Re: x86: kvmclock: abstract save/restore sched_clock_state

[Marcelo Tosatti <mtosatti@redhat.com>]

On Fri, Feb 10, 2012 at 03:32:11PM +0530, Amit Shah wrote:
> On (Thu) 09 Feb 2012 [16:13:29], Igor Mammedov wrote:
> 
> > Stalls are probably caused by uninitialized percpu hv_clock, with
> > following patch I don't see stalls. Although I might be just lucky.
> > http://git.kernel.org/?p=virt/kvm/kvm.git;a=commit;h=e2971ac7e1d186af059e088d305496c5cb47d487
> 
> Your commit does make things better, I don't see any stalls on the
> first resume.
> 
> However, a subsequent s4 causes the stall to re-appear on resume, and
> this time there are no stall messages; the kernel just sits there
> spinning on something.  I've not found the solution to this one yet (I
> had a commit similar to Marcelo's in the works, which got me to the
> previous works-but-stalls behaviour).

I cannot reproduce it here. Suspend/resume are operating normally after
several iterations. Igor do you see anything similar?

Amit, can you please enable CONFIG_PRINTK_TIME=y and post a full dmesg 
(both during suspend and also the new kernel during resume).

Thanks.

> > However there is/are a warning/s on suspend path and with following patch:
> 
> I didn't see this.

This is unrelated.