Include pml5_root in the set of special roots if and only if the host,
and thus NPT, is using 5-level paging. mmu_alloc_special_roots() expects
special roots to be allocated as a bundle, i.e. they're either all valid
or all NULL. But for pml5_root, that expectation only holds true if the
host uses 5-level paging, which causes KVM to WARN about pml5_root being
NULL when the other special roots are valid.
The silver lining of 4-level vs. 5-level NPT being tied to the host
kernel's paging level is that KVM's shadow root level is constant; unlike
VMX's EPT, KVM can't choose 4-level NPT based on guest.MAXPHYADDR. That
means KVM can still expect pml5_root to be bundled with the other special
roots, it just needs to be conditioned on the shadow root level.
Fixes: cb0f722aff6e ("KVM: x86/mmu: Support shadowing NPT when 5-level paging is enabled in host")
Reported-by: Maxim Levitsky <mlevitsk@xxxxxxxxxx>
Reviewed-by: Maxim Levitsky <mlevitsk@xxxxxxxxxx>
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
arch/x86/kvm/mmu/mmu.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 4853c033e6ce..39c7b5a587df 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3548,6 +3548,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
{
struct kvm_mmu *mmu = vcpu->arch.mmu;
+ bool need_pml5 = mmu->shadow_root_level > PT64_ROOT_4LEVEL;
u64 *pml5_root = NULL;
u64 *pml4_root = NULL;
u64 *pae_root;
@@ -3562,7 +3563,14 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
mmu->shadow_root_level < PT64_ROOT_4LEVEL)
return 0;
- if (mmu->pae_root && mmu->pml4_root && mmu->pml5_root)
+ /*
+ * NPT, the only paging mode that uses this horror, uses a fixed number
+ * of levels for the shadow page tables, e.g. all MMUs are 4-level or
+ * all MMus are 5-level. Thus, this can safely require that pml5_root
+ * is allocated if the other roots are valid and pml5 is needed, as any
+ * prior MMU would also have required pml5.
+ */
+ if (mmu->pae_root && mmu->pml4_root && (!need_pml5 || mmu->pml5_root))
return 0;
/*
@@ -3570,7 +3578,7 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
* bail if KVM ends up in a state where only one of the roots is valid.
*/
if (WARN_ON_ONCE(!tdp_enabled || mmu->pae_root || mmu->pml4_root ||
- mmu->pml5_root))
+ (need_pml5 && mmu->pml5_root)))
return -EIO;
/*
@@ -3586,7 +3594,7 @@ static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu)
if (!pml4_root)
goto err_pml4;
- if (mmu->shadow_root_level > PT64_ROOT_4LEVEL) {
+ if (need_pml5) {
pml5_root = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
if (!pml5_root)
goto err_pml5;
--
2.33.0.rc2.250.ged5fa647cd-goog
