[PATCH] regulator: wm831x-ldo - fix the logic to set REGULATOR_MODE_IDLE and REGULATOR_MODE_STANDBY modes

[PATCH] regulator: wm831x-ldo - fix the logic to set REGULATOR_MODE_IDLE and REGULATOR_MODE_STANDBY modes

[Axel Lin]

Problem description in current implementation:
When setting REGULATOR_MODE_IDLE mode, current implementation set
WM831X_LDO1_LP_MODE bit of ctrl_reg (which is wrong, it should clear the bit).
But due to a missing break statement for case REGULATOR_MODE_IDLE, the code
fall through to case REGULATOR_MODE_STANDBY and then clear
WM831X_LDO1_LP_MODE bit. So it still looks OK when checking the status
by wm831x_gp_ldo_get_mode().

When setting REGULATOR_MODE_STANDBY mode, it just does not work.
wm831x_gp_ldo_get_mode() will still return REGULATOR_MODE_IDLE because
the accordingly WM831X_LDO1_LP_MODE bit is clear.

Correct behavior should be:
Clear WM831X_LDO1_LP_MODE bit of ctrl_reg for REGULATOR_MODE_IDLE mode.
Set WM831X_LDO1_LP_MODE bit of ctrl_reg for REGULATOR_MODE_STANDBY mode.

Signed-off-by: Axel Lin <axel.lin@gmail.com>
---
 drivers/regulator/wm831x-ldo.c |    7 ++++---
 1 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c
index e686cdb..9edf8f6 100644
--- a/drivers/regulator/wm831x-ldo.c
+++ b/drivers/regulator/wm831x-ldo.c
@@ -215,8 +215,7 @@ static int wm831x_gp_ldo_set_mode(struct regulator_dev *rdev,
 
 	case REGULATOR_MODE_IDLE:
 		ret = wm831x_set_bits(wm831x, ctrl_reg,
-				      WM831X_LDO1_LP_MODE,
-				      WM831X_LDO1_LP_MODE);
+				      WM831X_LDO1_LP_MODE, 0);
 		if (ret < 0)
 			return ret;
 
@@ -225,10 +224,12 @@ static int wm831x_gp_ldo_set_mode(struct regulator_dev *rdev,
 				      WM831X_LDO1_ON_MODE);
 		if (ret < 0)
 			return ret;
+		break;
 
 	case REGULATOR_MODE_STANDBY:
 		ret = wm831x_set_bits(wm831x, ctrl_reg,
-				      WM831X_LDO1_LP_MODE, 0);
+				      WM831X_LDO1_LP_MODE,
+				      WM831X_LDO1_LP_MODE);
 		if (ret < 0)
 			return ret;
 
-- 
1.7.2

Re: [PATCH] regulator: wm831x-ldo - fix the logic to set REGULATOR_MODE_IDLE and REGULATOR_MODE_STANDBY modes

[Mark Brown]

On Mon, Sep 06, 2010 at 04:48:13PM +0800, Axel Lin wrote:
> Problem description in current implementation:
> When setting REGULATOR_MODE_IDLE mode, current implementation set
> WM831X_LDO1_LP_MODE bit of ctrl_reg (which is wrong, it should clear the bit).

Again, it would be really helpful if you could make your analysis
clearer - at no point do you explain why you think the chip settings
that result from your changes are correct.  Your message explains that
the status readback differs from the settings but it doesn't explain how
you know which bit of code is correct.  This means that your messages
set off alarm bells as it looks like you're just guessing about what
needs to be done to the chip.

In this case your patch appears to be OK so:

Acked-by: Mark Brown <broonie@opensource.wolfsonmicro.com>