[PATCH 0/2] KVM: x86: emulate wait-for-SIPI and SIPI-VMExit

[PATCH 0/2] KVM: x86: emulate wait-for-SIPI and SIPI-VMExit

[Paolo Bonzini]

The first patch is new, the second is a rebase of Yadong's patch

Paolo Bonzini (1):
  KVM: x86: fix apic_accept_events vs check_nested_events

Yadong Qi (1):
  KVM: x86: emulate wait-for-SIPI and SIPI-VMExit

 arch/x86/include/asm/vmx.h      |  1 +
 arch/x86/include/uapi/asm/vmx.h |  2 ++
 arch/x86/kvm/lapic.c            | 30 ++++++++++++++++---
 arch/x86/kvm/vmx/nested.c       | 53 ++++++++++++++++++++++++---------
 arch/x86/kvm/vmx/vmx.c          |  2 +-
 5 files changed, 69 insertions(+), 19 deletions(-)

-- 
2.26.2

[PATCH 1/2] KVM: x86: fix apic_accept_events vs check_nested_events

[Paolo Bonzini]

vmx_apic_init_signal_blocked is buggy in that it returns true
even in VMX non-root mode.  In non-root mode, however, INITs
are not latched, they just cause a vmexit.  Previously,
KVM was waiting for them to be processed when kvm_apic_accept_events
and in the meanwhile it ate the SIPIs that the processor received.

However, in order to implement the wait-for-SIPI activity state,
KVM will have to process KVM_APIC_SIPI in vmx_check_nested_events,
and it will not be possible anymore to disregard SIPIs in non-root
mode as the code is currently doing.

By calling kvm_x86_ops.nested_ops->check_events, we can force a vmexit
(with the side-effect of latching INITs) before incorrectly injecting
an INIT or SIPI in a guest, and therefore vmx_apic_init_signal_blocked
can do the right thing.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/lapic.c   | 30 ++++++++++++++++++++++++++----
 arch/x86/kvm/vmx/vmx.c |  2 +-
 2 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 105e7859d1f2..e3ee597ff540 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2843,14 +2843,35 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u8 sipi_vector;
+	int r;
 	unsigned long pe;
 
-	if (!lapic_in_kernel(vcpu) || !apic->pending_events)
+	if (!lapic_in_kernel(vcpu))
+		return;
+
+	/*
+	 * Read pending events before calling the check_events
+	 * callback.
+	 */
+	pe = smp_load_acquire(&apic->pending_events);
+	if (!pe)
 		return;
 
+	if (is_guest_mode(vcpu)) {
+		r = kvm_x86_ops.nested_ops->check_events(vcpu);
+		if (r < 0)
+			return;
+		/*
+		 * If an event has happened and caused a vmexit,
+		 * we know INITs are latched and therefore
+		 * we will not incorrectly deliver an APIC
+		 * event instead of a vmexit.
+		 */
+	}
+
 	/*
 	 * INITs are latched while CPU is in specific states
-	 * (SMM, VMX non-root mode, SVM with GIF=0).
+	 * (SMM, VMX root mode, SVM with GIF=0).
 	 * Because a CPU cannot be in these states immediately
 	 * after it has processed an INIT signal (and thus in
 	 * KVM_MP_STATE_INIT_RECEIVED state), just eat SIPIs
@@ -2858,13 +2879,13 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	 */
 	if (kvm_vcpu_latch_init(vcpu)) {
 		WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED);
-		if (test_bit(KVM_APIC_SIPI, &apic->pending_events))
+		if (test_bit(KVM_APIC_SIPI, &pe))
 			clear_bit(KVM_APIC_SIPI, &apic->pending_events);
 		return;
 	}
 
