Re: [git pull] scheduler/misc fixes

[David Miller]

From: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Date: Fri, 25 Apr 2008 10:24:18 +0200

> FWIW I do think this is a valid 'bug' fix in that the called user func()
> can now see its from interrupt context. in_interrupt() would have
> reported false due to the missing irq_enter()/irq_exit() - not sure if
> any smp_call_function() relies on it though.

Understood.

I thought a bit and I remember that I did notice long ago that x86 did
these irq_enter() calls in SMP call function processing, but it seemed
like pure overhead at the time and wasn't actually needed.

Anyways, Peter can you give your state machine thing another shot?
Maybe it will help us see what is wrong either in the sparc64 code
or in the NOHZ/sched bits.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/