Subject: Re: splx() optimization [was Re: SMP re-eetrancy in "bottom half"
To: None <thorpej@shagadelic.org>
From: YAMAMOTO Takashi <yamt@mwd.biglobe.ne.jp>
List: tech-kern
Date: 06/08/2005 07:55:48
> So long as you can be interrupted by something that needs to take the  
> kernel_lock, you basically need to also run in that perimeter.  So,  
> the only way to make incremental progress is to take the "tackle  
> highest IPL first" path.
> 
> -- thorpej

while i completely agree that the only sane way is "highest IPL first",
lock-per-IPL implies that no interrupt handlers take kernel_lock, i guess.
i think it can work if we don't care about performace.

YAMAMOTO Takashi