- 12 Jan, 2011 40 commits
-
-
Mark Brown authored
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 <skannan@codeaurora.org> Signed-off-by:
Mark Brown <broonie@opensource.wolfsonmicro.com> Signed-off-by:
Liam Girdwood <lrg@slimlogic.co.uk>
-
Mark Brown authored
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 authored
No point exposing functions that aren't used elsewhere to the global namespace and sparse warns about doing so. Signed-off-by:
-
Mark Brown authored
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:
-
Mark Brown authored
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 authored
Push all the callers of the chip set_voltage() operation out into a single function to facilitiate future refactoring. Signed-off-by:
-
Mark Brown authored
Signed-off-by:
-
Mark Brown authored
Signed-off-by:
-
Mark Brown authored
Since the MFD core for this device and the regulator drivers for these devices can be built modular we should also support modular build of the shared code for the regulator drivers, otherwise we try to link built in code against modular code with unfortunate results. Signed-off-by:
-
Yong Shen authored
add support for mc13892, tested on mx51 babbage board Signed-off-by:
Arnaud Patard <arnaud.patard@rtp-net.org> Signed-off-by:
Yong Shen <yong.shen@linaro.org> Acked-by:
Sascha Hauer <s.hauer@pengutronix.de> Acked-by:
Samuel Ortiz <sameo@linux.intel.com> Acked-by:
-
Yong Shen authored
move some common functions and micros of mc13783 regulaor driver to a seperate file, which makes it possible for mc13892 to share code. Signed-off-by:
-
Yong Shen authored
To make mc13783 and mc13892 share code, the register names should be changed to fit the new macro definitions in the comming patch. Signed-off-by:
-
Bengt Jonsson authored
The ab8500 regulator board configuration is updated and put in an array which can easily be used in the MFD board configuration. The regulator board configuration is also added to the MFD configuration in this patch. Signed-off-by:
Bengt Jonsson <bengt.g.jonsson@stericsson.com> Acked-by:
Linus Walleij <linus.walleij@stericsson.com> Acked-by:
-
Bengt Jonsson authored
This patch removes the macros for initializing the regulators. The purpose is to remove one layer of abstraction and make the code easier to read. Signed-off-by:
-
Bengt Jonsson authored
The verbose debug outputs register writes and reads that can be used to debug the driver. Signed-off-by:
-
Bengt Jonsson authored
Error handling is updated to catch NULL pointer errors. Signed-off-by:
-
Bengt Jonsson authored
The regulator enumeration is used for putting the regulator data in correct place in the info array. This should be matched in the board configuration. Variable names are updated to be more consistent, comments are corrected and macros have been edited to be consistent. Signed-off-by:
-
Bengt Jonsson authored
The AUX3 regulator voltage setting is changed in ab8500 v2 compared to ab8500 v1. This patch adds v2 support while keeping support for v1. Signed-off-by:
-
Bengt Jonsson authored
The find_regulator function was unused so it has been removed. The ab8500 pointer in the regulator info structure was unused and so it has also been removed. Signed-off-by:
-
Bengt Jonsson authored
For INTCORE and TVOUT regulators, the low power register bit is included in the mask so that enable will set the regulator in normal (high power) mode. ANAMIC1, ANAMIC2, DMIC regulator settings are swapped with each other so that the correct regulator gets enabled/disabled. ANA regulator register address is corrected. Signed-off-by:
-
Bengt Jonsson authored
The define for number of regulators is moved from ab8500-core to ab8500-regulator so that the regulator driver can be updated independently of ab8500-core. This also changes the platform configuration structure of ab8500-core so that it contains a pointer to the regulator_init_data array plus number of regulators instead of an fixed size array of pointers to regulator_init_data. Signed-off-by:
-
Cyril Chemparathy authored
TPS6524X provides three step-down converters and two general-purpose LDO voltage regulators. This device is interfaced using SPI. Signed-off-by:
Cyril Chemparathy <cyril@ti.com> Acked-by:
-
Mark Brown authored
Signed-off-by:
-
Mark Brown authored
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 authored
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:
-
Joe Perches authored
Align arguments. Signed-off-by:
Joe Perches <joe@perches.com> Acked-by:
-
Thomas Petazzoni authored
