The interrupt shadow created by STI or MOV-SS-like operations is part of
the VCPU state and must be preserved across migration. Transfer it in
the spare padding field of kvm_vcpu_events.interrupt.
As a side effect we now have to make vmx_set_interrupt_shadow robust
against both shadow types being set. Give MOV SS a higher priority and
skip STI in that case to avoid that VMX throws a fault on next entry.
Signed-off-by: Jan Kiszka <jan.kiszka@xxxxxxxxxxx>
---
Changes in v3 (aka "back to square #1"):
- export both MOV SS and STI shadows, do not collapse them
Documentation/kvm/api.txt | 11 ++++++++++-
arch/x86/include/asm/kvm.h | 7 ++++++-
arch/x86/include/asm/kvm_emulate.h | 3 ---
arch/x86/kvm/emulate.c | 5 +++--
arch/x86/kvm/svm.c | 2 +-
arch/x86/kvm/vmx.c | 8 ++++----
arch/x86/kvm/x86.c | 12 ++++++++++--
include/linux/kvm.h | 1 +
8 files changed, 35 insertions(+), 14 deletions(-)
diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index beb444a..9e5de5a 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -656,6 +656,7 @@ struct kvm_clock_data {
4.29 KVM_GET_VCPU_EVENTS
Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_vcpu_event (out)
@@ -676,7 +677,7 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 soft;
- __u8 pad;
+ __u8 shadow;
} interrupt;
struct {
__u8 injected;
@@ -688,9 +689,13 @@ struct kvm_vcpu_events {
__u32 flags;
};
+KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
+interrupt.shadow contains a valid state. Otherwise, this field is undefined.
+
4.30 KVM_SET_VCPU_EVENTS
Capability: KVM_CAP_VCPU_EVENTS
+Extended by: KVM_CAP_INTR_SHADOW
Architectures: x86
Type: vm ioctl
Parameters: struct kvm_vcpu_event (in)
@@ -709,6 +714,10 @@ current in-kernel state. The bits are:
KVM_VCPUEVENT_VALID_NMI_PENDING - transfer nmi.pending to the kernel
KVM_VCPUEVENT_VALID_SIPI_VECTOR - transfer sipi_vector
+If KVM_CAP_INTR_SHADOW is available, KVM_VCPUEVENT_VALID_SHADOW can be set in
+the flags field to signal that interrupt.shadow contains a valid state and
+shall be written into the VCPU.
+
5. The kvm_run structure
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index f46b79f..fb61170 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -257,6 +257,11 @@ struct kvm_reinject_control {
/* When set in flags, include corresponding fields on KVM_SET_VCPU_EVENTS */
#define KVM_VCPUEVENT_VALID_NMI_PENDING 0x00000001
#define KVM_VCPUEVENT_VALID_SIPI_VECTOR 0x00000002
+#define KVM_VCPUEVENT_VALID_SHADOW 0x00000004
+
+/* Interrupt shadow states */
+#define KVM_X86_SHADOW_INT_MOV_SS 0x01
+#define KVM_X86_SHADOW_INT_STI 0x02
/* for KVM_GET/SET_VCPU_EVENTS */
struct kvm_vcpu_events {
@@ -271,7 +276,7 @@ struct kvm_vcpu_events {
__u8 injected;
__u8 nr;
__u8 soft;
- __u8 pad;
+ __u8 shadow;
} interrupt;
struct {
__u8 injected;
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 7a6f54f..2666d7a 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -153,9 +153,6 @@ struct decode_cache {
struct fetch_cache fetch;
};
-#define X86_SHADOW_INT_MOV_SS 1
-#define X86_SHADOW_INT_STI 2
-
struct x86_emulate_ctxt {
/* Register state before/after emulation. */
struct kvm_vcpu *vcpu;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 9beda8e..135bc56 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2123,7 +2123,8 @@ special_insn:
sel = c->src.val;
if (c->modrm_reg == VCPU_SREG_SS)
- toggle_interruptibility(ctxt, X86_SHADOW_INT_MOV_SS);
+ toggle_interruptibility(ctxt,
+ KVM_X86_SHADOW_INT_MOV_SS);
if (c->modrm_reg <= 5) {
