Re: [PATCH] fix gettimeofday vs. update_gtod race

Nathan Lynch wrote:

Benjamin Herrenschmidt wrote:

quoted

On Wed, 2006-08-16 at 19:18 -0500, Nathan Lynch wrote:

quoted

No?  I didn't find anything about mftb having synchronizing
behavior.  How should we ensure that temp_varp is assigned before
reading the timebase?

I sync an isync would be enough.

I see, thanks.

Actually, after checking Book 2 and discussing with some other folks
I'm not so sure -- isync "may complete before storage accesses
associated with instructions preceding the isync instruction have been
performed."