Extend the regulator_set_voltage() function to take into account the voltage requirements of all consumers of the regulator being changed, in order to set the voltage to the minimum voltage acceptable to all consumers. The existing behaviour was that the latest regulator_set_voltage() call would win over previous regulator_set_voltage() calls even if setting the voltage to a non-acceptable level from other consumers. Signed-off-by:
Thomas Petazzoni <t-petazzoni@ti.com> Cc: Liam Girdwood <lrg@slimlogic.co.uk> Cc: Mark Brown <broonie@opensource.wolfsonmicro.com> Cc: Kevin Hilman <khilman@deeprootsystems.com> Acked-by:
-
Joe Perches authored
On Tue, 2010-11-30 at 10:52 +0000, Mark Brown wrote: > On Mon, Nov 29, 2010 at 05:12:56PM -0800, Joe Perches wrote: > > Just to please broonie... > > Signed-off-by: Joe Perches <joe@perches.com> > As usual when fixing review issues please revise your original patch > rather than posting a fresh patch. Here's an earlier comment: On Thu, 2010-11-18 at 13:30 +0000, Mark Brown wrote: > This looks reasonable, please rebase on top of Daniel's patches and > submit it properly (with changelog and so on). Sometimes it's simpler for an upstream maintainer to do something like: git am -s <patch1.mbox> patch -p1 < patch2.mbox git commit --amend file instead of back and forthing. Signed-off-by: -
Mark Brown authored
They're not needed and sparse is verbosely upset about them. Signed-off-by:
-
Mark Brown authored
Currently the regulator API uses the constraints structure passed in to the core throughout the lifetime of the object. This means that it is not possible to mark the constraints as __initdata so if the kernel supports many boards the constraints for all of them are kept around throughout the lifetime of the system, consuming memory needlessly. By copying constraints that are actually used we allow the use of __initdata, saving memory when multiple boards are supported. This also means the constraints can be const. Signed-off-by:
-
Mark Brown authored
Signed-off-by:
-
Mark Brown authored
The version hasn't been updated since the regulator API was merged in 2.6.27 so just remove it - now we're in mainline the kernel version is much more useful. Signed-off-by:
-
Mark Brown authored
Don't use %s to format fixed static strings into log messages, it just makes searching for and reading the message in the kernel source needlessly hard. Signed-off-by:
-
Daniel Walker authored
The regulator framework uses a lot of printks with a specific formatting using __func__. This converts them to use pr_ calls with a central format string. Cc: bleong@codeaurora.org Signed-off-by:
Daniel Walker <dwalker@codeaurora.org> Acked-by:
-
Daniel Walker authored
This adds a pr_fmt line which uses the __func__ macro. I also convert the current pr_ lines to remove their __func__ usage. Cc: bleong@codeaurora.org Signed-off-by:
-
Mark Brown authored
Signed-off-by:
-
Bengt Jonsson authored
Supply regulators are disabled only when the last reference count is removed on the child regulator (the use count goes from 1 to 0). This patch changes the behaviour of enable so the supply regulator is enabled only when the use count of the child regulator goes from 0 to 1. Signed-off-by:
-
Mark Brown authored
Provide some basic trace facilities to the regulator API. We generate events on regulator enable, disable and voltage setting over the actual hardware operations (which are assumed to be the expensive ones which require interaction with the actual device). This is intended to facilitate debug of the performance and behaviour with consumers allowing unified traces to be generated including the regulator operations within the context of the other components of the system. For enable we log the explicit delay for the voltage ramp separately to the interaction with the hardware to highlight the time consumed in I/O. We should add a similar delay for voltage changes, though there the relatively small magnitude of the changes in the context of the I/O costs makes it much less critical for most regulators. Only hardware interactions are currently traced as the primary focus is on the performance and synchronisation of actual hardware interactions. Additional tracepoints for debugging of the logical operations can be added later if required. Signed-off-by:
-
Mark Brown authored
Change the interface used by set_voltage() to report the selected value to the regulator core in terms of a selector used by list_voltage(). This allows the regulator core to know the voltage that was chosen without having to do an explict get_voltage(), which would be much more expensive as it will generally access hardware. Signed-off-by:
-
Mattias Wallin authored
This patch add locks around regulator supply enable. Signed-off-by:
Mattias Wallin <mattias.wallin@stericsson.com> Acked-by:
-
