Messages in this thread | | | Subject | Re: [PATCH] Mutilated form of Andi Kleen's AMD prefetch errata patch | From | Andi Kleen <> | Date | 01 Oct 2003 08:47:58 +0200 |
| |
Andrew Morton <akpm@osdl.org> writes:
> Looking at Andi's patch, it is also a dead box if the fault happens inside > down_write(mmap_sem). That should be fixed, methinks.
The only way to fix all that would be to move the instruction checks early into the fast path.
[On a P4 the overhead is 3.7268 vs 3.6594 microseconds for a fault that doesn't hit as measured by lmbench2's lat_sig. This was before the latest changes which added more checking, so the overhead is probably bigger now]
-Andi - 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/
| |