Hi,
On Mon, 2019-03-11 at 13:50 -0700, Sean Wang wrote:
Hi,
On Sun, Mar 10, 2019 at 8:49 PM Hsin-Hsiung Wang hsin-hsiung.wang@mediatek.com wrote:
From: Ran Bi ran.bi@mediatek.com
Alarm registers high byte was reserved for other functions. This add mask in alarm registers operation functions. This also fix error condition in interrupt handler.
Fixes: fc2979118f3f ("rtc: mediatek: Add MT6397 RTC driver")
add a Cc: stable@vger.kernel.org here to apply to all stable kernels for the critical fixup patch.
Signed-off-by: Ran Bi ran.bi@mediatek.com
drivers/rtc/rtc-mt6397.c | 47 +++++++++++++++++++++++++++++++++-------------- 1 file changed, 33 insertions(+), 14 deletions(-)
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c index e9a25ec..f85f1fc 100644 --- a/drivers/rtc/rtc-mt6397.c +++ b/drivers/rtc/rtc-mt6397.c @@ -55,6 +55,14 @@
#define RTC_AL_SEC 0x0018
+#define RTC_AL_SEC_MASK 0x003f +#define RTC_AL_MIN_MASK 0x003f +#define RTC_AL_HOU_MASK 0x001f +#define RTC_AL_DOM_MASK 0x001f +#define RTC_AL_DOW_MASK 0x0007 +#define RTC_AL_MTH_MASK 0x000f +#define RTC_AL_YEA_MASK 0x007f
#define RTC_PDN2 0x002e #define RTC_PDN2_PWRON_ALARM BIT(4)
@@ -111,7 +119,7 @@ static irqreturn_t mtk_rtc_irq_handler_thread(int irq, void *data) irqen = irqsta & ~RTC_IRQ_EN_AL; mutex_lock(&rtc->lock); if (regmap_write(rtc->regmap, rtc->addr_base + RTC_IRQ_EN,
irqen) < 0)
irqen) == 0) mtk_rtc_write_trigger(rtc); mutex_unlock(&rtc->lock);@@ -233,12 +241,12 @@ static int mtk_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm) alm->pending = !!(pdn2 & RTC_PDN2_PWRON_ALARM); mutex_unlock(&rtc->lock);
tm->tm_sec = data[RTC_OFFSET_SEC];tm->tm_min = data[RTC_OFFSET_MIN];tm->tm_hour = data[RTC_OFFSET_HOUR];tm->tm_mday = data[RTC_OFFSET_DOM];tm->tm_mon = data[RTC_OFFSET_MTH];tm->tm_year = data[RTC_OFFSET_YEAR];
tm->tm_sec = data[RTC_OFFSET_SEC] & RTC_AL_SEC_MASK;tm->tm_min = data[RTC_OFFSET_MIN] & RTC_AL_MIN_MASK;tm->tm_hour = data[RTC_OFFSET_HOUR] & RTC_AL_HOU_MASK;tm->tm_mday = data[RTC_OFFSET_DOM] & RTC_AL_DOM_MASK;tm->tm_mon = data[RTC_OFFSET_MTH] & RTC_AL_MTH_MASK;tm->tm_year = data[RTC_OFFSET_YEAR] & RTC_AL_YEA_MASK; tm->tm_year += RTC_MIN_YEAR_OFFSET; tm->tm_mon--;@@ -259,14 +267,25 @@ static int mtk_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm) tm->tm_year -= RTC_MIN_YEAR_OFFSET; tm->tm_mon++;
data[RTC_OFFSET_SEC] = tm->tm_sec;data[RTC_OFFSET_MIN] = tm->tm_min;data[RTC_OFFSET_HOUR] = tm->tm_hour;data[RTC_OFFSET_DOM] = tm->tm_mday;data[RTC_OFFSET_MTH] = tm->tm_mon;data[RTC_OFFSET_YEAR] = tm->tm_year;mutex_lock(&rtc->lock);
ret = regmap_bulk_read(rtc->regmap, rtc->addr_base + RTC_AL_SEC,data, RTC_OFFSET_COUNT);if (ret < 0)goto exit;Why did we need an additional regmap_bulk_read here? I would suppose data[RTC_OFFSET_*] & ~(RTC_AL_*_MASK) is always equal to 0.
In bootloader, RTC init part need to operate these RTC_AL_* registers high byte for RTC operating mode settings and data storage, while RTC_AL_* low byte was used as alarm register here. So we need an additional regmap_bulk_read here to keep the RTC settings correct.
It might be another fixup since change is not being mentioned in the git message.
data[RTC_OFFSET_SEC] = ((data[RTC_OFFSET_SEC] & ~(RTC_AL_SEC_MASK)) |(tm->tm_sec & RTC_AL_SEC_MASK));data[RTC_OFFSET_MIN] = ((data[RTC_OFFSET_MIN] & ~(RTC_AL_MIN_MASK)) |(tm->tm_min & RTC_AL_MIN_MASK));data[RTC_OFFSET_HOUR] = ((data[RTC_OFFSET_HOUR] & ~(RTC_AL_HOU_MASK)) |(tm->tm_hour & RTC_AL_HOU_MASK));data[RTC_OFFSET_DOM] = ((data[RTC_OFFSET_DOM] & ~(RTC_AL_DOM_MASK)) |(tm->tm_mday & RTC_AL_DOM_MASK));data[RTC_OFFSET_MTH] = ((data[RTC_OFFSET_MTH] & ~(RTC_AL_MTH_MASK)) |(tm->tm_mon & RTC_AL_MTH_MASK));data[RTC_OFFSET_YEAR] = ((data[RTC_OFFSET_YEAR] & ~(RTC_AL_YEA_MASK)) |(tm->tm_year & RTC_AL_YEA_MASK));if (alm->enabled) { ret = regmap_bulk_write(rtc->regmap, rtc->addr_base + RTC_AL_SEC,-- 1.9.1
Linux-mediatek mailing list Linux-mediatek@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-mediatek