Re: [RFC PATCH] x86/asm/irq: Don't use POPF but STI

[Andy Lutomirski]

On Tue, Apr 21, 2015 at 9:12 AM, Linus Torvalds
<torvalds@xxxxxxxxxxxxxxxxxxxx> wrote:
> On Tue, Apr 21, 2015 at 5:45 AM, Ingo Molnar <mingo@xxxxxxxxxx> wrote:
>>
>> Totally untested and not signed off yet: because we'd first have to
>> make sure (via irq flags debugging) that it's not used in reverse, to
>> re-disable interrupts:
>
> Not only might that happen in some place, I *really* doubt that a
> conditional 'sti' is actually any faster. The only way it's going to
> be measurably faster is if you run some microbenchmark so that the
> code is hot and the branch predicts well.
>
> "popf" is fast for the "no changes to IF" case, and is a smaller
> instruction anyway. I'd really hate to make this any more complex
> unless somebody has some real numbers for performance improvement
> (that is *not* just some cycle timing from a bogus test-case, but real
> measurements on a real load).
>
> And even *with* real measurements, I'd worry about the "use popf to
> clear IF" case.

Fair enough.  Maybe I'll benchmark this some day.

--Andy

>
>            Linus



-- 
Andy Lutomirski
AMA Capital Management, LLC
--
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/