diff options
author | Philip Avinash <avinashphilip@ti.com> | 2013-08-18 10:49:03 +0530 |
---|---|---|
committer | Sekhar Nori <nsekhar@ti.com> | 2013-09-25 04:16:37 +0530 |
commit | f1a4c52ff5913378b7baf05ac71f10282b341cf7 (patch) | |
tree | ca851636c3c3ea8bd510d70f4657631fff24260d /arch/arm/Kconfig | |
parent | 834acb2af6e8255a026c754fac3d1bc3f32b0c1a (diff) |
ARM: davinci: gpio: use gpiolib API instead of inline functions
Remove NEED_MACH_GPIO_H config select option for ARCH_DAVINCI
to start using gpiolib interface for davinci platforms. This makes
it easier to use the gpio driver on other platforms as it breaks
dependency on mach-davinci.
Latencies for gpio_get/set APIs will increase. On measurement,
latency was found to have increased by 18 microsecond with
gpiolib API as compared to inline APIs.
Measurement was done on DA850 EVM for gpio_get_value() API by
taking the printk timing across the call with interrupts disabled.
inline gpio API with interrupt disabled
[ 29.734337] before gpio_get
[ 29.736847] after gpio_get
Time difference 0.00251
gpio library with interrupt disabled
[ 272.876763] before gpio_get
[ 272.879291] after gpio_get
Time difference 0.002528
Latency increased by (0.002528 - 0.00251) = 18 microsecond.
While at it, remove GPIO_TYPE_DAVINCI enum definition as
gpio-davinci.c is converted to Linux device driver model.
Signed-off-by: Philip Avinash <avinashphilip@ti.com>
Signed-off-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
[nsekhar@ti.com: minor edits to commit message]
Signed-off-by: Sekhar Nori <nsekhar@ti.com>
Diffstat (limited to 'arch/arm/Kconfig')
-rw-r--r-- | arch/arm/Kconfig | 1 |
1 files changed, 0 insertions, 1 deletions
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 3f7714d8d2d..ad376709542 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -847,7 +847,6 @@ config ARCH_DAVINCI select GENERIC_CLOCKEVENTS select GENERIC_IRQ_CHIP select HAVE_IDE - select NEED_MACH_GPIO_H select TI_PRIV_EDMA select USE_OF select ZONE_DMA |