Messages in this thread |  | | Subject | Re: [RFC] framework for fpu usage in kernel | Date | Sun, 11 Feb 2001 20:26:44 +0000 (GMT) | From | Alan Cox <> |
| |
> memcopy is a really generic function, and calling it saves the current > fpu state into thread.i387.f{,x}save. IMHO that's wrong, memcopy must > save into a local buffer like raid5 checksumming.
The mmx copy is only done in task context. There are a whole variety of _horrible_ problems doing it in interrupt space so based on the considerable number of problems with prior attempts to get it right on IRQ and copyuser cases I didnt bother - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
|  |