Re: [PATCH 2/9] x86: introduce a set of platform feature flags

[H. Peter Anvin]

Pan, Jacob jun wrote:
>>> +#define platform_has(bit) \
>>> +	test_bit(bit, (unsigned long *)platform_feature)
>> test_bit and friends imply synchronization you probably  don't want or
>> need...
>>
> [[JPAN]] could you explain a little more? The disassembly shows the test_bit
> ends up as a testb instruction and a jump. Why there is synchronization
>  involved?
> Perhaps on some architectures?

test_bit() doesn't imply synchronization; set_bit() and clear_bit() do
(but not __set_bit() and __clear_bit(), just to really be confusing.)

	-hpa
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/