Re: [patch] x86_64: fix sched_clock() | KernelTrap

Re: [patch] x86_64: fix sched_clock()

view
thread

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

[view in full thread]

From: Rusty Russell

Subject: Re: [patch] x86_64: fix sched_clock()

Date: Sunday, May 27, 2007 - 8:12 pm

On Fri, 2007-05-25 at 13:05 +0200, Andi Kleen wrote:
quoted text> On Fri, May 25, 2007 at 11:03:15AM +0200, Andi Kleen wrote:
> > > This?    I sent it to you earlier this week:
> > 
> > Sorry haven't processed those yet.
> > 
> > Ah. The correct fix here is to clear the tsc flag in boot_cpu_data
> > when the option is set. Will do that.
> 
> Hmm I double checked this now; tsc_disable indeed clears
> X86_FEATURE_TSC in identify_cpu and that should be always
> called before anything sched_clock related runs on a CPU.

Yes, agreed.

quoted text> Also the only possibly faulting division is protected
> by a cpu_has_tsc which even checks boot_cpu_data. this means
> even if the resync frequency code was called for
> some reason before the identify_cpu of a AP it should
> still work. For the BP this definitely cannot happen.
> 
> I also tried it with qemu myself (both one and two cpus) and it worked
> 
> Rusty, was this really on a standard kernel? Was it with multiple
> CPUs? 

No, will re-check.  Drop it for now, if I can reproduce I'll produce the
real fix or a decent explanation.

Thanks,
Rusty.


-
unsubscribe noticeTo unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:

[patch] sched_clock(): cleanups, Ingo Molnar, (Fri May 25, 12:10 am)

Re: [patch] sched_clock(): cleanups, Satyam Sharma, (Fri May 25, 12:22 am)

Re: [patch] sched_clock(): cleanups, Ingo Molnar, (Fri May 25, 12:25 am)

Re: [patch] sched_clock(): cleanups, Ingo Molnar, (Fri May 25, 12:26 am)

Re: [patch] sched_clock(): cleanups, Andi Kleen, (Fri May 25, 12:31 am)

Re: [patch] sched_clock(): cleanups, Satyam Sharma, (Fri May 25, 12:35 am)

Re: [patch] sched_clock(): cleanups, Andi Kleen, (Fri May 25, 12:38 am)

Re: [patch] sched_clock(): cleanups, Peter Zijlstra, (Fri May 25, 12:39 am)

Re: [patch] sched_clock(): cleanups, Ingo Molnar, (Fri May 25, 12:39 am)

Re: [patch] sched_clock(): cleanups, Ingo Molnar, (Fri May 25, 12:43 am)

Re: [patch] sched_clock(): cleanups, Ingo Molnar, (Fri May 25, 12:49 am)

[patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 12:54 am)

Re: [patch] sched_clock(): cleanups, Andi Kleen, (Fri May 25, 12:58 am)

Re: [patch] x86_64: fix sched_clock(), Andi Kleen, (Fri May 25, 1:02 am)

Re: [patch] sched_clock(): cleanups, Ingo Molnar, (Fri May 25, 1:02 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 1:04 am)

[patch] i386, numaq: enable TSCs again, Ingo Molnar, (Fri May 25, 1:08 am)

Re: [patch] x86_64: fix sched_clock(), Peter Zijlstra, (Fri May 25, 1:15 am)

Re: [patch] sched_clock(): cleanups, Peter Zijlstra, (Fri May 25, 1:16 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 1:16 am)

Re: [patch] i386, numaq: enable TSCs again, William Lee Irwin III, (Fri May 25, 1:19 am)

Re: [patch] x86_64: fix sched_clock(), Andi Kleen, (Fri May 25, 1:20 am)

Re: [patch] sched_clock(): cleanups, Andi Kleen, (Fri May 25, 1:21 am)

Re: [patch] sched_clock(): cleanups, Peter Zijlstra, (Fri May 25, 1:22 am)

Re: [patch] i386, numaq: enable TSCs again, Andi Kleen, (Fri May 25, 1:22 am)

Re: [patch] i386, numaq: enable TSCs again, William Lee Irwin III, (Fri May 25, 1:25 am)

Re: [patch] i386, numaq: enable TSCs again, Ingo Molnar, (Fri May 25, 1:31 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 1:34 am)

Re: [patch] i386, numaq: enable TSCs again, William Lee Irwin III, (Fri May 25, 1:38 am)

Re: [patch] x86_64: fix sched_clock(), Andi Kleen, (Fri May 25, 1:41 am)

Re: [patch] i386, numaq: enable TSCs again, Ingo Molnar, (Fri May 25, 1:41 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 1:44 am)

Re: [patch] x86_64: fix sched_clock(), Andi Kleen, (Fri May 25, 1:45 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 1:55 am)

Re: [patch] x86_64: fix sched_clock(), Andrew Morton, (Fri May 25, 1:55 am)

Re: [patch] x86_64: fix sched_clock(), Andi Kleen, (Fri May 25, 2:03 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 2:19 am)

Re: [patch] x86_64: fix sched_clock(), Andi Kleen, (Fri May 25, 2:46 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 3:12 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 3:27 am)

Re: [patch] x86_64: fix sched_clock(), Andi Kleen, (Fri May 25, 4:05 am)

Re: [patch] x86_64: fix sched_clock(), Andi Kleen, (Fri May 25, 4:20 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 4:26 am)

Re: [patch] x86_64: fix sched_clock(), Ingo Molnar, (Fri May 25, 4:31 am)

[patch] sched_clock: fix preempt count imbalance, Ingo Molnar, (Fri May 25, 4:46 am)

[patch] sched_clock(): cleanups, #2, Ingo Molnar, (Fri May 25, 4:50 am)

Re: [patch] sched_clock(): cleanups, #2, Andi Kleen, (Fri May 25, 4:55 am)

Re: [patch] sched_clock(): cleanups, #2, Ingo Molnar, (Fri May 25, 5:02 am)

Re: [patch] sched_clock(): cleanups, #2, Andi Kleen, (Fri May 25, 5:15 am)

Re: [patch] sched_clock(): cleanups, #2, Andrew Morton, (Fri May 25, 9:17 am)

Re: [patch] sched_clock(): cleanups, #2, Daniel Walker, (Fri May 25, 9:26 am)

Re: [patch] sched_clock(): cleanups, #2, Andi Kleen, (Fri May 25, 9:33 am)

Re: [patch] sched_clock(): cleanups, #2, Linus Torvalds, (Fri May 25, 9:49 am)

Re: [patch] sched_clock(): cleanups, #2, Andi Kleen, (Fri May 25, 11:08 am)

Re: [patch] i386, numaq: enable TSCs again, Dave Hansen, (Fri May 25, 11:16 am)

Re: [patch] i386, numaq: enable TSCs again, john stultz, (Fri May 25, 11:23 am)

Re: [patch] sched_clock(): cleanups, #2, Ingo Molnar, (Fri May 25, 12:14 pm)

Re: [patch] sched_clock(): cleanups, #2, Linus Torvalds, (Fri May 25, 12:45 pm)

Re: [patch] x86_64: fix sched_clock(), Rusty Russell, (Sun May 27, 8:12 pm)