[PATCH] mmc: core: fix card detection regression
Kristina Martšenko
kristina.martsenko at gmail.com
Tue Nov 4 16:22:41 PST 2014
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 at i2se.com>
Signed-off-by: Kristina Martšenko <kristina.martsenko at 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(-)
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))
--
2.0.2
More information about the linux-arm-kernel
mailing list