Commit 2ed53c0d6cc9 ("x86/smpboot: Speed up suspend/resume by avoiding
100ms sleep for CPU offline during S3") introduced completions to CPU
offlining process. These completions are not initialized on Xen kernels
causing a panic in play_dead_common().
Move handling of die_complete into common routines to make them
available to Xen guests.
(Also, while at it, move these routines as well as die_complete under
ifdef CONFIG_HOTPLUG_CPU)
Signed-off-by: Boris Ostrovsky <[email protected]>
---
v2: Keep die_complete private to smpboot.c
arch/x86/include/asm/smp.h | 5 ++++-
arch/x86/kernel/smpboot.c | 13 +++++++++++--
arch/x86/xen/smp.c | 3 +++
3 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 8cd27e0..a78c509 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -149,7 +149,11 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
smp_ops.send_call_func_ipi(mask);
}
+#ifdef CONFIG_HOTPLUG_CPU
void cpu_disable_common(void);
+void cpu_die_common(unsigned int cpu);
+void play_dead_common(void);
+#endif
void native_smp_prepare_boot_cpu(void);
void native_smp_prepare_cpus(unsigned int max_cpus);
void native_smp_cpus_done(unsigned int max_cpus);
@@ -157,7 +161,6 @@ int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
int native_cpu_disable(void);
void native_cpu_die(unsigned int cpu);
void native_play_dead(void);
-void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
int wbinvd_on_all_cpus(void);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 2d5200e..6fe0fc1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -102,7 +102,9 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
EXPORT_PER_CPU_SYMBOL(cpu_info);
+#ifdef CONFIG_HOTPLUG_CPU
static DEFINE_PER_CPU(struct completion, die_complete);
+#endif
atomic_t init_deasserted;
@@ -1309,6 +1311,8 @@ void cpu_disable_common(void)
{
int cpu = smp_processor_id();
+ init_completion(&per_cpu(die_complete, smp_processor_id()));
+
remove_siblinginfo(cpu);
/* It's now safe to remove this processor from the online map */
@@ -1327,16 +1331,21 @@ int native_cpu_disable(void)
return ret;
clear_local_APIC();
- init_completion(&per_cpu(die_complete, smp_processor_id()));
cpu_disable_common();
return 0;
}
+void cpu_die_common(unsigned int cpu)
+{
+ wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
+}
+
void native_cpu_die(unsigned int cpu)
{
/* We don't do anything here: idle task is faking death itself. */
- wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
+
+ cpu_die_common(cpu);
/* They ack this in play_dead() by setting CPU_DEAD */
if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8650cdb..4c071ae 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -510,6 +510,9 @@ static void xen_cpu_die(unsigned int cpu)
current->state = TASK_UNINTERRUPTIBLE;
schedule_timeout(HZ/10);
}
+
+ cpu_die_common(cpu);
+
xen_smp_intr_free(cpu);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
--
1.8.1.4
On 16/10/14 17:47, Boris Ostrovsky wrote:
> Commit 2ed53c0d6cc9 ("x86/smpboot: Speed up suspend/resume by avoiding
> 100ms sleep for CPU offline during S3") introduced completions to CPU
> offlining process. These completions are not initialized on Xen kernels
> causing a panic in play_dead_common().
>
> Move handling of die_complete into common routines to make them
> available to Xen guests.
>
> (Also, while at it, move these routines as well as die_complete under
> ifdef CONFIG_HOTPLUG_CPU)
Reviewed-by: David Vrabel <[email protected]>
I can merge this via the Xen tree if that is preferred.
