KVM: x86: Add support for local interrupt requests from userspace

In order to enable userspace PIC support, the userspace PIC needs to
be able to inject local interrupts even when the APICs are in the
kernel.

KVM_INTERRUPT now supports sending local interrupts to an APIC when
APICs are in the kernel.

The ready_for_interrupt_request flag is now only set when the CPU/APIC
will immediately accept and inject an interrupt (i.e. APIC has not
masked the PIC).

When the PIC wishes to initiate an INTA cycle with, say, CPU0, it
kicks CPU0 out of the guest, and renedezvous with CPU0 once it arrives
in userspace.

When the CPU/APIC unmasks the PIC, a KVM_EXIT_IRQ_WINDOW_OPEN is
triggered, so that userspace has a chance to inject a PIC interrupt
if it had been pending.

Overall, this design can lead to a small number of spurious userspace
renedezvous. In particular, whenever the PIC transistions from low to
high while it is masked and whenever the PIC becomes unmasked while
it is low.

Note: this does not buffer more than one local interrupt in the
kernel, so the VMM needs to enter the guest in order to complete
interrupt injection before injecting an additional interrupt.

Compiles for x86.

Can pass the KVM Unit Tests.

Signed-off-by: Steve Rutherford <srutherford@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 89e71648d7481b868ec0172a72ab4771b99c51ad..e3e9c41721a2dc68588c3a6f04c7c8105f804645 100644 (file)
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -401,10 +401,9 @@ Capability: basic
 Architectures: x86, ppc, mips
 Type: vcpu ioctl
 Parameters: struct kvm_interrupt (in)
-Returns: 0 on success, -1 on error
+Returns: 0 on success, negative on failure.
 
-Queues a hardware interrupt vector to be injected.  This is only
-useful if in-kernel local APIC or equivalent is not used.
+Queues a hardware interrupt vector to be injected.
 
 /* for KVM_INTERRUPT */
 struct kvm_interrupt {
@@ -414,7 +413,14 @@ struct kvm_interrupt {
 
 X86:
 
-Note 'irq' is an interrupt vector, not an interrupt pin or line.
+Returns: 0 on success,
+        -EEXIST if an interrupt is already enqueued
+        -EINVAL the the irq number is invalid
+        -ENXIO if the PIC is in the kernel
+        -EFAULT if the pointer is invalid
+
+Note 'irq' is an interrupt vector, not an interrupt pin or line. This
+ioctl is useful if the in-kernel PIC is not used.
 
 PPC:
 

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7a5f9debbcd8f75fc74eaca0f8c006c082b890d9..76a5b30979b31e8d5a90a811ddfa543734e6b8a3 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -576,6 +576,7 @@ struct kvm_vcpu_arch {
        } pv;
 
        int pending_ioapic_eoi;
+       int pending_external_vector;
 };
 
 struct kvm_lpage_info {

diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index b653ae202c8eb43747eeefaf78b6dbea255a0923..097060e33bd6a67b0743a4cb3918b1baef765496 100644 (file)
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -37,15 +37,28 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL(kvm_cpu_has_pending_timer);
 
+/*
+ * check if there is a pending userspace external interrupt
+ */
+static int pending_userspace_extint(struct kvm_vcpu *v)
+{
+       return v->arch.pending_external_vector != -1;
+}
+
 /*
  * check if there is pending interrupt from
  * non-APIC source without intack.
  */
 static int kvm_cpu_has_extint(struct kvm_vcpu *v)
 {
-       if (kvm_apic_accept_pic_intr(v))
-               return pic_irqchip(v->kvm)->output;     /* PIC */
-       else
+       u8 accept = kvm_apic_accept_pic_intr(v);
+
+       if (accept) {
+               if (irqchip_split(v->kvm))
+                       return pending_userspace_extint(v);
+               else
+                       return pic_irqchip(v->kvm)->output;
+       } else
                return 0;
 }
 
