Subject: Re: inter-cpu coherency and kernel data structures
To: Bill Sommerfeld <>
From: Jason R Thorpe <>
List: tech-smp
Date: 08/14/2000 09:48:12
On Mon, Aug 14, 2000 at 09:31:36AM -0400, Bill Sommerfeld wrote:

 > A more interesting question is when a mutex is used only to serialize
 > updates to locations (such as a PTE) which are read without holding a
 > lock..  if we can't allow this for this in a simple way, we're going
 > to have to be a lot more paranoid about what we allow in MI code.

I don't think this is really much of a worry -- in cases like these,
the update will cause a barrier...

        -- Jason R. Thorpe <>