Messages in this thread | | | Subject | Re: [RFC] page-table walkers vs memory order | From | Peter Zijlstra <> | Date | Thu, 26 Jul 2012 10:11:39 +0200 |
| |
On Wed, 2012-07-25 at 15:09 -0700, Hugh Dickins wrote: > We find out after it hits us, and someone studies the disassembly - > if we're lucky enough to crash near the origin of the problem.
This is a rather painful way.. see
https://lkml.org/lkml/2009/1/5/555
we were lucky there in that the lack of ACCESS_ONCE() caused an infinite loop so we knew exactly where we got stuck.
| |