module_param(eager_page_split, bool, 0644);
/* Enable/disable SMT_RSB bug mitigation */
-bool __read_mostly mitigate_smt_rsb;
+static bool __read_mostly mitigate_smt_rsb;
module_param(mitigate_smt_rsb, bool, 0444);
/*
*/
if ((fault->error_code & PFERR_PRESENT_MASK) &&
!(fault->error_code & PFERR_RSVD_MASK))
- kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address,
- fault_mmu->root.hpa);
+ kvm_mmu_invalidate_addr(vcpu, fault_mmu, fault->address,
+ KVM_MMU_ROOT_CURRENT);
fault_mmu->inject_page_fault(vcpu, fault);
}
bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr)
{
- if ((dr != 4 && dr != 5) || !kvm_read_cr4_bits(vcpu, X86_CR4_DE))
+ if ((dr != 4 && dr != 5) || !kvm_is_cr4_bit_set(vcpu, X86_CR4_DE))
return true;
kvm_queue_exception(vcpu, UD_VECTOR);
void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0)
{
+ /*
+ * CR0.WP is incorporated into the MMU role, but only for non-nested,
+ * indirect shadow MMUs. If paging is disabled, no updates are needed
+ * as there are no permission bits to emulate. If TDP is enabled, the
+ * MMU's metadata needs to be updated, e.g. so that emulating guest
+ * translations does the right thing, but there's no need to unload the
+ * root as CR0.WP doesn't affect SPTEs.
+ */
+ if ((cr0 ^ old_cr0) == X86_CR0_WP) {
+ if (!(cr0 & X86_CR0_PG))
+ return;
+
+ if (tdp_enabled) {
+ kvm_init_mmu(vcpu);
+ return;
+ }
+ }
+
if ((cr0 ^ old_cr0) & X86_CR0_PG) {
kvm_clear_async_pf_completion_queue(vcpu);
kvm_async_pf_hash_reset(vcpu);
return 1;
if (!(cr0 & X86_CR0_PG) &&
- (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)))
+ (is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)))
return 1;
static_call(kvm_x86_set_cr0)(vcpu, cr0);
if (vcpu->arch.guest_state_protected)
return;
- if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+ if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) {
if (vcpu->arch.xcr0 != host_xcr0)
xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
if (static_cpu_has(X86_FEATURE_PKU) &&
vcpu->arch.pkru != vcpu->arch.host_pkru &&
((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) ||
- kvm_read_cr4_bits(vcpu, X86_CR4_PKE)))
+ kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)))
write_pkru(vcpu->arch.pkru);
#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
}
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (static_cpu_has(X86_FEATURE_PKU) &&
((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) ||
- kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) {
+ kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) {
vcpu->arch.pkru = rdpkru();
if (vcpu->arch.pkru != vcpu->arch.host_pkru)
write_pkru(vcpu->arch.host_pkru);
}
#endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
- if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
+ if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) {
if (vcpu->arch.xcr0 != host_xcr0)
xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
return 1;
if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) {
- if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID))
- return 1;
-
/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu))
return 1;
* PCIDs for them are also 0, because MOV to CR3 always flushes the TLB
* with PCIDE=0.
*/
- if (!kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))
+ if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE))
return;
for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++)
bool skip_tlb_flush = false;
unsigned long pcid = 0;
#ifdef CONFIG_X86_64
- bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
-
- if (pcid_enabled) {
+ if (kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) {
skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH;
cr3 &= ~X86_CR3_PCID_NOFLUSH;
pcid = cr3 & X86_CR3_PCID_MASK;
static unsigned num_emulated_msrs;
/*
- * List of msr numbers which are used to expose MSR-based features that
- * can be used by a hypervisor to validate requested CPU features.
+ * List of MSRs that control the existence of MSR-based features, i.e. MSRs
+ * that are effectively CPUID leafs. VMX MSRs are also included in the set of
+ * feature MSRs, but are handled separately to allow expedited lookups.
*/
-static const u32 msr_based_features_all[] = {
- MSR_IA32_VMX_BASIC,
- MSR_IA32_VMX_TRUE_PINBASED_CTLS,
- MSR_IA32_VMX_PINBASED_CTLS,
- MSR_IA32_VMX_TRUE_PROCBASED_CTLS,
- MSR_IA32_VMX_PROCBASED_CTLS,
- MSR_IA32_VMX_TRUE_EXIT_CTLS,
- MSR_IA32_VMX_EXIT_CTLS,
- MSR_IA32_VMX_TRUE_ENTRY_CTLS,
- MSR_IA32_VMX_ENTRY_CTLS,
- MSR_IA32_VMX_MISC,
- MSR_IA32_VMX_CR0_FIXED0,
- MSR_IA32_VMX_CR0_FIXED1,
- MSR_IA32_VMX_CR4_FIXED0,
- MSR_IA32_VMX_CR4_FIXED1,
- MSR_IA32_VMX_VMCS_ENUM,
- MSR_IA32_VMX_PROCBASED_CTLS2,
- MSR_IA32_VMX_EPT_VPID_CAP,
- MSR_IA32_VMX_VMFUNC,
-
+static const u32 msr_based_features_all_except_vmx[] = {
MSR_AMD64_DE_CFG,
MSR_IA32_UCODE_REV,
MSR_IA32_ARCH_CAPABILITIES,
MSR_IA32_PERF_CAPABILITIES,
};
-static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)];
+static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) +
+ (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)];
static unsigned int num_msr_based_features;
/*
+ * All feature MSRs except uCode revID, which tracks the currently loaded uCode
+ * patch, are immutable once the vCPU model is defined.
