[PATCH] KVM: LAPIC: Tune lapic_timer_advance_ns automatically

[PATCH] KVM: LAPIC: Tune lapic_timer_advance_ns automatically

[Wanpeng Li]

From: Wanpeng Li <wanpengli@tencent.com>

In cloud environment, lapic_timer_advance_ns is needed to be tuned for every CPU 
generations, and every host kernel versions(the kvm-unit-tests/tscdeadline_latency.flat 
is 5700 cycles for upstream kernel and 9600 cycles for our 3.10 product kernel, 
both preemption_timer=N, Skylake server).

This patch adds the capability to automatically tune lapic_timer_advance_ns
step by step, the initial value is 1000ns as d0659d946be05 (KVM: x86: add 
option to advance tscdeadline hrtimer expiration) recommended, it will be 
reduced when it is too early, and increased when it is too late. The guest_tsc 
and tsc_deadline are hard to equal, so we assume we are done when the delta 
is within a small scope e.g. 100 cycles. This patch reduces latency 
(kvm-unit-tests/tscdeadline_latency, busy waits, preemption_timer enabled)
from ~2600 cyles to ~1200 cyles on our Skylake server.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
 arch/x86/kvm/lapic.c | 7 +++++++
 arch/x86/kvm/x86.c   | 2 +-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index fbb0e6d..b756f12 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -70,6 +70,8 @@
 #define APIC_BROADCAST			0xFF
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
+static bool __read_mostly lapic_timer_advance_adjust_done = false;
+
 static inline int apic_test_vector(int vec, void *bitmap)
 {
 	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -1492,6 +1494,11 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 	if (guest_tsc < tsc_deadline)
 		__delay(min(tsc_deadline - guest_tsc,
 			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+	if (!lapic_timer_advance_adjust_done) {
+		lapic_timer_advance_ns += (s64)(guest_tsc - tsc_deadline) / 8;
+		if (abs(guest_tsc - tsc_deadline) < 100)
+			lapic_timer_advance_adjust_done = true;
+	}
 }
 
 static void start_sw_tscdeadline(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index edbf00e..e865d12 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,7 +136,7 @@ static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
 /* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 0;
+unsigned int lapic_timer_advance_ns = 1000;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
 EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
 
-- 
2.7.4

Re: [PATCH] KVM: LAPIC: Tune lapic_timer_advance_ns automatically

[Paolo Bonzini]

On 28/09/2018 08:12, Wanpeng Li wrote:
> From: Wanpeng Li <wanpengli@tencent.com>
> 
> In cloud environment, lapic_timer_advance_ns is needed to be tuned for every CPU 
> generations, and every host kernel versions(the kvm-unit-tests/tscdeadline_latency.flat 
> is 5700 cycles for upstream kernel and 9600 cycles for our 3.10 product kernel, 
> both preemption_timer=N, Skylake server).
> 
> This patch adds the capability to automatically tune lapic_timer_advance_ns
> step by step, the initial value is 1000ns as d0659d946be05 (KVM: x86: add 
> option to advance tscdeadline hrtimer expiration) recommended, it will be 
> reduced when it is too early, and increased when it is too late. The guest_tsc 
> and tsc_deadline are hard to equal, so we assume we are done when the delta 
> is within a small scope e.g. 100 cycles. This patch reduces latency 
> (kvm-unit-tests/tscdeadline_latency, busy waits, preemption_timer enabled)
> from ~2600 cyles to ~1200 cyles on our Skylake server.
> 
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Radim Krčmář <rkrcmar@redhat.com>
> Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> ---
>  arch/x86/kvm/lapic.c | 7 +++++++
>  arch/x86/kvm/x86.c   | 2 +-
>  2 files changed, 8 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index fbb0e6d..b756f12 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -70,6 +70,8 @@
>  #define APIC_BROADCAST			0xFF
>  #define X2APIC_BROADCAST		0xFFFFFFFFul
>  
> +static bool __read_mostly lapic_timer_advance_adjust_done = false;
> +
>  static inline int apic_test_vector(int vec, void *bitmap)
>  {
>  	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
> @@ -1492,6 +1494,11 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
>  	if (guest_tsc < tsc_deadline)
>  		__delay(min(tsc_deadline - guest_tsc,
>  			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
> +	if (!lapic_timer_advance_adjust_done) {
> +		lapic_timer_advance_ns += (s64)(guest_tsc - tsc_deadline) / 8;
> +		if (abs(guest_tsc - tsc_deadline) < 100)
> +			lapic_timer_advance_adjust_done = true;
> +	}
>  }
>  
>  static void start_sw_tscdeadline(struct kvm_lapic *apic)
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index edbf00e..e865d12 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -136,7 +136,7 @@ static u32 __read_mostly tsc_tolerance_ppm = 250;
>  module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
>  
>  /* lapic timer advance (tscdeadline mode only) in nanoseconds */
> -unsigned int __read_mostly lapic_timer_advance_ns = 0;
> +unsigned int lapic_timer_advance_ns = 1000;
>  module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
>  EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
>  
> 

Queued, thanks.

