Existence of PKS is enumerated via CPUID.(EAX=7H,ECX=0):ECX[31]. It is
enabled by setting CR4.PKS when long mode is active. PKS is only
implemented when EPT is enabled and requires the support of VM_{ENTRY,
EXIT}_LOAD_IA32_PKRS currently.
Signed-off-by: Chenyi Qiang <chenyi.qiang@xxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 3 ++-
arch/x86/kvm/cpuid.c | 3 ++-
arch/x86/kvm/vmx/vmx.c | 15 ++++++++++++---
arch/x86/kvm/x86.c | 9 +++++++--
4 files changed, 23 insertions(+), 7 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d5f0c3a71a41..d798433a2117 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -99,7 +99,8 @@
| X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
| X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
| X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \
- | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP))
+ | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \
+ | X86_CR4_PKS))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 3fd6eec202d7..6b725a3e84ec 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -354,7 +354,8 @@ void kvm_set_cpu_caps(void)
F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
- F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/
+ F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ |
+ 0 /*PKS*/
);
/* Set LA57 based on hardware capability. */
if (cpuid_ecx(7) & F(LA57))
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e5da5dbe19d4..ce24226e1aa3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3228,7 +3228,7 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
}
/*
- * SMEP/SMAP/PKU is disabled if CPU is in non-paging mode in
+ * SMEP/SMAP/PKU/PKS is disabled if CPU is in non-paging mode in
* hardware. To emulate this behavior, SMEP/SMAP/PKU needs
* to be manually disabled when guest switches to non-paging
* mode.
@@ -3236,10 +3236,11 @@ int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
* If !enable_unrestricted_guest, the CPU is always running
* with CR0.PG=1 and CR4 needs to be modified.
* If enable_unrestricted_guest, the CPU automatically
- * disables SMEP/SMAP/PKU when the guest sets CR0.PG=0.
+ * disables SMEP/SMAP/PKU/PKS when the guest sets CR0.PG=0.
*/
if (!is_paging(vcpu))
- hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE);
+ hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE |
+ X86_CR4_PKS);
}
vmcs_writel(CR4_READ_SHADOW, cr4);
@@ -7430,6 +7431,14 @@ static __init void vmx_set_cpu_caps(void)
if (vmx_pt_mode_is_host_guest())
kvm_cpu_cap_check_and_set(X86_FEATURE_INTEL_PT);
+ /*
+ * PKS is not yet implemented for shadow paging.
+ * If not support VM_{ENTRY, EXIT}_LOAD_IA32_PKRS,
+ * don't expose the PKS as well.
+ */
+ if (enable_ept && cpu_has_load_ia32_pkrs())
+ kvm_cpu_cap_check_and_set(X86_FEATURE_PKS);
+
if (vmx_umip_emulated())
kvm_cpu_cap_set(X86_FEATURE_UMIP);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ce856e0ece84..93ac708e951d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -976,7 +976,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
unsigned long old_cr4 = kvm_read_cr4(vcpu);
unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
X86_CR4_SMEP;
- unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE;
+ unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE |
+ X86_CR4_PKS;
if (kvm_valid_cr4(vcpu, cr4))
return 1;
@@ -1207,7 +1208,7 @@ static const u32 msrs_to_save_all[] = {
MSR_IA32_RTIT_ADDR1_A, MSR_IA32_RTIT_ADDR1_B,
MSR_IA32_RTIT_ADDR2_A, MSR_IA32_RTIT_ADDR2_B,
MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B,
- MSR_IA32_UMWAIT_CONTROL,
+ MSR_IA32_UMWAIT_CONTROL, MSR_IA32_PKRS,
MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_ARCH_PERFMON_FIXED_CTR0 + 3,
@@ -5426,6 +5427,10 @@ static void kvm_init_msr_list(void)
intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
continue;
break;
+ case MSR_IA32_PKRS:
+ if (!kvm_cpu_cap_has(X86_FEATURE_PKS))
+ continue;
+ break;
case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
--
2.17.1
