[PATCH v4 12/19] KVM: x86: Save/restore the nested flag of an exception

From: Xin Li (Intel)
Date: Fri Mar 28 2025 - 13:19:08 EST


Save/restore the nested flag of an exception during VM save/restore
and live migration to ensure a correct event stack level is chosen
when a nested exception is injected through FRED event delivery.

Signed-off-by: Xin Li (Intel) <xin@xxxxxxxxx>
---

Change in v4:
* Add live migration support for exception nested flag (Chao Gao).
---
Documentation/virt/kvm/api.rst | 19 +++++++++++++++++++
arch/x86/include/asm/kvm_host.h | 1 +
arch/x86/include/uapi/asm/kvm.h | 4 +++-
arch/x86/kvm/x86.c | 19 ++++++++++++++++++-
include/uapi/linux/kvm.h | 1 +
5 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1f8625b7646a..32c00b07bcf1 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -1184,6 +1184,10 @@ The following bits are defined in the flags field:
fields contain a valid state. This bit will be set whenever
KVM_CAP_EXCEPTION_PAYLOAD is enabled.

+- KVM_VCPUEVENT_VALID_NESTED_FLAG may be set to inform that the
+ exception is a nested exception. This bit will be set whenever
+ KVM_CAP_EXCEPTION_NESTED_FLAG is enabled.
+
- KVM_VCPUEVENT_VALID_TRIPLE_FAULT may be set to signal that the
triple_fault_pending field contains a valid state. This bit will
be set whenever KVM_CAP_X86_TRIPLE_FAULT_EVENT is enabled.
@@ -1283,6 +1287,10 @@ can be set in the flags field to signal that the
exception_has_payload, exception_payload, and exception.pending fields
contain a valid state and shall be written into the VCPU.

+If KVM_CAP_EXCEPTION_NESTED_FLAG is enabled, KVM_VCPUEVENT_VALID_NESTED_FLAG
+can be set in the flags field to inform that the exception is a nested
+exception and exception_is_nested shall be written into the VCPU.
+
If KVM_CAP_X86_TRIPLE_FAULT_EVENT is enabled, KVM_VCPUEVENT_VALID_TRIPLE_FAULT
can be set in flags field to signal that the triple_fault field contains
a valid state and shall be written into the VCPU.
@@ -8280,6 +8288,17 @@ aforementioned registers before the first KVM_RUN. These registers are VM
scoped, meaning that the same set of values are presented on all vCPUs in a
given VM.

+7.38 KVM_CAP_EXCEPTION_NESTED_FLAG
+----------------------------------
+
+:Architectures: x86
+:Parameters: args[0] whether feature should be enabled or not
+
+With this capability enabled, an exception is save/restored with the
+additional information of whether it was nested or not. FRED event
+delivery uses this information to ensure a correct event stack level
+is chosen when a VM entry injects a nested exception.
+
8. Other capabilities.
======================

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c5f92a1befc0..f8b9834f2f37 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1444,6 +1444,7 @@ struct kvm_arch {

bool guest_can_read_msr_platform_info;
bool exception_payload_enabled;
+ bool exception_nested_flag_enabled;

bool triple_fault_event;

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 460306b35a4b..6a3a39d04843 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -326,6 +326,7 @@ struct kvm_reinject_control {
#define KVM_VCPUEVENT_VALID_SMM 0x00000008
#define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010
#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT 0x00000020
+#define KVM_VCPUEVENT_VALID_NESTED_FLAG 0x00000040

/* Interrupt shadow states */
#define KVM_X86_SHADOW_INT_MOV_SS 0x01
@@ -363,7 +364,8 @@ struct kvm_vcpu_events {
struct {
__u8 pending;
} triple_fault;
- __u8 reserved[26];
+ __u8 reserved[25];
+ __u8 exception_is_nested;
__u8 exception_has_payload;
__u64 exception_payload;
};
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7f013ff97067..17b5a799f65d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4710,6 +4710,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_GET_MSR_FEATURES:
case KVM_CAP_MSR_PLATFORM_INFO:
case KVM_CAP_EXCEPTION_PAYLOAD:
+ case KVM_CAP_EXCEPTION_NESTED_FLAG:
case KVM_CAP_X86_TRIPLE_FAULT_EVENT:
case KVM_CAP_SET_GUEST_DEBUG:
case KVM_CAP_LAST_CPU:
@@ -5437,6 +5438,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->exception.error_code = ex->error_code;
events->exception_has_payload = ex->has_payload;
events->exception_payload = ex->payload;
+ events->exception_is_nested = ex->nested;

events->interrupt.injected =
vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
@@ -5462,6 +5464,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
| KVM_VCPUEVENT_VALID_SMM);
if (vcpu->kvm->arch.exception_payload_enabled)
events->flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
+ if (vcpu->kvm->arch.exception_nested_flag_enabled)
+ events->flags |= KVM_VCPUEVENT_VALID_NESTED_FLAG;
if (vcpu->kvm->arch.triple_fault_event) {
events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu);
events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT;
@@ -5476,7 +5480,8 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
| KVM_VCPUEVENT_VALID_SHADOW
| KVM_VCPUEVENT_VALID_SMM
| KVM_VCPUEVENT_VALID_PAYLOAD
- | KVM_VCPUEVENT_VALID_TRIPLE_FAULT))
+ | KVM_VCPUEVENT_VALID_TRIPLE_FAULT
+ | KVM_VCPUEVENT_VALID_NESTED_FLAG))
return -EINVAL;

if (events->flags & KVM_VCPUEVENT_VALID_PAYLOAD) {
@@ -5491,6 +5496,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
events->exception_has_payload = 0;
}

+ if (events->flags & KVM_VCPUEVENT_VALID_NESTED_FLAG) {
+ if (!vcpu->kvm->arch.exception_nested_flag_enabled)
+ return -EINVAL;
+ } else {
+ events->exception_is_nested = 0;
+ }
+
if ((events->exception.injected || events->exception.pending) &&
(events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
return -EINVAL;
@@ -5522,6 +5534,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.exception.error_code = events->exception.error_code;
vcpu->arch.exception.has_payload = events->exception_has_payload;
vcpu->arch.exception.payload = events->exception_payload;
+ vcpu->arch.exception.nested = events->exception_is_nested;

vcpu->arch.interrupt.injected = events->interrupt.injected;
vcpu->arch.interrupt.nr = events->interrupt.nr;
@@ -6644,6 +6657,10 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
kvm->arch.exception_payload_enabled = cap->args[0];
r = 0;
break;
+ case KVM_CAP_EXCEPTION_NESTED_FLAG:
+ kvm->arch.exception_nested_flag_enabled = cap->args[0];
+ r = 0;
+ break;
case KVM_CAP_X86_TRIPLE_FAULT_EVENT:
kvm->arch.triple_fault_event = cap->args[0];
r = 0;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index b6ae8ad8934b..5ef33256858f 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -930,6 +930,7 @@ struct kvm_enable_cap {
#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
#define KVM_CAP_X86_GUEST_MODE 238
#define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239
+#define KVM_CAP_EXCEPTION_NESTED_FLAG 240

struct kvm_irq_routing_irqchip {
__u32 irqchip;
--
2.48.1