diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index b87fa32835f28730a670c85f34926af99c958de9..5d8db4922df6a843d2d6cbd4191dd8a282805d54 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -688,9 +688,14 @@ MSRs that have been set successfully. Defines the vcpu responses to the cpuid instruction. Applications should use the KVM_SET_CPUID2 ioctl if available. -Note, when this IOCTL fails, KVM gives no guarantees that previous valid CPUID -configuration (if there is) is not corrupted. Userspace can get a copy of the -resulting CPUID configuration through KVM_GET_CPUID2 in case. +Caveat emptor: + - If this IOCTL fails, KVM gives no guarantees that previous valid CPUID + configuration (if there is) is not corrupted. Userspace can get a copy + of the resulting CPUID configuration through KVM_GET_CPUID2 in case. + - Using KVM_SET_CPUID{,2} after KVM_RUN, i.e. changing the guest vCPU model + after running the guest, may cause guest instability. + - Using heterogeneous CPUID configurations, modulo APIC IDs, topology, etc... + may cause guest instability. :: diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f1e4d5f2bf8ddec8187c8f9a73bdd9d057f41584..f8faf3efc08d7592dfea84661341ac962a862976 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -840,7 +840,7 @@ struct kvm_vcpu_arch { bool l1tf_flush_l1d; /* Host CPU on which VM-entry was most recently attempted */ - unsigned int last_vmentry_cpu; + int last_vmentry_cpu; /* AMD MSRC001_0015 Hardware Configuration */ u64 msr_hwcr; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1ab3fdb1f2e43d67ca04fb04f01fc4e79b2a9904..36201c02a4729196da1ef687a67b5a9f43871566 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4913,6 +4913,26 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_mmu.mmu_role.ext.valid = 0; vcpu->arch.nested_mmu.mmu_role.ext.valid = 0; kvm_mmu_reset_context(vcpu); + + /* + * KVM does not correctly handle changing guest CPUID after KVM_RUN, as + * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't + * tracked in kvm_mmu_page_role. As a result, KVM may miss guest page + * faults due to reusing SPs/SPTEs. Alert userspace, but otherwise + * sweep the problem under the rug. + * + * KVM's horrific CPUID ABI makes the problem all but impossible to + * solve, as correctly handling multiple vCPU models (with respect to + * paging and physical address properties) in a single VM would require + * tracking all relevant CPUID information in kvm_mmu_page_role. That + * is very undesirable as it would double the memory requirements for + * gfn_track (see struct kvm_mmu_page_role comments), and in practice + * no sane VMM mucks with the core vCPU model on the fly. + */ + if (vcpu->arch.last_vmentry_cpu != -1) { + pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n"); + pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n"); + } } void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4bd10fb1dfd6b28cc522c41c1df57713c0c5d8ee..c862783035b8fb42bcb1f07a91217854d9966b16 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10602,6 +10602,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) struct page *page; int r; + vcpu->arch.last_vmentry_cpu = -1; + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else