type_bits = (c->modrm_reg == 1) ? 9 : 1;
@@ -2374,7 +2375,7 @@ special_insn:
if (emulator_bad_iopl(ctxt))
kvm_inject_gp(ctxt->vcpu, 0);
else {
- toggle_interruptibility(ctxt, X86_SHADOW_INT_STI);
+ toggle_interruptibility(ctxt, KVM_X86_SHADOW_INT_STI);
ctxt->eflags |= X86_EFLAGS_IF;
c->dst.type = OP_NONE; /* Disable writeback. */
}
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 2e1e8d6..5f88a73 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -263,7 +263,7 @@ static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
u32 ret = 0;
if (svm->vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)
- ret |= X86_SHADOW_INT_STI | X86_SHADOW_INT_MOV_SS;
+ ret |= KVM_X86_SHADOW_INT_STI | KVM_X86_SHADOW_INT_MOV_SS;
return ret & mask;
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7c815b..ce5ec41 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -838,9 +838,9 @@ static u32 vmx_get_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
int ret = 0;
if (interruptibility & GUEST_INTR_STATE_STI)
- ret |= X86_SHADOW_INT_STI;
+ ret |= KVM_X86_SHADOW_INT_STI;
if (interruptibility & GUEST_INTR_STATE_MOV_SS)
- ret |= X86_SHADOW_INT_MOV_SS;
+ ret |= KVM_X86_SHADOW_INT_MOV_SS;
return ret & mask;
}
@@ -852,9 +852,9 @@ static void vmx_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
interruptibility &= ~(GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS);
- if (mask & X86_SHADOW_INT_MOV_SS)
+ if (mask & KVM_X86_SHADOW_INT_MOV_SS)
interruptibility |= GUEST_INTR_STATE_MOV_SS;
- if (mask & X86_SHADOW_INT_STI)
+ else if (mask & KVM_X86_SHADOW_INT_STI)
interruptibility |= GUEST_INTR_STATE_STI;
if ((interruptibility != interruptibility_old))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d1b5024..9b13e15 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2132,6 +2132,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft;
events->interrupt.nr = vcpu->arch.interrupt.nr;
events->interrupt.soft = 0;
+ events->interrupt.shadow =
+ kvm_x86_ops->get_interrupt_shadow(vcpu,
+ KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI);
events->nmi.injected = vcpu->arch.nmi_injected;
events->nmi.pending = vcpu->arch.nmi_pending;
@@ -2140,7 +2143,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->sipi_vector = vcpu->arch.sipi_vector;
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
- | KVM_VCPUEVENT_VALID_SIPI_VECTOR);
+ | KVM_VCPUEVENT_VALID_SIPI_VECTOR
+ | KVM_VCPUEVENT_VALID_SHADOW);
vcpu_put(vcpu);
}
@@ -2149,7 +2153,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING
- | KVM_VCPUEVENT_VALID_SIPI_VECTOR))
+ | KVM_VCPUEVENT_VALID_SIPI_VECTOR
+ | KVM_VCPUEVENT_VALID_SHADOW))
return -EINVAL;
vcpu_load(vcpu);
@@ -2164,6 +2169,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.interrupt.soft = events->interrupt.soft;
if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
kvm_pic_clear_isr_ack(vcpu->kvm);
+ if (events->flags & KVM_VCPUEVENT_VALID_SHADOW)
+ kvm_x86_ops->set_interrupt_shadow(vcpu,
+ events->interrupt.shadow);
vcpu->arch.nmi_injected = events->nmi.injected;
if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING)
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index dfa54be..46fb860 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -501,6 +501,7 @@ struct kvm_ioeventfd {
#define KVM_CAP_HYPERV_VAPIC 45
#define KVM_CAP_HYPERV_SPIN 46
#define KVM_CAP_PCI_SEGMENT 47
+#define KVM_CAP_INTR_SHADOW 48
#ifdef KVM_CAP_IRQ_ROUTING
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