David
> --- a/arch/x86/include/asm/smp.h
> +++ b/arch/x86/include/asm/smp.h
> @@ -149,7 +149,11 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
> smp_ops.send_call_func_ipi(mask);
> }
>
> +#ifdef CONFIG_HOTPLUG_CPU
> void cpu_disable_common(void);
> +void cpu_die_common(unsigned int cpu);
> +void play_dead_common(void);
> +#endif
> void native_smp_prepare_boot_cpu(void);
> void native_smp_prepare_cpus(unsigned int max_cpus);
> void native_smp_cpus_done(unsigned int max_cpus);
> @@ -157,7 +161,6 @@ int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
> int native_cpu_disable(void);
> void native_cpu_die(unsigned int cpu);
> void native_play_dead(void);
> -void play_dead_common(void);
> void wbinvd_on_cpu(int cpu);
> int wbinvd_on_all_cpus(void);
>
> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
> index 2d5200e..6fe0fc1 100644
> --- a/arch/x86/kernel/smpboot.c
> +++ b/arch/x86/kernel/smpboot.c
> @@ -102,7 +102,9 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
> DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
> EXPORT_PER_CPU_SYMBOL(cpu_info);
>
> +#ifdef CONFIG_HOTPLUG_CPU
> static DEFINE_PER_CPU(struct completion, die_complete);
> +#endif
>
> atomic_t init_deasserted;
>
> @@ -1309,6 +1311,8 @@ void cpu_disable_common(void)
> {
> int cpu = smp_processor_id();
>
> + init_completion(&per_cpu(die_complete, smp_processor_id()));
> +
> remove_siblinginfo(cpu);
>
> /* It's now safe to remove this processor from the online map */
> @@ -1327,16 +1331,21 @@ int native_cpu_disable(void)
> return ret;
>
> clear_local_APIC();
> - init_completion(&per_cpu(die_complete, smp_processor_id()));
> cpu_disable_common();
>
> return 0;
> }
>
> +void cpu_die_common(unsigned int cpu)
> +{
> + wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
> +}
> +
> void native_cpu_die(unsigned int cpu)
> {
> /* We don't do anything here: idle task is faking death itself. */
> - wait_for_completion_timeout(&per_cpu(die_complete, cpu), HZ);
> +
> + cpu_die_common(cpu);
>
> /* They ack this in play_dead() by setting CPU_DEAD */
> if (per_cpu(cpu_state, cpu) == CPU_DEAD) {
> diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
> index 8650cdb..4c071ae 100644
> --- a/arch/x86/xen/smp.c
> +++ b/arch/x86/xen/smp.c
> @@ -510,6 +510,9 @@ static void xen_cpu_die(unsigned int cpu)
> current->state = TASK_UNINTERRUPTIBLE;
> schedule_timeout(HZ/10);
> }
> +
> + cpu_die_common(cpu);
> +
> xen_smp_intr_free(cpu);
> xen_uninit_lock_cpu(cpu);
> xen_teardown_timer(cpu);
>
On 10/22/2014 08:32 AM, David Vrabel wrote:
> On 16/10/14 17:47, Boris Ostrovsky wrote:
>> Commit 2ed53c0d6cc9 ("x86/smpboot: Speed up suspend/resume by avoiding
>> 100ms sleep for CPU offline during S3") introduced completions to CPU
>> offlining process. These completions are not initialized on Xen kernels
>> causing a panic in play_dead_common().
>>
>> Move handling of die_complete into common routines to make them
>> available to Xen guests.
>>
>> (Also, while at it, move these routines as well as die_complete under
>> ifdef CONFIG_HOTPLUG_CPU)
>
> Reviewed-by: David Vrabel <[email protected]>
>
> I can merge this via the Xen tree if that is preferred.
>
Since it touches non-Xen code I'd rather not.
-hpa
On 10/16/2014 09:47 AM, Boris Ostrovsky wrote:
> diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
> index 8cd27e0..a78c509 100644
> --- a/arch/x86/include/asm/smp.h
> +++ b/arch/x86/include/asm/smp.h
> @@ -149,7 +149,11 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
> smp_ops.send_call_func_ipi(mask);
> }
>
> +#ifdef CONFIG_HOTPLUG_CPU
> void cpu_disable_common(void);
> +void cpu_die_common(unsigned int cpu);
> +void play_dead_common(void);
> +#endif
We generally don't #ifdef prototypes unless they are inlines or macros
in the unconfiged case.
-hpa
On 10/22/2014 11:37 AM, H. Peter Anvin wrote:
> On 10/16/2014 09:47 AM, Boris Ostrovsky wrote:
>> diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
>> index 8cd27e0..a78c509 100644
>> --- a/arch/x86/include/asm/smp.h
>> +++ b/arch/x86/include/asm/smp.h
>> @@ -149,7 +149,11 @@ static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
>> smp_ops.send_call_func_ipi(mask);
>> }
>>
>> +#ifdef CONFIG_HOTPLUG_CPU
>> void cpu_disable_common(void);
>> +void cpu_die_common(unsigned int cpu);
>> +void play_dead_common(void);
>> +#endif
> We generally don't #ifdef prototypes unless they are inlines or macros
> in the unconfiged case.
OK, I'll resend with these ifdefs removed.
Thanks.
-boris