On Thu, Feb 28, 2019 at 04:28:32PM +0800, Yang Weijiang wrote:
> On Thu, Feb 28, 2019 at 07:59:40AM -0800, Sean Christopherson wrote:
> > On Mon, Feb 25, 2019 at 09:27:11PM +0800, Yang Weijiang wrote:
> > > Guest CET SHSTK and IBT capability are reported via
> > > CPUID.(EAX=7, ECX=0):ECX[bit 7] and EDX[bit 20] respectively.
> > > Guest user mode and supervisor mode xsaves component size
> > > is reported via CPUID.(EAX=0xD, ECX=1):ECX[bit 11] and ECX[bit 12]
> > > respectively.
> > >
> > > Signed-off-by: Zhang Yi Z <yi.z.zhang@xxxxxxxxxxxxxxx>
> > > Signed-off-by: Yang Weijiang <weijiang.yang@xxxxxxxxx>
> > > ---
> > > arch/x86/kvm/cpuid.c | 60 +++++++++++++++++++++++++++++++++-----------
> > > arch/x86/kvm/x86.h | 4 +++
> > > 2 files changed, 50 insertions(+), 14 deletions(-)
> > >
> > > diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
> > > index cb1aece25b17..5e05756cc6db 100644
> > > --- a/arch/x86/kvm/cpuid.c
> > > +++ b/arch/x86/kvm/cpuid.c
> > > @@ -65,6 +65,16 @@ u64 kvm_supported_xcr0(void)
> > > return xcr0;
> > > }
> > >
> > > +u64 kvm_supported_xss(void)
> > > +{
> > > + u64 xss;
> > > +
> > > + rdmsrl(MSR_IA32_XSS, xss);
> > > + xss &= KVM_SUPPORTED_XSS;
> > > + return xss;
> > > +}
> > > +EXPORT_SYMBOL(kvm_supported_xss);
> > > +
> > > #define F(x) bit(X86_FEATURE_##x)
> > >
> > > /* For scattered features from cpufeatures.h; we currently expose none */
> > > @@ -323,6 +333,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
> > > u32 index, int *nent, int maxnent)
> > > {
> > > int r;
> > > + u32 eax, ebx, ecx, edx;
> > > unsigned f_nx = is_efer_nx() ? F(NX) : 0;
> > > #ifdef CONFIG_X86_64
> > > unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
> > > @@ -503,6 +514,20 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
> > > * if the host doesn't support it.
> > > */
> > > entry->edx |= F(ARCH_CAPABILITIES);
> > > +
> > > + /*
> > > + * Guest OS CET enabling is designed independent to
> > > + * host enabling, it only has dependency on Host HW
> > > + * capability, if it has, report CET support to
> > > + * Guest.
> > > + */
> > > + cpuid_count(7, 0, &eax, &ebx, &ecx, &edx);
> > > + if (ecx & F(SHSTK))
> > > + entry->ecx |= F(SHSTK);
> > > +
> > > + if (edx & F(IBT))
> > > + entry->edx |= F(IBT);
> >
> > There's no need to manually add these flags. They will be automatically
> > kept if supported in hardware because your previous patch, 02/08, added
> > them to the mask of features that can be exposed to the guest,
> > i.e. set them in kvm_cpuid_7_0_e{c,d}x_x86_features.
> >
> I shared the same thought as you before, but after I took a closer look at the
> kernel code, actually, when host CET feature is disabled by user via
> cmdline options(no_cet_shstk and no_cet_ibt), it'll mask out CET feature bits in
> boot_cpu_data.x86_capbility[] array, and cpuid_mask() will make the bits
> in previous definition lost, so these lines actually add them back when
> host CET is disabled.
'entry' is filled by do_cpuid_1_ent(), which does cpuid_count(), same as
your code, i.e. it's not affected by whether or not the host kernel is
using each feature.
> please check CET kernel patch here:
> https://lkml.org/lkml/2018/11/20/204
>
> > > +
> > > } else {
> > > entry->ebx = 0;
> > > entry->ecx = 0;
> > > @@ -564,14 +589,17 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
> > > }
> > > case 0xd: {
> > > int idx, i;
> > > - u64 supported = kvm_supported_xcr0();
> > > + u64 u_supported = kvm_supported_xcr0();
> > > + u64 s_supported = kvm_supported_xss();
> > > + u64 supported;
> > > + int compacted;
> > >
> > > - entry->eax &= supported;
> > > - entry->ebx = xstate_required_size(supported, false);
> > > + entry->eax &= u_supported;
> > > + entry->ebx = xstate_required_size(u_supported, false);
> > > entry->ecx = entry->ebx;
> > > - entry->edx &= supported >> 32;
> > > + entry->edx &= u_supported >> 32;
> > > entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
> > > - if (!supported)
> > > + if (!u_supported && !s_supported)
> > > break;
> > >
> > > for (idx = 1, i = 1; idx < 64; ++idx) {
> > > @@ -583,19 +611,23 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
> > > if (idx == 1) {
> > > entry[i].eax &= kvm_cpuid_D_1_eax_x86_features;
> > > cpuid_mask(&entry[i].eax, CPUID_D_1_EAX);
> > > - entry[i].ebx = 0;
> > > - if (entry[i].eax & (F(XSAVES)|F(XSAVEC)))
> > > - entry[i].ebx =
> > > - xstate_required_size(supported,
> > > - true);
> > > + supported = u_supported | s_supported;
> > > + compacted = entry[i].eax &
> > > + (F(XSAVES) | F(XSAVEC));
> > > + entry[i].ebx = xstate_required_size(supported,
> > > + compacted);
> > > + entry[i].ecx &= s_supported;
> > > + entry[i].edx = 0;
> > > } else {
> > > + supported = (entry[i].ecx & 1) ? s_supported :
> > > + u_supported;
> > > if (entry[i].eax == 0 || !(supported & mask))
> > > continue;
> > > - if (WARN_ON_ONCE(entry[i].ecx & 1))
> > > - continue;
> > > + entry[i].ecx &= 1;
> > > + entry[i].edx = 0;
> > > + if (entry[i].ecx)
> > > + entry[i].ebx = 0;
> > > }
> > > - entry[i].ecx = 0;
> > > - entry[i].edx = 0;
> > > entry[i].flags |=
> > > KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
> > > ++*nent;
> > > diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
> > > index 224cd0a47568..c61da41c3c5c 100644
> > > --- a/arch/x86/kvm/x86.h
> > > +++ b/arch/x86/kvm/x86.h
> > > @@ -283,6 +283,10 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
> > > | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \
> > > | XFEATURE_MASK_BNDCSR | XFEATURE_MASK_AVX512 \
> > > | XFEATURE_MASK_PKRU)
> > > +
> > > +#define KVM_SUPPORTED_XSS (XFEATURE_MASK_SHSTK_USER \
> > > + | XFEATURE_MASK_SHSTK_KERNEL)
> > > +
> > > extern u64 host_xcr0;
> > >
> > > extern u64 kvm_supported_xcr0(void);
> > > --
> > > 2.17.1
> > >
