On 27 August 2014 13:00, Linus Walleij <linus.walleij@xxxxxxxxxx> wrote:
> Currently the MMCI driver will only handle GPIO descriptors
> implicitly through the device tree probe glue in mmc_of_init(),
> but devices instatiated other ways such as through board files
> and passing descriptors using the GPIO descriptor table will
> not be able to exploit descriptors.
>
> Augment the driver to look for a GPIO descriptor if device
> tree is not used for the device, and if that doesn't work,
> fall back to platform data GPIO assignment using the old
> API. The end goal is to get rid of the platform data integer
> GPIO assingments from the kernel.
>
> This enable the MMCI-embedding platforms to be converted to
> GPIO descritor tables.
>
> Cc: Alexandre Courbot <gnurou@xxxxxxxxx>
> Cc: Russell King <linux@xxxxxxxxxxxxxxxx>
> Signed-off-by: Linus Walleij <linus.walleij@xxxxxxxxxx>
> ---
> drivers/mmc/host/mmci.c | 53 +++++++++++++++++++++++++++++++++++++++----------
> 1 file changed, 43 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
> index e4d470704150..37a6542f056c 100644
> --- a/drivers/mmc/host/mmci.c
> +++ b/drivers/mmc/host/mmci.c
> @@ -1658,16 +1658,49 @@ static int mmci_probe(struct amba_device *dev,
> writel(0, host->base + MMCIMASK1);
> writel(0xfff, host->base + MMCICLEAR);
>
> - /* If DT, cd/wp gpios must be supplied through it. */
> - if (!np && gpio_is_valid(plat->gpio_cd)) {
> - ret = mmc_gpio_request_cd(mmc, plat->gpio_cd, 0);
> - if (ret)
> - goto clk_disable;
> - }
> - if (!np && gpio_is_valid(plat->gpio_wp)) {
> - ret = mmc_gpio_request_ro(mmc, plat->gpio_wp);
> - if (ret)
> - goto clk_disable;
> + /*
> + * If:
> + * - not using DT but using a descriptor table, or
> + * - using a table of descriptors ALONGSIDE DT, or
> + * look up these descriptors named "cd" and "wp" right here, fail
> + * silently of these do not exist and proceed to try platform data
> + */
> + if (!np) {
> + ret = mmc_gpiod_request_cd(mmc, "cd", 0, false, 0);
> + if (!ret)
> + dev_info(mmc_dev(mmc), "got CD GPIO (table)\n");
> + else {
> + if (ret == -EPROBE_DEFER)
> + goto clk_disable;
> + else if (gpio_is_valid(plat->gpio_cd)) {
> + ret = mmc_gpio_request_cd(mmc, plat->gpio_cd, 0);
> + if (ret)
> + goto clk_disable;
> + else
> + dev_info(mmc_dev(mmc), "got CD GPIO (pdata)\n");
> + } else {
> + dev_dbg(mmc_dev(mmc),
> + "no CD GPIO in DT, table or pdata\n");
> + }
> + }
> +
> + ret = mmc_gpiod_request_ro(mmc, "wp", 0, false, 0);
> + if (!ret)
> + dev_info(mmc_dev(mmc), "got WP GPIO (table)\n");
> + else {
> + if (ret == -EPROBE_DEFER)
> + goto clk_disable;
> + else if (gpio_is_valid(plat->gpio_wp)) {
> + ret = mmc_gpio_request_ro(mmc, plat->gpio_wp);
> + if (ret)
> + goto clk_disable;
> + else
> + dev_info(mmc_dev(mmc), "got WP GPIO (pdata)\n");
> + } else {
> + dev_dbg(mmc_dev(mmc),
> + "no WP GPIO in DT, table or pdata\n");
> + }
Just a nitpick; and unless it's important to you, could you remove all
the dev_info|dbg - we didn't need them before, why now?
Kind regards
Uffe
> + }
> }
>
> ret = devm_request_irq(&dev->dev, dev->irq[0], mmci_irq, IRQF_SHARED,
> --
> 1.9.3
>
--
To unsubscribe from this list: send the line "unsubscribe linux-mmc" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
