On Tue, Feb 08, 2022 at 10:44:41AM +0100, Bartosz Golaszewski wrote: > On Sat, Feb 5, 2022 at 12:33 AM Damien Le Moal > <damien.lemoal@xxxxxxxxxxxxxxxxxx> wrote: > > > > On 2/4/22 22:02, Niklas Cassel wrote: > > > From: Niklas Cassel <niklas.cassel@xxxxxxx> > > > > > > Setting the output of a GPIO to 1 using gpiod_set_value(), followed by > > > reading the same GPIO using gpiod_get_value(), will currently yield an > > > incorrect result. > > > > > > This is because the SiFive GPIO device stores the output values in reg_set, > > > not reg_dat. > > > > > > Supply the flag BGPIOF_READ_OUTPUT_REG_SET to bgpio_init() so that the > > > generic driver reads the correct register. > > > > > > Signed-off-by: Niklas Cassel <niklas.cassel@xxxxxxx> > > > > This probably needs a Fixes tag. I have not checked which patch though. > > > > I added the tag and queued this for fixes, thanks! Hello Bart, Thank you for queueing and amending the Fixes tag! Kind regards, Niklas > > Bart > > > > --- > > > The patch was tested on a canaan,k210 board (canaan,k210-gpiohs compatible > > > string). It would be nice with a Tested-by from someone with a SiFive board. > > > > > > However, the u-boot driver for this device already behaves exactly the same > > > as this driver does after my patch, for all platforms using the driver. > > > > > > drivers/gpio/gpio-sifive.c | 2 +- > > > 1 file changed, 1 insertion(+), 1 deletion(-) > > > > > > diff --git a/drivers/gpio/gpio-sifive.c b/drivers/gpio/gpio-sifive.c > > > index 403f9e833d6a..7d82388b4ab7 100644 > > > --- a/drivers/gpio/gpio-sifive.c > > > +++ b/drivers/gpio/gpio-sifive.c > > > @@ -223,7 +223,7 @@ static int sifive_gpio_probe(struct platform_device *pdev) > > > NULL, > > > chip->base + SIFIVE_GPIO_OUTPUT_EN, > > > chip->base + SIFIVE_GPIO_INPUT_EN, > > > - 0); > > > + BGPIOF_READ_OUTPUT_REG_SET); > > > if (ret) { > > > dev_err(dev, "unable to init generic GPIO\n"); > > > return ret; > > > > > > -- > > Damien Le Moal > > Western Digital Research