On 05/01/15 13:21, Hans de Goede wrote:
> 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@xxxxxxxxx>
>>> Signed-off-by: Hans de Goede <hdegoede@xxxxxxxxxx>
>>> ---
>>> 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.
Ok. Well, I can't say I'm very happy about that, but if that's the
common accepted way, I'm fine. I'll queue this for fbdev fixes.
Tomi
Attachment:
signature.asc
Description: OpenPGP digital signature
