On Tue, Feb 12, 2008 at 04:08:16PM -0500, Neil Horman wrote:
> >
> > Neil, is it possible to do some serial console debugging to find out
> > where exactly we are hanging? Beats me, what's that operation which can
> > not be executed while being in NMI handler and makes system to hang. I am
> >
On Tue, Feb 12, 2008 at 04:08:16PM -0500, Neil Horman wrote:
Neil, is it possible to do some serial console debugging to find out
where exactly we are hanging? Beats me, what's that operation which can
not be executed while being in NMI handler and makes system to hang. I am
also
Neil Horman <[EMAIL PROTECTED]> writes:
>>
>> Neil, is it possible to do some serial console debugging to find out
>> where exactly we are hanging? Beats me, what's that operation which can
>> not be executed while being in NMI handler and makes system to hang. I am
>> also curious to know if it
Neil Horman [EMAIL PROTECTED] writes:
Neil, is it possible to do some serial console debugging to find out
where exactly we are hanging? Beats me, what's that operation which can
not be executed while being in NMI handler and makes system to hang. I am
also curious to know if it is nested
>
> Neil, is it possible to do some serial console debugging to find out
> where exactly we are hanging? Beats me, what's that operation which can
> not be executed while being in NMI handler and makes system to hang. I am
> also curious to know if it is nested NMI case.
>
> Thanks
> Vivek
>
Neil, is it possible to do some serial console debugging to find out
where exactly we are hanging? Beats me, what's that operation which can
not be executed while being in NMI handler and makes system to hang. I am
also curious to know if it is nested NMI case.
Thanks
Vivek
Hey-
On Fri, Feb 08, 2008 at 11:45:44AM -0500, Vivek Goyal wrote:
> On Fri, Feb 08, 2008 at 11:14:22AM -0500, Neil Horman wrote:
> > On Thu, Feb 07, 2008 at 01:24:04PM +0100, Ingo Molnar wrote:
> > >
> > > * Neil Horman <[EMAIL PROTECTED]> wrote:
> > >
> > > > Ingo noted a few posts down the nmi_exit
Ingo Molnar <[EMAIL PROTECTED]> writes:
>
> try a dummy iret, something like:
>
> asm volatile ("pushf; push $1f; iret; 1: \n");
>
> to get the CPU out of its 'nested NMI' state. (totally untested)
Just if you do this while running on the NMI stack (and I think
you do if you insert it at the
On Fri, Feb 08, 2008 at 11:14:22AM -0500, Neil Horman wrote:
> On Thu, Feb 07, 2008 at 01:24:04PM +0100, Ingo Molnar wrote:
> >
> > * Neil Horman <[EMAIL PROTECTED]> wrote:
> >
> > > Ingo noted a few posts down the nmi_exit doesn't actually write to the
> > > APIC EOI register, so yeah, I
On Thu, Feb 07, 2008 at 01:24:04PM +0100, Ingo Molnar wrote:
>
> * Neil Horman <[EMAIL PROTECTED]> wrote:
>
> > Ingo noted a few posts down the nmi_exit doesn't actually write to the
> > APIC EOI register, so yeah, I agree, its bogus (and I apologize, I
> > should have checked that more
On Thu, Feb 07, 2008 at 01:24:04PM +0100, Ingo Molnar wrote:
* Neil Horman [EMAIL PROTECTED] wrote:
Ingo noted a few posts down the nmi_exit doesn't actually write to the
APIC EOI register, so yeah, I agree, its bogus (and I apologize, I
should have checked that more carefully).
On Fri, Feb 08, 2008 at 11:14:22AM -0500, Neil Horman wrote:
On Thu, Feb 07, 2008 at 01:24:04PM +0100, Ingo Molnar wrote:
* Neil Horman [EMAIL PROTECTED] wrote:
Ingo noted a few posts down the nmi_exit doesn't actually write to the
APIC EOI register, so yeah, I agree, its bogus
On Thu, Feb 07, 2008 at 01:24:04PM +0100, Ingo Molnar wrote:
>
> * Neil Horman <[EMAIL PROTECTED]> wrote:
>
> > Ingo noted a few posts down the nmi_exit doesn't actually write to the
> > APIC EOI register, so yeah, I agree, its bogus (and I apologize, I
> > should have checked that more
* Neil Horman <[EMAIL PROTECTED]> wrote:
> Ingo noted a few posts down the nmi_exit doesn't actually write to the
> APIC EOI register, so yeah, I agree, its bogus (and I apologize, I
> should have checked that more carefully). Nevertheless, this patch
> consistently allowed a hangning
On Wed, Feb 06, 2008 at 05:31:11PM -0700, Eric W. Biederman wrote:
> Ingo Molnar <[EMAIL PROTECTED]> writes:
>
> > * H. Peter Anvin <[EMAIL PROTECTED]> wrote:
> >
> >>> I am wondering if interrupts are disabled on crashing cpu or if
> >>> crashing cpu is inside die_nmi(), how would it
On Wed, Feb 06, 2008 at 05:31:11PM -0700, Eric W. Biederman wrote:
Ingo Molnar [EMAIL PROTECTED] writes:
* H. Peter Anvin [EMAIL PROTECTED] wrote:
I am wondering if interrupts are disabled on crashing cpu or if
crashing cpu is inside die_nmi(), how would it stop/prevent delivery
of
* Neil Horman [EMAIL PROTECTED] wrote:
Ingo noted a few posts down the nmi_exit doesn't actually write to the
APIC EOI register, so yeah, I agree, its bogus (and I apologize, I
should have checked that more carefully). Nevertheless, this patch
consistently allowed a hangning machine to
On Thu, Feb 07, 2008 at 01:24:04PM +0100, Ingo Molnar wrote:
* Neil Horman [EMAIL PROTECTED] wrote:
Ingo noted a few posts down the nmi_exit doesn't actually write to the
APIC EOI register, so yeah, I agree, its bogus (and I apologize, I
should have checked that more carefully).