@@ -91,9 +104,16 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
  */
 static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
-       if (kvm_cpu_has_extint(v))
-               return kvm_pic_read_irq(v->kvm); /* PIC */
-       return -1;
+       if (kvm_cpu_has_extint(v)) {
+               if (irqchip_split(v->kvm)) {
+                       int vector = v->arch.pending_external_vector;
+
+                       v->arch.pending_external_vector = -1;
+                       return vector;
+               } else
+                       return kvm_pic_read_irq(v->kvm); /* PIC */
+       } else
+               return -1;
 }
 
 /*

diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 2f9703dcd913013b3cd05da828835836ebf097ec..ae5c78f2337d3f1359c99116cf5811ffe190b17a 100644 (file)
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -83,6 +83,14 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
        return kvm->arch.vpic;
 }
 
+static inline int pic_in_kernel(struct kvm *kvm)
+{
+       int ret;
+
+       ret = (pic_irqchip(kvm) != NULL);
+       return ret;
+}
+
 static inline int irqchip_split(struct kvm *kvm)
 {
        return kvm->arch.irqchip_split;

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4aeed2086c5e1caef22c14098330450179e94dd8..8b97c54edebcc30b6b8f758e4fb6fd615b0dd328 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2662,12 +2662,24 @@ static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 {
        if (irq->irq >= KVM_NR_INTERRUPTS)
                return -EINVAL;
-       if (irqchip_in_kernel(vcpu->kvm))
+
+       if (!irqchip_in_kernel(vcpu->kvm)) {
+               kvm_queue_interrupt(vcpu, irq->irq, false);
+               kvm_make_request(KVM_REQ_EVENT, vcpu);
+               return 0;
+       }
+
+       /*
+        * With in-kernel LAPIC, we only use this to inject EXTINT, so
+        * fail for in-kernel 8259.
+        */
+       if (pic_in_kernel(vcpu->kvm))
                return -ENXIO;
 
-       kvm_queue_interrupt(vcpu, irq->irq, false);
-       kvm_make_request(KVM_REQ_EVENT, vcpu);
+       if (vcpu->arch.pending_external_vector != -1)
+               return -EEXIST;
 
+       vcpu->arch.pending_external_vector = irq->irq;
        return 0;
 }
 
@@ -5796,9 +5808,15 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
  */
 static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
 {
-       return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) &&
-               vcpu->run->request_interrupt_window &&
-               kvm_arch_interrupt_allowed(vcpu));
+       if (!vcpu->run->request_interrupt_window || pic_in_kernel(vcpu->kvm))
+               return false;
+
+       if (kvm_cpu_has_interrupt(vcpu))
+               return false;
+
+       return (irqchip_split(vcpu->kvm)
+               ? kvm_apic_accept_pic_intr(vcpu)
+               : kvm_arch_interrupt_allowed(vcpu));
 }
 
 static void post_kvm_run_save(struct kvm_vcpu *vcpu)
@@ -5809,13 +5827,17 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
        kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0;
        kvm_run->cr8 = kvm_get_cr8(vcpu);
        kvm_run->apic_base = kvm_get_apic_base(vcpu);
-       if (irqchip_in_kernel(vcpu->kvm))
-               kvm_run->ready_for_interrupt_injection = 1;
-       else
+       if (!irqchip_in_kernel(vcpu->kvm))
                kvm_run->ready_for_interrupt_injection =
                        kvm_arch_interrupt_allowed(vcpu) &&
                        !kvm_cpu_has_interrupt(vcpu) &&
                        !kvm_event_needs_reinjection(vcpu);
+       else if (!pic_in_kernel(vcpu->kvm))
+               kvm_run->ready_for_interrupt_injection =
+                       kvm_apic_accept_pic_intr(vcpu) &&
+                       !kvm_cpu_has_interrupt(vcpu);
+       else
+               kvm_run->ready_for_interrupt_injection = 1;
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
@@ -7403,6 +7425,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
        kvm_async_pf_hash_reset(vcpu);
        kvm_pmu_init(vcpu);
 
+       vcpu->arch.pending_external_vector = -1;
+
        return 0;
 
 fail_free_mce_banks: