Messages in this thread | | | Date | Mon, 06 Dec 1999 21:51:30 +0100 | From | Manfred Spraul <> | Subject | Re: [patch] Re: setitimer lowlatency-2.2.13-A1 questions |
| |
Andrea Arcangeli wrote: > > > > >Is there a special reason why do_bottom_half() calls __sti() and __cli() > >directly? This seems wrong, what about using the normal > >__save_flags()/__sti()/__restore_flags()? > > The irq handler case by design doesn't need it. You must enter there with > irq disabled and you must exit with irq disabled (so you must enabled > and disable by hand before and after running the bhs). > > For the ret to userspace case it could decrease a bit the bh latency but > it seems not a big issue, as right now a ret from syscall will act like > while returning from an irq after the bottom half path. > I know that it's safe: * "real interrupts" need it. * schedule() calls "spin_lock_irq()" immediately after returning from do_bottom_half(). * interrupts are cleared during IRET.
But nevertheless I think that it's ugly that a function sometimes (even worse: rarely) disables interrupts: What if a cpu doesn't reenable interrupts during return to user space? do_bottom_half() is not architecture specific.
-- Manfred
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |