[PATCH 3/5] KVM: x86: account KVM_SET_CLOCK downtime in steal time

[Dongli Zhang <dongli.zhang@oracle.com>]

The KVM_CLOCK_REALTIME has been introduced to help track the downtime of
live migration. KVM uses that realtime value to advance guest clock, but
the same blackout is not reflected in KVM steal time.

Account that same delta in steal time directly in kvm_vm_ioctl_set_clock(),
only when KVM_CLOCK_REALTIME is used. This keeps the KVM-only solution
self-contained and avoids adding a new KVM ioctl or requiring additional
userspace changes (i.e. QEMU).

Record the per-VM downtime delta when KVM_SET_CLOCK receives
KVM_CLOCK_REALTIME, and fold it into the existing x86 steal accounting
path. Initialize each vCPU's local cursor
(vcpu->arch.st.last_downtime_steal) when the guest enables
MSR_KVM_STEAL_TIME so previously accumulated blackout is not charged.

Note that this means a vCPU may observe additional steal time after
blackout even if the host side contribution from current->sched_info
did not increase during that interval.

Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
---
 arch/x86/include/asm/kvm_host.h |  3 +++
 arch/x86/kvm/x86.c              | 25 +++++++++++++++++++++++--
 2 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1f1f29128c5d..920441b1abf0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -959,6 +959,7 @@ struct kvm_vcpu_arch {
 		u8 preempted;
 		u64 msr_val;
 		u64 last_steal;
+		u64 last_downtime_steal;
 		struct gfn_to_hva_cache cache;
 		bool need_reset;
 	} st;
@@ -1506,6 +1507,8 @@ struct kvm_arch {
 	u64 master_kernel_ns;
 	u64 master_cycle_now;
 
+	atomic64_t downtime_steal;
+
 #ifdef CONFIG_KVM_HYPERV
 	struct kvm_hv hyperv;
 #endif
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eec578894ad5..452293fc0505 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3751,6 +3751,7 @@ 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 downtime_steal;
 	u64 steal;
 	u32 version;
 
@@ -3838,6 +3839,11 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	steal += current->sched_info.run_delay -
 		vcpu->arch.st.last_steal;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
+
+	downtime_steal = atomic64_read(&vcpu->kvm->arch.downtime_steal);
+	steal += downtime_steal - vcpu->arch.st.last_downtime_steal;
+	vcpu->arch.st.last_downtime_steal = downtime_steal;
+
 	unsafe_put_user(steal, &st->steal, out);
 
 	version += 1;
@@ -4185,6 +4191,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			break;
 
 		vcpu->arch.st.need_reset = true;
+		vcpu->arch.st.last_downtime_steal =
+			atomic64_read(&vcpu->kvm->arch.downtime_steal);
+
 		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 
 		break;
@@ -7250,8 +7259,18 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp)
 		/*
 		 * Avoid stepping the kvmclock backwards.
 		 */
-		if (now_real_ns > data.realtime)
-			data.clock += now_real_ns - data.realtime;
+		if (now_real_ns > data.realtime) {
+			u64 downtime_ns = now_real_ns - data.realtime;
+
+			data.clock += downtime_ns;
+
+			if (sched_info_on()) {
+				atomic64_add(downtime_ns,
+					     &kvm->arch.downtime_steal);
+				kvm_make_all_cpus_request(kvm,
+							  KVM_REQ_STEAL_UPDATE);
+			}
+		}
 	}
 
 	if (ka->use_master_clock)
@@ -13389,6 +13408,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.hv_root_tdp = INVALID_PAGE;
 #endif
 
+	atomic64_set(&kvm->arch.downtime_steal, 0);
+
 	kvm_apicv_init(kvm);
 	kvm_hv_init_vm(kvm);
 	kvm_xen_init_vm(kvm);
-- 
2.39.3