[RFC v2 7/7] KVM: VMX: Enable PKS for nested VM

From: Chenyi Qiang
Date: Tue Oct 13 2020 - 22:10:29 EST

Next message: Chenyi Qiang: "[RFC v2 3/7] KVM: MMU: Rename the pkru to pkr"
Previous message: Chenyi Qiang: "[kvm-unit-tests PATCH] x86: Add tests for PKS"
In reply to: Chenyi Qiang: "[kvm-unit-tests PATCH] x86: Add tests for PKS"
Next in thread: Chenyi Qiang: "[RFC v2 3/7] KVM: MMU: Rename the pkru to pkr"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

PKS MSR passes through guest directly. Configure the MSR to match the
L0/L1 settings so that nested VM runs PKS properly.

Signed-off-by: Chenyi Qiang <chenyi.qiang@xxxxxxxxx>
---
arch/x86/kvm/vmx/nested.c | 37 +++++++++++++++++++++++++++++++++++--
arch/x86/kvm/vmx/vmcs12.c | 2 ++
arch/x86/kvm/vmx/vmcs12.h | 6 +++++-
arch/x86/kvm/vmx/vmx.c | 10 ++++++++++
arch/x86/kvm/vmx/vmx.h | 1 +
5 files changed, 53 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 14f56e8dd060..66c74d10dda5 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -652,6 +652,12 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
MSR_IA32_PRED_CMD,
MSR_TYPE_W);

+ if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PKRS))
+ nested_vmx_disable_intercept_for_msr(
+ msr_bitmap_l1, msr_bitmap_l0,
+ MSR_IA32_PKRS,
+ MSR_TYPE_R | MSR_TYPE_W);
+
kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false);

return true;
@@ -2433,6 +2439,10 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
if (kvm_mpx_supported() && vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+
+ if (vmx->nested.nested_run_pending &&
+ (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PKRS))
+ vmcs_write64(GUEST_IA32_PKRS, vmcs12->guest_ia32_pkrs);
}

if (nested_cpu_has_xsaves(vmcs12))
@@ -2521,6 +2531,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
+
+ if (kvm_cpu_cap_has(X86_FEATURE_PKS) &&
+ (!vmx->nested.nested_run_pending ||
+ !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PKRS)))
+ vmcs_write64(GUEST_IA32_PKRS, vmx->nested.vmcs01_guest_pkrs);
vmx_set_rflags(vcpu, vmcs12->guest_rflags);

/* EXCEPTION_BITMAP and CR0_GUEST_HOST_MASK should basically be the
@@ -2861,6 +2876,10 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
vmcs12->host_ia32_perf_global_ctrl)))
return -EINVAL;

+ if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PKRS) &&
+ CC(!kvm_pkrs_valid(vmcs12->host_ia32_pkrs)))
+ return -EINVAL;
+
#ifdef CONFIG_X86_64
ia32e = !!(vcpu->arch.efer & EFER_LMA);
#else
@@ -3010,6 +3029,10 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
if (nested_check_guest_non_reg_state(vmcs12))
return -EINVAL;

+ if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PKRS) &&
+ CC(!kvm_pkrs_valid(vmcs12->guest_ia32_pkrs)))
+ return -EINVAL;
+
return 0;
}

@@ -3320,6 +3343,9 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
if (kvm_mpx_supported() &&
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
+ if (kvm_cpu_cap_has(X86_FEATURE_PKS) &&
+ !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PKRS))
+ vmx->nested.vmcs01_guest_pkrs = vmcs_read64(GUEST_IA32_PKRS);

/*
* Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and*
@@ -3913,6 +3939,7 @@ static bool is_vmcs12_ext_field(unsigned long field)
case GUEST_IDTR_BASE:
case GUEST_PENDING_DBG_EXCEPTIONS:
case GUEST_BNDCFGS:
+ case GUEST_IA32_PKRS:
return true;
default:
break;
@@ -3964,6 +3991,8 @@ static void sync_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
if (kvm_mpx_supported())
vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
+ if (guest_cpuid_has(vcpu, X86_FEATURE_PKS))
+ vmcs12->guest_ia32_pkrs = vmcs_read64(GUEST_IA32_PKRS);

vmx->nested.need_sync_vmcs02_to_vmcs12_rare = false;
}
@@ -4199,6 +4228,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
vmcs12->host_ia32_perf_global_ctrl));

+ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PKRS)
+ vmcs_write64(GUEST_IA32_PKRS, vmcs12->host_ia32_pkrs);
+
/* Set L1 segment info according to Intel SDM
27.5.2 Loading Host Segment and Descriptor-Table Registers */
seg = (struct kvm_segment) {
@@ -6319,7 +6351,8 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
#ifdef CONFIG_X86_64
VM_EXIT_HOST_ADDR_SPACE_SIZE |
#endif
- VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+ VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
+ VM_EXIT_LOAD_IA32_PKRS;
msrs->exit_ctls_high |=
VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
@@ -6338,7 +6371,7 @@ void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
#ifdef CONFIG_X86_64
VM_ENTRY_IA32E_MODE |
#endif
- VM_ENTRY_LOAD_IA32_PAT;
+ VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_PKRS;
msrs->entry_ctls_high |=
(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);

diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c
index c8e51c004f78..df7b2143b807 100644
--- a/arch/x86/kvm/vmx/vmcs12.c
+++ b/arch/x86/kvm/vmx/vmcs12.c
@@ -61,9 +61,11 @@ const unsigned short vmcs_field_to_offset_table[] = {
FIELD64(GUEST_PDPTR2, guest_pdptr2),
FIELD64(GUEST_PDPTR3, guest_pdptr3),
FIELD64(GUEST_BNDCFGS, guest_bndcfgs),
+ FIELD64(GUEST_IA32_PKRS, guest_ia32_pkrs),
FIELD64(HOST_IA32_PAT, host_ia32_pat),
FIELD64(HOST_IA32_EFER, host_ia32_efer),
FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl),
+ FIELD64(HOST_IA32_PKRS, host_ia32_pkrs),
FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control),
FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control),
FIELD(EXCEPTION_BITMAP, exception_bitmap),
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 80232daf00ff..009b4c317375 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -69,7 +69,9 @@ struct __packed vmcs12 {
u64 vm_function_control;
u64 eptp_list_address;
u64 pml_address;
- u64 padding64[3]; /* room for future expansion */
+ u64 guest_ia32_pkrs;
+ u64 host_ia32_pkrs;
+ u64 padding64[1]; /* room for future expansion */
/*
* To allow migration of L1 (complete with its L2 guests) between
* machines of different natural widths (32 or 64 bit), we cannot have
@@ -256,6 +258,8 @@ static inline void vmx_check_vmcs12_offsets(void)
CHECK_OFFSET(vm_function_control, 296);
CHECK_OFFSET(eptp_list_address, 304);
CHECK_OFFSET(pml_address, 312);
+ CHECK_OFFSET(guest_ia32_pkrs, 320);
+ CHECK_OFFSET(host_ia32_pkrs, 328);
CHECK_OFFSET(cr0_guest_host_mask, 344);
CHECK_OFFSET(cr4_guest_host_mask, 352);
CHECK_OFFSET(cr0_read_shadow, 360);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ce24226e1aa3..7635104a4eb7 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7260,6 +7260,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
cr4_fixed1_update(X86_CR4_PKE, ecx, feature_bit(PKU));
cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP));
cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57));
+ cr4_fixed1_update(X86_CR4_PKS, ecx, feature_bit(PKS));

#undef cr4_fixed1_update
}
@@ -7279,6 +7280,15 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS;
}
}
+
+ if (kvm_cpu_cap_has(X86_FEATURE_PKS) &&
+ guest_cpuid_has(vcpu, X86_FEATURE_PKS)) {
+ vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_IA32_PKRS;
+ vmx->nested.msrs.exit_ctls_high |= VM_EXIT_LOAD_IA32_PKRS;
+ } else {
+ vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_IA32_PKRS;
+ vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_LOAD_IA32_PKRS;
+ }
}

static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a0e47720f60c..6b21b3529afb 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -177,6 +177,7 @@ struct nested_vmx {
/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
u64 vmcs01_debugctl;
u64 vmcs01_guest_bndcfgs;
+ u64 vmcs01_guest_pkrs;

/* to migrate it to L1 if L2 writes to L1's CR8 directly */
int l1_tpr_threshold;
--
2.17.1

Next message: Chenyi Qiang: "[RFC v2 3/7] KVM: MMU: Rename the pkru to pkr"
Previous message: Chenyi Qiang: "[kvm-unit-tests PATCH] x86: Add tests for PKS"
In reply to: Chenyi Qiang: "[kvm-unit-tests PATCH] x86: Add tests for PKS"
Next in thread: Chenyi Qiang: "[RFC v2 3/7] KVM: MMU: Rename the pkru to pkr"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]