aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/cpuidle
diff options
context:
space:
mode:
authorDaniel Lezcano <daniel.lezcano@linaro.org>2013-09-22 22:29:57 +0200
committerDaniel Lezcano <daniel.lezcano@linaro.org>2013-10-16 23:46:13 +0200
commit5ad945ea58f6cab7490dc149974ccb6514cc569a (patch)
tree806f516647e1e0676eb9b63e35e4e35e8fc93cde /drivers/cpuidle
parentMerge back earlier cpuidle material for v3.13. (diff)
downloadlinux-dev-5ad945ea58f6cab7490dc149974ccb6514cc569a.tar.xz
linux-dev-5ad945ea58f6cab7490dc149974ccb6514cc569a.zip
ARM: at91: cpuidle: Convert to platform driver
Using the platform driver model is a good way to separate the cpuidle specific code from the low level pm code. It allows to remove the dependency between these two components. The platform_device is located in the pm code and a 'set' function has been added to set the standby function from the AT91_SOC_START initialization function. Each SoC with a cpuidle driver will set the standby function in the platform_data field at init time. Then pm code will register the cpuidle platform device. The cpuidle driver will register the platform_driver and use the device's platform_data as a standby callback in the idle path. The at91_pm_enter function contains a { if then else } based on cpu_is_xx similar to what was in cpuidle. This is considered dangerous when adding a new SoC. Like the cpuidle driver, a standby ops is defined and assigned when the SoC init function specifies what is its standby function and reused in the at91_pm_enter's 'case' block. Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> Acked-by: Jean-Christophe PLAGNIOL-VILLARD <plagnioj@jcrosoft.com> Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Diffstat (limited to 'drivers/cpuidle')
0 files changed, 0 insertions, 0 deletions