Upgrade to 4.4.50-rt62

The current kernel is based on rt kernel v4.4.6-rt14. We will upgrade it
to 4.4.50-rt62.
The command to achieve it is:
a) Clone a git repo from
git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git

b) Get the diff between this two changesets:
git diff 640eca2901f3435e616157b11379d3223a44b391
705619beeea1b0b48219a683fd1a901a86fdaf5e

where the two commits are:
[yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only
640eca2901f3435e616157b11379d3223a44b391
640eca2901f3 v4.4.6-rt14
localversion-rt
[yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only
705619beeea1b0b48219a683fd1a901a86fdaf5e
705619beeea1 Linux 4.4.50-rt62
localversion-rt

c) One patch has been backported thus revert the patch before applying.

 filterdiff -p1 -x scripts/package/Makefile
~/tmp/v4.4.6-rt14-4.4.50-rt62.diff  |patch -p1 --dry-run

Upstream status: backport

Change-Id: I244d57a32f6066e5a5b9915f9fbf99e7bbca6e01
Signed-off-by: Yunhong Jiang <yunhong.jiang@linux.intel.com>

8 files changed, 128 insertions, 55 deletions

diff --git a/kernel/drivers/spi/spi-fsl-dspi.c b/kernel/drivers/spi/spi-fsl-dspi.c
index 39412c909..a3965cac1 100644
--- a/kernel/drivers/spi/spi-fsl-dspi.c
+++ b/kernel/drivers/spi/spi-fsl-dspi.c
@@ -753,7 +753,6 @@ static int dspi_remove(struct platform_device *pdev)
 	/* Disconnect from the SPI framework */
 	clk_disable_unprepare(dspi->clk);
 	spi_unregister_master(dspi->master);
-	spi_master_put(dspi->master);
 
 	return 0;
 }
diff --git a/kernel/drivers/spi/spi-orion.c b/kernel/drivers/spi/spi-orion.c
index a87cfd4ba..61a86d391 100644
--- a/kernel/drivers/spi/spi-orion.c
+++ b/kernel/drivers/spi/spi-orion.c
@@ -127,37 +127,62 @@ static int orion_spi_baudrate_set(struct spi_device *spi, unsigned int speed)
 	tclk_hz = clk_get_rate(orion_spi->clk);
 
 	if (devdata->typ == ARMADA_SPI) {
-		unsigned int clk, spr, sppr, sppr2, err;
-		unsigned int best_spr, best_sppr, best_err;
-
-		best_err = speed;
-		best_spr = 0;
-		best_sppr = 0;
-
-		/* Iterate over the valid range looking for best fit */
-		for (sppr = 0; sppr < 8; sppr++) {
-			sppr2 = 0x1 << sppr;
-
-			spr = tclk_hz / sppr2;
-			spr = DIV_ROUND_UP(spr, speed);
-			if ((spr == 0) || (spr > 15))
-				continue;
-
-			clk = tclk_hz / (spr * sppr2);
-			err = speed - clk;
-
-			if (err < best_err) {
-				best_spr = spr;
-				best_sppr = sppr;
-				best_err = err;
-			}
-		}
+		/*
+		 * Given the core_clk (tclk_hz) and the target rate (speed) we
+		 * determine the best values for SPR (in [0 .. 15]) and SPPR (in
+		 * [0..7]) such that
+		 *
+		 * 	core_clk / (SPR * 2 ** SPPR)
+		 *
+		 * is as big as possible but not bigger than speed.
+		 */
 
-		if ((best_sppr == 0) && (best_spr == 0))
-			return -EINVAL;
+		/* best integer divider: */
+		unsigned divider = DIV_ROUND_UP(tclk_hz, speed);
+		unsigned spr, sppr;
+
+		if (divider < 16) {
+			/* This is the easy case, divider is less than 16 */
+			spr = divider;
+			sppr = 0;
+
+		} else {
+			unsigned two_pow_sppr;
+			/*
+			 * Find the highest bit set in divider. This and the
+			 * three next bits define SPR (apart from rounding).
+			 * SPPR is then the number of zero bits that must be
+			 * appended:
+			 */
+			sppr = fls(divider) - 4;
+
+			/*
+			 * As SPR only has 4 bits, we have to round divider up
+			 * to the next multiple of 2 ** sppr.
+			 */
+			two_pow_sppr = 1 << sppr;
+			divider = (divider + two_pow_sppr - 1) & -two_pow_sppr;
+
+			/*
+			 * recalculate sppr as rounding up divider might have
+			 * increased it enough to change the position of the
+			 * highest set bit. In this case the bit that now
+			 * doesn't make it into SPR is 0, so there is no need to
+			 * round again.
+			 */
+			sppr = fls(divider) - 4;
+			spr = divider >> sppr;
+
+			/*
+			 * Now do range checking. SPR is constructed to have a
+			 * width of 4 bits, so this is fine for sure. So we
+			 * still need to check for sppr to fit into 3 bits:
+			 */
+			if (sppr > 7)
+				return -EINVAL;
+		}
 
