On Thursday 08 November 2007 01:20, Matt Mackall wrote:
On Wed, Nov 07, 2007 at 12:30:45PM -0800, Andrew Morton wrote:
Ow. Yes, from my reading delay_tsc() can return early (or afterpreempt_disable is lousy documentation here. This and other cases
heat-death-of-the-universe) if the TSCs are offset and if preemption
migrates the calling task between CPUs.
I suppose a lameo fix would be to disable preemption in delay_tsc().
(lots of per_cpu users, IIRC) actually want a migrate_disable() which
is a proper subset. We can simply implement migrate_disable() as
preempt_disable() for now and come back later and implement a proper
migrate_disable() that still allows preemption (and thus avoids the
latency).
We could actually do this right now. migrate_disable() can be just changing
the cpu affinity of the current thread to current cpu and then restoring it afterwards. That should even work from interrupt context.
get_cpu() etc. could be changed to use this then too.