| Message ID | 1415146961-25993-1-git-send-email-kristina.martsenko@gmail.com |
|---|---|
| State | New |
| Headers | show |
Hi Kristina, On Tue, Nov 4, 2014 at 10:22 PM, Kristina Martšenko <kristina.martsenko@gmail.com> wrote: > Since commit 89168b489915 ("mmc: core: restore detect line inversion > semantics"), the SD card on i.MX28 (and possibly other) devices isn't > detected and booting stops at: > > [ 4.120617] Waiting for root device /dev/mmcblk0p3... > > This is caused by the MMC_CAP2_CD_ACTIVE_HIGH flag being set incorrectly > when the host controller doesn't use a GPIO for card detection (but > instead uses a dedicated pin). In this case mmc_gpiod_request_cd() will > return before assigning to the gpio_invert variable, leaving the > variable uninitialized. The variable then gets used to set the flag. > This patch fixes the issue by making sure gpio_invert is set to false > when a GPIO isn't used. After this patch, i.MX28 boots fine. > > The MMC_CAP2_RO_ACTIVE_HIGH (write protect) flag is also set incorrectly > for the exact same reason (it uses the same uninitialized variable), so > this patch fixes that too. > > Fixes: 89168b489915 ("mmc: core: restore detect line inversion semantics") > Reported-by: Stefan Wahren <stefan.wahren@i2se.com> > Signed-off-by: Kristina Martšenko <kristina.martsenko@gmail.com> This fixes mx28 card detection, thanks! Tested-by: Fabio Estevam <fabio.estevam@freescale.com>
On 5 November 2014 01:22, Kristina Martšenko <kristina.martsenko@gmail.com> wrote: > Since commit 89168b489915 ("mmc: core: restore detect line inversion > semantics"), the SD card on i.MX28 (and possibly other) devices isn't > detected and booting stops at: > > [ 4.120617] Waiting for root device /dev/mmcblk0p3... > > This is caused by the MMC_CAP2_CD_ACTIVE_HIGH flag being set incorrectly > when the host controller doesn't use a GPIO for card detection (but > instead uses a dedicated pin). In this case mmc_gpiod_request_cd() will > return before assigning to the gpio_invert variable, leaving the > variable uninitialized. The variable then gets used to set the flag. > This patch fixes the issue by making sure gpio_invert is set to false > when a GPIO isn't used. After this patch, i.MX28 boots fine. > > The MMC_CAP2_RO_ACTIVE_HIGH (write protect) flag is also set incorrectly > for the exact same reason (it uses the same uninitialized variable), so > this patch fixes that too. > > Fixes: 89168b489915 ("mmc: core: restore detect line inversion semantics") > Reported-by: Stefan Wahren <stefan.wahren@i2se.com> > Signed-off-by: Kristina Martšenko <kristina.martsenko@gmail.com> Thanks! Applied for fixes. Kind regards Uffe
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index 03c53b72a2d6..270d58a4c43d 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -311,7 +311,8 @@ int mmc_of_parse(struct mmc_host *host) struct device_node *np; u32 bus_width; int len, ret; - bool cap_invert, gpio_invert; + bool cd_cap_invert, cd_gpio_invert = false; + bool ro_cap_invert, ro_gpio_invert = false; if (!host->parent || !host->parent->of_node) return 0; @@ -359,16 +360,13 @@ int mmc_of_parse(struct mmc_host *host) if (of_find_property(np, "non-removable", &len)) { host->caps |= MMC_CAP_NONREMOVABLE; } else { - if (of_property_read_bool(np, "cd-inverted")) - cap_invert = true; - else - cap_invert = false; + cd_cap_invert = of_property_read_bool(np, "cd-inverted"); if (of_find_property(np, "broken-cd", &len)) host->caps |= MMC_CAP_NEEDS_POLL; ret = mmc_gpiod_request_cd(host, "cd", 0, true, - 0, &gpio_invert); + 0, &cd_gpio_invert); if (ret) { if (ret == -EPROBE_DEFER) return ret; @@ -391,17 +389,14 @@ int mmc_of_parse(struct mmc_host *host) * both inverted, the end result is that the CD line is * not inverted. */ - if (cap_invert ^ gpio_invert) + if (cd_cap_invert ^ cd_gpio_invert) host->caps2 |= MMC_CAP2_CD_ACTIVE_HIGH; } /* Parse Write Protection */ - if (of_property_read_bool(np, "wp-inverted")) - cap_invert = true; - else - cap_invert = false; + ro_cap_invert = of_property_read_bool(np, "wp-inverted"); - ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &gpio_invert); + ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &ro_gpio_invert); if (ret) { if (ret == -EPROBE_DEFER) goto out; @@ -414,7 +409,7 @@ int mmc_of_parse(struct mmc_host *host) dev_info(host->parent, "Got WP GPIO\n"); /* See the comment on CD inversion above */ - if (cap_invert ^ gpio_invert) + if (ro_cap_invert ^ ro_gpio_invert) host->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH; if (of_find_property(np, "cap-sd-highspeed", &len))
Since commit 89168b489915 ("mmc: core: restore detect line inversion semantics"), the SD card on i.MX28 (and possibly other) devices isn't detected and booting stops at: [ 4.120617] Waiting for root device /dev/mmcblk0p3... This is caused by the MMC_CAP2_CD_ACTIVE_HIGH flag being set incorrectly when the host controller doesn't use a GPIO for card detection (but instead uses a dedicated pin). In this case mmc_gpiod_request_cd() will return before assigning to the gpio_invert variable, leaving the variable uninitialized. The variable then gets used to set the flag. This patch fixes the issue by making sure gpio_invert is set to false when a GPIO isn't used. After this patch, i.MX28 boots fine. The MMC_CAP2_RO_ACTIVE_HIGH (write protect) flag is also set incorrectly for the exact same reason (it uses the same uninitialized variable), so this patch fixes that too. Fixes: 89168b489915 ("mmc: core: restore detect line inversion semantics") Reported-by: Stefan Wahren <stefan.wahren@i2se.com> Signed-off-by: Kristina Martšenko <kristina.martsenko@gmail.com> --- This is a different version of the previous patch [1], so I haven't included the Reviewed-by and Tested-by's. Would be nice if someone could test this version as well. [1] http://thread.gmane.org/gmane.linux.kernel.gpio/4609/focus=29576 drivers/mmc/core/host.c | 21 ++++++++------------- 1 file changed, 8 insertions(+), 13 deletions(-)