-		prescale = ((best_sppr & 0x6) << 5) |
-			((best_sppr & 0x1) << 4) | best_spr;
+		prescale = ((sppr & 0x6) << 5) | ((sppr & 0x1) << 4) | spr;
 	} else {
 		/*
 		 * the supported rates are: 4,6,8...30
diff --git a/kernel/drivers/spi/spi-pxa2xx.c b/kernel/drivers/spi/spi-pxa2xx.c
index b25dc71b0..3cac73e4c 100644
--- a/kernel/drivers/spi/spi-pxa2xx.c
+++ b/kernel/drivers/spi/spi-pxa2xx.c
@@ -111,7 +111,7 @@ static const struct lpss_config lpss_platforms[] = {
 		.reg_general = -1,
 		.reg_ssp = 0x20,
 		.reg_cs_ctrl = 0x24,
-		.reg_capabilities = 0xfc,
+		.reg_capabilities = -1,
 		.rx_threshold = 1,
 		.tx_threshold_lo = 32,
 		.tx_threshold_hi = 56,
@@ -548,7 +548,14 @@ static void reset_sccr1(struct driver_data *drv_data)
 	u32 sccr1_reg;
 
 	sccr1_reg = pxa2xx_spi_read(drv_data, SSCR1) & ~drv_data->int_cr1;
-	sccr1_reg &= ~SSCR1_RFT;
+	switch (drv_data->ssp_type) {
+	case QUARK_X1000_SSP:
+		sccr1_reg &= ~QUARK_X1000_SSCR1_RFT;
+		break;
+	default:
+		sccr1_reg &= ~SSCR1_RFT;
+		break;
+	}
 	sccr1_reg |= chip->threshold;
 	pxa2xx_spi_write(drv_data, SSCR1, sccr1_reg);
 }
diff --git a/kernel/drivers/spi/spi-rockchip.c b/kernel/drivers/spi/spi-rockchip.c
index 79a8bc4f6..035767c02 100644
--- a/kernel/drivers/spi/spi-rockchip.c
+++ b/kernel/drivers/spi/spi-rockchip.c
@@ -265,7 +265,10 @@ static inline u32 rx_max(struct rockchip_spi *rs)
 static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	u32 ser;
-	struct rockchip_spi *rs = spi_master_get_devdata(spi->master);
+	struct spi_master *master = spi->master;
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	pm_runtime_get_sync(rs->dev);
 
 	ser = readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & SER_MASK;
 
@@ -290,6 +293,8 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 		ser &= ~(1 << spi->chip_select);
 
 	writel_relaxed(ser, rs->regs + ROCKCHIP_SPI_SER);
+
+	pm_runtime_put_sync(rs->dev);
 }
 
 static int rockchip_spi_prepare_message(struct spi_master *master,
diff --git a/kernel/drivers/spi/spi-sh-msiof.c b/kernel/drivers/spi/spi-sh-msiof.c
index a7934ab00..d22de4c8c 100644
--- a/kernel/drivers/spi/spi-sh-msiof.c
+++ b/kernel/drivers/spi/spi-sh-msiof.c
@@ -263,6 +263,9 @@ static void sh_msiof_spi_set_clk_regs(struct sh_msiof_spi_priv *p,
 
 	for (k = 0; k < ARRAY_SIZE(sh_msiof_spi_div_table); k++) {
 		brps = DIV_ROUND_UP(div, sh_msiof_spi_div_table[k].div);
+		/* SCR_BRDV_DIV_1 is valid only if BRPS is x 1/1 or x 1/2 */
+		if (sh_msiof_spi_div_table[k].div == 1 && brps > 2)
+			continue;
 		if (brps <= 32) /* max of brdv is 32 */
 			break;
 	}
diff --git a/kernel/drivers/spi/spi-sun4i.c b/kernel/drivers/spi/spi-sun4i.c
index fbb0a4d74..39d7c7c70 100644
--- a/kernel/drivers/spi/spi-sun4i.c
+++ b/kernel/drivers/spi/spi-sun4i.c
@@ -170,13 +170,17 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 {
 	struct sun4i_spi *sspi = spi_master_get_devdata(master);
 	unsigned int mclk_rate, div, timeout;
+	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
 	u32 reg;
 