-	pe = xchg(&apic->pending_events, 0);
 	if (test_bit(KVM_APIC_INIT, &pe)) {
+		clear_bit(KVM_APIC_INIT, &apic->pending_events);
 		kvm_vcpu_reset(vcpu, true);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
 			vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -2873,6 +2894,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 	}
 	if (test_bit(KVM_APIC_SIPI, &pe) &&
 	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
+		clear_bit(KVM_APIC_SIPI, &apic->pending_events);
 		/* evaluate pending_events before reading the vector */
 		smp_rmb();
 		sipi_vector = apic->sipi_vector;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 47b8357b9751..64339121a4f0 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7558,7 +7558,7 @@ static void enable_smi_window(struct kvm_vcpu *vcpu)
 
 static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
 {
-	return to_vmx(vcpu)->nested.vmxon;
+	return to_vmx(vcpu)->nested.vmxon && !is_guest_mode(vcpu);
 }
 
 static void vmx_migrate_timers(struct kvm_vcpu *vcpu)
-- 
2.26.2

[PATCH 2/2] KVM: x86: emulate wait-for-SIPI and SIPI-VMExit

[Paolo Bonzini]

From: Yadong Qi <yadong.qi@intel.com>

Background: We have a lightweight HV, it needs INIT-VMExit and
SIPI-VMExit to wake-up APs for guests since it do not monitor
the Local APIC. But currently virtual wait-for-SIPI(WFS) state
is not supported in nVMX, so when running on top of KVM, the L1
HV cannot receive the INIT-VMExit and SIPI-VMExit which cause
the L2 guest cannot wake up the APs.

According to Intel SDM Chapter 25.2 Other Causes of VM Exits,
SIPIs cause VM exits when a logical processor is in
wait-for-SIPI state.

In this patch:
    1. introduce SIPI exit reason,
    2. introduce wait-for-SIPI state for nVMX,
    3. advertise wait-for-SIPI support to guest.

When L1 hypervisor is not monitoring Local APIC, L0 need to emulate
INIT-VMExit and SIPI-VMExit to L1 to emulate INIT-SIPI-SIPI for
L2. L2 LAPIC write would be traped by L0 Hypervisor(KVM), L0 should
emulate the INIT/SIPI vmexit to L1 hypervisor to set proper state
for L2's vcpu state.

Handle procdure:
Source vCPU:
    L2 write LAPIC.ICR(INIT).
    L0 trap LAPIC.ICR write(INIT): inject a latched INIT event to target
       vCPU.
Target vCPU:
    L0 emulate an INIT VMExit to L1 if is guest mode.
    L1 set guest VMCS, guest_activity_state=WAIT_SIPI, vmresume.
    L0 set vcpu.mp_state to INIT_RECEIVED if (vmcs12.guest_activity_state
       == WAIT_SIPI).

Source vCPU:
    L2 write LAPIC.ICR(SIPI).
    L0 trap LAPIC.ICR write(INIT): inject a latched SIPI event to traget
       vCPU.
Target vCPU:
    L0 emulate an SIPI VMExit to L1 if (vcpu.mp_state == INIT_RECEIVED).
    L1 set CS:IP, guest_activity_state=ACTIVE, vmresume.
    L0 resume to L2.
    L2 start-up.

Signed-off-by: Yadong Qi <yadong.qi@intel.com>
Message-Id: <20200922052343.84388-1-yadong.qi@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/vmx.h      |  1 +
 arch/x86/include/uapi/asm/vmx.h |  2 ++
 arch/x86/kvm/vmx/nested.c       | 53 ++++++++++++++++++++++++---------
 3 files changed, 42 insertions(+), 14 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index f8ba5289ecb0..38ca445a8429 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -113,6 +113,7 @@
 #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK	0x0000001f
 #define VMX_MISC_SAVE_EFER_LMA			0x00000020
 #define VMX_MISC_ACTIVITY_HLT			0x00000040
+#define VMX_MISC_ACTIVITY_WAIT_SIPI		0x00000100
 #define VMX_MISC_ZERO_LEN_INS			0x40000000
 #define VMX_MISC_MSR_LIST_MULTIPLIER		512
 
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index b8ff9e8ac0d5..ada955c5ebb6 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -32,6 +32,7 @@
 #define EXIT_REASON_EXTERNAL_INTERRUPT  1
 #define EXIT_REASON_TRIPLE_FAULT        2
 #define EXIT_REASON_INIT_SIGNAL			3
+#define EXIT_REASON_SIPI_SIGNAL         4
 
