[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Xen-devel] [RFC PATCH V2 11/11] x86: tsc: avoid system instability in hibernation
- To: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
- From: "Rafael J. Wysocki" <rafael@xxxxxxxxxx>
- Date: Mon, 13 Jan 2020 22:50:59 +0100
- Cc: "konrad.wilk@xxxxxxxxx" <konrad.wilk@xxxxxxxxx>, "Valentin, Eduardo" <eduval@xxxxxxxxxx>, "len.brown@xxxxxxxxx" <len.brown@xxxxxxxxx>, "x86@xxxxxxxxxx" <x86@xxxxxxxxxx>, "linux-mm@xxxxxxxxx" <linux-mm@xxxxxxxxx>, "pavel@xxxxxx" <pavel@xxxxxx>, "hpa@xxxxxxxxx" <hpa@xxxxxxxxx>, "boris.ostrovsky@xxxxxxxxxx" <boris.ostrovsky@xxxxxxxxxx>, "sstabellini@xxxxxxxxxx" <sstabellini@xxxxxxxxxx>, "fllinden@xxxxxxxxxx" <fllinden@xxxxxxxxxx>, "Kamata, Munehisa" <kamatam@xxxxxxxxxx>, "mingo@xxxxxxxxxx" <mingo@xxxxxxxxxx>, "xen-devel@xxxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxxx>, "Singh, Balbir" <sblbir@xxxxxxxxxx>, "axboe@xxxxxxxxx" <axboe@xxxxxxxxx>, "linux-pm@xxxxxxxxxxxxxxx" <linux-pm@xxxxxxxxxxxxxxx>, "Agarwal, Anchal" <anchalag@xxxxxxxxxx>, "bp@xxxxxxxxx" <bp@xxxxxxxxx>, "tglx@xxxxxxxxxxxxx" <tglx@xxxxxxxxxxxxx>, "jgross@xxxxxxxx" <jgross@xxxxxxxx>, "netdev@xxxxxxxxxxxxxxx" <netdev@xxxxxxxxxxxxxxx>, "Woodhouse@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" <Woodhouse@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx>, "rjw@xxxxxxxxxxxxx" <rjw@xxxxxxxxxxxxx>, "linux-kernel@xxxxxxxxxxxxxxx" <linux-kernel@xxxxxxxxxxxxxxx>, "vkuznets@xxxxxxxxxx" <vkuznets@xxxxxxxxxx>, "davem@xxxxxxxxxxxxx" <davem@xxxxxxxxxxxxx>, "Woodhouse, David" <dwmw@xxxxxxxxxxxx>, "roger.pau@xxxxxxxxxx" <roger.pau@xxxxxxxxxx>
- Delivery-date: Mon, 13 Jan 2020 21:51:27 +0000
- List-id: Xen developer discussion <xen-devel.lists.xenproject.org>
On Mon, Jan 13, 2020 at 1:43 PM Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
>
> On Mon, Jan 13, 2020 at 11:43:18AM +0000, Singh, Balbir wrote:
> > For your original comment, just wanted to clarify the following:
> >
> > 1. After hibernation, the machine can be resumed on a different but
> > compatible
> > host (these are VM images hibernated)
> > 2. This means the clock between host1 and host2 can/will be different
> >
> > In your comments are you making the assumption that the host(s) is/are the
> > same? Just checking the assumptions being made and being on the same page
> > with
> > them.
>
> I would expect this to be the same problem we have as regular suspend,
> after power off the TSC will have been reset, so resume will have to
> somehow bridge that gap. I've no idea if/how it does that.
In general, this is done by timekeeping_resume() and the only special
thing done for the TSC appears to be the tsc_verify_tsc_adjust(true)
call in tsc_resume().
> I remember some BIOSes had crazy TSC ideas for suspend2ram, and we grew
> tsc_restore_sched_clock_state() for it.
>
> Playing crazy games like what you're doing just isn't it though.
Right.
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel
|