 	/* We don't support transfer larger than the FIFO */
 	if (tfr->len > SUN4I_FIFO_DEPTH)
-		return -EINVAL;
+		return -EMSGSIZE;
+
+	if (tfr->tx_buf && tfr->len >= SUN4I_FIFO_DEPTH)
+		return -EMSGSIZE;
 
 	reinit_completion(&sspi->done);
 	sspi->tx_buf = tfr->tx_buf;
@@ -269,8 +273,12 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 	sun4i_spi_write(sspi, SUN4I_BURST_CNT_REG, SUN4I_BURST_CNT(tfr->len));
 	sun4i_spi_write(sspi, SUN4I_XMIT_CNT_REG, SUN4I_XMIT_CNT(tx_len));
 
-	/* Fill the TX FIFO */
-	sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH);
+	/*
+	 * Fill the TX FIFO
+	 * Filling the FIFO fully causes timeout for some reason
+	 * at least on spi2 on A10s
+	 */
+	sun4i_spi_fill_fifo(sspi, SUN4I_FIFO_DEPTH - 1);
 
 	/* Enable the interrupts */
 	sun4i_spi_write(sspi, SUN4I_INT_CTL_REG, SUN4I_INT_CTL_TC);
@@ -279,9 +287,16 @@ static int sun4i_spi_transfer_one(struct spi_master *master,
 	reg = sun4i_spi_read(sspi, SUN4I_CTL_REG);
 	sun4i_spi_write(sspi, SUN4I_CTL_REG, reg | SUN4I_CTL_XCH);
 
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(1000));
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
 	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
diff --git a/kernel/drivers/spi/spi-sun6i.c b/kernel/drivers/spi/spi-sun6i.c
index ac48f5970..e77add01b 100644
--- a/kernel/drivers/spi/spi-sun6i.c
+++ b/kernel/drivers/spi/spi-sun6i.c
@@ -160,6 +160,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 {
 	struct sun6i_spi *sspi = spi_master_get_devdata(master);
 	unsigned int mclk_rate, div, timeout;
+	unsigned int start, end, tx_time;
 	unsigned int tx_len = 0;
 	int ret = 0;
 	u32 reg;
@@ -269,9 +270,16 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
 	sun6i_spi_write(sspi, SUN6I_TFR_CTL_REG, reg | SUN6I_TFR_CTL_XCH);
 
+	tx_time = max(tfr->len * 8 * 2 / (tfr->speed_hz / 1000), 100U);
+	start = jiffies;
 	timeout = wait_for_completion_timeout(&sspi->done,
-					      msecs_to_jiffies(1000));
+					      msecs_to_jiffies(tx_time));
+	end = jiffies;
 	if (!timeout) {
+		dev_warn(&master->dev,
+			 "%s: timeout transferring %u bytes@%iHz for %i(%i)ms",
+			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
+			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
 		goto out;
 	}
diff --git a/kernel/drivers/spi/spi-ti-qspi.c b/kernel/drivers/spi/spi-ti-qspi.c
index 64318fcfa..5044c6198 100644
--- a/kernel/drivers/spi/spi-ti-qspi.c
+++ b/kernel/drivers/spi/spi-ti-qspi.c
@@ -94,6 +94,7 @@ struct ti_qspi {
 #define QSPI_FLEN(n)			((n - 1) << 0)
 #define QSPI_WLEN_MAX_BITS		128
 #define QSPI_WLEN_MAX_BYTES		16
+#define QSPI_WLEN_MASK			QSPI_WLEN(QSPI_WLEN_MAX_BITS)
 