 #define EXIT_REASON_INTERRUPT_WINDOW    7
 #define EXIT_REASON_NMI_WINDOW          8
@@ -94,6 +95,7 @@
 	{ EXIT_REASON_EXTERNAL_INTERRUPT,    "EXTERNAL_INTERRUPT" }, \
 	{ EXIT_REASON_TRIPLE_FAULT,          "TRIPLE_FAULT" }, \
 	{ EXIT_REASON_INIT_SIGNAL,           "INIT_SIGNAL" }, \
+	{ EXIT_REASON_SIPI_SIGNAL,           "SIPI_SIGNAL" }, \
 	{ EXIT_REASON_INTERRUPT_WINDOW,      "INTERRUPT_WINDOW" }, \
 	{ EXIT_REASON_NMI_WINDOW,            "NMI_WINDOW" }, \
 	{ EXIT_REASON_TASK_SWITCH,           "TASK_SWITCH" }, \
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 89af692deb7e..c35eec55b2c6 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2952,7 +2952,8 @@ static int nested_vmx_check_vmcs_link_ptr(struct kvm_vcpu *vcpu,
 static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12)
 {
 	if (CC(vmcs12->guest_activity_state != GUEST_ACTIVITY_ACTIVE &&
-	       vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT))
+	       vmcs12->guest_activity_state != GUEST_ACTIVITY_HLT &&
+	       vmcs12->guest_activity_state != GUEST_ACTIVITY_WAIT_SIPI))
 		return -EINVAL;
 
 	return 0;
@@ -3559,19 +3560,29 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 */
 	nested_cache_shadow_vmcs12(vcpu, vmcs12);
 
-	/*
-	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be
-	 * awakened by event injection or by an NMI-window VM-exit or
-	 * by an interrupt-window VM-exit, halt the vcpu.
-	 */
-	if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
-	    !(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
-	    !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) &&
-	    !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) &&
-	      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
+	switch (vmcs12->guest_activity_state) {
+	case GUEST_ACTIVITY_HLT:
+		/*
+		 * If we're entering a halted L2 vcpu and the L2 vcpu won't be
+		 * awakened by event injection or by an NMI-window VM-exit or
+		 * by an interrupt-window VM-exit, halt the vcpu.
+		 */
+		if (!(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
+		    !nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING) &&
+		    !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) &&
+		      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
+			vmx->nested.nested_run_pending = 0;
+			return kvm_vcpu_halt(vcpu);
+		}
+		break;
+	case GUEST_ACTIVITY_WAIT_SIPI:
 		vmx->nested.nested_run_pending = 0;
-		return kvm_vcpu_halt(vcpu);
+		vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
+		break;
+	default:
+		break;
 	}
+
 	return 1;
 
 vmentry_failed:
@@ -3797,7 +3808,20 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
 			return -EBUSY;
 		nested_vmx_update_pending_dbg(vcpu);
 		clear_bit(KVM_APIC_INIT, &apic->pending_events);
-		nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
+		if (vcpu->arch.mp_state != KVM_MP_STATE_INIT_RECEIVED)
+			nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
+		return 0;
+	}
+
+	if (lapic_in_kernel(vcpu) &&
+	    test_bit(KVM_APIC_SIPI, &apic->pending_events)) {
+		if (block_nested_events)
+			return -EBUSY;
+
+		clear_bit(KVM_APIC_SIPI, &apic->pending_events);
+		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+			nested_vmx_vmexit(vcpu, EXIT_REASON_SIPI_SIGNAL, 0,
+						apic->sipi_vector & 0xFFUL);
 		return 0;
 	}
 
@@ -6483,7 +6507,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 	msrs->misc_low |=
 		MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
 		VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
-		VMX_MISC_ACTIVITY_HLT;
+		VMX_MISC_ACTIVITY_HLT |
+		VMX_MISC_ACTIVITY_WAIT_SIPI;
 	msrs->misc_high = 0;
 
 	/*
-- 
2.26.2