Re: [PATCH v5] KVM: halt-polling: poll for the upcoming fire timers

[Paolo Bonzini <pbonzini@redhat.com>]

On 25/05/2016 04:47, Wanpeng Li wrote:
> From: Wanpeng Li <wanpeng.li@hotmail.com>
> 
> If an emulated lapic timer will fire soon(in the scope of 10us the
> base of dynamic halt-polling, lower-end of message passing workload
> latency TCP_RR's poll time < 10us) we can treat it as a short halt,
> and poll to wait it fire, the fire callback apic_timer_fn() will set
> KVM_REQ_PENDING_TIMER, and this flag will be check during busy poll.
> This can avoid context switch overhead and the latency which we wake
> up vCPU.

As discussed on IRC, I would like to understand why the adaptive
adjustment of halt_poll_ns is failing.  It seems like you have so few
halts that you don't get halt_poll_ns>0.  Yet, when the VM halts, it's
very close to the timer tick---often enough for this patch to have an
effect.

Please send a trace of halt_poll_ns_grow and halt_poll_ns_shrink
tracepoints, so that we can find out more about this.

Thanks,

Paolo

> This feature is slightly different from current advance expiration 
> way. Advance expiration rely on the vCPU is running(do polling before 
> vmentry). But in some cases, the timer interrupt may be blocked by 
> other thread(i.e., IF bit is clear) and vCPU cannot be scheduled to 
> run immediately. So even advance the timer early, vCPU may still see 
> the latency. But polling is different, it ensures the vCPU to aware 
> the timer expiration before schedule out.
> 
> echo HRTICK > /sys/kernel/debug/sched_features in dynticks guests in 
> order to use high-res preemption tick. So task switch will trigger by 
> hrtimer fire in guests. halt_poll_ns_timer is set to 10000ns. 
> 
> Context switching - times in microseconds - smaller is better
> -------------------------------------------------------------------------
> Host                 OS  2p/0K 2p/16K 2p/64K 8p/16K 8p/64K 16p/16K 16p/64K
>                          ctxsw  ctxsw  ctxsw ctxsw  ctxsw   ctxsw   ctxsw
> --------- ------------- ------ ------ ------ ------ ------ ------- -------
> kernel     Linux 4.6.0+ 7.9800   11.0   10.8   14.6 9.4300    13.0    10.2 vanilla
> kernel     Linux 4.6.0+   15.3   13.6   10.7   12.5 9.0000    12.8 7.38000 poll
> 
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Radim Krčmář <rkrcmar@redhat.com>
> Cc: David Matlack <dmatlack@google.com>
> Cc: Christian Borntraeger <borntraeger@de.ibm.com>
> Cc: Yang Zhang <yang.zhang.wz@gmail.com>
> Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
> ---
> v4 -> v5:
>  * add module parameter halt_poll_ns_timer to enable/disable this feature
> v3 -> v4:
>  * add module parameter halt_poll_ns_timer
>  * rename patch subject since lapic maybe just for x86.
> v2 -> v3:
>  * add Yang's statement to patch description
> v1 -> v2:
>  * add return statement to non-x86 archs
>  * capture never expire case for x86 (hrtimer is not started)
> 
>  arch/arm/include/asm/kvm_host.h     |  4 ++++
>  arch/arm64/include/asm/kvm_host.h   |  4 ++++
>  arch/mips/include/asm/kvm_host.h    |  4 ++++
>  arch/powerpc/include/asm/kvm_host.h |  4 ++++
>  arch/s390/include/asm/kvm_host.h    |  4 ++++
>  arch/x86/kvm/lapic.c                | 11 +++++++++++
>  arch/x86/kvm/lapic.h                |  1 +
>  arch/x86/kvm/x86.c                  |  5 +++++
>  include/linux/kvm_host.h            |  1 +
>  virt/kvm/kvm_main.c                 | 13 ++++++++++---
>  10 files changed, 48 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
> index 0df6b1f..fdfbed9 100644
> --- a/arch/arm/include/asm/kvm_host.h
> +++ b/arch/arm/include/asm/kvm_host.h
> @@ -292,6 +292,10 @@ static inline void kvm_arch_sync_events(struct kvm *kvm) {}
>  static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
>  static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
>  static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
> +static inline u64 kvm_arch_timer_remaining(struct kvm_vcpu *vcpu)
> +{
> +	return -1ULL;
> +}
>  
>  static inline void kvm_arm_init_debug(void) {}
>  static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
> index e63d23b..f510d71 100644
> --- a/arch/arm64/include/asm/kvm_host.h
> +++ b/arch/arm64/include/asm/kvm_host.h
> @@ -371,6 +371,10 @@ static inline void kvm_arch_sync_events(struct kvm *kvm) {}
>  static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
>  static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
>  static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
> +static inline u64 kvm_arch_timer_remaining(struct kvm_vcpu *vcpu)
> +{
> +	return -1ULL;
> +}
>  
>  void kvm_arm_init_debug(void);
>  void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
> diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
> index 6733ac5..baf9472 100644
> --- a/arch/mips/include/asm/kvm_host.h
> +++ b/arch/mips/include/asm/kvm_host.h
> @@ -814,6 +814,10 @@ static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
