On Thu, Apr 01, 2021, Maxim Levitsky wrote:
> Similar to the rest of guest page accesses after migration,
> this should be delayed to KVM_REQ_GET_NESTED_STATE_PAGES
> request.
FWIW, I still object to this approach, and this patch has a plethora of issues.
I'm not against deferring various state loading to KVM_RUN, but wholesale moving
all of GUEST_CR3 processing without in-depth consideration of all the side
effects is a really bad idea.
> Signed-off-by: Maxim Levitsky <mlevi...@redhat.com>
> ---
> arch/x86/kvm/vmx/nested.c | 14 +++++++++-----
> 1 file changed, 9 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> index fd334e4aa6db..b44f1f6b68db 100644
> --- a/arch/x86/kvm/vmx/nested.c
> +++ b/arch/x86/kvm/vmx/nested.c
> @@ -2564,11 +2564,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu,
> struct vmcs12 *vmcs12,
> return -EINVAL;
> }
>
> - /* Shadow page tables on either EPT or shadow page tables. */
> - if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3,
> nested_cpu_has_ept(vmcs12),
> - entry_failure_code))
> - return -EINVAL;
> -
> /*
> * Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12
> * on nested VM-Exit, which can occur without actually running L2 and
> @@ -3109,11 +3104,16 @@ static bool nested_get_evmcs_page(struct kvm_vcpu
> *vcpu)
> static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
> {
> struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
> + enum vm_entry_failure_code entry_failure_code;
> struct vcpu_vmx *vmx = to_vmx(vcpu);
> struct kvm_host_map *map;
> struct page *page;
> u64 hpa;
>
> + if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3,
> nested_cpu_has_ept(vmcs12),
> + &entry_failure_code))
This results in KVM_RUN returning 0 without filling vcpu->run->exit_reason.
Speaking from experience, debugging those types of issues is beyond painful.
It also means CR3 is double loaded in the from_vmentry case.
And it will cause KVM to incorrectly return NVMX_VMENTRY_KVM_INTERNAL_ERROR
if a consistency check fails when nested_get_vmcs12_pages() is called on
from_vmentry. E.g. run unit tests with this and it will silently disappear.
diff --git a/x86/vmx_tests.c b/x86/vmx_tests.c
index bbb006a..b8ccc69 100644
--- a/x86/vmx_tests.c
+++ b/x86/vmx_tests.c
@@ -8172,6 +8172,16 @@ static void test_guest_segment_base_addr_fields(void)
vmcs_write(GUEST_AR_ES, ar_saved);
}
+static void test_guest_cr3(void)
+{
+ u64 cr3_saved = vmcs_read(GUEST_CR3);
+
+ vmcs_write(GUEST_CR3, -1ull);
+ test_guest_state("Bad CR3 fails VM-Enter", true, -1ull, "GUEST_CR3");
+
+ vmcs_write(GUEST_DR7, cr3_saved);
+}
+
/*
* Check that the virtual CPU checks the VMX Guest State Area as
* documented in the Intel SDM.
@@ -8181,6 +8191,8 @@ static void vmx_guest_state_area_test(void)
vmx_set_test_stage(1);
test_set_guest(guest_state_test_main);
+ test_guest_cr3();
+
/*
* The IA32_SYSENTER_ESP field and the IA32_SYSENTER_EIP field
* must each contain a canonical address.
> + return false;
> +
> if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
> /*
> * Translate L1 physical address to host physical
> @@ -3357,6 +3357,10 @@ enum nvmx_vmentry_status
> nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
> }
>
> if (from_vmentry) {
> + if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3,
> + nested_cpu_has_ept(vmcs12), &entry_failure_code))
This alignment is messed up; it looks like two separate function calls.
> + goto vmentry_fail_vmexit_guest_mode;
> +
> failed_index = nested_vmx_load_msr(vcpu,
>
> vmcs12->vm_entry_msr_load_addr,
>
> vmcs12->vm_entry_msr_load_count);
> --
> 2.26.2
>
