xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
From: Joao Martins <joao.m.martins@oracle.com>
To: Jan Beulich <JBeulich@suse.com>
Cc: xen-devel <xen-devel@lists.xenproject.org>,
	Wei Liu <wei.liu2@citrix.com>,
	Dario Faggioli <dario.faggioli@eu.citrix.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>
Subject: Re: [PATCH] x86/time: use correct (local) time stamp in constant-TSC calibration fast path
Date: Thu, 9 Jun 2016 13:11:51 +0100	[thread overview]
Message-ID: <57595D07.90107@oracle.com> (raw)
In-Reply-To: <575976AE02000078000F3695@prv-mh.provo.novell.com>



On 06/09/2016 01:01 PM, Jan Beulich wrote:
> This looks like a copy and paste mistake in commit 1b6a99892d ("x86:
> Simpler time handling when TSC is constant across all power saving
> states"), responsible for occasional many-microsecond cross-CPU skew of
> what NOW() returns.
> 
> Also improve the correlation between local TSC and stime stamps
> obtained at the end of the two calibration handlers: Compute the stime
> one from the TSC one, instead of doing another rdtsc() for that
> compuation.
> 
> Signed-off-by: Jan Beulich <jbeulich@suse.com>
> ---
> As to 4.7 inclusion: This of course looks like a pretty blatant mistake
> that has been there for many years (and hence many releases). There's
> certainly non-zero risk that I'm overlooking something here (despite
> Joao apparently having come to the same conclusion), so I can't really
> make up my mind on whether to request this patch to be put there right
> away, or rather having linger in -unstable for a while.
> 
Initially I thought of this as a fix too, but then wouldn't having
t->stime_local_stamp be c->stime_local_stamp, render no use to the
platform timer reads done on calibration? Unless we would change
update_vcpu_system to use stime_master_stamp instead?
stime_master_stamp field isn't used anywhere other than the dom0 injected
cpu_frequency_change or when at boot seeding the cpu_time struct on
init_percpu_time (and the already mentioned use on local_time_calibration) ?
init_percpu_time also takes a different read of the platform timer per
cpu and could probably be inherited by a read done on the boot processor
and written on remaining CPUs, so that all would start from the same stamp.
IOW - this sounds like time we are turning stime to be totally TSC except
when initially seeding each cpu_time?

> --- a/xen/arch/x86/time.c
> +++ b/xen/arch/x86/time.c
> @@ -998,7 +998,7 @@ static void local_time_calibration(void)
>          /* Atomically read cpu_calibration struct and write cpu_time struct. */
>          local_irq_disable();
>          t->local_tsc_stamp    = c->local_tsc_stamp;
> -        t->stime_local_stamp  = c->stime_master_stamp;
> +        t->stime_local_stamp  = c->stime_local_stamp;
>          t->stime_master_stamp = c->stime_master_stamp;
>          local_irq_enable();
>          update_vcpu_system_time(current);
> @@ -1275,7 +1275,7 @@ static void time_calibration_tsc_rendezv
>      }
>  
>      c->local_tsc_stamp = rdtsc();
> -    c->stime_local_stamp = get_s_time();
> +    c->stime_local_stamp = get_s_time_fixed(c->local_tsc_stamp);
>      c->stime_master_stamp = r->master_stime;
>  
>      raise_softirq(TIME_CALIBRATE_SOFTIRQ);
> @@ -1305,7 +1305,7 @@ static void time_calibration_std_rendezv
>      }
>  
>      c->local_tsc_stamp = rdtsc();
> -    c->stime_local_stamp = get_s_time();
> +    c->stime_local_stamp = get_s_time_fixed(c->local_tsc_stamp);
>      c->stime_master_stamp = r->master_stime;
>  
>      raise_softirq(TIME_CALIBRATE_SOFTIRQ);
> 
> 
> 

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel

  parent reply	other threads:[~2016-06-09 12:11 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-09 12:01 Jan Beulich
2016-06-09 12:10 ` Andrew Cooper
2016-06-09 12:11 ` Joao Martins [this message]
2016-06-09 12:57   ` Jan Beulich
2016-06-09 15:00     ` Joao Martins
2016-06-09 15:52       ` Jan Beulich
2016-06-09 18:19         ` Joao Martins
2016-06-10  6:59           ` Jan Beulich
2016-06-10  9:29             ` Jan Beulich
2016-06-10 17:07               ` Joao Martins
2016-06-09 12:12 ` Wei Liu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=57595D07.90107@oracle.com \
    --to=joao.m.martins@oracle.com \
    --cc=JBeulich@suse.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=dario.faggioli@eu.citrix.com \
    --cc=wei.liu2@citrix.com \
    --cc=xen-devel@lists.xenproject.org \
    --subject='Re: [PATCH] x86/time: use correct (local) time stamp in constant-TSC calibration fast path' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).