Re: [PATCH v1 1/1] target/i386: Save/restore the nested flag of an exception

[Zhao Liu <zhao1.liu@intel.com>]

On Wed, Jul 23, 2025 at 11:22:11AM -0700, Xin Li (Intel) wrote:
> Date: Wed, 23 Jul 2025 11:22:11 -0700
> From: "Xin Li (Intel)" <xin@zytor.com>
> Subject: [PATCH v1 1/1] target/i386: Save/restore the nested flag of an
>  exception
> X-Mailer: git-send-email 2.50.1
> 
> 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.
> 
> The event stack level used by FRED event delivery depends on whether
> the event was a nested exception encountered during delivery of an
> earlier event, because a nested exception is "regarded" as happening
> on ring 0.  E.g., when #PF is configured to use stack level 1 in
> IA32_FRED_STKLVLS MSR:
>   - nested #PF will be delivered on the stack pointed by IA32_FRED_RSP1
>     MSR when encountered in ring 3 and ring 0.
>   - normal #PF will be delivered on the stack pointed by IA32_FRED_RSP0
>     MSR when encountered in ring 3.
>   - normal #PF will be delivered on the stack pointed by IA32_FRED_RSP1
>     MSR when encountered in ring 0.
> 
> As such Qemu needs to track if an event is a nested event during VM
> context save/restore and live migration.
> 
> Signed-off-by: Xin Li (Intel) <xin@zytor.com>
> ---
>  linux-headers/asm-x86/kvm.h |  4 +++-
>  linux-headers/linux/kvm.h   |  1 +
>  target/i386/cpu.c           |  1 +
>  target/i386/cpu.h           |  1 +
>  target/i386/kvm/kvm.c       | 35 +++++++++++++++++++++++++++++++++++
>  target/i386/kvm/kvm_i386.h  |  1 +
>  target/i386/machine.c       |  1 +
>  7 files changed, 43 insertions(+), 1 deletion(-)

> diff --git a/target/i386/kvm/kvm_i386.h b/target/i386/kvm/kvm_i386.h
> index 5f83e8850a..7e765b6833 100644
> --- a/target/i386/kvm/kvm_i386.h
> +++ b/target/i386/kvm/kvm_i386.h
> @@ -54,6 +54,7 @@ typedef struct KvmCpuidInfo {
>  bool kvm_is_vm_type_supported(int type);
>  bool kvm_has_adjust_clock_stable(void);
>  bool kvm_has_exception_payload(void);
> +bool kvm_has_exception_nested_flag(void);
>  void kvm_synchronize_all_tsc(void);
>  
>  void kvm_get_apic_state(DeviceState *d, struct kvm_lapic_state *kapic);
> diff --git a/target/i386/machine.c b/target/i386/machine.c
> index dd2dac1d44..a452d2c97e 100644
> --- a/target/i386/machine.c
> +++ b/target/i386/machine.c
> @@ -458,6 +458,7 @@ static const VMStateDescription vmstate_exception_info = {
>          VMSTATE_UINT8(env.exception_injected, X86CPU),
>          VMSTATE_UINT8(env.exception_has_payload, X86CPU),
>          VMSTATE_UINT64(env.exception_payload, X86CPU),
> +        VMSTATE_UINT8(env.exception_is_nested, X86CPU),

A new field needs to bump up the version of vmstate_exception_info, but
I'm afraid this will break backward-migration compatibility. So what
about adding a subsction? For example,

diff --git a/target/i386/machine.c b/target/i386/machine.c
index a452d2c97e4c..6ce3cb8af6a6 100644
--- a/target/i386/machine.c
+++ b/target/i386/machine.c
@@ -433,6 +433,24 @@ static bool steal_time_msr_needed(void *opaque)
     return cpu->env.steal_time_msr != 0;
 }

+static bool exception_nested_needed(void *opaque)
+{
+    X86CPU *cpu = opaque;
+
+    return cpu->env.exception_is_nested;
+}
+
+static const VMStateDescription vmstate_exceprtion_nested = {
+    .name = "cpu/exception_nested",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .needed = exception_nested_needed,
+    .fields = (const VMStateField[]) {
+        VMSTATE_UINT8(env.exception_is_nested, X86CPU),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
 static bool exception_info_needed(void *opaque)
 {
     X86CPU *cpu = opaque;
@@ -458,8 +476,11 @@ static const VMStateDescription vmstate_exception_info = {
         VMSTATE_UINT8(env.exception_injected, X86CPU),
         VMSTATE_UINT8(env.exception_has_payload, X86CPU),
         VMSTATE_UINT64(env.exception_payload, X86CPU),
-        VMSTATE_UINT8(env.exception_is_nested, X86CPU),
         VMSTATE_END_OF_LIST()
+    },
+    .subsections = (const VMStateDescription * const []) {
+        &vmstate_exceprtion_nested,
+        NULL,
     }
 };

---
In addition, I think it's better to update header files in a seperate
patch.

Thanks,
Zhao