[PATCH] KVM: x86: Include host suspended time in steal time.

[Suleiman Souhlal <suleiman@google.com>]

When the host resumes from a suspend, the guest thinks any task
that was running during the suspend ran for a long time, even though
the effective run time was much shorter, which can end up having
negative effects with scheduling. This can be particularly noticeable
if the guest task was RT, as it can end up getting throttled for a
long time.

To mitigate this issue, we include the time that the host was
suspended in steal time, which lets the guest can subtract the
duration from the tasks' runtime.

Signed-off-by: Suleiman Souhlal <suleiman@google.com>
---
 arch/x86/kvm/x86.c       | 23 ++++++++++++++++++++++-
 include/linux/kvm_host.h |  4 ++++
 2 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0763a0f72a067f..94bbdeef843863 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3669,7 +3669,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	struct kvm_steal_time __user *st;
 	struct kvm_memslots *slots;
 	gpa_t gpa = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS;
-	u64 steal;
+	u64 steal, suspend_duration;
 	u32 version;
 
 	if (kvm_xen_msr_enabled(vcpu->kvm)) {
@@ -3696,6 +3696,12 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 			return;
 	}
 
+	suspend_duration = 0;
+	if (READ_ONCE(vcpu->suspended)) {
+		suspend_duration = vcpu->kvm->last_suspend_duration;
+		vcpu->suspended = 0;
+	}
+
 	st = (struct kvm_steal_time __user *)ghc->hva;
 	/*
 	 * Doing a TLB flush here, on the guest's behalf, can avoid
@@ -3749,6 +3755,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	unsafe_get_user(steal, &st->steal, out);
 	steal += current->sched_info.run_delay -
 		vcpu->arch.st.last_steal;
+	steal += suspend_duration;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
 	unsafe_put_user(steal, &st->steal, out);
 
@@ -6920,6 +6927,7 @@ static int kvm_arch_suspend_notifier(struct kvm *kvm)
 
 	mutex_lock(&kvm->lock);
 	kvm_for_each_vcpu(i, vcpu, kvm) {
+		WRITE_ONCE(vcpu->suspended, 1);
 		if (!vcpu->arch.pv_time.active)
 			continue;
 
@@ -6932,15 +6940,28 @@ static int kvm_arch_suspend_notifier(struct kvm *kvm)
 	}
 	mutex_unlock(&kvm->lock);
 
+	kvm->suspended_time = ktime_get_boottime_ns();
+
 	return ret ? NOTIFY_BAD : NOTIFY_DONE;
 }
 
+static int
+kvm_arch_resume_notifier(struct kvm *kvm)
+{
+	kvm->last_suspend_duration = ktime_get_boottime_ns() -
+	    kvm->suspended_time;
+	return NOTIFY_DONE;
+}
+
 int kvm_arch_pm_notifier(struct kvm *kvm, unsigned long state)
 {
 	switch (state) {
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
 		return kvm_arch_suspend_notifier(kvm);
+	case PM_POST_HIBERNATION:
+	case PM_POST_SUSPEND:
+		return kvm_arch_resume_notifier(kvm);
 	}
 
 	return NOTIFY_DONE;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 692c01e41a18ef..2d37af9a348648 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -366,6 +366,8 @@ struct kvm_vcpu {
 	} async_pf;
 #endif
 
+	bool suspended;
+
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 	/*
 	 * Cpu relax intercept or pause loop exit optimization
@@ -840,6 +842,8 @@ struct kvm {
 	struct xarray mem_attr_array;
 #endif
 	char stats_id[KVM_STATS_NAME_SIZE];
+	u64 last_suspend_duration;
+	u64 suspended_time;
 };
 
 #define kvm_err(fmt, ...) \
-- 
2.45.2.993.g49e7a77208-goog