>  static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
>  static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
>  static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
> +static inline u64 kvm_arch_timer_remaining(struct kvm_vcpu *vcpu)
> +{
> +	return -1ULL;
> +}
>  static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
>  
>  #endif /* __MIPS_KVM_HOST_H__ */
> diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
> index ec35af3..5986c79 100644
> --- a/arch/powerpc/include/asm/kvm_host.h
> +++ b/arch/powerpc/include/asm/kvm_host.h
> @@ -729,5 +729,9 @@ static inline void kvm_arch_exit(void) {}
>  static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
>  static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
>  static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
> +static inline u64 kvm_arch_timer_remaining(struct kvm_vcpu *vcpu)
> +{
> +	return -1ULL;
> +}
>  
>  #endif /* __POWERPC_KVM_HOST_H__ */
> diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
> index 37b9017..bdb01a1 100644
> --- a/arch/s390/include/asm/kvm_host.h
> +++ b/arch/s390/include/asm/kvm_host.h
> @@ -696,6 +696,10 @@ static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
>  		struct kvm_memory_slot *slot) {}
>  static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
>  static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
> +static inline u64 kvm_arch_timer_remaining(struct kvm_vcpu *vcpu)
> +{
> +	return -1ULL;
> +}
>  
>  void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu);
>  
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index bbb5b28..cfeeac3 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -256,6 +256,17 @@ static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic)
>  	return apic->lapic_timer.timer_mode == APIC_LVT_TIMER_TSCDEADLINE;
>  }
>  
> +u64 apic_get_timer_expire(struct kvm_vcpu *vcpu)
> +{
> +	struct kvm_lapic *apic = vcpu->arch.apic;
> +	struct hrtimer *timer = &apic->lapic_timer.timer;
> +
> +	if (!hrtimer_active(timer))
> +		return -1ULL;
> +	else
> +		return ktime_to_ns(hrtimer_get_remaining(timer));
> +}
> +
>  static inline int apic_lvt_nmi_mode(u32 lvt_val)
>  {
>  	return (lvt_val & (APIC_MODE_MASK | APIC_LVT_MASKED)) == APIC_DM_NMI;
> diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
> index 891c6da..ee4da6c 100644
> --- a/arch/x86/kvm/lapic.h
> +++ b/arch/x86/kvm/lapic.h
> @@ -212,4 +212,5 @@ bool kvm_intr_is_single_vcpu_fast(struct kvm *kvm, struct kvm_lapic_irq *irq,
>  			struct kvm_vcpu **dest_vcpu);
>  int kvm_vector_to_index(u32 vector, u32 dest_vcpus,
>  			const unsigned long *bitmap, u32 bitmap_size);
> +u64 apic_get_timer_expire(struct kvm_vcpu *vcpu);
>  #endif
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index c805cf4..1b89a68 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -7623,6 +7623,11 @@ bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
>  struct static_key kvm_no_apic_vcpu __read_mostly;
>  EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu);
>  
> +u64 kvm_arch_timer_remaining(struct kvm_vcpu *vcpu)
> +{
> +	return apic_get_timer_expire(vcpu);
> +}
> +
>  int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
>  {
>  	struct page *page;
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index b1fa8f1..14d6c23 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -663,6 +663,7 @@ int kvm_vcpu_yield_to(struct kvm_vcpu *target);
>  void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
>  void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
>  void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
> +u64 kvm_arch_timer_remaining(struct kvm_vcpu *vcpu);
>  
>  void kvm_flush_remote_tlbs(struct kvm *kvm);
>  void kvm_reload_remote_mmus(struct kvm *kvm);
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index dd4ac9d..4c1914a 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -78,6 +78,10 @@ module_param(halt_poll_ns_grow, uint, S_IRUGO | S_IWUSR);
>  static unsigned int halt_poll_ns_shrink;
>  module_param(halt_poll_ns_shrink, uint, S_IRUGO | S_IWUSR);
>  
> +/* lower-end of message passing workload latency TCP_RR's poll time < 10us */
> +static unsigned int halt_poll_ns_timer = 0;
> +module_param(halt_poll_ns_timer, uint, S_IRUGO | S_IWUSR);
> +
>  /*
>   * Ordering of locks:
>   *
> @@ -2014,12 +2018,15 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
>  	ktime_t start, cur;
>  	DECLARE_SWAITQUEUE(wait);
>  	bool waited = false;
> -	u64 block_ns;
> +	u64 block_ns, delta, remaining;
>  
> +	remaining = kvm_arch_timer_remaining(vcpu);
>  	start = cur = ktime_get();
> -	if (vcpu->halt_poll_ns) {
> -		ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
> +	if (vcpu->halt_poll_ns || remaining < halt_poll_ns_timer) {
> +		ktime_t stop;
>  
> +		delta = vcpu->halt_poll_ns ? vcpu->halt_poll_ns : remaining;
> +		stop = ktime_add_ns(ktime_get(), delta);
>  		++vcpu->stat.halt_attempted_poll;
>  		do {
>  			/*
>