Hi folks
I upgraded one of my 32bit chroots on a x86-64 machine runing under Xen
lately. All binaries started to segfault. Some extensive checks later
show the vdso as the culprit. Later I found
with the same problem. The full story can be found in the Debian bug
544145[1].
It happens with Linux
On 08/30/09 11:16, Bastian Blank wrote:
> Hi folks
>
> I upgraded one of my 32bit chroots on a x86-64 machine runing under Xen
> lately. All binaries started to segfault. Some extensive checks later
> show the vdso as the culprit. Later I found
> with the same problem. The full story can be found
On Thu, Sep 03, 2009 at 01:51:35PM -0700, Jeremy Fitzhardinge wrote:
> On 08/30/09 11:16, Bastian Blank wrote:
> > I upgraded one of my 32bit chroots on a x86-64 machine runing under Xen
> > lately. All binaries started to segfault. Some extensive checks later
> > show the vdso as the culprit. Late
On Thu, Sep 03, 2009 at 03:06:32PM -0700, Jeremy Fitzhardinge wrote:
> On 09/03/09 15:02, Bastian Blank wrote:
> > AFAIK only AMD support the syscall instruction, so yes it is an AMD
> > machine. And yes, disabling the only thing that make the glibc call this
> > instruction works around it.
> The
On 09/03/09 15:02, Bastian Blank wrote:
> AFAIK only AMD support the syscall instruction, so yes it is an AMD
> machine. And yes, disabling the only thing that make the glibc call this
> instruction works around it.
>
The bug actually appears to be in xen_sysret32, ie the crash happens on
the w
On Fri, Sep 04, 2009 at 09:07:39AM -0700, Jeremy Fitzhardinge wrote:
> But for some reason that's triggering a failsafe callback, which invokes
> a GP.
Hmm, not in my tests. It always returned to userspace correctly and died
some operations later, usually the "ret". This then produced either a
seg
On 09/03/09 15:36, Bastian Blank wrote:
> This function looks weird. It tries to restores the user code segment.
> But the documentation from AMD explicitely stat that the CS and SS are
> restored from the STAR register.
And STAR is always set with:
wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 |
On Fri, Sep 04, 2009 at 09:07:39AM -0700, Jeremy Fitzhardinge wrote:
> On 09/03/09 15:36, Bastian Blank wrote:
> > This function looks weird. It tries to restores the user code segment.
> > But the documentation from AMD explicitely stat that the CS and SS are
> > restored from the STAR register.
>
On 09/04/09 09:20, Bastian Blank wrote:
> On Fri, Sep 04, 2009 at 09:07:39AM -0700, Jeremy Fitzhardinge wrote:
>
>> But for some reason that's triggering a failsafe callback, which invokes
>> a GP.
>>
> Hmm, not in my tests. It always returned to userspace correctly and died
> some operatio
On Fri, Sep 04, 2009 at 07:46:05PM +0200, Bastian Blank wrote:
> On Fri, Sep 04, 2009 at 09:07:39AM -0700, Jeremy Fitzhardinge wrote:
> > On 09/03/09 15:36, Bastian Blank wrote:
> > > This function looks weird. It tries to restores the user code segment.
> > > But the documentation from AMD explici
10 matches
Mail list logo
