[Lucid-ec2] SRU: XEN: Do not force sched_clock_stable
Leann Ogasawara
leann.ogasawara at canonical.com
Tue May 17 18:54:21 UTC 2011
On Tue, 2011-05-17 at 19:29 +0200, Stefan Bader wrote:
> SRU Justification
>
> Impact: When applying the Xen patchset one endif seems to have gone to
> the wrong place. So instead of not setting sched_clock_stable it is done
> all the time.
>
> Fix: Move endif so the whole code segment is covered.
>
> Testcase: Can cause various effects and depends on CPU (see below).
> Incorrect CPU time but likely also causing the unexplainable process
> gets stuck or clone/fork issues.
>
> ---
>
> From 5f1bda076198807960d023c4d1551485c8d77ef5 Mon Sep 17 00:00:00 2001
> From: Stefan Bader <stefan.bader at canonical.com>
> Date: Tue, 17 May 2011 19:16:30 +0200
> Subject: [PATCH] UBUNTU: SAUCE: XEN: Do not force sched_clock_stable
>
> BugLink: http://bugs.launchpad.net/bugs/727459
>
> This is part of the changes that have been found while syncing up
> the patchsets. Apparently when applying the endif went into the
> wrong place and causes the clock to be assumed always stable. Which
> causes problems on certain CPUs (probably the fork/clone hang as well
> as processes getting stuck for a longer time).
>
> Signed-off-by: Stefan Bader <stefan.bader at canonical.com>
Acked-by: Leann Ogasawara <leann.ogasawara at canonical.com>
> ---
> arch/x86/kernel/cpu/intel.c | 2 +-
> 1 files changed, 1 insertions(+), 1 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
> index 0aad121..f582b21 100644
> --- a/arch/x86/kernel/cpu/intel.c
> +++ b/arch/x86/kernel/cpu/intel.c
> @@ -97,8 +97,8 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
> set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
> #ifndef CONFIG_XEN
> if (!check_tsc_unstable())
> -#endif
> sched_clock_stable = 1;
> +#endif
> }
>
> /*
> --
> 1.7.0.4
>
>
More information about the kernel-team
mailing list