Paolo

Re: [PATCH] KVM: LAPIC: Tune lapic_timer_advance_ns automatically

[Liran Alon]

> On 28 Sep 2018, at 9:12, Wanpeng Li <kernellwp@gmail.com> wrote:
> 
> From: Wanpeng Li <wanpengli@tencent.com>
> 
> In cloud environment, lapic_timer_advance_ns is needed to be tuned for every CPU 
> generations, and every host kernel versions(the kvm-unit-tests/tscdeadline_latency.flat 
> is 5700 cycles for upstream kernel and 9600 cycles for our 3.10 product kernel, 
> both preemption_timer=N, Skylake server).
> 
> This patch adds the capability to automatically tune lapic_timer_advance_ns
> step by step, the initial value is 1000ns as d0659d946be05 (KVM: x86: add 
> option to advance tscdeadline hrtimer expiration) recommended, it will be 
> reduced when it is too early, and increased when it is too late. The guest_tsc 
> and tsc_deadline are hard to equal, so we assume we are done when the delta 
> is within a small scope e.g. 100 cycles. This patch reduces latency 
> (kvm-unit-tests/tscdeadline_latency, busy waits, preemption_timer enabled)
> from ~2600 cyles to ~1200 cyles on our Skylake server.
> 
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Radim Krčmář <rkrcmar@redhat.com>
> Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> ---
> arch/x86/kvm/lapic.c | 7 +++++++
> arch/x86/kvm/x86.c   | 2 +-
> 2 files changed, 8 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index fbb0e6d..b756f12 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -70,6 +70,8 @@
> #define APIC_BROADCAST			0xFF
> #define X2APIC_BROADCAST		0xFFFFFFFFul
> 
> +static bool __read_mostly lapic_timer_advance_adjust_done = false;
> +
> static inline int apic_test_vector(int vec, void *bitmap)
> {
> 	return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
> @@ -1492,6 +1494,11 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
> 	if (guest_tsc < tsc_deadline)
> 		__delay(min(tsc_deadline - guest_tsc,
> 			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
> +	if (!lapic_timer_advance_adjust_done) {
> +		lapic_timer_advance_ns += (s64)(guest_tsc - tsc_deadline) / 8;

I don’t understand how this “/ 8” converts between guest TSC units to host nanoseconds.

I think that instead you should do something like:
s64 ns = (s64)(guest_tsc - tsc_deadline) * 1000000ULL;
do_div(ns, vcpu->arch.virtual_tsc_khz);
lapic_timer_advance_ns += ns;

> +		if (abs(guest_tsc - tsc_deadline) < 100)

I would put this “100” hard-coded value as some “#define” to make code more clear.

> +			lapic_timer_advance_adjust_done = true;
> +	}
> }
> 
> static void start_sw_tscdeadline(struct kvm_lapic *apic)
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index edbf00e..e865d12 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -136,7 +136,7 @@ static u32 __read_mostly tsc_tolerance_ppm = 250;
> module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
> 
> /* lapic timer advance (tscdeadline mode only) in nanoseconds */
> -unsigned int __read_mostly lapic_timer_advance_ns = 0;
> +unsigned int lapic_timer_advance_ns = 1000;
> module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
> EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
> 
> -- 
> 2.7.4
> 

Re: [PATCH] KVM: LAPIC: Tune lapic_timer_advance_ns automatically

[Wanpeng Li]

