lkml.org 
[lkml]   [2017]   [Aug]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patches in this message
/
SubjectRe: [PATCH v2 1/4] KVM: add spinlock optimization framework
From
Date
On 08/08/2017 10:42, David Hildenbrand wrote:
>
>> +bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
>> +{
>> + return false;
>> +}
>
> why don't we need an EXPORT_SYMBOL here?

Is it used outside the KVM module? I think no architecture actually needs
to export it.

>> -void kvm_vcpu_on_spin(struct kvm_vcpu *me)
>> +void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool me_in_kern)
>> {
>> struct kvm *kvm = me->kvm;
>> struct kvm_vcpu *vcpu;
>> @@ -2348,6 +2348,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
>> continue;
>> if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
>> continue;
>> + if (me_in_kern && !kvm_arch_vcpu_in_kernel(vcpu))
>> + continue;
>
>
> hm, does this patch compile? (me_in_kern)

Why not? :) This is what I have:

From d62a40d49f44ff7e789a15416316ef1cba93fa85 Mon Sep 17 00:00:00 2001
From: "Longpeng(Mike)" <longpeng2@huawei.com>
Date: Tue, 8 Aug 2017 12:05:32 +0800
Subject: [PATCH 1/4] KVM: add spinlock optimization framework

If a vcpu exits due to request a user mode spinlock, then
the spinlock-holder may be preempted in user mode or kernel mode.
(Note that not all architectures trap spin loops in user mode,
only AMD x86 and ARM/ARM64 currently do).

But if a vcpu exits in kernel mode, then the holder must be
preempted in kernel mode, so we should choose a vcpu in kernel mode
as a more likely candidate for the lock holder.

This introduces kvm_arch_vcpu_in_kernel() to decide whether the
vcpu is in kernel-mode when it's preempted. kvm_vcpu_on_spin's
new argument says the same of the spinning VCPU.

Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/arm/kvm/handle_exit.c | 2 +-
arch/arm64/kvm/handle_exit.c | 2 +-
arch/mips/kvm/mips.c | 5 +++++
arch/powerpc/kvm/powerpc.c | 5 +++++
arch/s390/kvm/diag.c | 2 +-
arch/s390/kvm/kvm-s390.c | 5 +++++
arch/x86/kvm/hyperv.c | 2 +-
arch/x86/kvm/svm.c | 2 +-
arch/x86/kvm/vmx.c | 2 +-
arch/x86/kvm/x86.c | 5 +++++
include/linux/kvm_host.h | 3 ++-
virt/kvm/arm/arm.c | 5 +++++
virt/kvm/kvm_main.c | 4 +++-
13 files changed, 36 insertions(+), 8 deletions(-)

diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 54442e375354..196122bb6968 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -67,7 +67,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) {
trace_kvm_wfx(*vcpu_pc(vcpu), true);
vcpu->stat.wfe_exit_stat++;
- kvm_vcpu_on_spin(vcpu);
+ kvm_vcpu_on_spin(vcpu, false);
} else {
trace_kvm_wfx(*vcpu_pc(vcpu), false);
vcpu->stat.wfi_exit_stat++;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 17d8a1677a0b..da57622cacca 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -84,7 +84,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
vcpu->stat.wfe_exit_stat++;
- kvm_vcpu_on_spin(vcpu);
+ kvm_vcpu_on_spin(vcpu, false);
} else {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
vcpu->stat.wfi_exit_stat++;
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index d4b2ad18eef2..70208bed5a15 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -98,6 +98,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
return !!(vcpu->arch.pending_exceptions);
}

+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return 1;
}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1a75c0b5f4ca..6184c45015f3 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -58,6 +58,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
return !!(v->arch.pending_exceptions) || kvm_request_pending(v);
}

+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return 1;
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index ce865bd4f81d..6182edebea3d 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -150,7 +150,7 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
vcpu->stat.diagnose_44++;
- kvm_vcpu_on_spin(vcpu);
+ kvm_vcpu_on_spin(vcpu, false);
return 0;
}

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index af09d3437631..0b0c689f1d9a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2447,6 +2447,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
return kvm_s390_vcpu_has_irq(vcpu, 0);
}

