[Qemu-devel] [PATCH 1/1 V2] kernel/kvm: fix improper nmi emulation

[Lai Jiangshan]

From: Kenji Kaneshige <address@hidden>

Currently, NMI interrupt is blindly sent to all the vCPUs when NMI
button event happens. This doesn't properly emulate real hardware on
which NMI button event triggers LINT1. Because of this, NMI is sent to
the processor even when LINT1 is maskied in LVT. For example, this
causes the problem that kdump initiated by NMI sometimes doesn't work
on KVM, because kdump assumes NMI is masked on CPUs other than CPU0.

With this patch, KVM_NMI ioctl is handled as follows.

- When in-kernel irqchip is enabled, KVM_NMI ioctl is handled as a
  request of triggering LINT1 on the processor. LINT1 is emulated in
  in-kernel irqchip.

- When in-kernel irqchip is disabled, KVM_NMI ioctl is handled as a
  request of injecting NMI to the processor. This assumes LINT1 is
  already emulated in userland.

(laijs) Changed from v1:
Add KVM_NMI API document
Add KVM_CAP_USER_NMI

Signed-off-by: Kenji Kaneshige <address@hidden>
Tested-by: Lai Jiangshan <address@hidden>
---
 Documentation/virtual/kvm/api.txt |   20 ++++++++++++++++++++
 arch/x86/kvm/irq.h                |    1 +
 arch/x86/kvm/lapic.c              |    7 +++++++
 arch/x86/kvm/x86.c                |   12 ++++++++++++
 include/linux/kvm.h               |    3 +++
 5 files changed, 43 insertions(+), 0 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt 
b/Documentation/virtual/kvm/api.txt
index b0e4b9c..5c24cc3 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1430,6 +1430,26 @@ is supported; 2 if the processor requires all virtual 
machines to have
 an RMA, or 1 if the processor can use an RMA but doesn't require it,
 because it supports the Virtual RMA (VRMA) facility.
 
+4.64 KVM_NMI
+
+Capability: KVM_CAP_USER_NMI
+Architectures: x86
+Type: vcpu ioctl
+Parameters: none
+Returns: 0 on success, -1 on error
+
+This ioctl injects NMI to the vcpu.
+
+If with capability KVM_CAP_LAPIC_NMI, KVM_NMI ioctl is handled as follows:
+
+       - When in-kernel irqchip is enabled, KVM_NMI ioctl is handled as a
+         request of triggering LINT1 on the processor. LINT1 is emulated in
+         in-kernel lapic irqchip.
+
+       - When in-kernel irqchip is disabled, KVM_NMI ioctl is handled as a
+         request of injecting NMI to the processor. This assumes LINT1 is
+         already emulated in userland lapic.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 53e2d08..0c96315 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -95,6 +95,7 @@ void kvm_pic_reset(struct kvm_kpic_state *s);
 void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu);
+void kvm_apic_lint1_deliver(struct kvm_vcpu *vcpu);
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
 void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu);
 void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 57dcbd4..87fe36a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1039,6 +1039,13 @@ void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
                kvm_apic_local_deliver(apic, APIC_LVT0);
 }
 
+void kvm_apic_lint1_deliver(struct kvm_vcpu *vcpu)
+{
+       struct kvm_lapic *apic = vcpu->arch.apic;
+
+       kvm_apic_local_deliver(apic, APIC_LVT1);
+}
+
 static struct kvm_timer_ops lapic_timer_ops = {
        .is_periodic = lapic_is_periodic,
 };
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 84a28ea..6862ef7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2729,12 +2729,24 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu 
*vcpu,
        return 0;
 }
 
+#ifdef KVM_CAP_LAPIC_NMI
+static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
+{
+       if (irqchip_in_kernel(vcpu->kvm))
+               kvm_apic_lint1_deliver(vcpu);
+       else
+               kvm_inject_nmi(vcpu);
+
+       return 0;
+}
+#else
 static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
 {
        kvm_inject_nmi(vcpu);
 
        return 0;
 }
+#endif
 
 static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
                                           struct kvm_tpr_access_ctl *tac)
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index aace6b8..5253a5c 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -554,6 +554,9 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_SMT 64
 #define KVM_CAP_PPC_RMA        65
 #define KVM_CAP_S390_GMAP 71
+#ifdef KVM_CAP_USER_NMI
+#define KVM_CAP_LAPIC_NMI 72
+#endif
 
 #ifdef KVM_CAP_IRQ_ROUTING