On Mon, 8 Oct 2018 at 05:02, Liran Alon <liran.alon@oracle.com> wrote:
>
>
>
> > On 28 Sep 2018, at 9:12, Wanpeng Li <kernellwp@gmail.com> wrote:
> >
> > From: Wanpeng Li <wanpengli@tencent.com>
> >
> > In cloud environment, lapic_timer_advance_ns is needed to be tuned for every CPU
> > generations, and every host kernel versions(the kvm-unit-tests/tscdeadline_latency.flat
> > is 5700 cycles for upstream kernel and 9600 cycles for our 3.10 product kernel,
> > both preemption_timer=N, Skylake server).
> >
> > This patch adds the capability to automatically tune lapic_timer_advance_ns
> > step by step, the initial value is 1000ns as d0659d946be05 (KVM: x86: add
> > option to advance tscdeadline hrtimer expiration) recommended, it will be
> > reduced when it is too early, and increased when it is too late. The guest_tsc
> > and tsc_deadline are hard to equal, so we assume we are done when the delta
> > is within a small scope e.g. 100 cycles. This patch reduces latency
> > (kvm-unit-tests/tscdeadline_latency, busy waits, preemption_timer enabled)
> > from ~2600 cyles to ~1200 cyles on our Skylake server.
> >
> > Cc: Paolo Bonzini <pbonzini@redhat.com>
> > Cc: Radim Krčmář <rkrcmar@redhat.com>
> > Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> > ---
> > arch/x86/kvm/lapic.c | 7 +++++++
> > arch/x86/kvm/x86.c   | 2 +-
> > 2 files changed, 8 insertions(+), 1 deletion(-)
> >
> > diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> > index fbb0e6d..b756f12 100644
> > --- a/arch/x86/kvm/lapic.c
> > +++ b/arch/x86/kvm/lapic.c
> > @@ -70,6 +70,8 @@
> > #define APIC_BROADCAST                        0xFF
> > #define X2APIC_BROADCAST              0xFFFFFFFFul
> >
> > +static bool __read_mostly lapic_timer_advance_adjust_done = false;
> > +
> > static inline int apic_test_vector(int vec, void *bitmap)
> > {
> >       return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
> > @@ -1492,6 +1494,11 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
> >       if (guest_tsc < tsc_deadline)
> >               __delay(min(tsc_deadline - guest_tsc,
> >                       nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
> > +     if (!lapic_timer_advance_adjust_done) {
> > +             lapic_timer_advance_ns += (s64)(guest_tsc - tsc_deadline) / 8;
>
> I don’t understand how this “/ 8” converts between guest TSC units to host nanoseconds.

Oh, I miss it. In addition, /8 here I mean adjust
lapic_timer_advance_ns step by step. I can observe big fluctuated
value between early and late when running real guest os like linux
instead of kvm-unit-tests. After more testing, I saw
lapic_timer_advance_ns can be overflow since the delta between
guest_tsc and tsc_deadline is too huge.

>
> I think that instead you should do something like:
> s64 ns = (s64)(guest_tsc - tsc_deadline) * 1000000ULL;
> do_div(ns, vcpu->arch.virtual_tsc_khz);
> lapic_timer_advance_ns += ns;
>
> > +             if (abs(guest_tsc - tsc_deadline) < 100)
>
> I would put this “100” hard-coded value as some “#define” to make code more clear.

How about something like below:

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index fbb0e6d..354eb13c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -70,6 +70,9 @@
 #define APIC_BROADCAST            0xFF
 #define X2APIC_BROADCAST        0xFFFFFFFFul

+static bool __read_mostly lapic_timer_advance_adjust_done = false;
+#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
+
 static inline int apic_test_vector(int vec, void *bitmap)
 {
     return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -1472,7 +1475,7 @@ static bool lapic_timer_int_injected(struct
kvm_vcpu *vcpu)
 void wait_lapic_expire(struct kvm_vcpu *vcpu)
 {
     struct kvm_lapic *apic = vcpu->arch.apic;
-    u64 guest_tsc, tsc_deadline;
+    u64 guest_tsc, tsc_deadline, ns;

     if (!lapic_in_kernel(vcpu))
         return;
@@ -1492,6 +1495,19 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
     if (guest_tsc < tsc_deadline)
         __delay(min(tsc_deadline - guest_tsc,
             nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+    if (!lapic_timer_advance_adjust_done) {
+        if (guest_tsc < tsc_deadline) {
+            ns = (tsc_deadline - guest_tsc) * 1000000ULL;
+            do_div(ns, vcpu->arch.virtual_tsc_khz);
+            lapic_timer_advance_ns -= min((unsigned int)ns,
lapic_timer_advance_ns / 8);
+        } else {
+            ns = (guest_tsc - tsc_deadline) * 1000000ULL;
+            do_div(ns, vcpu->arch.virtual_tsc_khz);
+            lapic_timer_advance_ns += min((unsigned int)ns,
lapic_timer_advance_ns / 8);
+        }
+        if (ns < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
+            lapic_timer_advance_adjust_done = true;
+    }
 }

 static void start_sw_tscdeadline(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ca71773..1f3f955 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,7 +136,7 @@ static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);