Ingo Molnar <[EMAIL PROTECTED]> writes:
> * Eric W. Biederman <[EMAIL PROTECTED]> wrote:
>
>> Looking at the patch the local_irq_enable() is totally bogus. As soon
>> was we hit machine_crash_shutdown the first thing we do is disable
>> irqs.
>
> yeah.
>
>> I'm wondering if someone was using
* Eric W. Biederman <[EMAIL PROTECTED]> wrote:
> Looking at the patch the local_irq_enable() is totally bogus. As soon
> was we hit machine_crash_shutdown the first thing we do is disable
> irqs.
yeah.
> I'm wondering if someone was using the switch cpus on crash patch that
> was floating
Ingo Molnar <[EMAIL PROTECTED]> writes:
> * H. Peter Anvin <[EMAIL PROTECTED]> wrote:
>
>>> I am wondering if interrupts are disabled on crashing cpu or if
>>> crashing cpu is inside die_nmi(), how would it stop/prevent delivery
>>> of NMI IPI to other cpus.
>>
>> I don't see how it would.
>
>
On Thu, Feb 07, 2008 at 12:36:57AM +0100, Ingo Molnar wrote:
>
> * H. Peter Anvin <[EMAIL PROTECTED]> wrote:
>
> >> I am wondering if interrupts are disabled on crashing cpu or if
> >> crashing cpu is inside die_nmi(), how would it stop/prevent delivery
> >> of NMI IPI to other cpus.
> >
> > I
* H. Peter Anvin <[EMAIL PROTECTED]> wrote:
>> I am wondering if interrupts are disabled on crashing cpu or if
>> crashing cpu is inside die_nmi(), how would it stop/prevent delivery
>> of NMI IPI to other cpus.
>
> I don't see how it would.
cross-CPU IPIs are a bit fragile on some PC
Vivek Goyal wrote:
I am wondering if interrupts are disabled on crashing cpu or if crashing
cpu is inside die_nmi(), how would it stop/prevent delivery of NMI IPI to
other cpus.
I don't see how it would.
-hpa
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel"
* Vivek Goyal <[EMAIL PROTECTED]> wrote:
> On Wed, Feb 06, 2008 at 11:00:01PM +0100, Ingo Molnar wrote:
> >
> > * Neil Horman <[EMAIL PROTECTED]> wrote:
> >
> > > if (!user_mode_vm(regs)) {
> > > + nmi_exit();
> > > + local_irq_enable();
> > >
On Wed, Feb 06, 2008 at 11:00:01PM +0100, Ingo Molnar wrote:
>
> * Neil Horman <[EMAIL PROTECTED]> wrote:
>
> > if (!user_mode_vm(regs)) {
> > + nmi_exit();
> > + local_irq_enable();
> > current->thread.trap_no = 2;
> > crash_kexec(regs);
>
>
* Neil Horman <[EMAIL PROTECTED]> wrote:
> if (!user_mode_vm(regs)) {
> + nmi_exit();
> + local_irq_enable();
> current->thread.trap_no = 2;
> crash_kexec(regs);
looks good to me, but please move the local_irq_enable() to within
On Wed, Feb 06, 2008 at 12:21:30PM -0800, H. Peter Anvin wrote:
> Neil Horman wrote:
> >Can an APIC accept an NMI while already handling an NMI? I didn't think
> >they
> >would interrupt one another, but rather, pend until such time as the
> >previous
> >NMI was cleared
>
> The CPU certainly
On Wed, Feb 06, 2008 at 03:12:23PM -0500, Neil Horman wrote:
> On Wed, Feb 06, 2008 at 02:40:40PM -0500, Vivek Goyal wrote:
> > On Wed, Feb 06, 2008 at 02:25:55PM -0500, Neil Horman wrote:
> > > Hey all-
> > > A hang on kdump was reported to me awhile back, only when systems died
> > > via nmi
Neil Horman wrote:
Can an APIC accept an NMI while already handling an NMI? I didn't think they
would interrupt one another, but rather, pend until such time as the previous
NMI was cleared
The CPU certainly won't (there is a hidden flag that's cleared on IRET
which disables NMI; it's
On Wed, Feb 06, 2008 at 02:40:40PM -0500, Vivek Goyal wrote:
> On Wed, Feb 06, 2008 at 02:25:55PM -0500, Neil Horman wrote:
> > Hey all-
> > A hang on kdump was reported to me awhile back, only when systems died
> > via nmi watchdog panic. The hang wouldn't always be in the same place, but
>
On Wed, Feb 06, 2008 at 02:25:55PM -0500, Neil Horman wrote:
> Hey all-
> A hang on kdump was reported to me awhile back, only when systems died
