From c7c288d178cb0b78d3464a616b16b1aa0b316049 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 21 Oct 2026 18:54:06 -0700 Subject: [PATCH] KVM: x86: Unconditionally reset MMU context when emulating INIT Force an MMU reset when emulating an INIT even if paging was already disabled, as the MMU page role includes guest_mode (L2), i.e. an INIT while L2 is running with CR0.PG=0 will result in KVM running L1 with a stale MMU context. Alternatively, the reset could be scoped strictly to paging being enabled or L2 being active, but SMM is also encoded in the page role. Even though it _should_ be impossible for the vCPU to be INIT'd while SMM is active, there's zero value in not handling SMM. At that point, the only scenario where KVM _doesn't_ need to reset the MMU context is on an INIT with the vCPU running in Real Mode or Unpaged Protect Mode, and while INIT in those modes is somewhat common, it's far from a hot path and re-initializing the MMU is not expensive, especially when the role isn't changing (KVM elides most of the re-configuration in that case). Note, like the Fixes commit, this bug only affects nested SVM as INIT is an unconditional intercept on VMX, i.e. it's impossible to emulate INIT while L2 is active. Temporarily keep the guest TLB flush when CR0.PG is being cleared even though it is fully redundant with the flush that is emitted on all INIT events (KVM itself only does RESET when a vCPU is being created, i.e. when CR0.PG must be '0'). Fixes: ed129ec9057f ("KVM: x86: forcibly leave nested mode on vCPU reset") Reported-by: Stefan Teodorescu Reported-by: Oren Yomtov Reported-by: Chris Mason Cc: stable@vger.kernel.org Cc: Yosry Ahmed Signed-off-by: Sean Christopherson Message-ID: <20261022015407.279870-2-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 27 ++++++++++++++++----------- 1 file changed, 16 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c4a06214cde6..09c6df00ebb6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9731,18 +9731,23 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_x86_call(set_efer)(vcpu, 0); kvm_x86_call(update_exception_bitmap)(vcpu); - /* - * On the standard CR0/CR4/EFER modification paths, there are several - * complex conditions determining whether the MMU has to be reset and/or - * which PCIDs have to be flushed. However, CR0.WP and the paging-related - * bits in CR4 and EFER are irrelevant if CR0.PG was '0'; and a reset+flush - * is needed anyway if CR0.PG was '1' (which can only happen for INIT, as - * CR0 will be '0' prior to RESET). So we only need to check CR0.PG here. - */ - if (old_cr0 & X86_CR0_PG) { + if (old_cr0 & X86_CR0_PG) kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); - kvm_mmu_reset_context(vcpu); - } + + /* + * Unconditionally reset the MMU, even though super strictly speaking, + * a MMU reset is only necessary if and only one of the page role bits + * is changing. All of the CR0/CR4/EFER bits effectively get covered + * by checking CR0.PG=1, as CR0.WP and the paging-related bits in CR4 + * and EFER are irrelevant if CR0.PG was '0'. Subtly, if the vCPU was + * in guest mode (L2) or SMM (although emulating INIT in SMM _should_ + * be impossible), an MMU reset is also necessary as "guest mode" and + * "smm" are both encoded in the shadow page role. As a result, the + * only scenarios where an MMU reset is *not* needed is if the vCPU is + * in Real Mode or Unpaged Protected Mode, and micro-optimizing those + * paths are not worth the risk of running with a stale MMU context. + */ + kvm_mmu_reset_context(vcpu); /* * Intel's SDM states that all TLB entries are flushed on INIT. AMD's