+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
{
atomic_or(PROG_BLOCK_SIE, &vcpu->arch.sie_block->prog20);
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index bf9992300efa..5243d54f73ab 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1274,7 +1274,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)

switch (code) {
case HVCALL_NOTIFY_LONG_SPIN_WAIT:
- kvm_vcpu_on_spin(vcpu);
+ kvm_vcpu_on_spin(vcpu, false);
break;
case HVCALL_POST_MESSAGE:
case HVCALL_SIGNAL_EVENT:
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2432bb952a30..0cc486fd9871 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3749,7 +3749,7 @@ static int interrupt_window_interception(struct vcpu_svm *svm)

static int pause_interception(struct vcpu_svm *svm)
{
- kvm_vcpu_on_spin(&(svm->vcpu));
+ kvm_vcpu_on_spin(&svm->vcpu, false);
return 1;
}

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 2c0f5287fb78..fef784c22190 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6781,7 +6781,7 @@ static int handle_pause(struct kvm_vcpu *vcpu)
if (ple_gap)
grow_ple_window(vcpu);

- kvm_vcpu_on_spin(vcpu);
+ kvm_vcpu_on_spin(vcpu, false);
return kvm_skip_emulated_instruction(vcpu);
}

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 33fd6b6419ef..aba9d038d09e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8432,6 +8432,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
}

+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 28112d7917c1..6882538eda32 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -720,7 +720,7 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data,
bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
int kvm_vcpu_yield_to(struct kvm_vcpu *target);
-void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
+void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible);
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);

@@ -800,6 +800,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
void kvm_arch_hardware_unsetup(void);
void kvm_arch_check_processor_compat(void *rtn);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);

#ifndef __KVM_HAVE_ARCH_VM_ALLOC
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index a39a1e161e63..862f820d06d4 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -416,6 +416,11 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
&& !v->arch.power_off && !v->arch.pause);
}

+bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
/* Just ensure a guest exit from a particular CPU */
static void exit_vm_noop(void *info)
{
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 15252d723b54..e17c40d986f3 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2317,7 +2317,7 @@ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
#endif
}

-void kvm_vcpu_on_spin(struct kvm_vcpu *me)
+void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
{
struct kvm *kvm = me->kvm;
struct kvm_vcpu *vcpu;
@@ -2348,6 +2348,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
continue;
if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
continue;
+ if (yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu))
+ continue;
if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
continue;

--
1.8.3.1

From 325c00511ab67d7e46e887ecea0d8b6b91005948 Mon Sep 17 00:00:00 2001
From: "Longpeng(Mike)" <longpeng2@huawei.com>
Date: Tue, 8 Aug 2017 12:05:33 +0800
Subject: [PATCH 2/4] KVM: X86: implement the logic for spinlock optimization

get_cpl requires vcpu_load, so we must cache the result (whether the
vcpu was preempted when its cpl=0) in kvm_vcpu_arch.

Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 3 +++
arch/x86/kvm/hyperv.c | 2 +-
arch/x86/kvm/svm.c | 5 ++++-
arch/x86/kvm/vmx.c | 8 +++++++-
arch/x86/kvm/x86.c | 7 ++++++-
5 files changed, 21 insertions(+), 4 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 87ac4fba6d8e..1679aabcabe5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -688,6 +688,9 @@ struct kvm_vcpu_arch {

/* GPA available (AMD only) */
bool gpa_available;
+
+ /* be preempted when it's in kernel-mode(cpl=0) */
+ bool preempted_in_kernel;
};

struct kvm_lpage_info {
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 5243d54f73ab..dc97f2544b6f 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1274,7 +1274,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)

switch (code) {
case HVCALL_NOTIFY_LONG_SPIN_WAIT:
- kvm_vcpu_on_spin(vcpu, false);
+ kvm_vcpu_on_spin(vcpu, true);
break;
case HVCALL_POST_MESSAGE:
case HVCALL_SIGNAL_EVENT:
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 0cc486fd9871..fc027f2e87d1 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3749,7 +3749,10 @@ static int interrupt_window_interception(struct vcpu_svm *svm)

static int pause_interception(struct vcpu_svm *svm)
{
- kvm_vcpu_on_spin(&svm->vcpu, false);
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ bool in_kernel = (svm_get_cpl(vcpu) == 0);
+
+ kvm_vcpu_on_spin(vcpu, in_kernel);
return 1;
}

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fef784c22190..46d08b389e36 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6781,7 +6781,13 @@ static int handle_pause(struct kvm_vcpu *vcpu)
if (ple_gap)
grow_ple_window(vcpu);

