[PATCH][v3] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint

[PATCH][v3] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint

[Li RongQing]

If guest kernel is configured with nopvspin, or CONFIG_PARAVIRT_SPINLOCK
is disabled, or guest find its has dedicated pCPUs from realtime hint
feature, the pvspinlock will be disabled, and vCPU preemption check
is disabled too.

but KVM still can emulating HLT for vCPU for both cases, and check if vCPU
is preempted or not, and can boost performance

so move the setting of pv_ops.lock.vcpu_is_preempted to kvm_guest_init, make
it not depend on pvspinlock

Like unixbench, single copy, vcpu with dedicated pCPU and guest kernel with
nopvspin, but emulating HLT for vCPU`:

Testcase                                  Base    with patch
System Benchmarks Index Values            INDEX     INDEX
Dhrystone 2 using register variables     3278.4    3277.7
Double-Precision Whetstone                822.8     825.8
Execl Throughput                         1296.5     941.1
File Copy 1024 bufsize 2000 maxblocks    2124.2    2142.7
File Copy 256 bufsize 500 maxblocks      1335.9    1353.6
File Copy 4096 bufsize 8000 maxblocks    4256.3    4760.3
Pipe Throughput                          1050.1    1054.0
Pipe-based Context Switching              243.3     352.0
Process Creation                          820.1     814.4
Shell Scripts (1 concurrent)             2169.0    2086.0
Shell Scripts (8 concurrent)             7710.3    7576.3
System Call Overhead                      672.4     673.9
                                      ========    =======
System Benchmarks Index Score             1467.2   1483.0

Signed-off-by: Li RongQing <lirongqing@baidu.com>
---
diff v3: fix building failure when CONFIG_PARAVIRT_SPINLOCK is disable
         and setting preemption check only when unhalt
diff v2: move setting preemption check to kvm_guest_init

 arch/x86/kernel/kvm.c | 74 +++++++++++++++++++++++++--------------------------
 1 file changed, 37 insertions(+), 37 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d77481ec..959f919 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -752,6 +752,39 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
 }
 #endif
 
+#ifdef CONFIG_X86_32
+__visible bool __kvm_vcpu_is_preempted(long cpu)
+{
+	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
+
+	return !!(src->preempted & KVM_VCPU_PREEMPTED);
+}
+PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
+
+#else
+
+#include <asm/asm-offsets.h>
+
+extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
+
+/*
+ * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
+ * restoring to/from the stack.
+ */
+asm(
+".pushsection .text;"
+".global __raw_callee_save___kvm_vcpu_is_preempted;"
+".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
+"__raw_callee_save___kvm_vcpu_is_preempted:"
+"movq	__per_cpu_offset(,%rdi,8), %rax;"
+"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
+"setne	%al;"
+"ret;"
+".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
+".popsection");
+
+#endif
+
 static void __init kvm_guest_init(void)
 {
 	int i;
@@ -764,6 +797,10 @@ static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		has_steal_clock = 1;
 		static_call_update(pv_steal_clock, kvm_steal_clock);
+
+		if (kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+			pv_ops.lock.vcpu_is_preempted =
+				PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
 	}
 
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -1005,39 +1042,6 @@ static void kvm_wait(u8 *ptr, u8 val)
 	}
 }
 
-#ifdef CONFIG_X86_32
-__visible bool __kvm_vcpu_is_preempted(long cpu)
-{
-	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
-
-	return !!(src->preempted & KVM_VCPU_PREEMPTED);
-}
-PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
-
-#else
-
-#include <asm/asm-offsets.h>
-
-extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
-
-/*
- * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
- * restoring to/from the stack.
- */
-asm(
-".pushsection .text;"
-".global __raw_callee_save___kvm_vcpu_is_preempted;"
-".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
-"__raw_callee_save___kvm_vcpu_is_preempted:"
-"movq	__per_cpu_offset(,%rdi,8), %rax;"
-"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
-"setne	%al;"
-"ret;"
-".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
-".popsection");
-
-#endif
-
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
@@ -1081,10 +1085,6 @@ void __init kvm_spinlock_init(void)
 	pv_ops.lock.wait = kvm_wait;
 	pv_ops.lock.kick = kvm_kick_cpu;
 
-	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
-		pv_ops.lock.vcpu_is_preempted =
-			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
-	}
 	/*
 	 * When PV spinlock is enabled which is preferred over
 	 * virt_spin_lock(), virt_spin_lock_key's value is meaningless.
-- 
2.9.4

Re: [PATCH][v3] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint

[Paolo Bonzini]

