From 9ba32a10ac2dcf62b632ecdde7ec3a339a4c7efa Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 6 Sep 2021 20:25:46 +0800 Subject: [PATCH] KVM: x86/mmu: Verify shadow walk doesn't terminate early in page faults WARN and bail if the shadow walk for faulting in a SPTE terminates early, i.e. doesn't reach the expected level because the walk encountered a terminal SPTE. The shadow walks for page faults are subtle in that they install non-leaf SPTEs (zapping leaf SPTEs if necessary!) in the loop body, and consume the newly created non-leaf SPTE in the loop control, e.g. __shadow_walk_next(). In other words, the walks guarantee that the walk will stop if and only if the target level is reached by installing non-leaf SPTEs to guarantee the walk remains valid. Opportunistically use fault->goal-level instead of it.level in FNAME(fetch) to further clarify that KVM always installs the leaf SPTE at the target level. Reviewed-by: Lai Jiangshan Signed-off-by: Sean Christopherson Signed-off-by: Lai Jiangshan Message-Id: <20210906122547.263316-1-jiangshanlai@gmail.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 3 +++ arch/x86/kvm/mmu/paging_tmpl.h | 7 +++++-- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 5ba0a844f5760..2ddbabad5bd2e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3012,6 +3012,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) account_huge_nx_page(vcpu->kvm, sp); } + if (WARN_ON_ONCE(it.level != fault->goal_level)) + return -EFAULT; + ret = mmu_set_spte(vcpu, it.sptep, ACC_ALL, fault->write, fault->goal_level, base_gfn, fault->pfn, fault->prefault, fault->map_writable); diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 6bc0dbc0bafff..7a8a2d14a3c7d 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -760,9 +760,12 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, } } + if (WARN_ON_ONCE(it.level != fault->goal_level)) + return -EFAULT; + ret = mmu_set_spte(vcpu, it.sptep, gw->pte_access, fault->write, - it.level, base_gfn, fault->pfn, fault->prefault, - fault->map_writable); + fault->goal_level, base_gfn, fault->pfn, + fault->prefault, fault->map_writable); if (ret == RET_PF_SPURIOUS) return ret; -- 2.39.5