Re: [BUG] 2.5.65: Caching MSR_IA32_SYSENTER_CS kills dosemu

Linus Torvalds (torvalds@transmeta.com)
Tue, 1 Apr 2003 15:13:58 -0800 (PST)


On 1 Apr 2003, Robert Love wrote:
>
> Actually, do they do disable preemption - if they do not, something is
> broken.

Ok, I was too lazy to check. Anyway, the test-patch is worth trying, since
one of the areas fixed had no pre-emption protection regardless (ie it
used just a plain "smp_processor_id()"), and the patch should be
technically equivalent (just uglier) to a proper get_cpu().

> Because, even on UP, preemption can lead to a race over a variable that
> has no locking because its per-CPU. But it would need locking
> otherwise, and thus we do need to disable preemption.

Yes, that was certainly the case here.

Linus

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