[PATCH v2] KVM: x86: Convert INIT and SIPI signals into synchronously handled requests

[Jan Kiszka <jan.kiszka@web.de>]

From: Jan Kiszka <jan.kiszka@siemens.com>

A VCPU sending INIT or SIPI to some other VCPU races for setting the
remote VCPU's mp_state. When we were unlucky, KVM_MP_STATE_INIT_RECEIVED
was overwritten by kvm_emulate_halt and, thus, got lost.

Fix this by raising requests on the sender side that will then be
handled synchronously over the target VCPU context.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---

Changes in v2:
 - check transition to INIT_RECEIVED in vcpu_enter_guest
 - removed return value of kvm_check_init_and_sipi - caller has to
   check for relevant transition afterward
 - add write barrier after setting sipi_vector

 arch/x86/kvm/lapic.c     |   11 ++++++-----
 arch/x86/kvm/x86.c       |   15 +++++++++++++++
 include/linux/kvm_host.h |    2 ++
 3 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 02b51dd..7986c9f 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -731,8 +731,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	case APIC_DM_INIT:
 		if (!trig_mode || level) {
 			result = 1;
-			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
+			kvm_make_request(KVM_REQ_INIT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		} else {
 			apic_debug("Ignoring de-assert INIT to vcpu %d\n",
@@ -743,11 +742,13 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	case APIC_DM_STARTUP:
 		apic_debug("SIPI to vcpu %d vector 0x%02x\n",
 			   vcpu->vcpu_id, vector);
-		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
+		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED ||
+		    test_bit(KVM_REQ_INIT, &vcpu->requests)) {
 			result = 1;
 			vcpu->arch.sipi_vector = vector;
-			vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
-			kvm_make_request(KVM_REQ_EVENT, vcpu);
+			/* make sure sipi_vector is visible for the receiver */
+			smp_wmb();
+			kvm_make_request(KVM_REQ_SIPI, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}
 		break;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d0cf737..0be04b9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5641,6 +5641,15 @@ static void update_eoi_exitmap(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap);
 }
 
+static void kvm_check_init_and_sipi(struct kvm_vcpu *vcpu)
+{
+	if (kvm_check_request(KVM_REQ_INIT, vcpu))
+		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+	if (kvm_check_request(KVM_REQ_SIPI, vcpu) &&
+	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+		vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
+}
+
 static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -5649,6 +5658,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_immediate_exit = 0;
 
 	if (vcpu->requests) {
+		kvm_check_init_and_sipi(vcpu);
+		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
+			r = 1;
+			goto out;
+		}
 		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
@@ -6977,6 +6991,7 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
+	kvm_check_init_and_sipi(vcpu);
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
 		!vcpu->arch.apf.halted)
 		|| !list_empty_careful(&vcpu->async_pf.done)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 722cae7..1a191c9 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -124,6 +124,8 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_MCLOCK_INPROGRESS 20
 #define KVM_REQ_EPR_EXIT          21
 #define KVM_REQ_EOIBITMAP         22
+#define KVM_REQ_INIT              23
+#define KVM_REQ_SIPI              24
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
-- 
1.7.3.4