KVM: x86/xen: Add support for vCPU runstate information

This is how Xen guests do steal time accounting. The hypervisor records
the amount of time spent in each of running/runnable/blocked/offline
states.

In the Xen accounting, a vCPU is still in state RUNSTATE_running while
in Xen for a hypercall or I/O trap, etc. Only if Xen explicitly schedules
does the state become RUNSTATE_blocked. In KVM this means that even when
the vCPU exits the kvm_run loop, the state remains RUNSTATE_running.

The VMM can explicitly set the vCPU to RUNSTATE_blocked by using the
KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT attribute, and can also use
KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST to retrospectively add a given
amount of time to the blocked state and subtract it from the running
state.

The state_entry_time corresponds to get_kvmclock_ns() at the time the
vCPU entered the current state, and the total times of all four states
should always add up to state_entry_time.

Co-developed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20210301125309.874953-2-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 39 insertions, 1 deletions

diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h
index 87eaf2be9549..463a7844a8ca 100644
--- a/arch/x86/kvm/xen.h
+++ b/arch/x86/kvm/xen.h
@@ -23,6 +23,12 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data);
 int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc);
 void kvm_xen_destroy_vm(struct kvm *kvm);
 
+static inline bool kvm_xen_msr_enabled(struct kvm *kvm)
+{
+	return static_branch_unlikely(&kvm_xen_enabled.key) &&
+		kvm->arch.xen_hvm_config.msr;
+}
+
 static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm)
 {
 	return static_branch_unlikely(&kvm_xen_enabled.key) &&
@@ -48,6 +54,11 @@ static inline void kvm_xen_destroy_vm(struct kvm *kvm)
 {
 }
 
+static inline bool kvm_xen_msr_enabled(struct kvm *kvm)
+{
+	return false;
+}
+
 static inline bool kvm_xen_hypercall_enabled(struct kvm *kvm)
 {
 	return false;
@@ -61,10 +72,31 @@ static inline int kvm_xen_has_interrupt(struct kvm_vcpu *vcpu)
 
 int kvm_xen_hypercall(struct kvm_vcpu *vcpu);
 
-/* 32-bit compatibility definitions, also used natively in 32-bit build */
 #include <asm/pvclock-abi.h>
 #include <asm/xen/interface.h>
+#include <xen/interface/vcpu.h>
 
+void kvm_xen_update_runstate_guest(struct kvm_vcpu *vcpu, int state);
+
+static inline void kvm_xen_runstate_set_running(struct kvm_vcpu *vcpu)
+{
+	kvm_xen_update_runstate_guest(vcpu, RUNSTATE_running);
+}
+
+static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * If the vCPU wasn't preempted but took a normal exit for
+	 * some reason (hypercalls, I/O, etc.), that is accounted as
+	 * still RUNSTATE_running, as the VMM is still operating on
+	 * behalf of the vCPU. Only if the VMM does actually block
+	 * does it need to enter RUNSTATE_blocked.
+	 */
+	if (vcpu->preempted)
+		kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable);
+}
+
+/* 32-bit compatibility definitions, also used natively in 32-bit build */
 struct compat_arch_vcpu_info {
 	unsigned int cr2;
 	unsigned int pad[5];
@@ -97,4 +129,10 @@ struct compat_shared_info {
 	struct compat_arch_shared_info arch;
 };
 
+struct compat_vcpu_runstate_info {
+    int state;
+    uint64_t state_entry_time;
+    uint64_t time[4];
+} __attribute__((packed));
+
 #endif /* __ARCH_X86_KVM_XEN_H__ */