linux.git/drivers/regulator/core.c, branch v2.6.38

regulator: Add initial per-regulator debugfs support

2011-01-12T14:33:05+00:00

We only expose the use and open counts to userspace, providing a tiny
bit of insight into what the API is up to.

Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Make regulator_has_full_constraints a bool

2011-01-12T14:33:05+00:00

It's a boolean value so use the type.

Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Clean up logging a bit

2011-01-12T14:33:05+00:00

The recent introduction of standard regulator API logging macros means
that all our log messages have at least the function name in them and
logging that the constraints are for the regulator API is probably a
bit much.

Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Optimise out noop voltage changes

2011-01-12T14:33:05+00:00

If a consumer sets the same voltage range as is currently configured
for that consumer there's no need to run through setting the voltage
again. This pattern may occur with some CPUfreq implementations where
the same voltage range is used for multiple frequencies.

Reported-by: Saravana Kannan 
Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Add API to re-apply voltage to hardware

2011-01-12T14:33:05+00:00

When cooperating with an external control source the regulator setup
may be changed underneath the API. Currently consumers can just redo
the regulator_set_voltage() to restore a previously set configuration
but provide an explicit API for doing this as optimsations in the
regulator_set_voltage() implementation will shortly prevent that.

Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Only notify voltage changes when they succeed

2011-01-12T14:33:05+00:00

Currently we notify a voltage change whenever we exit set_voltage(),
even if the change failed for some reason (eg, a constraints issue).
This shouldn't cause any substantial ill effects but is wasteful as
listeners get notified on noops. Fix this by moving the notification
into _do_set_voltage() and only notifying if we don't return an error.

Reported-by: Saravana Kannan 
Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Provide a selector based set_voltage_sel() operation

2011-01-12T14:33:04+00:00

Many regulator drivers implement voltage setting by looping through a
table of possible values, normally because the set of available voltages
can't be mapped onto selectors with simple calcuation. Factor out these
loops by providing a variant of set_voltage() which takes a selector rather
than a voltage range as an argument and implementing a loop through the
available selectors in the core.

This is not going to be suitable for use with all devices as when the
regulator voltage can be mapped onto selector values with a simple
calculation the linear scan through the available values will be more
expensive than just doing the calculation, especially for regulators
that provide fine grained voltage control.

Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Factor out voltage set operation into a separate function

2011-01-12T14:33:04+00:00

Push all the callers of the chip set_voltage() operation out into a single
function to facilitiate future refactoring.

Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Allow drivers to report voltages as selectors

2011-01-12T14:33:01+00:00

Since drivers already have to provide an API for translating selectors
into voltages they may as well just report the selector values directly
to the core API rather than implement the lookup themselves. The old
interface is left in place for now, but may be removed in future.

Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood

regulator: Use _regulator_get_voltage() consistently

2011-01-12T14:33:01+00:00

Rather than referencing the get_voltage() operation directly in the
ops struct use the internal _regulator_get_voltage() API call to do
so, facilitating refactoring.

Signed-off-by: Mark Brown 
Signed-off-by: Liam Girdwood