[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250723175341.1284463-16-xin@zytor.com>
Date: Wed, 23 Jul 2025 10:53:33 -0700
From: "Xin Li (Intel)" <xin@...or.com>
To: linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
linux-doc@...r.kernel.org
Cc: pbonzini@...hat.com, seanjc@...gle.com, corbet@....net, tglx@...utronix.de,
mingo@...hat.com, bp@...en8.de, dave.hansen@...ux.intel.com,
x86@...nel.org, hpa@...or.com, xin@...or.com, luto@...nel.org,
peterz@...radead.org, andrew.cooper3@...rix.com, chao.gao@...el.com,
hch@...radead.org
Subject: [PATCH v5 15/23] KVM: x86: Save/restore the nested flag of an exception
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@...or.com>
Tested-by: Xuelian Guo <xuelian.guo@...el.com>
---
Change in v5:
* Add TB from Xuelian Guo.
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 b3a54ac0d653..756cd19a76e4 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.
@@ -8651,6 +8659,17 @@ given VM.
When this capability is enabled, KVM resets the VCPU when setting
MP_STATE_INIT_RECEIVED through IOCTL. The original MP_STATE is preserved.
+7.44 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 04fa24ed1594..8e8d4ba77afc 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1465,6 +1465,7 @@ struct kvm_arch {
bool has_mapped_host_mmio;
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 e019111e2150..cc566215837e 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 1632ece82a85..daaddd59d97d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4753,6 +4753,7 @@ 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:
@@ -5497,6 +5498,7 @@ 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;
@@ -5522,6 +5524,8 @@ 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;
@@ -5536,7 +5540,8 @@ 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) {
@@ -5551,6 +5556,13 @@ 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;
@@ -5576,6 +5588,7 @@ 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;
@@ -6561,6 +6574,10 @@ 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 aeb2ca10b190..b2f2f5bcf712 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -961,6 +961,7 @@ struct kvm_enable_cap {
#define KVM_CAP_ARM_EL2 240
#define KVM_CAP_ARM_EL2_E2H0 241
#define KVM_CAP_RISCV_MP_STATE_RESET 242
+#define KVM_CAP_EXCEPTION_NESTED_FLAG 243
struct kvm_irq_routing_irqchip {
__u32 irqchip;
--
2.50.1
Powered by blists - more mailing lists