[stable-0.15,1/6] qemu-kvm: fix improper nmi emulation

Commit Message

Andreas Färber Oct. 9, 2012, 6:08 p.m. UTC

From: Lai Jiangshan <[e-mail]>

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, inject-nmi request is handled as follows.

- When in-kernel irqchip is disabled, deliver LINT1 instead of NMI
  interrupt.
- When in-kernel irqchip is enabled, get the in-kernel LAPIC states
  and test the APIC_LVT_MASKED, if LINT1 is unmasked, and then
  delivering the NMI directly. (Suggested by Jan Kiszka)

Changed from old version:
  re-implement it by the Jan's suggestion.
  fix the race found by Jan.

Signed-off-by: Lai Jiangshan <[e-mail]>
Reported-by: Kenji Kaneshige <[e-mail]>
Signed-off-by: Avi Kivity <[e-mail]>
(cherry picked from commit 67feec6ed854b3618b37ccf050b90192cbb96e0f)

Signed-off-by: Andreas Färber <[e-mail]>
---
 hw/apic.c |   33 +++++++++++++++++++++++++++++++++
 hw/apic.h |    1 +
 monitor.c |    6 +++++-
 3 Dateien geändert, 39 Zeilen hinzugefügt(+), 1 Zeile entfernt(-)

Patch

diff --git a/hw/apic.c b/hw/apic.c
index a45b57f..243900d 100644
--- a/hw/apic.c
+++ b/hw/apic.c
@@ -204,6 +204,39 @@  void apic_deliver_pic_intr(DeviceState *d, int level)
     }
 }
 
+static inline uint32_t kapic_reg(struct kvm_lapic_state *kapic, int reg_id);
+
+static void kvm_irqchip_deliver_nmi(void *p)
+{
+    APICState *s = p;
+    struct kvm_lapic_state klapic;
+    uint32_t lvt;
+
+    kvm_get_lapic(s->cpu_env, &klapic);
+    lvt = kapic_reg(&klapic, 0x32 + APIC_LVT_LINT1);
+
+    if (lvt & APIC_LVT_MASKED) {
+        return;
+    }
+
+    if (((lvt >> 8) & 7) != APIC_DM_NMI) {
+        return;
+    }
+
+    kvm_vcpu_ioctl(s->cpu_env, KVM_NMI);
+}
+
+void apic_deliver_nmi(DeviceState *d)
+{
+    APICState *s = DO_UPCAST(APICState, busdev.qdev, d);
+
+    if (kvm_irqchip_in_kernel()) {
+        run_on_cpu(s->cpu_env, kvm_irqchip_deliver_nmi, s);
+    } else {
+        apic_local_deliver(s, APIC_LVT_LINT1);
+    }
+}
+
 #define foreach_apic(apic, deliver_bitmask, code) \
 {\
     int __i, __j, __mask;\
diff --git a/hw/apic.h b/hw/apic.h
index c857d52..3a4be0a 100644
--- a/hw/apic.h
+++ b/hw/apic.h
@@ -10,6 +10,7 @@  void apic_deliver_irq(uint8_t dest, uint8_t dest_mode,
                              uint8_t trigger_mode);
 int apic_accept_pic_intr(DeviceState *s);
 void apic_deliver_pic_intr(DeviceState *s, int level);
+void apic_deliver_nmi(DeviceState *d);
 int apic_get_interrupt(DeviceState *s);
 void apic_reset_irq_delivered(void);
 int apic_get_irq_delivered(void);
diff --git a/monitor.c b/monitor.c
index 7680929..6af0673 100644
--- a/monitor.c
+++ b/monitor.c
@@ -2604,7 +2604,11 @@  static int do_inject_nmi(Monitor *mon, const QDict *qdict, QObject **ret_data)
     CPUState *env;
 
     for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        cpu_interrupt(env, CPU_INTERRUPT_NMI);
+        if (!env->apic_state) {
+            cpu_interrupt(env, CPU_INTERRUPT_NMI);
+        } else {
+            apic_deliver_nmi(env->apic_state);
+        }
     }
 
     return 0;