linux-kernel - Re: [PATCH v3 4/6] cpufreq: powernv: Call throttle_check() on receiving OCC

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date:	Fri, 08 May 2015 16:11:54 +0200
From:	"Rafael J. Wysocki" <rjw@...ysocki.net>
To:	Preeti U Murthy <preeti@...ux.vnet.ibm.com>
Cc:	linuxppc-dev@...abs.org, linux-pm@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Shilpasri G Bhat <shilpa.bhat@...ux.vnet.ibm.com>,
	viresh.kumar@...aro.org
Subject: Re: [PATCH v3 4/6] cpufreq: powernv: Call throttle_check() on receiving OCC_THROTTLE

On Friday, May 08, 2015 09:16:44 AM Preeti U Murthy wrote:
> On 05/08/2015 02:29 AM, Rafael J. Wysocki wrote:
> > On Thursday, May 07, 2015 05:49:22 PM Preeti U Murthy wrote:
> >> On 05/05/2015 02:11 PM, Preeti U Murthy wrote:
> >>> On 05/05/2015 12:03 PM, Shilpasri G Bhat wrote:
> >>>> Hi Preeti,
> >>>>
> >>>> On 05/05/2015 09:30 AM, Preeti U Murthy wrote:
> >>>>> Hi Shilpa,
> >>>>>
> >>>>> On 05/04/2015 02:24 PM, Shilpasri G Bhat wrote:
> >>>>>> Re-evaluate the chip's throttled state on recieving OCC_THROTTLE
> >>>>>> notification by executing *throttle_check() on any one of the cpu on
> >>>>>> the chip. This is a sanity check to verify if we were indeed
> >>>>>> throttled/unthrottled after receiving OCC_THROTTLE notification.
> >>>>>>
> >>>>>> We cannot call *throttle_check() directly from the notification
> >>>>>> handler because we could be handling chip1's notification in chip2. So
> >>>>>> initiate an smp_call to execute *throttle_check(). We are irq-disabled
> >>>>>> in the notification handler, so use a worker thread to smp_call
> >>>>>> throttle_check() on any of the cpu in the chipmask.
> >>>>>
> >>>>> I see that the first patch takes care of reporting *per-chip* throttling
> >>>>> for pmax capping condition. But where are we taking care of reporting
> >>>>> "pstate set to safe" and "freq control disabled" scenarios per-chip ?
> >>>>>
> >>>>
> >>>> IMO let us not have "psafe" and "freq control disabled" states managed per-chip.
> >>>> Because when the above two conditions occur it is likely to happen across all
> >>>> chips during an OCC reset cycle. So I am setting 'throttled' to false on
> >>>> OCC_ACTIVE and re-verifying if it actually is the case by invoking
> >>>> *throttle_check().
> >>>
> >>> Alright like I pointed in the previous reply, a comment to indicate that
> >>> psafe and freq control disabled conditions will fail when occ is
> >>> inactive and that all chips face the consequence of this will help.
> >>
> >> From your explanation on the thread of the first patch of this series,
> >> this will not be required.
> >>
> >> So,
> >> Reviewed-by: Preeti U Murthy <preeti@...ux.vnet.ibm.com>
> > 
> > OK, so is the whole series reviewed now?
> 
> Yes the whole series has been reviewed.

OK, I'll queue it up for 4.2, then, thanks!


-- 
I speak only for myself.
Rafael J. Wysocki, Intel Open Source Technology Center.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/