lkml.org 
[lkml]   [2021]   [Mar]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH] KVM: X86: Properly account for guest CPU time when considering context tracking
Date
From: Wanpeng Li <wanpengli@tencent.com>

The bugzilla https://bugzilla.kernel.org/show_bug.cgi?id=209831
reported that the guest time remains 0 when running a while true
loop in the guest.

The commit 87fa7f3e98a131 ("x86/kvm: Move context tracking where it
belongs") moves guest_exit_irqoff() close to vmexit breaks the
tick-based time accouting when the ticks that happen after IRQs are
disabled are incorrectly accounted to the host/system time. This is
because we exit the guest state too early.

vtime-based time accounting is tied to context tracking, keep the
guest_exit_irqoff() around vmexit code when both vtime-based time
accounting and specific cpu is context tracking mode active.
Otherwise, leave guest_exit_irqoff() after handle_exit_irqoff()
and explicit IRQ window for tick-based time accouting.

Fixes: 87fa7f3e98a131 ("x86/kvm: Move context tracking where it belongs")
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
arch/x86/kvm/svm/svm.c | 3 ++-
arch/x86/kvm/vmx/vmx.c | 3 ++-
arch/x86/kvm/x86.c | 2 ++
3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 58a45bb..55fb5ce 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3812,7 +3812,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
* into world and some more.
*/
lockdep_hardirqs_off(CALLER_ADDR0);
- guest_exit_irqoff();
+ if (vtime_accounting_enabled_this_cpu())
+ guest_exit_irqoff();

instrumentation_begin();
trace_hardirqs_off_finish();
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 32cf828..85695b3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6689,7 +6689,8 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
* into world and some more.
*/
lockdep_hardirqs_off(CALLER_ADDR0);
- guest_exit_irqoff();
+ if (vtime_accounting_enabled_this_cpu())
+ guest_exit_irqoff();

instrumentation_begin();
trace_hardirqs_off_finish();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fe806e8..234c8b3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9185,6 +9185,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
++vcpu->stat.exits;
local_irq_disable();
kvm_after_interrupt(vcpu);
+ if (!vtime_accounting_enabled_this_cpu())
+ guest_exit_irqoff();

if (lapic_in_kernel(vcpu)) {
s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta;
--
2.7.4
\
 
 \ /
  Last update: 2021-03-29 11:45    [W:0.055 / U:0.028 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site