On 3/9/22 09:46, Li RongQing wrote:
> If guest kernel is configured with nopvspin, or CONFIG_PARAVIRT_SPINLOCK
> is disabled, or guest find its has dedicated pCPUs from realtime hint
> feature, the pvspinlock will be disabled, and vCPU preemption check
> is disabled too.
> 
> but KVM still can emulating HLT for vCPU for both cases, and check if vCPU
> is preempted or not, and can boost performance
> 
> so move the setting of pv_ops.lock.vcpu_is_preempted to kvm_guest_init, make
> it not depend on pvspinlock
> 
> Like unixbench, single copy, vcpu with dedicated pCPU and guest kernel with
> nopvspin, but emulating HLT for vCPU`:
> 
> Testcase                                  Base    with patch
> System Benchmarks Index Values            INDEX     INDEX
> Dhrystone 2 using register variables     3278.4    3277.7
> Double-Precision Whetstone                822.8     825.8
> Execl Throughput                         1296.5     941.1
> File Copy 1024 bufsize 2000 maxblocks    2124.2    2142.7
> File Copy 256 bufsize 500 maxblocks      1335.9    1353.6
> File Copy 4096 bufsize 8000 maxblocks    4256.3    4760.3
> Pipe Throughput                          1050.1    1054.0
> Pipe-based Context Switching              243.3     352.0
> Process Creation                          820.1     814.4
> Shell Scripts (1 concurrent)             2169.0    2086.0
> Shell Scripts (8 concurrent)             7710.3    7576.3
> System Call Overhead                      672.4     673.9
>                                        ========    =======
> System Benchmarks Index Score             1467.2   1483.0
> 
> Signed-off-by: Li RongQing <lirongqing@baidu.com>
> ---
> diff v3: fix building failure when CONFIG_PARAVIRT_SPINLOCK is disable
>           and setting preemption check only when unhalt
> diff v2: move setting preemption check to kvm_guest_init
> 
>   arch/x86/kernel/kvm.c | 74 +++++++++++++++++++++++++--------------------------
>   1 file changed, 37 insertions(+), 37 deletions(-)
> 
> diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
> index d77481ec..959f919 100644
> --- a/arch/x86/kernel/kvm.c
> +++ b/arch/x86/kernel/kvm.c
> @@ -752,6 +752,39 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
>   }
>   #endif
>   
> +#ifdef CONFIG_X86_32
> +__visible bool __kvm_vcpu_is_preempted(long cpu)
> +{
> +	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
> +
> +	return !!(src->preempted & KVM_VCPU_PREEMPTED);
> +}
> +PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
> +
> +#else
> +
> +#include <asm/asm-offsets.h>
> +
> +extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
> +
> +/*
> + * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
> + * restoring to/from the stack.
> + */
> +asm(
> +".pushsection .text;"
> +".global __raw_callee_save___kvm_vcpu_is_preempted;"
> +".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
> +"__raw_callee_save___kvm_vcpu_is_preempted:"
> +"movq	__per_cpu_offset(,%rdi,8), %rax;"
> +"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
> +"setne	%al;"
> +"ret;"
> +".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
> +".popsection");
> +
> +#endif
> +
>   static void __init kvm_guest_init(void)
>   {
>   	int i;
> @@ -764,6 +797,10 @@ static void __init kvm_guest_init(void)
>   	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
>   		has_steal_clock = 1;
>   		static_call_update(pv_steal_clock, kvm_steal_clock);
> +
> +		if (kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
> +			pv_ops.lock.vcpu_is_preempted =
> +				PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
>   	}

Is it necessary to check PV_UNHALT?  The bit is present anyway in the 
steal time struct, unless it's a very old kernel.  And it's safe to 
always return zero if the bit is not present.

Paolo

答复: [PATCH][v3] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint

[Li,Rongqing]

