[PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it

[PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it

[Linus Walleij]

The code in mmc_spi_initsequence() tries to send a burst with
high chipselect and for this reason hardcodes the device into
SPI_CS_HIGH.

This is not good because the SPI_CS_HIGH flag indicates
logical "asserted" CS not always the physical level. In
some cases the signal is inverted in the GPIO library and
in that case SPI_CS_HIGH is already set, and enforcing
SPI_CS_HIGH again will actually drive it low.

Instead of hard-coding this, toggle the polarity so if the
default is LOW it goes high to assert chipselect but if it
is already high then toggle it low instead.

Cc: Phil Elwell <phil@raspberrypi.org>
Reported-by: Mark Brown <broonie@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/mmc/host/mmc_spi.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 74c6cfbf9172..1f02f54f09c0 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -1134,17 +1134,22 @@ static void mmc_spi_initsequence(struct mmc_spi_host *host)
 	 * SPI protocol.  Another is that when chipselect is released while
 	 * the card returns BUSY status, the clock must issue several cycles
 	 * with chipselect high before the card will stop driving its output.
+	 *
+	 * SPI_CS_HIGH means "asserted" here. In some cases like when using
+	 * GPIOs for chip select, SPI_CS_HIGH is set but this will be logically
+	 * inverted by gpiolib, so if we want to ascertain to drive it high
+	 * we should toggle the default with an XOR as we do here.
 	 */
-	host->spi->mode |= SPI_CS_HIGH;
+	host->spi->mode ^= SPI_CS_HIGH;
 	if (spi_setup(host->spi) != 0) {
 		/* Just warn; most cards work without it. */
 		dev_warn(&host->spi->dev,
 				"can't change chip-select polarity\n");
-		host->spi->mode &= ~SPI_CS_HIGH;
+		host->spi->mode ^= SPI_CS_HIGH;
 	} else {
 		mmc_spi_readbytes(host, 18);
 
-		host->spi->mode &= ~SPI_CS_HIGH;
+		host->spi->mode ^= SPI_CS_HIGH;
 		if (spi_setup(host->spi) != 0) {
 			/* Wot, we can't get the same setup we had before? */
 			dev_err(&host->spi->dev,
-- 
2.23.0

Re: [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it

[Mark Brown]

[-- Attachment #1: Type: text/plain, Size: 252 bytes --]

On Wed, Dec 04, 2019 at 04:27:49PM +0100, Linus Walleij wrote:
> The code in mmc_spi_initsequence() tries to send a burst with
> high chipselect and for this reason hardcodes the device into
> SPI_CS_HIGH.

Reviewed-by: Mark Brown <broonie@kernel.org>

[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

Re: [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it

[Ulf Hansson]

On Wed, 4 Dec 2019 at 16:29, Linus Walleij <linus.walleij@linaro.org> wrote:
>
> The code in mmc_spi_initsequence() tries to send a burst with
> high chipselect and for this reason hardcodes the device into
> SPI_CS_HIGH.
>
> This is not good because the SPI_CS_HIGH flag indicates
> logical "asserted" CS not always the physical level. In
> some cases the signal is inverted in the GPIO library and
> in that case SPI_CS_HIGH is already set, and enforcing
> SPI_CS_HIGH again will actually drive it low.
>
> Instead of hard-coding this, toggle the polarity so if the
> default is LOW it goes high to assert chipselect but if it
> is already high then toggle it low instead.
>
> Cc: Phil Elwell <phil@raspberrypi.org>
> Reported-by: Mark Brown <broonie@kernel.org>
> Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

Seems like we should add a stable tag, right?

In any case, I have applied this for next to let it cook for a while, thanks!

