| Message ID | 20191204152749.12652-1-linus.walleij@linaro.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | mmc: spi: Toggle SPI polarity, do not hardcode it | expand |
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>
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 >
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
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
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,
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(-)