err:%d abort timeout:%d\n",
-			__func__, err, timeout);
+	if (err || err_poll_status || timeout)
+		dev_err(qspi->dev, "%s err:%d err_poll_status:%d abort timeout:%d\n",
+			__func__, err, err_poll_status, timeout);
 
 	return err;
 }
 
+static int stm32_qspi_poll_status(struct spi_mem *mem, const struct spi_mem_op *op,
+				  u16 mask, u16 match,
+				  unsigned long initial_delay_us,
+				  unsigned long polling_rate_us,
+				  unsigned long timeout_ms)
+{
+	struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->master);
+	int ret;
+
+	if (!spi_mem_supports_op(mem, op))
+		return -EOPNOTSUPP;
+
+	ret = pm_runtime_get_sync(qspi->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(qspi->dev);
+		return ret;
+	}
+
+	mutex_lock(&qspi->lock);
+
+	writel_relaxed(mask, qspi->io_base + QSPI_PSMKR);
+	writel_relaxed(match, qspi->io_base + QSPI_PSMAR);
+	qspi->fmode = CCR_FMODE_APM;
+	qspi->status_timeout = timeout_ms;
+
+	ret = stm32_qspi_send(mem, op);
+	mutex_unlock(&qspi->lock);
+
+	pm_runtime_mark_last_busy(qspi->dev);
+	pm_runtime_put_autosuspend(qspi->dev);
+
+	return ret;
+}
+
 static int stm32_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 {
 	struct stm32_qspi *qspi = spi_controller_get_devdata(mem->spi->master);
@@ -527,7 +595,7 @@ static int stm32_qspi_setup(struct spi_device *spi)
 	flash->presc = presc;
 
 	mutex_lock(&qspi->lock);
-	qspi->cr_reg = 3 << CR_FTHRES_SHIFT | CR_SSHIFT | CR_EN;
+	qspi->cr_reg = CR_APMS | 3 << CR_FTHRES_SHIFT | CR_SSHIFT | CR_EN;
 	writel_relaxed(qspi->cr_reg, qspi->io_base + QSPI_CR);
 
 	/* set dcr fsize to max address */
@@ -607,6 +675,7 @@ static const struct spi_controller_mem_ops stm32_qspi_mem_ops = {
 	.exec_op	= stm32_qspi_exec_op,
 	.dirmap_create	= stm32_qspi_dirmap_create,
 	.dirmap_read	= stm32_qspi_dirmap_read,
+	.poll_status	= stm32_qspi_poll_status,
 };
 
 static int stm32_qspi_probe(struct platform_device *pdev)
@@ -661,6 +730,7 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	}
 
 	init_completion(&qspi->data_completion);
+	init_completion(&qspi->match_completion);
 
 	qspi->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(qspi->clk)) {
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 6bb92f26833e..6988956b8492 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -170,6 +170,28 @@ struct spinand_op;
 struct spinand_device;
 
 #define SPINAND_MAX_ID_LEN	4
+/*
+ * For erase, write and read operation, we got the following timings :
+ * tBERS (erase) 1ms to 4ms
+ * tPROG 300us to 400us
+ * tREAD 25us to 100us
+ * In order to minimize latency, the min value is divided by 4 for the
+ * initial delay, and dividing by 20 for the poll delay.
+ * For reset, 5us/10us/500us if the device is respectively
+ * reading/programming/erasing when the RESET occurs. Since we always
+ * issue a RESET when the device is IDLE, 5us is selected for both initial
+ * and poll delay.
+ */
+#define SPINAND_READ_INITIAL_DELAY_US	6
+#define SPINAND_READ_POLL_DELAY_US	5
+#define SPINAND_RESET_INITIAL_DELAY_US	5
+#define SPINAND_RESET_POLL_DELAY_US	5
+#define SPINAND_WRITE_INITIAL_DELAY_US	75
+#define SPINAND_WRITE_POLL_DELAY_US	15
+#define SPINAND_ERASE_INITIAL_DELAY_US	250
+#define SPINAND_ERASE_POLL_DELAY_US	50
+
+#define SPINAND_WAITRDY_TIMEOUT_MS	400
 
 /**
  * struct spinand_id - SPI NAND id structure
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index 2b65c9edc34e..85e2ff7b840d 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -250,6 +250,9 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem)
  *		  the currently mapped area), and the caller of
  *		  spi_mem_dirmap_write() is responsible for calling it again in
  *		  this case.
+ * @poll_status: poll memory device status until (status & mask) == match or
+ *               when the timeout has expired. It fills the data buffer with
+ *               the last status value.
  *
  * This interface should be implemented by SPI controllers providing an
  * high-level interface to execute SPI memory operation, which is usually the
@@ -274,6 +277,12 @@ struct spi_controller_mem_ops {
 			       u64 offs, size_t len, void *buf);
 	ssize_t (*dirmap_write)(struct spi_mem_dirmap_desc *desc,
 				u64 offs, size_t len, const void *buf);
+	int (*poll_status)(struct spi_mem *mem,
+			   const struct spi_mem_op *op,
+			   u16 mask, u16 match,
+			   unsigned long initial_delay_us,
+			   unsigned long polling_rate_us,
+			   unsigned long timeout_ms);
 };
 
 /**
@@ -369,6 +378,13 @@ devm_spi_mem_dirmap_create(struct device *dev, struct spi_mem *mem,
 void devm_spi_mem_dirmap_destroy(struct device *dev,
 				 struct spi_mem_dirmap_desc *desc);
 
+int spi_mem_poll_status(struct spi_mem *mem,
+			const struct spi_mem_op *op,
+			u16 mask, u16 match,
+			unsigned long initial_delay_us,
+			unsigned long polling_delay_us,
+			u16 timeout_ms);
+
 int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv,
 				       struct module *owner);