+ */
+static bool kvm_is_immutable_feature_msr(u32 msr)
+{
+ int i;
+
+ if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR)
+ return true;
+
+ for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) {
+ if (msr == msr_based_features_all_except_vmx[i])
+ return msr != MSR_IA32_UCODE_REV;
+ }
+
+ return false;
+}
+
+/*
* Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM
* does not yet virtualize. These include:
* 10 - MISC_PACKAGE_CTRLS
static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
{
+ u64 val;
+
+ /*
+ * Disallow writes to immutable feature MSRs after KVM_RUN. KVM does
+ * not support modifying the guest vCPU model on the fly, e.g. changing
+ * the nVMX capabilities while L2 is running is nonsensical. Ignore
+ * writes of the same value, e.g. to allow userspace to blindly stuff
+ * all MSRs when emulating RESET.
+ */
+ if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index)) {
+ if (do_get_msr(vcpu, index, &val) || *data != val)
+ return -EINVAL;
+
+ return 0;
+ }
+
return kvm_set_msr_ignored_check(vcpu, index, *data, true);
}
if (data & ~kvm_caps.supported_perf_cap)
return 1;
+ /*
+ * Note, this is not just a performance optimization! KVM
+ * disallows changing feature MSRs after the vCPU has run; PMU
+ * refresh will bug the VM if called after the vCPU has run.
+ */
+ if (vcpu->arch.perf_capabilities == data)
+ break;
+
vcpu->arch.perf_capabilities = data;
kvm_pmu_refresh(vcpu);
- return 0;
+ break;
+ case MSR_IA32_PRED_CMD:
+ if (!msr_info->host_initiated && !guest_has_pred_cmd_msr(vcpu))
+ return 1;
+
+ if (!boot_cpu_has(X86_FEATURE_IBPB) || (data & ~PRED_CMD_IBPB))
+ return 1;
+ if (!data)
+ break;
+
+ wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
+ break;
+ case MSR_IA32_FLUSH_CMD:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D))
+ return 1;
+
+ if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH))
+ return 1;
+ if (!data)
+ break;
+
+ wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+ break;
case MSR_EFER:
return set_efer(vcpu, msr_info);
case MSR_K7_HWCR:
r = 0;
break;
case KVM_CAP_XSAVE2: {
- u64 guest_perm = xstate_get_guest_group_perm();
-
- r = xstate_required_size(kvm_caps.supported_xcr0 & guest_perm, false);
+ r = xstate_required_size(kvm_get_filtered_xcr0(), false);
if (r < sizeof(struct kvm_xsave))
r = sizeof(struct kvm_xsave);
break;
return 0;
if (mce->status & MCI_STATUS_UC) {
if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) ||
- !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) {
+ !kvm_is_cr4_bit_set(vcpu, X86_CR4_MCE)) {
kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
return 0;
}
return r;
}
+static void kvm_probe_feature_msr(u32 msr_index)
+{
+ struct kvm_msr_entry msr = {
+ .index = msr_index,
+ };
+
+ if (kvm_get_msr_feature(&msr))
+ return;
+
+ msr_based_features[num_msr_based_features++] = msr_index;
+}
+
static void kvm_probe_msr_to_save(u32 msr_index)
{
u32 dummy[2];
msrs_to_save[num_msrs_to_save++] = msr_index;
}
-static void kvm_init_msr_list(void)
+static void kvm_init_msr_lists(void)
{
unsigned i;
emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i];
}
- for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) {
- struct kvm_msr_entry msr;
+ for (i = KVM_FIRST_EMULATED_VMX_MSR; i <= KVM_LAST_EMULATED_VMX_MSR; i++)
+ kvm_probe_feature_msr(i);
- msr.index = msr_based_features_all[i];
- if (kvm_get_msr_feature(&msr))
- continue;
-
- msr_based_features[num_msr_based_features++] = msr_based_features_all[i];
- }
+ for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++)
+ kvm_probe_feature_msr(msr_based_features_all_except_vmx[i]);
}
static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len,
kvm_caps.max_guest_tsc_khz = max;
}
kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits;
- kvm_init_msr_list();
+ kvm_init_msr_lists();
return 0;
out_unwind_ops:
vcpu->run->hypercall.args[0] = gpa;
vcpu->run->hypercall.args[1] = npages;
vcpu->run->hypercall.args[2] = attrs;
- vcpu->run->hypercall.longmode = op_64_bit;
+ vcpu->run->hypercall.flags = 0;
+ if (op_64_bit)
+ vcpu->run->hypercall.flags |= KVM_EXIT_HYPERCALL_LONG_MODE;
+
+ WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ);
vcpu->arch.complete_userspace_io = complete_hypercall_exit;
return 0;
}
return 1;
}
- pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE);
+ pcid_enabled = kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE);
switch (type) {
case INVPCID_TYPE_INDIV_ADDR: