Re: [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops

Re: [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops

[Konrad Rzeszutek Wilk]

On Tue, Aug 29, 2017 at 11:46:35AM +0000, Yang Zhang wrote:
> So far, pv_idle_ops.poll is the only ops for pv_idle. .poll is called in
> idle path which will polling for a while before we enter the real idle
> state.
> 
> In virtualization, idle path includes several heavy operations
> includes timer access(LAPIC timer or TSC deadline timer) which will hurt
> performance especially for latency intensive workload like message
> passing task. The cost is mainly come from the vmexit which is a
> hardware context switch between VM and hypervisor. Our solution is to
> poll for a while and do not enter real idle path if we can get the
> schedule event during polling.
> 
> Poll may cause the CPU waste so we adopt a smart polling mechanism to
> reduce the useless poll.
> 
> Signed-off-by: Yang Zhang <yang.zhang.wz@gmail.com>
> Signed-off-by: Quan Xu <quan.xu0@gmail.com>
> Cc: Jeremy Fitzhardinge <jeremy@goop.org>
> Cc: Chris Wright <chrisw@sous-sol.org>
> Cc: Alok Kataria <akataria@vmware.com>
> Cc: Rusty Russell <rusty@rustcorp.com.au>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: "H. Peter Anvin" <hpa@zytor.com>
> Cc: x86@kernel.org
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Andy Lutomirski <luto@kernel.org>
> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
> Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
> Cc: Kees Cook <keescook@chromium.org>
> Cc: virtualization@lists.linux-foundation.org
> Cc: linux-kernel@vger.kernel.org

Adding xen-devel.

Juergen, we really should replace Jeremy's name with xen-devel or
your name.. Wasn't there an patch by you that took some of the 
mainternship over it?

> ---
>  arch/x86/include/asm/paravirt.h       | 5 +++++
>  arch/x86/include/asm/paravirt_types.h | 6 ++++++
>  arch/x86/kernel/paravirt.c            | 6 ++++++
>  3 files changed, 17 insertions(+)
> 
> diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
> index 9ccac19..6d46760 100644
> --- a/arch/x86/include/asm/paravirt.h
> +++ b/arch/x86/include/asm/paravirt.h
> @@ -202,6 +202,11 @@ static inline unsigned long long paravirt_read_pmc(int counter)
>  
>  #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
>  
> +static inline void paravirt_idle_poll(void)
> +{
> +	PVOP_VCALL0(pv_idle_ops.poll);
> +}
> +
>  static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
>  {
>  	PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
> diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
> index 9ffc36b..cf45726 100644
> --- a/arch/x86/include/asm/paravirt_types.h
> +++ b/arch/x86/include/asm/paravirt_types.h
> @@ -324,6 +324,10 @@ struct pv_lock_ops {
>  	struct paravirt_callee_save vcpu_is_preempted;
>  } __no_randomize_layout;
>  
> +struct pv_idle_ops {
> +	void (*poll)(void);
> +} __no_randomize_layout;
> +
>  /* This contains all the paravirt structures: we get a convenient
>   * number for each function using the offset which we use to indicate
>   * what to patch. */
> @@ -334,6 +338,7 @@ struct paravirt_patch_template {
>  	struct pv_irq_ops pv_irq_ops;
>  	struct pv_mmu_ops pv_mmu_ops;
>  	struct pv_lock_ops pv_lock_ops;
> +	struct pv_idle_ops pv_idle_ops;
>  } __no_randomize_layout;
>  
>  extern struct pv_info pv_info;
> @@ -343,6 +348,7 @@ struct paravirt_patch_template {
>  extern struct pv_irq_ops pv_irq_ops;
>  extern struct pv_mmu_ops pv_mmu_ops;
>  extern struct pv_lock_ops pv_lock_ops;
> +extern struct pv_idle_ops pv_idle_ops;
>  
>  #define PARAVIRT_PATCH(x)					\
>  	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
> index bc0a849..1b5b247 100644
> --- a/arch/x86/kernel/paravirt.c
> +++ b/arch/x86/kernel/paravirt.c
> @@ -128,6 +128,7 @@ static void *get_call_destination(u8 type)
>  #ifdef CONFIG_PARAVIRT_SPINLOCKS
>  		.pv_lock_ops = pv_lock_ops,
>  #endif
> +		.pv_idle_ops = pv_idle_ops,
>  	};
>  	return *((void **)&tmpl + type);
>  }
> @@ -312,6 +313,10 @@ struct pv_time_ops pv_time_ops = {
>  	.steal_clock = native_steal_clock,
>  };
>  
> +struct pv_idle_ops pv_idle_ops = {
> +	.poll = paravirt_nop,
> +};
> +
>  __visible struct pv_irq_ops pv_irq_ops = {
>  	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
>  	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
> @@ -471,3 +476,4 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
>  EXPORT_SYMBOL    (pv_mmu_ops);
>  EXPORT_SYMBOL_GPL(pv_info);
>  EXPORT_SYMBOL    (pv_irq_ops);
> +EXPORT_SYMBOL    (pv_idle_ops);
> -- 
> 1.8.3.1
> 

Re: [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops

[Juergen Gross]

On 29/08/17 15:55, Konrad Rzeszutek Wilk wrote:
> On Tue, Aug 29, 2017 at 11:46:35AM +0000, Yang Zhang wrote:
>> So far, pv_idle_ops.poll is the only ops for pv_idle. .poll is called in
>> idle path which will polling for a while before we enter the real idle
>> state.
>>
>> In virtualization, idle path includes several heavy operations
>> includes timer access(LAPIC timer or TSC deadline timer) which will hurt
>> performance especially for latency intensive workload like message
>> passing task. The cost is mainly come from the vmexit which is a
>> hardware context switch between VM and hypervisor. Our solution is to
>> poll for a while and do not enter real idle path if we can get the
>> schedule event during polling.
>>
>> Poll may cause the CPU waste so we adopt a smart polling mechanism to
>> reduce the useless poll.
>>
>> Signed-off-by: Yang Zhang <yang.zhang.wz@gmail.com>
>> Signed-off-by: Quan Xu <quan.xu0@gmail.com>
>> Cc: Jeremy Fitzhardinge <jeremy@goop.org>
>> Cc: Chris Wright <chrisw@sous-sol.org>
>> Cc: Alok Kataria <akataria@vmware.com>
>> Cc: Rusty Russell <rusty@rustcorp.com.au>
>> Cc: Thomas Gleixner <tglx@linutronix.de>
>> Cc: Ingo Molnar <mingo@redhat.com>
>> Cc: "H. Peter Anvin" <hpa@zytor.com>
>> Cc: x86@kernel.org
>> Cc: Peter Zijlstra <peterz@infradead.org>
>> Cc: Andy Lutomirski <luto@kernel.org>
>> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
>> Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
>> Cc: Kees Cook <keescook@chromium.org>
>> Cc: virtualization@lists.linux-foundation.org
>> Cc: linux-kernel@vger.kernel.org
> 
> Adding xen-devel.
> 
> Juergen, we really should replace Jeremy's name with xen-devel or
> your name..

I wouldn't mind being added. What does Jeremy think of being removed?

> Wasn't there an patch by you that took some of the 
> mainternship over it?

I added include/linux/hypervisor.h to the PARAVIRT section and offered
to maintain it in case the PARAVIRT maintainers didn't want to.


Juergen

Re: [RFC PATCH v2 1/7] x86/paravirt: Add pv_idle_ops to paravirt ops

[Yang Zhang]

On 2017/8/29 21:55, Konrad Rzeszutek Wilk wrote:
> On Tue, Aug 29, 2017 at 11:46:35AM +0000, Yang Zhang wrote:
>> So far, pv_idle_ops.poll is the only ops for pv_idle. .poll is called in
>> idle path which will polling for a while before we enter the real idle
>> state.
>>
>> In virtualization, idle path includes several heavy operations
>> includes timer access(LAPIC timer or TSC deadline timer) which will hurt
>> performance especially for latency intensive workload like message
>> passing task. The cost is mainly come from the vmexit which is a
>> hardware context switch between VM and hypervisor. Our solution is to
>> poll for a while and do not enter real idle path if we can get the
>> schedule event during polling.
>>
>> Poll may cause the CPU waste so we adopt a smart polling mechanism to
>> reduce the useless poll.
>>
>> Signed-off-by: Yang Zhang <yang.zhang.wz@gmail.com>
>> Signed-off-by: Quan Xu <quan.xu0@gmail.com>
>> Cc: Jeremy Fitzhardinge <jeremy@goop.org>
>> Cc: Chris Wright <chrisw@sous-sol.org>
>> Cc: Alok Kataria <akataria@vmware.com>
>> Cc: Rusty Russell <rusty@rustcorp.com.au>
>> Cc: Thomas Gleixner <tglx@linutronix.de>
>> Cc: Ingo Molnar <mingo@redhat.com>
>> Cc: "H. Peter Anvin" <hpa@zytor.com>
>> Cc: x86@kernel.org
>> Cc: Peter Zijlstra <peterz@infradead.org>
>> Cc: Andy Lutomirski <luto@kernel.org>
>> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
>> Cc: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
>> Cc: Kees Cook <keescook@chromium.org>
>> Cc: virtualization@lists.linux-foundation.org
>> Cc: linux-kernel@vger.kernel.org
> 
> Adding xen-devel.
> 
> Juergen, we really should replace Jeremy's name with xen-devel or
> your name.. Wasn't there an patch by you that took some of the
> mainternship over it?