 /* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 0;
+unsigned int __read_mostly lapic_timer_advance_ns = 1000;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
 EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);

Re: [PATCH] KVM: LAPIC: Tune lapic_timer_advance_ns automatically

[Liran Alon]

> On 8 Oct 2018, at 13:59, Wanpeng Li <kernellwp@gmail.com> wrote:
> 
> On Mon, 8 Oct 2018 at 05:02, Liran Alon <liran.alon@oracle.com> wrote:
>> 
>> 
>> 
>>> On 28 Sep 2018, at 9:12, Wanpeng Li <kernellwp@gmail.com> wrote:
>>> 
>>> From: Wanpeng Li <wanpengli@tencent.com>
>>> 
>>> In cloud environment, lapic_timer_advance_ns is needed to be tuned for every CPU
>>> generations, and every host kernel versions(the kvm-unit-tests/tscdeadline_latency.flat
>>> is 5700 cycles for upstream kernel and 9600 cycles for our 3.10 product kernel,
>>> both preemption_timer=N, Skylake server).
>>> 
>>> This patch adds the capability to automatically tune lapic_timer_advance_ns
>>> step by step, the initial value is 1000ns as d0659d946be05 (KVM: x86: add
>>> option to advance tscdeadline hrtimer expiration) recommended, it will be
>>> reduced when it is too early, and increased when it is too late. The guest_tsc
>>> and tsc_deadline are hard to equal, so we assume we are done when the delta
>>> is within a small scope e.g. 100 cycles. This patch reduces latency
>>> (kvm-unit-tests/tscdeadline_latency, busy waits, preemption_timer enabled)
>>> from ~2600 cyles to ~1200 cyles on our Skylake server.
>>> 
>>> Cc: Paolo Bonzini <pbonzini@redhat.com>
>>> Cc: Radim Krčmář <rkrcmar@redhat.com>
>>> Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
>>> ---
>>> arch/x86/kvm/lapic.c | 7 +++++++
>>> arch/x86/kvm/x86.c   | 2 +-
>>> 2 files changed, 8 insertions(+), 1 deletion(-)
>>> 
>>> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
>>> index fbb0e6d..b756f12 100644
>>> --- a/arch/x86/kvm/lapic.c
>>> +++ b/arch/x86/kvm/lapic.c
>>> @@ -70,6 +70,8 @@
>>> #define APIC_BROADCAST                        0xFF
>>> #define X2APIC_BROADCAST              0xFFFFFFFFul
>>> 
>>> +static bool __read_mostly lapic_timer_advance_adjust_done = false;
>>> +
>>> static inline int apic_test_vector(int vec, void *bitmap)
>>> {
>>>      return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
>>> @@ -1492,6 +1494,11 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
>>>      if (guest_tsc < tsc_deadline)
>>>              __delay(min(tsc_deadline - guest_tsc,
>>>                      nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
>>> +     if (!lapic_timer_advance_adjust_done) {
>>> +             lapic_timer_advance_ns += (s64)(guest_tsc - tsc_deadline) / 8;
>> 
>> I don’t understand how this “/ 8” converts between guest TSC units to host nanoseconds.
> 
> Oh, I miss it. In addition, /8 here I mean adjust
> lapic_timer_advance_ns step by step. I can observe big fluctuated

If that’s the case, I would also put the “8” as a #define to make it more clear of it’s purpose.

