On Tue, Dec 10, 2019 at 10:52 AM Ulf Hansson <ulf.hansson@xxxxxxxxxx> wrote: > On Wed, 4 Dec 2019 at 16:29, Linus Walleij <linus.walleij@xxxxxxxxxx> 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@xxxxxxxxxxxxxxx> > > Reported-by: Mark Brown <broonie@xxxxxxxxxx> > > Signed-off-by: Linus Walleij <linus.walleij@xxxxxxxxxx> > > 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