Hi Konard, I didn't test it in Xen side since i don't have the 
environment but i can add it for Xen in next version if you think it is 
useful to Xen as well.

> 
>> ---
>>   arch/x86/include/asm/paravirt.h       | 5 +++++
>>   arch/x86/include/asm/paravirt_types.h | 6 ++++++
>>   arch/x86/kernel/paravirt.c            | 6 ++++++
>>   3 files changed, 17 insertions(+)
>>
>> diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
>> index 9ccac19..6d46760 100644
>> --- a/arch/x86/include/asm/paravirt.h
>> +++ b/arch/x86/include/asm/paravirt.h
>> @@ -202,6 +202,11 @@ static inline unsigned long long paravirt_read_pmc(int counter)
>>   
>>   #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
>>   
>> +static inline void paravirt_idle_poll(void)
>> +{
>> +	PVOP_VCALL0(pv_idle_ops.poll);
>> +}
>> +
>>   static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
>>   {
>>   	PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
>> diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
>> index 9ffc36b..cf45726 100644
>> --- a/arch/x86/include/asm/paravirt_types.h
>> +++ b/arch/x86/include/asm/paravirt_types.h
>> @@ -324,6 +324,10 @@ struct pv_lock_ops {
>>   	struct paravirt_callee_save vcpu_is_preempted;
>>   } __no_randomize_layout;
>>   
>> +struct pv_idle_ops {
>> +	void (*poll)(void);
>> +} __no_randomize_layout;
>> +
>>   /* This contains all the paravirt structures: we get a convenient
>>    * number for each function using the offset which we use to indicate
>>    * what to patch. */
>> @@ -334,6 +338,7 @@ struct paravirt_patch_template {
>>   	struct pv_irq_ops pv_irq_ops;
>>   	struct pv_mmu_ops pv_mmu_ops;
>>   	struct pv_lock_ops pv_lock_ops;
>> +	struct pv_idle_ops pv_idle_ops;
>>   } __no_randomize_layout;
>>   
>>   extern struct pv_info pv_info;
>> @@ -343,6 +348,7 @@ struct paravirt_patch_template {
>>   extern struct pv_irq_ops pv_irq_ops;
>>   extern struct pv_mmu_ops pv_mmu_ops;
>>   extern struct pv_lock_ops pv_lock_ops;
>> +extern struct pv_idle_ops pv_idle_ops;
>>   
>>   #define PARAVIRT_PATCH(x)					\
>>   	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
>> diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
>> index bc0a849..1b5b247 100644
>> --- a/arch/x86/kernel/paravirt.c
>> +++ b/arch/x86/kernel/paravirt.c
>> @@ -128,6 +128,7 @@ static void *get_call_destination(u8 type)
>>   #ifdef CONFIG_PARAVIRT_SPINLOCKS
>>   		.pv_lock_ops = pv_lock_ops,
>>   #endif
>> +		.pv_idle_ops = pv_idle_ops,
>>   	};
>>   	return *((void **)&tmpl + type);
>>   }
>> @@ -312,6 +313,10 @@ struct pv_time_ops pv_time_ops = {
>>   	.steal_clock = native_steal_clock,
>>   };
>>   
>> +struct pv_idle_ops pv_idle_ops = {
>> +	.poll = paravirt_nop,
>> +};
>> +
>>   __visible struct pv_irq_ops pv_irq_ops = {
>>   	.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
>>   	.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
>> @@ -471,3 +476,4 @@ struct pv_mmu_ops pv_mmu_ops __ro_after_init = {
>>   EXPORT_SYMBOL    (pv_mmu_ops);
>>   EXPORT_SYMBOL_GPL(pv_info);
>>   EXPORT_SYMBOL    (pv_irq_ops);
>> +EXPORT_SYMBOL    (pv_idle_ops);
>> -- 
>> 1.8.3.1
>>


-- 
Yang
Alibaba Cloud Computing