- kvm_vcpu_on_spin(vcpu, false);
+ /*
+ * Intel sdm vol3 ch-25.1.3 says: The "PAUSE-loop exiting"
+ * VM-execution control is ignored if CPL > 0. OTOH, KVM
+ * never set PAUSE_EXITING and just only uses PLE,
+ * so the vcpu must be CPL=0 if it gets a PAUSE exit.
+ */
+ kvm_vcpu_on_spin(vcpu, true);
return kvm_skip_emulated_instruction(vcpu);
}

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index aba9d038d09e..bee9ad0ed4cd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2873,6 +2873,10 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
int idx;
+
+ if (vcpu->preempted)
+ vcpu->arch.preempted_in_kernel = !kvm_x86_ops->get_cpl(vcpu);
+
/*
* Disable page faults because we're in atomic context here.
* kvm_write_guest_offset_cached() would call might_fault()
@@ -7985,6 +7989,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
kvm_pmu_init(vcpu);

vcpu->arch.pending_external_vector = -1;
+ vcpu->arch.preempted_in_kernel = false;

kvm_hv_vcpu_init(vcpu);

@@ -8434,7 +8439,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)

bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
- return false;
+ return vcpu->arch.preempted_in_kernel;
}

int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
--
1.8.3.1

From c83cf5cf8d972ea37b55db7e059767f5e3af55d0 Mon Sep 17 00:00:00 2001
From: "Longpeng(Mike)" <longpeng2@huawei.com>
Date: Tue, 8 Aug 2017 12:05:34 +0800
Subject: [PATCH 3/4] KVM: s390: implements the kvm_arch_vcpu_in_kernel()

This implements kvm_arch_vcpu_in_kernel() for s390. DIAG is a privileged
operation, so it cannot be called from problem state (user mode).

Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/s390/kvm/diag.c | 2 +-
arch/s390/kvm/kvm-s390.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 6182edebea3d..5ee90020382d 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -150,7 +150,7 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 5, "%s", "diag time slice end");
vcpu->stat.diagnose_44++;
- kvm_vcpu_on_spin(vcpu, false);
+ kvm_vcpu_on_spin(vcpu, true);
return 0;
}

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0b0c689f1d9a..e46177bde829 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2449,7 +2449,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)

bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
- return false;
+ return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE);
}

void kvm_s390_vcpu_block(struct kvm_vcpu *vcpu)
--
1.8.3.1

From 3d7c9a55166d7f0d955774360bca72a13b4ee96c Mon Sep 17 00:00:00 2001
From: "Longpeng(Mike)" <longpeng2@huawei.com>
Date: Tue, 8 Aug 2017 12:05:35 +0800
Subject: [PATCH 4/4] KVM: arm: implements the kvm_arch_vcpu_in_kernel()

This implements the kvm_arch_vcpu_in_kernel() for ARM, and adjusts
the calls to kvm_vcpu_on_spin().

Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/arm/kvm/handle_exit.c | 2 +-
arch/arm64/kvm/handle_exit.c | 2 +-
virt/kvm/arm/arm.c | 2 +-
3 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c
index 196122bb6968..cf8bf6bf87c4 100644
--- a/arch/arm/kvm/handle_exit.c
+++ b/arch/arm/kvm/handle_exit.c
@@ -67,7 +67,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) {
trace_kvm_wfx(*vcpu_pc(vcpu), true);
vcpu->stat.wfe_exit_stat++;
- kvm_vcpu_on_spin(vcpu, false);
+ kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
} else {
trace_kvm_wfx(*vcpu_pc(vcpu), false);
vcpu->stat.wfi_exit_stat++;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index da57622cacca..7debb74843a0 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -84,7 +84,7 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run)
if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true);
vcpu->stat.wfe_exit_stat++;
- kvm_vcpu_on_spin(vcpu, false);
+ kvm_vcpu_on_spin(vcpu, vcpu_mode_priv(vcpu));
} else {
trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false);
vcpu->stat.wfi_exit_stat++;
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 862f820d06d4..b9f68e4add71 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -418,7 +418,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)

bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
- return false;
+ return vcpu_mode_priv(vcpu);
}

/* Just ensure a guest exit from a particular CPU */
--
1.8.3.1
\
 
 \ /
  Last update: 2017-08-08 11:02    [W:0.072 / U:0.340 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site