> value between early and late when running real guest os like linux
> instead of kvm-unit-tests. After more testing, I saw
> lapic_timer_advance_ns can be overflow since the delta between
> guest_tsc and tsc_deadline is too huge.
> 
>> 
>> I think that instead you should do something like:
>> s64 ns = (s64)(guest_tsc - tsc_deadline) * 1000000ULL;
>> do_div(ns, vcpu->arch.virtual_tsc_khz);
>> lapic_timer_advance_ns += ns;
>> 
>>> +             if (abs(guest_tsc - tsc_deadline) < 100)
>> 
>> I would put this “100” hard-coded value as some “#define” to make code more clear.
> 
> How about something like below:
> 
> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> index fbb0e6d..354eb13c 100644
> --- a/arch/x86/kvm/lapic.c
> +++ b/arch/x86/kvm/lapic.c
> @@ -70,6 +70,9 @@
> #define APIC_BROADCAST            0xFF
> #define X2APIC_BROADCAST        0xFFFFFFFFul
> 
> +static bool __read_mostly lapic_timer_advance_adjust_done = false;
> +#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
> +
> static inline int apic_test_vector(int vec, void *bitmap)
> {
>     return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
> @@ -1472,7 +1475,7 @@ static bool lapic_timer_int_injected(struct
> kvm_vcpu *vcpu)
> void wait_lapic_expire(struct kvm_vcpu *vcpu)
> {
>     struct kvm_lapic *apic = vcpu->arch.apic;
> -    u64 guest_tsc, tsc_deadline;
> +    u64 guest_tsc, tsc_deadline, ns;
> 
>     if (!lapic_in_kernel(vcpu))
>         return;
> @@ -1492,6 +1495,19 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
>     if (guest_tsc < tsc_deadline)
>         __delay(min(tsc_deadline - guest_tsc,
>             nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
> +    if (!lapic_timer_advance_adjust_done) {
> +        if (guest_tsc < tsc_deadline) {
> +            ns = (tsc_deadline - guest_tsc) * 1000000ULL;
> +            do_div(ns, vcpu->arch.virtual_tsc_khz);
> +            lapic_timer_advance_ns -= min((unsigned int)ns,
> lapic_timer_advance_ns / 8);
> +        } else {
> +            ns = (guest_tsc - tsc_deadline) * 1000000ULL;
> +            do_div(ns, vcpu->arch.virtual_tsc_khz);
> +            lapic_timer_advance_ns += min((unsigned int)ns,
> lapic_timer_advance_ns / 8);
> +        }
> +        if (ns < LAPIC_TIMER_ADVANCE_ADJUST_DONE)

Didn’t you meant to compare here that abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE?
This is also a good example on why I would also rename LAPIC_TIMER_ADVANCE_ADJUST_DONE to something
which indicates it represents a number in guest TSC units.

> +            lapic_timer_advance_adjust_done = true;
> +    }
> }
> 
> static void start_sw_tscdeadline(struct kvm_lapic *apic)
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index ca71773..1f3f955 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -136,7 +136,7 @@ static u32 __read_mostly tsc_tolerance_ppm = 250;
> module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
> 
> /* lapic timer advance (tscdeadline mode only) in nanoseconds */
> -unsigned int __read_mostly lapic_timer_advance_ns = 0;
> +unsigned int __read_mostly lapic_timer_advance_ns = 1000;
> module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
> EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);

Re: [PATCH] KVM: LAPIC: Tune lapic_timer_advance_ns automatically

[Wanpeng Li]