Kind regards
Uffe



> ---
>  drivers/mmc/host/mmc_spi.c | 11 ++++++++---
>  1 file changed, 8 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
> index 74c6cfbf9172..1f02f54f09c0 100644
> --- a/drivers/mmc/host/mmc_spi.c
> +++ b/drivers/mmc/host/mmc_spi.c
> @@ -1134,17 +1134,22 @@ static void mmc_spi_initsequence(struct mmc_spi_host *host)
>          * SPI protocol.  Another is that when chipselect is released while
>          * the card returns BUSY status, the clock must issue several cycles
>          * with chipselect high before the card will stop driving its output.
> +        *
> +        * SPI_CS_HIGH means "asserted" here. In some cases like when using
> +        * GPIOs for chip select, SPI_CS_HIGH is set but this will be logically
> +        * inverted by gpiolib, so if we want to ascertain to drive it high
> +        * we should toggle the default with an XOR as we do here.
>          */
> -       host->spi->mode |= SPI_CS_HIGH;
> +       host->spi->mode ^= SPI_CS_HIGH;
>         if (spi_setup(host->spi) != 0) {
>                 /* Just warn; most cards work without it. */
>                 dev_warn(&host->spi->dev,
>                                 "can't change chip-select polarity\n");
> -               host->spi->mode &= ~SPI_CS_HIGH;
> +               host->spi->mode ^= SPI_CS_HIGH;
>         } else {
>                 mmc_spi_readbytes(host, 18);
>
> -               host->spi->mode &= ~SPI_CS_HIGH;
> +               host->spi->mode ^= SPI_CS_HIGH;
>                 if (spi_setup(host->spi) != 0) {
>                         /* Wot, we can't get the same setup we had before? */
>                         dev_err(&host->spi->dev,
> --
> 2.23.0
>

Re: [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it

[Linus Walleij]

On Tue, Dec 10, 2019 at 10:52 AM Ulf Hansson <ulf.hansson@linaro.org> wrote:
> On Wed, 4 Dec 2019 at 16:29, Linus Walleij <linus.walleij@linaro.org> wrote:
> >
> > The code in mmc_spi_initsequence() tries to send a burst with
> > high chipselect and for this reason hardcodes the device into
> > SPI_CS_HIGH.
> >
> > This is not good because the SPI_CS_HIGH flag indicates
> > logical "asserted" CS not always the physical level. In
> > some cases the signal is inverted in the GPIO library and
> > in that case SPI_CS_HIGH is already set, and enforcing
> > SPI_CS_HIGH again will actually drive it low.
> >
> > Instead of hard-coding this, toggle the polarity so if the
> > default is LOW it goes high to assert chipselect but if it
> > is already high then toggle it low instead.
> >
> > Cc: Phil Elwell <phil@raspberrypi.org>
> > Reported-by: Mark Brown <broonie@kernel.org>
> > Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
>
> Seems like we should add a stable tag, right?

Yeah I agree.

> In any case, I have applied this for next to let it cook for a while, thanks!

Good, thanks!

Yours,
Linus Walleij

Re: [PATCH] mmc: spi: Toggle SPI polarity, do not hardcode it

[Ulf Hansson]

On Wed, 11 Dec 2019 at 00:11, Linus Walleij <linus.walleij@linaro.org> wrote:
>
> On Tue, Dec 10, 2019 at 10:52 AM Ulf Hansson <ulf.hansson@linaro.org> wrote:
> > On Wed, 4 Dec 2019 at 16:29, Linus Walleij <linus.walleij@linaro.org> wrote:
> > >
> > > The code in mmc_spi_initsequence() tries to send a burst with
> > > high chipselect and for this reason hardcodes the device into
> > > SPI_CS_HIGH.
> > >
> > > This is not good because the SPI_CS_HIGH flag indicates
> > > logical "asserted" CS not always the physical level. In
> > > some cases the signal is inverted in the GPIO library and
> > > in that case SPI_CS_HIGH is already set, and enforcing
> > > SPI_CS_HIGH again will actually drive it low.
> > >
> > > Instead of hard-coding this, toggle the polarity so if the
> > > default is LOW it goes high to assert chipselect but if it
> > > is already high then toggle it low instead.
> > >
> > > Cc: Phil Elwell <phil@raspberrypi.org>
> > > Reported-by: Mark Brown <broonie@kernel.org>
> > > Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
> >
> > Seems like we should add a stable tag, right?
>
> Yeah I agree.

Alright. I have amended the patch to add the tag.

Kind regards
Uffe