Re: Concurrent bottom halves

Andrea Arcangeli (andrea@e-mind.com)
Fri, 26 Feb 1999 19:20:52 +0100 (CET)


On Fri, 26 Feb 1999, B. James Phillippe wrote:

>I understand that a bh is not re-entrant, if that's what you mean. But do

All bh are not reentrant in respect of all other bh. You can't have two bh
_handlers_ running at the same time.

>I want some other routine to be able to start working on encrypting these
>queued packets without having to wait for net_bh to finish. This way

The first thing that came me in mind if I would in you, would be to do an
hack and force the irq handler (or the apic_timer_interrupt in SMP) to
run_task_queue(&multi_thread) a new task queue that will going to race
with the bh handlers. I think it's not stuff for 2.2.x and I am not sure
my fastest thought is the best way to handle the multithread taskqueue
thing.

BTW, I hope I am not missing something in my thoughts... ;)

Andrea Arcangeli

-
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/