From db25c218ba9167f3239fe081584f8f4528bdc346 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 15 Apr 2026 00:52:34 +0000 Subject: [PATCH 1/2] KVM: x86: Fix shadow paging use-after-free due to unexpected GFN cve CVE-2026-46113 commit-author Sean Christopherson commit 0cb2af2ea66ad8ff195c156ea690f11216285bdf The shadow MMU computes GFNs for direct shadow pages using sp->gfn plus the SPTE index. This assumption breaks for shadow paging if the guest page tables are modified between VM entries (similar to commit aad885e77496, "KVM: x86/mmu: Drop/zap existing present SPTE even when creating an MMIO SPTE", 2026-03-27). The flow is as follows: - a PDE is installed for a 2MB mapping, and a page in that area is accessed. KVM creates a kvm_mmu_page consisting of 512 4KB pages; the kvm_mmu_page is marked by FNAME(fetch) as direct-mapped because the guest's mapping is a huge page (and thus contiguous). - the PDE mapping is changed from outside the guest. - the guest accesses another page in the same 2MB area. KVM installs a new leaf SPTE and rmap entry; the SPTE uses the "correct" GFN (i.e. based on the new mapping, as changed in the previous step) but that GFN is outside of the [sp->gfn, sp->gfn + 511] range; therefore the rmap entry cannot be found and removed when the kvm_mmu_page is zapped. - the memslot that covers the first 2MB mapping is deleted, and the kvm_mmu_page for the now-invalid GPA is zapped. However, rmap_remove() only looks at the [sp->gfn, sp->gfn + 511] range established in step 1, and fails to find the rmap entry that was recorded by step 3. - any operation that causes an rmap walk for the same page accessed by step 3 then walks a stale rmap and dereferences a freed kvm_mmu_page. This includes dirty logging or MMU notifier invalidations (e.g., from MADV_DONTNEED). The underlying issue is that KVM's walking of shadow PTEs assumes that if a SPTE is present when KVM wants to install a non-leaf SPTE, then the existing kvm_mmu_page must be for the correct gfn. Because the only way for the gfn to be wrong is if KVM messed up and failed to zap a SPTE... which shouldn't happen, but *actually* only happens in response to a guest write. That bug dates back literally forever, as even the first version of KVM assumes that the GFN matches and walks into the "wrong" shadow page. However, that was only an imprecision until 2032a93d66fa ("KVM: MMU: Don't allocate gfns page for direct mmu pages") came along. Fix it by checking for a target gfn mismatch and zapping the existing SPTE. That way the old SP and rmap entries are gone, KVM installs the rmap in the right location, and everyone is happy. Fixes: 2032a93d66fa ("KVM: MMU: Don't allocate gfns page for direct mmu pages") Fixes: 6aa8b732ca01 ("kvm: userspace interface") Reported-by: Alexander Bulekov Reported-by: Fred Griffoul Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson Link: https://patch.msgid.link/20260503201029.106481-1-pbonzini@redhat.com/ Signed-off-by: Paolo Bonzini (cherry picked from commit 0cb2af2ea66ad8ff195c156ea690f11216285bdf) Signed-off-by: Shreeya Patel --- arch/x86/kvm/mmu/mmu.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 8895c98f00920..6140702e1f08f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -183,6 +183,8 @@ struct kmem_cache *mmu_page_header_cache; static struct percpu_counter kvm_total_used_mmu_pages; static void mmu_spte_set(u64 *sptep, u64 spte); +static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, + u64 *spte, struct list_head *invalid_list); struct kvm_mmu_role_regs { const unsigned long cr0; @@ -1220,19 +1222,6 @@ static void drop_spte(struct kvm *kvm, u64 *sptep) rmap_remove(kvm, sptep); } -static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush) -{ - struct kvm_mmu_page *sp; - - sp = sptep_to_sp(sptep); - WARN_ON_ONCE(sp->role.level == PG_LEVEL_4K); - - drop_spte(kvm, sptep); - - if (flush) - kvm_flush_remote_tlbs_sptep(kvm, sptep); -} - /* * Write-protect on the specified @sptep, @pt_protect indicates whether * spte write-protection is caused by protecting shadow page table. @@ -2328,7 +2317,8 @@ static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu, { union kvm_mmu_page_role role; - if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep)) + if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep) && + spte_to_child_sp(*sptep) && spte_to_child_sp(*sptep)->gfn == gfn) return ERR_PTR(-EEXIST); role = kvm_mmu_child_role(sptep, direct, access); @@ -2406,13 +2396,16 @@ static void __link_shadow_page(struct kvm *kvm, BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); - /* - * If an SPTE is present already, it must be a leaf and therefore - * a large one. Drop it, and flush the TLB if needed, before - * installing sp. - */ - if (is_shadow_present_pte(*sptep)) - drop_large_spte(kvm, sptep, flush); + if (is_shadow_present_pte(*sptep)) { + struct kvm_mmu_page *parent_sp; + LIST_HEAD(invalid_list); + + parent_sp = sptep_to_sp(sptep); + WARN_ON_ONCE(parent_sp->role.level == PG_LEVEL_4K); + + mmu_page_zap_pte(kvm, parent_sp, sptep, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, true); + } spte = make_nonleaf_spte(sp->spt, sp_ad_disabled(sp)); From a44bb67360ba9d73b143b21adb7530538280da5e Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 12 Jun 2026 22:18:12 +0200 Subject: [PATCH 2/2] KVM: x86: Fix shadow paging use-after-free due to unexpected role cve CVE-2026-53359 commit-author Paolo Bonzini commit 81ccda30b4e83d8f5cc4fd50503c44e3a33abfeb Commit 0cb2af2ea66ad ("KVM: x86: Fix shadow paging use-after-free due to unexpected GFN") fixed a shadow paging mismatch between stored and computed GFNs; the bug could be triggered by changing a PDE mapping from outside the guest, and then deleting a memslot. The rmap_remove() call would miss entries created after the PDE change because the GFN of the leaf SPTE does not match the GFN of the struct kvm_mmu_page. A similar hole however remains if the modified PDE points to a non-leaf page. In this case the gfn can be made to match, but the role does not match: the original large 2MB page creates a kvm_mmu_page with direct=1, while the new 4KB needs a kvm_mmu_page with direct=0. However, kvm_mmu_get_child_sp() does not compare the role, and therefore reuses the page. The next step is installing a leaf (4KB) SPTE on the new path which records an rmap entry under the gfn resolved by the walk. But when that child is zapped its parent kvm_mmu_page has direct=1 and kvm_mmu_page_get_gfn() computes the gfn for the 4KB page as sp->gfn + index instead of using sp->shadowed_translation[] (or sp->gfns[] in older kernels). It therefore fails to remove the recorded entry. When the memslot is dropped the shadow page is freed but the rmap entry survives, as in the scenario that was already fixed. Code that later walks that gfn (dirty logging, MMU notifier invalidation, and so on) dereferences an sptep that lies in the freed page, causing the use-after-free. Fixes: 2032a93d66fa ("KVM: MMU: Don't allocate gfns page for direct mmu pages") Reported-by: Hyunwoo Kim Signed-off-by: Paolo Bonzini (cherry picked from commit 81ccda30b4e83d8f5cc4fd50503c44e3a33abfeb) Signed-off-by: Shreeya Patel --- arch/x86/kvm/mmu/mmu.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6140702e1f08f..8996c8965424a 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2315,13 +2315,15 @@ static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, bool direct, unsigned int access) { - union kvm_mmu_page_role role; + union kvm_mmu_page_role role = kvm_mmu_child_role(sptep, direct, access); - if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep) && - spte_to_child_sp(*sptep) && spte_to_child_sp(*sptep)->gfn == gfn) + if (is_shadow_present_pte(*sptep) && + !is_large_pte(*sptep) && + spte_to_child_sp(*sptep) && + spte_to_child_sp(*sptep)->gfn == gfn && + spte_to_child_sp(*sptep)->role.word == role.word) return ERR_PTR(-EEXIST); - role = kvm_mmu_child_role(sptep, direct, access); return kvm_mmu_get_shadow_page(vcpu, gfn, role); }