 /* STATUS REGISTER */
 #define BUSY				0x01
@@ -224,16 +225,16 @@ static inline int ti_qspi_poll_wc(struct ti_qspi *qspi)
 	return  -ETIMEDOUT;
 }
 
-static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t,
+			  int count)
 {
-	int wlen, count, xfer_len;
+	int wlen, xfer_len;
 	unsigned int cmd;
 	const u8 *txbuf;
 	u32 data;
 
 	txbuf = t->tx_buf;
 	cmd = qspi->cmd | QSPI_WR_SNGL;
-	count = t->len;
 	wlen = t->bits_per_word >> 3;	/* in bytes */
 	xfer_len = wlen;
 
@@ -293,9 +294,10 @@ static int qspi_write_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 	return 0;
 }
 
-static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t,
+			 int count)
 {
-	int wlen, count;
+	int wlen;
 	unsigned int cmd;
 	u8 *rxbuf;
 
@@ -312,7 +314,6 @@ static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 		cmd |= QSPI_RD_SNGL;
 		break;
 	}
-	count = t->len;
 	wlen = t->bits_per_word >> 3;	/* in bytes */
 
 	while (count) {
@@ -343,12 +344,13 @@ static int qspi_read_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 	return 0;
 }
 
-static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t)
+static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t,
+			     int count)
 {
 	int ret;
 
 	if (t->tx_buf) {
-		ret = qspi_write_msg(qspi, t);
+		ret = qspi_write_msg(qspi, t, count);
 		if (ret) {
 			dev_dbg(qspi->dev, "Error while writing\n");
 			return ret;
@@ -356,7 +358,7 @@ static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 	}
 
 	if (t->rx_buf) {
-		ret = qspi_read_msg(qspi, t);
+		ret = qspi_read_msg(qspi, t, count);
 		if (ret) {
 			dev_dbg(qspi->dev, "Error while reading\n");
 			return ret;
@@ -373,7 +375,8 @@ static int ti_qspi_start_transfer_one(struct spi_master *master,
 	struct spi_device *spi = m->spi;
 	struct spi_transfer *t;
 	int status = 0, ret;
-	int frame_length;
+	unsigned int frame_len_words, transfer_len_words;
+	int wlen;
 
 	/* setup device control reg */
 	qspi->dc = 0;
@@ -385,30 +388,38 @@ static int ti_qspi_start_transfer_one(struct spi_master *master,
 	if (spi->mode & SPI_CS_HIGH)
 		qspi->dc |= QSPI_CSPOL(spi->chip_select);
 
-	frame_length = (m->frame_length << 3) / spi->bits_per_word;
-
-	frame_length = clamp(frame_length, 0, QSPI_FRAME);
+	frame_len_words = 0;
+	list_for_each_entry(t, &m->transfers, transfer_list)
+		frame_len_words += t->len / (t->bits_per_word >> 3);
+	frame_len_words = min_t(unsigned int, frame_len_words, QSPI_FRAME);
 
 	/* setup command reg */
 	qspi->cmd = 0;
 	qspi->cmd |= QSPI_EN_CS(spi->chip_select);
-	qspi->cmd |= QSPI_FLEN(frame_length);
+	qspi->cmd |= QSPI_FLEN(frame_len_words);
 
 	ti_qspi_write(qspi, qspi->dc, QSPI_SPI_DC_REG);
 
 	mutex_lock(&qspi->list_lock);
 
 	list_for_each_entry(t, &m->transfers, transfer_list) {
-		qspi->cmd |= QSPI_WLEN(t->bits_per_word);
+		qspi->cmd = ((qspi->cmd & ~QSPI_WLEN_MASK) |
+			     QSPI_WLEN(t->bits_per_word));
+
+		wlen = t->bits_per_word >> 3;
+		transfer_len_words = min(t->len / wlen, frame_len_words);
 
-		ret = qspi_transfer_msg(qspi, t);
+		ret = qspi_transfer_msg(qspi, t, transfer_len_words * wlen);
 		if (ret) {
 			dev_dbg(qspi->dev, "transfer message failed\n");
 			mutex_unlock(&qspi->list_lock);
 			return -EINVAL;
 		}
 
-		m->actual_length += t->len;
+		m->actual_length += transfer_len_words * wlen;
+		frame_len_words -= transfer_len_words;
+		if (frame_len_words == 0)
+			break;
 	}
 
 	mutex_unlock(&qspi->list_lock);