KVM: x86: Drop current_vcpu for kvm_running_vcpu + kvm_arch_vcpu variable

Use the generic kvm_running_vcpu plus a new 'handling_intr_from_guest'
variable in kvm_arch_vcpu instead of the semi-redundant current_vcpu.
kvm_before/after_interrupt() must be called while the vCPU is loaded,
(which protects against preemption), thus kvm_running_vcpu is guaranteed
to be non-NULL when handling_intr_from_guest is non-zero.

Switching to kvm_get_running_vcpu() will allows moving KVM's perf
callbacks to generic code, and the new flag will be used in a future
patch to more precisely identify the "NMI from guest" case.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Link: https://lore.kernel.org/r/20211111020738.2512932-11-seanjc@google.com

Author: sean-jc

arch/x86/include/asm/kvm_host.h

@@ -773,6 +773,7 @@ struct kvm_vcpu_arch {
 	unsigned nmi_pending; /* NMI queued after currently running handler */
 	bool nmi_injected;    /* Trying to inject an NMI this entry */
 	bool smi_pending;    /* SMI queued after currently running handler */
+	u8 handling_intr_from_guest;
 
 	struct kvm_mtrr mtrr_state;
 	u64 pat;
@@ -1895,8 +1896,6 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
 int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
 
-unsigned int kvm_guest_state(void);
-
 void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 				     u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);

arch/x86/kvm/pmu.c

@@ -87,7 +87,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event,
 		 * woken up. So we should wake it, but this is impossible from
 		 * NMI context. Do it from irq work instead.
 		 */
-		if (!kvm_guest_state())
+		if (!kvm_handling_nmi_from_guest(pmc->vcpu))
 			irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
 		else
 			kvm_make_request(KVM_REQ_PMI, pmc->vcpu);

arch/x86/kvm/x86.c

@@ -8469,15 +8469,17 @@ static void kvm_timer_init(void)
 			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
-DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
-EXPORT_PER_CPU_SYMBOL_GPL(current_vcpu);
+static inline bool kvm_pmi_in_guest(struct kvm_vcpu *vcpu)
+{
+	return vcpu && vcpu->arch.handling_intr_from_guest;
+}
 
-unsigned int kvm_guest_state(void)
+static unsigned int kvm_guest_state(void)
 {
-	struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 	unsigned int state;
 
-	if (!vcpu)
+	if (!kvm_pmi_in_guest(vcpu))
 		return 0;
 
 	state = PERF_GUEST_ACTIVE;
@@ -8489,20 +8491,21 @@ unsigned int kvm_guest_state(void)
 
 static unsigned long kvm_guest_get_ip(void)
 {
-	struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 
-	if (WARN_ON_ONCE(!vcpu))
+	/* Retrieving the IP must be guarded by a call to kvm_guest_state(). */
+	if (WARN_ON_ONCE(!kvm_pmi_in_guest(vcpu)))
 		return 0;
 
 	return kvm_rip_read(vcpu);
 }
 
 static unsigned int kvm_handle_intel_pt_intr(void)
 {
-	struct kvm_vcpu *vcpu = __this_cpu_read(current_vcpu);
+	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 
 	/* '0' on failure so that the !PT case can use a RET0 static call. */
-	if (!vcpu)
+	if (!kvm_pmi_in_guest(vcpu))
 		return 0;
 
 	kvm_make_request(KVM_REQ_PMI, vcpu);

arch/x86/kvm/x86.h

@@ -385,18 +385,20 @@ static inline bool kvm_cstate_in_guest(struct kvm *kvm)
 	return kvm->arch.cstate_in_guest;
 }
 
-DECLARE_PER_CPU(struct kvm_vcpu *, current_vcpu);
-
 static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu)
 {
-	__this_cpu_write(current_vcpu, vcpu);
+	WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 1);
 }
 
 static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
 {
-	__this_cpu_write(current_vcpu, NULL);
+	WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 0);
 }
 
+static inline bool kvm_handling_nmi_from_guest(struct kvm_vcpu *vcpu)
+{
+	return !!vcpu->arch.handling_intr_from_guest;
+}
 
 static inline bool kvm_pat_valid(u64 data)
 {