KVM: x86: Reinstate kvm_vcpu_arch.guest_supported_xcr0

Reinstate the per-vCPU guest_supported_xcr0 by partially reverting
commit 988896bb6182; the implicit assessment that guest_supported_xcr0 is
always the same as guest_fpu.fpstate->user_xfeatures was incorrect.

kvm_vcpu_after_set_cpuid() isn't the only place that sets user_xfeatures,
as user_xfeatures is set to fpu_user_cfg.default_features when guest_fpu
is allocated via fpu_alloc_guest_fpstate() => __fpstate_reset().
guest_supported_xcr0 on the other hand is zero-allocated.  If userspace
never invokes KVM_SET_CPUID2, supported XCR0 will be '0', whereas the
allowed user XFEATURES will be non-zero.

Practically speaking, the edge case likely doesn't matter as no sane
userspace will live migrate a VM without ever doing KVM_SET_CPUID2. The
primary motivation is to prepare for KVM intentionally and explicitly
setting bits in user_xfeatures that are not set in guest_supported_xcr0.

Because KVM_{G,S}ET_XSAVE can be used to svae/restore FP+SSE state even
if the host doesn't support XSAVE, KVM needs to set the FP+SSE bits in
user_xfeatures even if they're not allowed in XCR0, e.g. because XCR0
isn't exposed to the guest.  At that point, the simplest fix is to track
the two things separately (allowed save/restore vs. allowed XCR0).

Fixes: 988896bb6182 ("x86/kvm/fpu: Remove kvm_vcpu_arch.guest_supported_xcr0")
Cc: stable@vger.kernel.org
Cc: Leonardo Bras <leobras@redhat.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220824033057.3576315-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2c96c43c313a260659f82a822afe2a7f9c8a78ce..aa381ab69a1911ffb5afde4e49dc26ab67edc783 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -729,6 +729,7 @@ struct kvm_vcpu_arch {
        struct fpu_guest guest_fpu;
 
        u64 xcr0;
+       u64 guest_supported_xcr0;
 
        struct kvm_pio_request pio;
        void *pio_data;

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 75dcf7a72605f335d0f104b26986d17cc5cd81ec..2e0f27ad736a16285fd2b84b7a6cec7d210089bf 100644 (file)
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -315,7 +315,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
        struct kvm_lapic *apic = vcpu->arch.apic;
        struct kvm_cpuid_entry2 *best;
-       u64 guest_supported_xcr0;
 
        best = kvm_find_cpuid_entry(vcpu, 1);
        if (best && apic) {
@@ -327,10 +326,10 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
                kvm_apic_set_version(vcpu);
        }
 
-       guest_supported_xcr0 =
+       vcpu->arch.guest_supported_xcr0 =
                cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
 
-       vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0;
+       vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0;
 
        kvm_update_pv_runtime(vcpu);
 

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 43a6a7efc6ece04365b20be62893a521bd29c7c0..c95cf18a796c8f2a2ac8e59962edb624e9019d5e 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1011,15 +1011,10 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state);
 
-static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu)
-{
-       return vcpu->arch.guest_fpu.fpstate->user_xfeatures;
-}
-
 #ifdef CONFIG_X86_64
 static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu)
 {
-       return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC;
+       return vcpu->arch.guest_supported_xcr0 & XFEATURE_MASK_USER_DYNAMIC;
 }
 #endif
 
@@ -1042,7 +1037,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
         * saving.  However, xcr0 bit 0 is always set, even if the
         * emulated CPU does not support XSAVE (see kvm_vcpu_reset()).
         */
-       valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP;
+       valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP;
        if (xcr0 & ~valid_bits)
                return 1;