On Mon, 8 Oct 2018 at 20:04, Liran Alon <liran.alon@oracle.com> wrote:
>
>
>
> > On 8 Oct 2018, at 13:59, Wanpeng Li <kernellwp@gmail.com> wrote:
> >
> > On Mon, 8 Oct 2018 at 05:02, Liran Alon <liran.alon@oracle.com> wrote:
> >>
> >>
> >>
> >>> On 28 Sep 2018, at 9:12, Wanpeng Li <kernellwp@gmail.com> wrote:
> >>>
> >>> From: Wanpeng Li <wanpengli@tencent.com>
> >>>
> >>> In cloud environment, lapic_timer_advance_ns is needed to be tuned for every CPU
> >>> generations, and every host kernel versions(the kvm-unit-tests/tscdeadline_latency.flat
> >>> is 5700 cycles for upstream kernel and 9600 cycles for our 3.10 product kernel,
> >>> both preemption_timer=N, Skylake server).
> >>>
> >>> This patch adds the capability to automatically tune lapic_timer_advance_ns
> >>> step by step, the initial value is 1000ns as d0659d946be05 (KVM: x86: add
> >>> option to advance tscdeadline hrtimer expiration) recommended, it will be
> >>> reduced when it is too early, and increased when it is too late. The guest_tsc
> >>> and tsc_deadline are hard to equal, so we assume we are done when the delta
> >>> is within a small scope e.g. 100 cycles. This patch reduces latency
> >>> (kvm-unit-tests/tscdeadline_latency, busy waits, preemption_timer enabled)
> >>> from ~2600 cyles to ~1200 cyles on our Skylake server.
> >>>
> >>> Cc: Paolo Bonzini <pbonzini@redhat.com>
> >>> Cc: Radim Krčmář <rkrcmar@redhat.com>
> >>> Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
> >>> ---
> >>> arch/x86/kvm/lapic.c | 7 +++++++
> >>> arch/x86/kvm/x86.c   | 2 +-
> >>> 2 files changed, 8 insertions(+), 1 deletion(-)
> >>>
> >>> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> >>> index fbb0e6d..b756f12 100644
> >>> --- a/arch/x86/kvm/lapic.c
> >>> +++ b/arch/x86/kvm/lapic.c
> >>> @@ -70,6 +70,8 @@
> >>> #define APIC_BROADCAST                        0xFF
> >>> #define X2APIC_BROADCAST              0xFFFFFFFFul
> >>>
> >>> +static bool __read_mostly lapic_timer_advance_adjust_done = false;
> >>> +
> >>> static inline int apic_test_vector(int vec, void *bitmap)
> >>> {
> >>>      return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
> >>> @@ -1492,6 +1494,11 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
> >>>      if (guest_tsc < tsc_deadline)
> >>>              __delay(min(tsc_deadline - guest_tsc,
> >>>                      nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
> >>> +     if (!lapic_timer_advance_adjust_done) {
> >>> +             lapic_timer_advance_ns += (s64)(guest_tsc - tsc_deadline) / 8;
> >>
> >> I don’t understand how this “/ 8” converts between guest TSC units to host nanoseconds.
> >
> > Oh, I miss it. In addition, /8 here I mean adjust
> > lapic_timer_advance_ns step by step. I can observe big fluctuated
>
> If that’s the case, I would also put the “8” as a #define to make it more clear of it’s purpose.
>
> > value between early and late when running real guest os like linux
> > instead of kvm-unit-tests. After more testing, I saw
> > lapic_timer_advance_ns can be overflow since the delta between
> > guest_tsc and tsc_deadline is too huge.
> >
> >>
> >> I think that instead you should do something like:
> >> s64 ns = (s64)(guest_tsc - tsc_deadline) * 1000000ULL;
> >> do_div(ns, vcpu->arch.virtual_tsc_khz);
> >> lapic_timer_advance_ns += ns;
> >>
> >>> +             if (abs(guest_tsc - tsc_deadline) < 100)
> >>
> >> I would put this “100” hard-coded value as some “#define” to make code more clear.
> >
> > How about something like below:
> >
> > diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
> > index fbb0e6d..354eb13c 100644
> > --- a/arch/x86/kvm/lapic.c
> > +++ b/arch/x86/kvm/lapic.c
> > @@ -70,6 +70,9 @@
> > #define APIC_BROADCAST            0xFF
> > #define X2APIC_BROADCAST        0xFFFFFFFFul
> >
> > +static bool __read_mostly lapic_timer_advance_adjust_done = false;
> > +#define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
> > +
> > static inline int apic_test_vector(int vec, void *bitmap)
> > {
> >     return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
> > @@ -1472,7 +1475,7 @@ static bool lapic_timer_int_injected(struct
> > kvm_vcpu *vcpu)
> > void wait_lapic_expire(struct kvm_vcpu *vcpu)
> > {
> >     struct kvm_lapic *apic = vcpu->arch.apic;
> > -    u64 guest_tsc, tsc_deadline;
> > +    u64 guest_tsc, tsc_deadline, ns;
> >
> >     if (!lapic_in_kernel(vcpu))
> >         return;
> > @@ -1492,6 +1495,19 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
> >     if (guest_tsc < tsc_deadline)
> >         __delay(min(tsc_deadline - guest_tsc,
> >             nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
> > +    if (!lapic_timer_advance_adjust_done) {
> > +        if (guest_tsc < tsc_deadline) {
> > +            ns = (tsc_deadline - guest_tsc) * 1000000ULL;
> > +            do_div(ns, vcpu->arch.virtual_tsc_khz);
> > +            lapic_timer_advance_ns -= min((unsigned int)ns,
> > lapic_timer_advance_ns / 8);
> > +        } else {
> > +            ns = (guest_tsc - tsc_deadline) * 1000000ULL;
> > +            do_div(ns, vcpu->arch.virtual_tsc_khz);
> > +            lapic_timer_advance_ns += min((unsigned int)ns,
> > lapic_timer_advance_ns / 8);
> > +        }
> > +        if (ns < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
>
> Didn’t you meant to compare here that abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE?
> This is also a good example on why I would also rename LAPIC_TIMER_ADVANCE_ADJUST_DONE to something
> which indicates it represents a number in guest TSC units.

Done in v2.

Regards,
Wanpeng Li