[PATCH] ACPI: processor: Fix CPU0 wakeup in acpi_idle_play_dead()

[PATCH] ACPI: processor: Fix CPU0 wakeup in acpi_idle_play_dead()

[Vitaly Kuznetsov]

Commit 496121c02127 ("ACPI: processor: idle: Allow probing on platforms
with one ACPI C-state") broke CPU0 hotplug on certain systems, e.g.
I'm observing the following on AWS Nitro (e.g r5b.xlarge but other
instance types are affected as well):

 # echo 0 > /sys/devices/system/cpu/cpu0/online
 # echo 1 > /sys/devices/system/cpu/cpu0/online
 <10 seconds delay>
 -bash: echo: write error: Input/output error

In fact, the above mentioned commit only revealed the problem and did
not introduce it. On x86, to wakeup CPU an NMI is being used and
hlt_play_dead()/mwait_play_dead() loops are prepared to handle it:

	/*
	 * If NMI wants to wake up CPU0, start CPU0.
	 */
	if (wakeup_cpu0())
		start_cpu0();

cpuidle_play_dead() -> acpi_idle_play_dead() (which is now being called on
systems where it wasn't called before the above mentioned commit) serves
the same purpose but it doesn't have a path for CPU0. What happens now on
wakeup is:
- NMI is sent to CPU0
- wakeup_cpu0_nmi() works as expected
- we get back to while (1) loop in acpi_idle_play_dead()
- safe_halt() puts CPU0 to sleep again.

The straightforward/minimal fix is add the special handling for CPU0 on x86
and that's what the patch is doing.

Fixes: 496121c02127 ("ACPI: processor: idle: Allow probing on platforms with one ACPI C-state")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/include/asm/smp.h    | 1 +
 arch/x86/kernel/smpboot.c     | 2 +-
 drivers/acpi/processor_idle.c | 7 +++++++
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index c0538f82c9a2..57ef2094af93 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -132,6 +132,7 @@ void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
+bool wakeup_cpu0(void);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 02813a7f3a7c..f877150a91da 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1659,7 +1659,7 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
-static bool wakeup_cpu0(void)
+bool wakeup_cpu0(void)
 {
 	if (smp_processor_id() == 0 && enable_start_cpu0)
 		return true;
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index d93e400940a3..eb1101b16c08 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -29,6 +29,7 @@
  */
 #ifdef CONFIG_X86
 #include <asm/apic.h>
+#include <asm/cpu.h>
 #endif
 
 #define _COMPONENT              ACPI_PROCESSOR_COMPONENT
@@ -541,6 +542,12 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
 			wait_for_freeze();
 		} else
 			return -ENODEV;
+
+#ifdef CONFIG_X86
+		/* If NMI wants to wake up CPU0, start CPU0. */
+		if (wakeup_cpu0())
+			start_cpu0();
+#endif
 	}
 
 	/* Never reached */
-- 
2.30.2

Re: [PATCH] ACPI: processor: Fix CPU0 wakeup in acpi_idle_play_dead()

[Rafael J. Wysocki]

On Wed, Mar 24, 2021 at 4:23 PM Vitaly Kuznetsov <vkuznets@redhat.com> wrote:
>
> Commit 496121c02127 ("ACPI: processor: idle: Allow probing on platforms
> with one ACPI C-state") broke CPU0 hotplug on certain systems, e.g.
> I'm observing the following on AWS Nitro (e.g r5b.xlarge but other
> instance types are affected as well):
>
>  # echo 0 > /sys/devices/system/cpu/cpu0/online
>  # echo 1 > /sys/devices/system/cpu/cpu0/online
>  <10 seconds delay>
>  -bash: echo: write error: Input/output error
>
> In fact, the above mentioned commit only revealed the problem and did
> not introduce it. On x86, to wakeup CPU an NMI is being used and
> hlt_play_dead()/mwait_play_dead() loops are prepared to handle it:
>
>         /*
>          * If NMI wants to wake up CPU0, start CPU0.
>          */
>         if (wakeup_cpu0())
>                 start_cpu0();
>
> cpuidle_play_dead() -> acpi_idle_play_dead() (which is now being called on
> systems where it wasn't called before the above mentioned commit) serves
> the same purpose but it doesn't have a path for CPU0. What happens now on
> wakeup is:
> - NMI is sent to CPU0
> - wakeup_cpu0_nmi() works as expected
> - we get back to while (1) loop in acpi_idle_play_dead()
> - safe_halt() puts CPU0 to sleep again.
>
> The straightforward/minimal fix is add the special handling for CPU0 on x86
> and that's what the patch is doing.
>
> Fixes: 496121c02127 ("ACPI: processor: idle: Allow probing on platforms with one ACPI C-state")
> Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>

This looks reasonable to me, but I'll give others some time to respond.