> via nmi watchdog panic. The hang wouldn't always be in the same place, but it
> would usually be somewhere down in purgatory. In looking at the
Hey all-
A hang on kdump was reported to me awhile back, only when systems died
via nmi watchdog panic. The hang wouldn't always be in the same place, but it
would usually be somewhere down in purgatory. In looking at the code, it
occured to me that since, during an nmi interrupt, we
Hey all-
A hang on kdump was reported to me awhile back, only when systems died
via nmi watchdog panic. The hang wouldn't always be in the same place, but it
would usually be somewhere down in purgatory. In looking at the code, it
occured to me that since, during an nmi interrupt, we
On Wed, Feb 06, 2008 at 02:25:55PM -0500, Neil Horman wrote:
Hey all-
A hang on kdump was reported to me awhile back, only when systems died
via nmi watchdog panic. The hang wouldn't always be in the same place, but it
would usually be somewhere down in purgatory. In looking at the
On Wed, Feb 06, 2008 at 03:12:23PM -0500, Neil Horman wrote:
On Wed, Feb 06, 2008 at 02:40:40PM -0500, Vivek Goyal wrote:
On Wed, Feb 06, 2008 at 02:25:55PM -0500, Neil Horman wrote:
Hey all-
A hang on kdump was reported to me awhile back, only when systems died
via nmi watchdog
On Wed, Feb 06, 2008 at 12:21:30PM -0800, H. Peter Anvin wrote:
Neil Horman wrote:
Can an APIC accept an NMI while already handling an NMI? I didn't think
they
would interrupt one another, but rather, pend until such time as the
previous
NMI was cleared
The CPU certainly won't (there
* Neil Horman [EMAIL PROTECTED] wrote:
if (!user_mode_vm(regs)) {
+ nmi_exit();
+ local_irq_enable();
current-thread.trap_no = 2;
crash_kexec(regs);
looks good to me, but please move the local_irq_enable() to within
crash_kexec()
On Wed, Feb 06, 2008 at 11:00:01PM +0100, Ingo Molnar wrote:
* Neil Horman [EMAIL PROTECTED] wrote:
if (!user_mode_vm(regs)) {
+ nmi_exit();
+ local_irq_enable();
current-thread.trap_no = 2;
crash_kexec(regs);
looks good to me, but
* Vivek Goyal [EMAIL PROTECTED] wrote:
On Wed, Feb 06, 2008 at 11:00:01PM +0100, Ingo Molnar wrote:
* Neil Horman [EMAIL PROTECTED] wrote:
if (!user_mode_vm(regs)) {
+ nmi_exit();
+ local_irq_enable();
current-thread.trap_no = 2;
Vivek Goyal wrote:
I am wondering if interrupts are disabled on crashing cpu or if crashing
cpu is inside die_nmi(), how would it stop/prevent delivery of NMI IPI to
other cpus.
I don't see how it would.
-hpa
--
To unsubscribe from this list: send the line unsubscribe linux-kernel
* H. Peter Anvin [EMAIL PROTECTED] wrote:
I am wondering if interrupts are disabled on crashing cpu or if
crashing cpu is inside die_nmi(), how would it stop/prevent delivery
of NMI IPI to other cpus.
I don't see how it would.
cross-CPU IPIs are a bit fragile on some PC platforms. So if
Ingo Molnar [EMAIL PROTECTED] writes:
* H. Peter Anvin [EMAIL PROTECTED] wrote:
I am wondering if interrupts are disabled on crashing cpu or if
crashing cpu is inside die_nmi(), how would it stop/prevent delivery
of NMI IPI to other cpus.
I don't see how it would.
cross-CPU IPIs are a
* Eric W. Biederman [EMAIL PROTECTED] wrote:
Looking at the patch the local_irq_enable() is totally bogus. As soon
was we hit machine_crash_shutdown the first thing we do is disable
irqs.
yeah.
I'm wondering if someone was using the switch cpus on crash patch that
was floating around.
Ingo Molnar [EMAIL PROTECTED] writes:
* Eric W. Biederman [EMAIL PROTECTED] wrote:
Looking at the patch the local_irq_enable() is totally bogus. As soon
was we hit machine_crash_shutdown the first thing we do is disable
irqs.
yeah.
I'm wondering if someone was using the switch cpus on
45 matches
Mail list logo
