From 4535a0c603c5c8c64bb6e4056a44dbe4ede1136f Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Mon, 3 May 2021 17:08:51 +0200 Subject: [PATCH] KVM: nVMX: Always make an attempt to map eVMCS after migration BugLink: https://bugs.launchpad.net/bugs/1931292 commit f5c7e8425f18fdb9bdb7d13340651d7876890329 upstream. When enlightened VMCS is in use and nested state is migrated with vmx_get_nested_state()/vmx_set_nested_state() KVM can't map evmcs page right away: evmcs gpa is not 'struct kvm_vmx_nested_state_hdr' and we can't read it from VP assist page because userspace may decide to restore HV_X64_MSR_VP_ASSIST_PAGE after restoring nested state (and QEMU, for example, does exactly that). To make sure eVMCS is mapped /vmx_set_nested_state() raises KVM_REQ_GET_NESTED_STATE_PAGES request. Commit f2c7ef3ba955 ("KVM: nSVM: cancel KVM_REQ_GET_NESTED_STATE_PAGES on nested vmexit") added KVM_REQ_GET_NESTED_STATE_PAGES clearing to nested_vmx_vmexit() to make sure MSR permission bitmap is not switched when an immediate exit from L2 to L1 happens right after migration (caused by a pending event, for example). Unfortunately, in the exact same situation we still need to have eVMCS mapped so nested_sync_vmcs12_to_shadow() reflects changes in VMCS12 to eVMCS. As a band-aid, restore nested_get_evmcs_page() when clearing KVM_REQ_GET_NESTED_STATE_PAGES in nested_vmx_vmexit(). The 'fix' is far from being ideal as we can't easily propagate possible failures and even if we could, this is most likely already too late to do so. The whole 'KVM_REQ_GET_NESTED_STATE_PAGES' idea for mapping eVMCS after migration seems to be fragile as we diverge too much from the 'native' path when vmptr loading happens on vmx_set_nested_state(). Fixes: f2c7ef3ba955 ("KVM: nSVM: cancel KVM_REQ_GET_NESTED_STATE_PAGES on nested vmexit") Signed-off-by: Vitaly Kuznetsov Message-Id: <20210503150854.1144255-2-vkuznets@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini Signed-off-by: Greg Kroah-Hartman Signed-off-by: Kamal Mostafa Signed-off-by: Stefan Bader --- arch/x86/kvm/vmx/nested.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0c41ffb7957f..9aec6b4476cd 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3140,15 +3140,8 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) nested_vmx_handle_enlightened_vmptrld(vcpu, false); if (evmptrld_status == EVMPTRLD_VMFAIL || - evmptrld_status == EVMPTRLD_ERROR) { - pr_debug_ratelimited("%s: enlightened vmptrld failed\n", - __func__); - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + evmptrld_status == EVMPTRLD_ERROR) return false; - } } return true; @@ -3236,8 +3229,16 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { - if (!nested_get_evmcs_page(vcpu)) + if (!nested_get_evmcs_page(vcpu)) { + pr_debug_ratelimited("%s: enlightened vmptrld failed\n", + __func__); + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + vcpu->run->internal.suberror = + KVM_INTERNAL_ERROR_EMULATION; + vcpu->run->internal.ndata = 0; + return false; + } if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -4467,7 +4468,15 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); - kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { + /* + * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map + * Enlightened VMCS after migration and we still need to + * do that when something is forcing L2->L1 exit prior to + * the first L2 run. + */ + (void)nested_get_evmcs_page(vcpu); + } /* Service the TLB flush request for L2 before switching to L1. */ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) -- 2.39.5