[PATCH] simplefb: Fix build failure on Sparc

[Hans de Goede]

Hi,

On 05-01-15 12:17, Tomi Valkeinen wrote:
> On 05/01/15 10:15, Hans de Goede wrote:
>> of_platform_device_create is only defined when CONFIG_OF_ADDRESS is set,
>> which is normally always the case when CONFIG_OF is defined, except on Sparc,
>> so explicitly check for CONFIG_OF_ADDRESS rather then for CONFIG_OF.
>>
>> Reported-by: kbuild test robot <fengguang.wu at intel.com>
>> Signed-off-by: Hans de Goede <hdegoede at redhat.com>
>> ---
>>   drivers/video/fbdev/simplefb.c | 2 +-
>>   1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/drivers/video/fbdev/simplefb.c b/drivers/video/fbdev/simplefb.c
>> index 92cac80..1085c04 100644
>> --- a/drivers/video/fbdev/simplefb.c
>> +++ b/drivers/video/fbdev/simplefb.c
>> @@ -402,7 +402,7 @@ static int __init simplefb_init(void)
>>   	if (ret)
>>   		return ret;
>>
>> -	if (IS_ENABLED(CONFIG_OF) && of_chosen) {
>> +	if (IS_ENABLED(CONFIG_OF_ADDRESS) && of_chosen) {
>>   		for_each_child_of_node(of_chosen, np) {
>>   			if (of_device_is_compatible(np, "simple-framebuffer"))
>>   				of_platform_device_create(np, NULL, NULL);
>>
>
> Doesn't this depend on the compiler optimizing the
> of_platform_device_create call away?

Yes it does.

> Isn't that rather dangerous assumption?

The kernel relies on being build with optimization enabled in various places,
this specific construction was suggested during review (by Grant Likely IIRC)
I initially had an #ifdef here. Note that this construction is used in various
places throughout the kernel and it seems to be used more and more often.

Regards,

Hans