On 6/14/2013 3:05 PM, Philip Avinash wrote: > Remove NEED_MACH_GPIO_H config select option for ARCH_DAVINCI to start > use gpiolib interface for davinci platforms. However with this software > latencies for gpio_get/set APIs will affect. Latency has increased by 18 > microsecond with gpiolib API as compared with inline API's. > > Software latency is calculated on da850 EVM for gpio_get_value API by > taking the printk timing for API execution with interrupts disabled. > Experiment has done for inline and gpiolib API interface. > > 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. > > Also being here > - Moved following definitions from mach folder to include directory > struct davinci_gpio_controller > Macro GPIO(x) > inline function __gpio_mask
> - Removed GPIO_TYPE_DAVINCI enum definition as GPIO Davinci is converted > to Linux device driver model. This is bit out-of-place here. Why not do it along with removal of its last usage in <soc>.c files? Rest of the patch looks good to me. Thanks, Sekhar -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
