KVM: x86: Defer vtime accounting 'til after IRQ handling

commit 160457140187c5fb127b844e5a85f87f00a01b14 upstream.

Defer the call to account guest time until after servicing any IRQ(s)
that happened in the guest or immediately after VM-Exit.  Tick-based
accounting of vCPU time relies on PF_VCPU being set when the tick IRQ
handler runs, and IRQs are blocked throughout the main sequence of
vcpu_enter_guest(), including the call into vendor code to actually
enter and exit the guest.

This fixes a bug where reported guest time remains '0', even when
running an infinite loop in the guest:

  https://bugzilla.kernel.org/show_bug.cgi?id=209831

Fixes: 87fa7f3e98a131 ("x86/kvm: Move context tracking where it belongs")
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210505002735.1684165-4-seanjc@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index ca7a717477e702c84f46a3c5d96e4e1ad645c84a..9d4eb114613c2bc0cca171bd4beea567bb1f0779 100644 (file)
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3532,15 +3532,15 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
         * have them in state 'on' as recorded before entering guest mode.
         * Same as enter_from_user_mode().
         *
-        * guest_exit_irqoff() restores host context and reinstates RCU if
-        * enabled and required.
+        * context_tracking_guest_exit() restores host context and reinstates
+        * RCU if enabled and required.
         *
         * This needs to be done before the below as native_read_msr()
         * contains a tracepoint and x86_spec_ctrl_restore_host() calls
         * into world and some more.
         */
        lockdep_hardirqs_off(CALLER_ADDR0);
-       guest_exit_irqoff();
+       context_tracking_guest_exit();
 
        instrumentation_begin();
        trace_hardirqs_off_finish();

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d7f8d2167fda0be0fedb2d5e7ce734b1d762842b..45877364e6829168af0b94910d7319c80393f0c6 100644 (file)
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6640,15 +6640,15 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
         * have them in state 'on' as recorded before entering guest mode.
         * Same as enter_from_user_mode().
         *
-        * guest_exit_irqoff() restores host context and reinstates RCU if
-        * enabled and required.
+        * context_tracking_guest_exit() restores host context and reinstates
+        * RCU if enabled and required.
         *
         * This needs to be done before the below as native_read_msr()
         * contains a tracepoint and x86_spec_ctrl_restore_host() calls
         * into world and some more.
         */
        lockdep_hardirqs_off(CALLER_ADDR0);
-       guest_exit_irqoff();
+       context_tracking_guest_exit();
 
        instrumentation_begin();
        trace_hardirqs_off_finish();

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c071a83d543ae2db055042c7cfa96ff3f1e06ce4..7f767d59b09d31cab9ff8a5e0cb06d6e3547c4a8 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9063,6 +9063,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
        local_irq_disable();
        kvm_after_interrupt(vcpu);
 
+       /*
+        * Wait until after servicing IRQs to account guest time so that any
+        * ticks that occurred while running the guest are properly accounted
+        * to the guest.  Waiting until IRQs are enabled degrades the accuracy
+        * of accounting via context tracking, but the loss of accuracy is
+        * acceptable for all known use cases.
+        */
+       vtime_account_guest_exit();
+
        if (lapic_in_kernel(vcpu)) {
                s64 delta = vcpu->arch.apic->lapic_timer.advance_expire_delta;
                if (delta != S64_MIN) {