> ---
>  arch/x86/include/asm/smp.h    | 1 +
>  arch/x86/kernel/smpboot.c     | 2 +-
>  drivers/acpi/processor_idle.c | 7 +++++++
>  3 files changed, 9 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
> index c0538f82c9a2..57ef2094af93 100644
> --- a/arch/x86/include/asm/smp.h
> +++ b/arch/x86/include/asm/smp.h
> @@ -132,6 +132,7 @@ void native_play_dead(void);
>  void play_dead_common(void);
>  void wbinvd_on_cpu(int cpu);
>  int wbinvd_on_all_cpus(void);
> +bool wakeup_cpu0(void);
>
>  void native_smp_send_reschedule(int cpu);
>  void native_send_call_func_ipi(const struct cpumask *mask);
> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
> index 02813a7f3a7c..f877150a91da 100644
> --- a/arch/x86/kernel/smpboot.c
> +++ b/arch/x86/kernel/smpboot.c
> @@ -1659,7 +1659,7 @@ void play_dead_common(void)
>         local_irq_disable();
>  }
>
> -static bool wakeup_cpu0(void)
> +bool wakeup_cpu0(void)
>  {
>         if (smp_processor_id() == 0 && enable_start_cpu0)
>                 return true;
> diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
> index d93e400940a3..eb1101b16c08 100644
> --- a/drivers/acpi/processor_idle.c
> +++ b/drivers/acpi/processor_idle.c
> @@ -29,6 +29,7 @@
>   */
>  #ifdef CONFIG_X86
>  #include <asm/apic.h>
> +#include <asm/cpu.h>
>  #endif
>
>  #define _COMPONENT              ACPI_PROCESSOR_COMPONENT
> @@ -541,6 +542,12 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
>                         wait_for_freeze();
>                 } else
>                         return -ENODEV;
> +
> +#ifdef CONFIG_X86
> +               /* If NMI wants to wake up CPU0, start CPU0. */
> +               if (wakeup_cpu0())
> +                       start_cpu0();
> +#endif
>         }
>
>         /* Never reached */
> --
> 2.30.2
>

Re: [PATCH] ACPI: processor: Fix CPU0 wakeup in acpi_idle_play_dead()

[Rafael J. Wysocki]

On Wed, Mar 24, 2021 at 4:37 PM Rafael J. Wysocki <rafael@kernel.org> wrote:
>
> On Wed, Mar 24, 2021 at 4:23 PM Vitaly Kuznetsov <vkuznets@redhat.com> wrote:
> >
> > Commit 496121c02127 ("ACPI: processor: idle: Allow probing on platforms
> > with one ACPI C-state") broke CPU0 hotplug on certain systems, e.g.
> > I'm observing the following on AWS Nitro (e.g r5b.xlarge but other
> > instance types are affected as well):
> >
> >  # echo 0 > /sys/devices/system/cpu/cpu0/online
> >  # echo 1 > /sys/devices/system/cpu/cpu0/online
> >  <10 seconds delay>
> >  -bash: echo: write error: Input/output error
> >
> > In fact, the above mentioned commit only revealed the problem and did
> > not introduce it. On x86, to wakeup CPU an NMI is being used and
> > hlt_play_dead()/mwait_play_dead() loops are prepared to handle it:
> >
> >         /*
> >          * If NMI wants to wake up CPU0, start CPU0.
> >          */
> >         if (wakeup_cpu0())
> >                 start_cpu0();
> >
> > cpuidle_play_dead() -> acpi_idle_play_dead() (which is now being called on
> > systems where it wasn't called before the above mentioned commit) serves
> > the same purpose but it doesn't have a path for CPU0. What happens now on
> > wakeup is:
> > - NMI is sent to CPU0
> > - wakeup_cpu0_nmi() works as expected
> > - we get back to while (1) loop in acpi_idle_play_dead()
> > - safe_halt() puts CPU0 to sleep again.
> >
> > The straightforward/minimal fix is add the special handling for CPU0 on x86
> > and that's what the patch is doing.
> >
> > Fixes: 496121c02127 ("ACPI: processor: idle: Allow probing on platforms with one ACPI C-state")
> > Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
>
> This looks reasonable to me, but I'll give others some time to respond.

No comments, so applied as 5.12-rc material, thanks!

> > ---
> >  arch/x86/include/asm/smp.h    | 1 +
> >  arch/x86/kernel/smpboot.c     | 2 +-
> >  drivers/acpi/processor_idle.c | 7 +++++++
> >  3 files changed, 9 insertions(+), 1 deletion(-)
> >
> > diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
> > index c0538f82c9a2..57ef2094af93 100644
> > --- a/arch/x86/include/asm/smp.h
> > +++ b/arch/x86/include/asm/smp.h
> > @@ -132,6 +132,7 @@ void native_play_dead(void);
> >  void play_dead_common(void);
> >  void wbinvd_on_cpu(int cpu);
> >  int wbinvd_on_all_cpus(void);
> > +bool wakeup_cpu0(void);
> >
> >  void native_smp_send_reschedule(int cpu);
> >  void native_send_call_func_ipi(const struct cpumask *mask);
> > diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
> > index 02813a7f3a7c..f877150a91da 100644
> > --- a/arch/x86/kernel/smpboot.c
> > +++ b/arch/x86/kernel/smpboot.c
> > @@ -1659,7 +1659,7 @@ void play_dead_common(void)
> >         local_irq_disable();
> >  }
> >
> > -static bool wakeup_cpu0(void)
> > +bool wakeup_cpu0(void)
> >  {
> >         if (smp_processor_id() == 0 && enable_start_cpu0)
> >                 return true;
> > diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
> > index d93e400940a3..eb1101b16c08 100644
> > --- a/drivers/acpi/processor_idle.c
> > +++ b/drivers/acpi/processor_idle.c
> > @@ -29,6 +29,7 @@
> >   */
> >  #ifdef CONFIG_X86
> >  #include <asm/apic.h>
> > +#include <asm/cpu.h>
> >  #endif
> >
> >  #define _COMPONENT              ACPI_PROCESSOR_COMPONENT
> > @@ -541,6 +542,12 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index)
> >                         wait_for_freeze();
> >                 } else
> >                         return -ENODEV;
> > +
> > +#ifdef CONFIG_X86
> > +               /* If NMI wants to wake up CPU0, start CPU0. */
> > +               if (wakeup_cpu0())
> > +                       start_cpu0();
> > +#endif
> >         }
> >
> >         /* Never reached */
> > --
> > 2.30.2
> >