KVM: x86: Load guest FPU state when access XSAVE-managed MSRs

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.

Co-developed-by: Yang Weijiang <weijiang.yang@intel.com>
Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
Reviewed-by: Maxim Levitsky <mlevitsk@redhat.com>
Tested-by: Mathias Krause <minipli@grsecurity.net>
Tested-by: John Allen <john.allen@amd.com>
Tested-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Chao Gao <chao.gao@intel.com>
[sean: drop S_CET, add big comment, move accessors to x86.c]
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Reviewed-by: Xin Li (Intel) <xin@zytor.com>
Link: https://lore.kernel.org/r/20250919223258.1604852-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 831c5e488de3a50e6a299125f1edfd8422048729..c2e11f3d50fbbaded0607541ab4c867cacda5c45 100644 (file)
--- 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)                                            \
@@ -3801,6 +3804,67 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
        mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
 }
 
+/*
+ * Returns true if the MSR in question is managed via XSTATE, i.e. is context
+ * switched with the rest of guest FPU state.  Note!  S_CET is _not_ context
+ * switched via XSTATE even though it _is_ saved/restored via XSAVES/XRSTORS.
+ * Because S_CET is loaded on VM-Enter and VM-Exit via dedicated VMCS fields,
+ * the value saved/restored via XSTATE is always the host's value.  That detail
+ * is _extremely_ important, as the guest's S_CET must _never_ be resident in
+ * hardware while executing in the host.  Loading guest values for U_CET and
+ * PL[0-3]_SSP while executing in the kernel is safe, as U_CET is specific to
+ * userspace, and PL[0-3]_SSP are only consumed when transitioning to lower
+ * privilege levels, i.e. are effectively only consumed by userspace as well.
+ */
+static bool is_xstate_managed_msr(struct kvm_vcpu *vcpu, u32 msr)
+{
+       if (!vcpu)
+               return false;
+
+       switch (msr) {
+       case MSR_IA32_U_CET:
+               return guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK) ||
+                      guest_cpu_cap_has(vcpu, X86_FEATURE_IBT);
+       case MSR_IA32_PL0_SSP ... MSR_IA32_PL3_SSP:
+               return guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK);
+       default:
+               return false;
+       }
+}
+
+/*
+ * Lock (and if necessary, re-load) the guest FPU, i.e. XSTATE, and access an
+ * MSR that is managed via XSTATE.  Note, the caller is responsible for doing
+ * the initial FPU load, this helper only ensures that guest state is resident
+ * in hardware (the kernel can load its FPU state in IRQ context).
+ */
+static __always_inline void kvm_access_xstate_msr(struct kvm_vcpu *vcpu,
+                                                 struct msr_data *msr_info,
+                                                 int access)
+{
+       BUILD_BUG_ON(access != MSR_TYPE_R && access != MSR_TYPE_W);
+
+       KVM_BUG_ON(!is_xstate_managed_msr(vcpu, msr_info->index), vcpu->kvm);
+       KVM_BUG_ON(!vcpu->arch.guest_fpu.fpstate->in_use, vcpu->kvm);
+
+       kvm_fpu_get();
+       if (access == MSR_TYPE_R)
+               rdmsrq(msr_info->index, msr_info->data);
+       else
+               wrmsrq(msr_info->index, msr_info->data);
+       kvm_fpu_put();
+}
+
+static __maybe_unused void kvm_set_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+       kvm_access_xstate_msr(vcpu, msr_info, MSR_TYPE_W);
+}
+
+static __maybe_unused void kvm_get_xstate_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+       kvm_access_xstate_msr(vcpu, msr_info, MSR_TYPE_R);
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
        u32 msr = msr_info->index;
@@ -4551,11 +4615,25 @@ 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 and thus can be accessed
+                * via RDMSR/WRMSR.
+                */
+               if (!fpu_loaded && is_xstate_managed_msr(vcpu, 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;
 }
@@ -5965,6 +6043,7 @@ static int kvm_get_set_one_reg(struct kvm_vcpu *vcpu, unsigned int ioctl,
        struct kvm_one_reg one_reg;
        struct kvm_x86_reg_id *reg;
        u64 __user *user_val;
+       bool load_fpu;
        int r;
 
        if (copy_from_user(&one_reg, argp, sizeof(one_reg)))
@@ -5991,12 +6070,18 @@ static int kvm_get_set_one_reg(struct kvm_vcpu *vcpu, unsigned int ioctl,
 
        guard(srcu)(&vcpu->kvm->srcu);
 
+       load_fpu = is_xstate_managed_msr(vcpu, reg->index);
+       if (load_fpu)
+               kvm_load_guest_fpu(vcpu);
+
        user_val = u64_to_user_ptr(one_reg.addr);
        if (ioctl == KVM_GET_ONE_REG)
                r = kvm_get_one_msr(vcpu, reg->index, user_val);
        else
                r = kvm_set_one_msr(vcpu, reg->index, user_val);
 
+       if (load_fpu)
+               kvm_put_guest_fpu(vcpu);
        return r;
 }