Messages in this thread |  | | Date | Fri, 22 Sep 2000 00:14:14 +0200 | From | "Andi Kleen" <> | Subject | Re: Question: Using floating point in the kernel |
| |
On Thu, Sep 21, 2000 at 11:08:36PM +0100, Alan Cox wrote: > > On Thu, Sep 21, 2000 at 11:36:17AM +0000, John Alvord wrote: > > > A 2.5-time problem is that portions of the kernel are planned to > > > become interruptible... so saving and restoring around a certain usage > > > would be insufficient. > > > > It is sufficient when you do tsk->flags |= PF_USEDFPU first. > > Unless you sleep
Unless I'm missing something the lazy FPU state save in the 2.4 switch_to will do the right thing at least on x86. Your kernel FPU state will overwrite the user FPU state in current, but that's ok because it is undefined anyways (and you restore the correct state when you wake up again)
-Andi
- 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/
|  |