> -----邮件原件-----
> 发件人: Paolo Bonzini <pbonzini@redhat.com>
> 发送时间: 2022年3月9日 17:29
> 收件人: Li,Rongqing <lirongqing@baidu.com>; seanjc@google.com;
> vkuznets@redhat.com; jmattson@google.com; x86@kernel.org;
> kvm@vger.kernel.org; wanpengli@tencent.com
> 主题: Re: [PATCH][v3] KVM: x86: Support the vCPU preemption check with
> nopvspin and realtime hint
> 
> On 3/9/22 09:46, Li RongQing wrote:
> > If guest kernel is configured with nopvspin, or
> > CONFIG_PARAVIRT_SPINLOCK is disabled, or guest find its has dedicated
> > pCPUs from realtime hint feature, the pvspinlock will be disabled, and
> > vCPU preemption check is disabled too.
> >
> > but KVM still can emulating HLT for vCPU for both cases, and check if
> > vCPU is preempted or not, and can boost performance
> >
> > so move the setting of pv_ops.lock.vcpu_is_preempted to
> > kvm_guest_init, make it not depend on pvspinlock
> >
> > Like unixbench, single copy, vcpu with dedicated pCPU and guest kernel
> > with nopvspin, but emulating HLT for vCPU`:
> >
> > Testcase                                  Base    with patch
> > System Benchmarks Index Values            INDEX     INDEX
> > Dhrystone 2 using register variables     3278.4    3277.7
> > Double-Precision Whetstone                822.8     825.8
> > Execl Throughput                         1296.5     941.1
> > File Copy 1024 bufsize 2000 maxblocks    2124.2    2142.7
> > File Copy 256 bufsize 500 maxblocks      1335.9    1353.6
> > File Copy 4096 bufsize 8000 maxblocks    4256.3    4760.3
> > Pipe Throughput                          1050.1    1054.0
> > Pipe-based Context Switching              243.3     352.0
> > Process Creation                          820.1     814.4
> > Shell Scripts (1 concurrent)             2169.0    2086.0
> > Shell Scripts (8 concurrent)             7710.3    7576.3
> > System Call Overhead                      672.4     673.9
> >                                        ========    =======
> > System Benchmarks Index Score             1467.2   1483.0
> >
> > Signed-off-by: Li RongQing <lirongqing@baidu.com>
> > ---
> > diff v3: fix building failure when CONFIG_PARAVIRT_SPINLOCK is disable
> >           and setting preemption check only when unhalt diff v2: move
> > setting preemption check to kvm_guest_init
> >
> >   arch/x86/kernel/kvm.c | 74
> +++++++++++++++++++++++++--------------------------
> >   1 file changed, 37 insertions(+), 37 deletions(-)
> >
> > diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index
> > d77481ec..959f919 100644
> > --- a/arch/x86/kernel/kvm.c
> > +++ b/arch/x86/kernel/kvm.c
> > @@ -752,6 +752,39 @@ static void kvm_crash_shutdown(struct pt_regs
> *regs)
> >   }
> >   #endif
> >
> > +#ifdef CONFIG_X86_32
> > +__visible bool __kvm_vcpu_is_preempted(long cpu) {
> > +	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
> > +
> > +	return !!(src->preempted & KVM_VCPU_PREEMPTED); }
> > +PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
> > +
> > +#else
> > +
> > +#include <asm/asm-offsets.h>
> > +
> > +extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
> > +
> > +/*
> > + * Hand-optimize version for x86-64 to avoid 8 64-bit register saving
> > +and
> > + * restoring to/from the stack.
> > + */
> > +asm(
> > +".pushsection .text;"
> > +".global __raw_callee_save___kvm_vcpu_is_preempted;"
> > +".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
> > +"__raw_callee_save___kvm_vcpu_is_preempted:"
> > +"movq	__per_cpu_offset(,%rdi,8), %rax;"
> > +"cmpb	$0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
> > +"setne	%al;"
> > +"ret;"
> > +".size
> __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_v
> cpu_is_preempted;"
> > +".popsection");
> > +
> > +#endif
> > +
> >   static void __init kvm_guest_init(void)
> >   {
> >   	int i;
> > @@ -764,6 +797,10 @@ static void __init kvm_guest_init(void)
> >   	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
> >   		has_steal_clock = 1;
> >   		static_call_update(pv_steal_clock, kvm_steal_clock);
> > +
> > +		if (kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
> > +			pv_ops.lock.vcpu_is_preempted =
> > +				PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
> >   	}
> 
> Is it necessary to check PV_UNHALT?  The bit is present anyway in the steal
> time struct, unless it's a very old kernel.  And it's safe to always return zero if
> the bit is not present.
> 

I think calling _kvm_vcpu_is_preempted should be avoid in some unnecessary condition, like no unhalt, which means that vcpu do not exit for hlt and vcpu is not preempted?

-Li 

Re: 答复: [PATCH][v3] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint

[Paolo Bonzini]

On 3/9/22 12:17, Li,Rongqing wrote:
>> Is it necessary to check PV_UNHALT?  The bit is present anyway in
>> the steal time struct, unless it's a very old kernel.  And it's
>> safe to always return zero if the bit is not present.
> 
> I think calling _kvm_vcpu_is_preempted should be avoid in some
> unnecessary condition, like no unhalt, which means that vcpu do not
> exit for hlt and vcpu is not preempted?

PV_UNHALT can be cleared by userspace just because the user requested 
it.  (In fact, what KVM does when it clears it automatically is not 
really a good idea...).

Paolo

答复: 答复: [PATCH][v3] KVM: x86: Support the vCPU preemption check with nopvspin and realtime hint

[Li,Rongqing]

Hi:

I am sorry, I send a new version

https://patchwork.kernel.org/project/kvm/patch/1646891689-53368-1-git-send-email-lirongqing@baidu.com/

thanks

-Li