On 9/9/2025 5:39 PM, Chao Gao wrote:
From: Sean Christopherson <seanjc@xxxxxxxxxx>
Load the guest's FPU state if userspace is accessing MSRs whose values
are managed by XSAVES. Introduce two helpers, kvm_{get,set}_xstate_msr(),
to facilitate access to such kind of MSRs.
If MSRs supported in kvm_caps.supported_xss are passed through to guest,
the guest MSRs are swapped with host's before vCPU exits to userspace and
after it reenters kernel before next VM-entry.
Because the modified code is also used for the KVM_GET_MSRS device ioctl(),
explicitly check @vcpu is non-null before attempting to load guest state.
The XSAVE-managed MSRs cannot be retrieved via the device ioctl() without
loading guest FPU state (which doesn't exist).
Note that guest_cpuid_has() is not queried as host userspace is allowed to
access MSRs that have not been exposed to the guest, e.g. it might do
KVM_SET_MSRS prior to KVM_SET_CPUID2.
The two helpers are put here in order to manifest accessing xsave-managed
MSRs requires special check and handling to guarantee the correctness of
read/write to the MSRs.
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Co-developed-by: Yang Weijiang <weijiang.yang@xxxxxxxxx>
Signed-off-by: Yang Weijiang <weijiang.yang@xxxxxxxxx>
Reviewed-by: Maxim Levitsky <mlevitsk@xxxxxxxxxx>
Tested-by: Mathias Krause <minipli@xxxxxxxxxxxxxx>
Tested-by: John Allen <john.allen@xxxxxxx>
Tested-by: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
Signed-off-by: Chao Gao <chao.gao@xxxxxxxxx>
---
v14:
- s/rdmsrl/rdmsrq, s/wrmsrl/wrmsrq (Xin)
- return true in is_xstate_managed_msr() for MSR_IA32_S_CET
---
arch/x86/kvm/x86.c | 36 +++++++++++++++++++++++++++++++++++-
arch/x86/kvm/x86.h | 24 ++++++++++++++++++++++++
2 files changed, 59 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c15e8c00dc7d..7c0a07be6b64 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,6 +136,9 @@ static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2);
static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2);
static DEFINE_MUTEX(vendor_module_lock);
+static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
+static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
+
struct kvm_x86_ops kvm_x86_ops __read_mostly;
#define KVM_X86_OP(func) \
@@ -4566,6 +4569,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
}
EXPORT_SYMBOL_GPL(kvm_get_msr_common);
+/*
+ * Returns true if the MSR in question is managed via XSTATE, i.e. is context
+ * switched with the rest of guest FPU state.
+ */
+static bool is_xstate_managed_msr(u32 index)
+{
+ switch (index) {
+ case MSR_IA32_S_CET:
+ case MSR_IA32_U_CET:
+ case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP:
+ return true;
+ default:
+ return false;
+ }
+}
+
/*
* Read or write a bunch of msrs. All parameters are kernel addresses.
*
@@ -4576,11 +4595,26 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs,
int (*do_msr)(struct kvm_vcpu *vcpu,
unsigned index, u64 *data))
{
+ bool fpu_loaded = false;
int i;
- for (i = 0; i < msrs->nmsrs; ++i)
+ for (i = 0; i < msrs->nmsrs; ++i) {
+ /*
+ * If userspace is accessing one or more XSTATE-managed MSRs,
+ * temporarily load the guest's FPU state so that the guest's
+ * MSR value(s) is resident in hardware, i.e. so that KVM can
+ * get/set the MSR via RDMSR/WRMSR.
+ */
+ if (vcpu && !fpu_loaded && kvm_caps.supported_xss &&
why not check vcpu->arch.guest_supported_xss?
+ is_xstate_managed_msr(entries[i].index)) {
+ kvm_load_guest_fpu(vcpu);
+ fpu_loaded = true;
+ }
if (do_msr(vcpu, entries[i].index, &entries[i].data))
break;
+ }
+ if (fpu_loaded)
+ kvm_put_guest_fpu(vcpu);
return i;
}
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index eb3088684e8a..34afe43579bb 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -701,4 +701,28 @@ int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl,
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
+/*
+ * Lock and/or reload guest FPU and access xstate MSRs. For accesses initiated
+ * by host, guest FPU is loaded in __msr_io(). For accesses initiated by guest,
+ * guest FPU should have been loaded already.
+ */
+
+static inline void kvm_get_xstate_msr(struct kvm_vcpu *vcpu,
+ struct msr_data *msr_info)
+{
+ KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm);
+ kvm_fpu_get();
+ rdmsrq(msr_info->index, msr_info->data);
+ kvm_fpu_put();
+}
+
+static inline void kvm_set_xstate_msr(struct kvm_vcpu *vcpu,
+ struct msr_data *msr_info)
+{
+ KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm);
+ kvm_fpu_get();
+ wrmsrq(msr_info->index, msr_info->data);
+ kvm_fpu_put();
+}
+
#endif
