From e70f812ccdd6f45b002ff054b0108bbf8db1c0ed Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Thu, 17 Sep 2026 20:36:58 -0700 Subject: [PATCH] KVM: x86: Restrict saved GPA writes to hardware write faults A GPA supplied by a hardware page fault describes the access that faulted, not an arbitrary instruction decoded afterwards. A guest can change an MMIO read into a store before KVM fetches the instruction. The saved-GPA shortcut then skips the write-aware guest page-table walk and can issue a write through a guest-read-only mapping. Carry hardware write-fault information into the emulator and retain it alongside the saved GPA. For guests without protected page tables, only reuse that GPA for a write when hardware reported a write access. Reads and faults with unknown access direction do not authorize an emulated write; fall back to the existing permission-aware translation in those cases. Keep the authorization across MMIO completion without decoding a new instruction, and reset it when initializing a fresh emulator context. This also covers writes reached through the cmpxchg fallback. Preserve the shortcut for hardware-reported writes and for the read side of read-modify-write emulation after such a fault. For guests with protected page tables, preserve the existing behavior and always allow writes through the saved GPA. An RMW instruction can fault on its initial read, and KVM cannot walk the protected guest page tables to check the subsequent write. Track this property in common KVM state for SEV and TDX. Also account for legacy SEV initialization and encryption-context copies and moves. Fixes: 0f89b207b04a ("kvm: svm: Use the hardware provided GPA instead of page walk") Reported-by: Oleg Boiko Assisted-by: Codex:gpt-6-astra Signed-off-by: Kyle Zeng Link: https://patch.msgid.link/20260918033658.21842-1-kylebot@openai.com [sean: clear has_protected_page_tables on the source after migration] Signed-off-by: Sean Christopherson --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/kvm_emulate.h | 4 ++-- arch/x86/kvm/mmu/mmu.c | 3 +++ arch/x86/kvm/svm/sev.c | 5 +++++ arch/x86/kvm/vmx/tdx.c | 1 + arch/x86/kvm/x86.c | 17 ++++++++++++++--- arch/x86/kvm/x86.h | 3 +++ 7 files changed, 29 insertions(+), 5 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3335c4b1afad..2159f1ba4f33 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1168,6 +1168,7 @@ struct kvm_arch { u8 mmu_valid_gen; u8 vm_type; bool has_private_mem; + bool has_protected_page_tables; bool has_protected_state; bool has_protected_eoi; bool has_protected_pmu; diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 3e375af15c03..10886bea82c9 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -354,8 +354,8 @@ struct x86_emulate_ctxt { bool have_exception; struct x86_exception exception; - /* GPA available */ - bool gpa_available; + /* Saved GPA and permitted emulated accesses. */ + u64 gpa_access; gpa_t gpa_val; /* diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f037fa665414..21a9a11b9ce6 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6638,6 +6638,9 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err return r; emulate: + if (error_code & PFERR_WRITE_MASK) + emulation_type |= EMULTYPE_PF_WRITE; + return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index cfe990f80504..dd0943cd0133 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -560,6 +560,7 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp, INIT_LIST_HEAD(&sev->regions_list); INIT_LIST_HEAD(&sev->mirror_vms); sev->need_init = false; + kvm->arch.has_protected_page_tables = true; kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV); @@ -2041,12 +2042,14 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm) dst->pages_locked = src->pages_locked; dst->es_active = src->es_active; dst->vmsa_features = src->vmsa_features; + dst_kvm->arch.has_protected_page_tables = true; src->asid = 0; src->active = false; src->handle = 0; src->pages_locked = 0; src->es_active = false; + src_kvm->arch.has_protected_page_tables = false; list_cut_before(&dst->regions_list, &src->regions_list, &src->regions_list); @@ -2907,6 +2910,7 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd) mutex_unlock(&sev_mirror_lock); mirror_sev->active = true; + kvm->arch.has_protected_page_tables = true; mirror_sev->asid = source_sev->asid; mirror_sev->fd = source_sev->fd; mirror_sev->es_active = source_sev->es_active; @@ -2965,6 +2969,7 @@ void sev_vm_init(struct kvm *kvm) kvm->arch.has_protected_state = true; fallthrough; case KVM_X86_SEV_VM: + kvm->arch.has_protected_page_tables = true; kvm->arch.pre_fault_allowed = !kvm->arch.has_private_mem; to_kvm_sev_info(kvm)->need_init = true; break; diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index a0bc9f818f43..2d2febd4a5ef 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -616,6 +616,7 @@ int tdx_vm_init(struct kvm *kvm) { struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm); + kvm->arch.has_protected_page_tables = true; kvm->arch.has_protected_state = true; /* * TDX Module doesn't allow the hypervisor to modify the EOI-bitmap, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index be117e09cdd2..de77b222870e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5120,7 +5120,8 @@ static int emulator_read_write_onepage(unsigned long addr, void *val, * operation using rep will only have the initial GPA from the NPF * occurred. */ - if (ctxt->gpa_available && emulator_can_use_gpa(ctxt) && + if ((ctxt->gpa_access & (write ? ACC_WRITE_MASK : ACC_READ_MASK)) && + emulator_can_use_gpa(ctxt) && (addr & ~PAGE_MASK) == (ctxt->gpa_val & ~PAGE_MASK)) { gpa = ctxt->gpa_val; ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write); @@ -5969,7 +5970,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) kvm_x86_call(get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); - ctxt->gpa_available = false; + ctxt->gpa_access = 0; ctxt->eflags = kvm_get_rflags(vcpu); ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; @@ -6485,7 +6486,17 @@ restart: /* With shadow page tables, cr2 contains a GVA or nGPA. */ if (vcpu->arch.mmu->root_role.direct) { - ctxt->gpa_available = true; + ctxt->gpa_access = ACC_READ_MASK; + /* + * Always allow writes for guests with protected page + * tables, as KVM can't walk the guest's page tables, + * i.e. KVM can't get the RMW protections for a given + * GVA to see if the write side of a RMW operation + * should be allowed. + */ + if ((emulation_type & EMULTYPE_PF_WRITE) || + vcpu->kvm->arch.has_protected_page_tables) + ctxt->gpa_access |= ACC_WRITE_MASK; ctxt->gpa_val = cr2_or_gpa; } } else { diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 2d747c20965c..cbcf8e3ff31a 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -407,6 +407,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * EMULTYPE_PF - Set when an intercepted #PF triggers the emulation, in which case * the CR2/GPA value pass on the stack is valid. * + * EMULTYPE_PF_WRITE - Set with EMULTYPE_PF when hardware reports a write access. + * * EMULTYPE_COMPLETE_USER_EXIT - Set when the emulator should update interruptibility * state and inject single-step #DBs after skipping * an instruction (after completing userspace I/O). @@ -445,6 +447,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, #define EMULTYPE_COMPLETE_USER_EXIT (1 << 7) #define EMULTYPE_WRITE_PF_TO_SP (1 << 8) #define EMULTYPE_SKIP_SOFT_INT (1 << 9) +#define EMULTYPE_PF_WRITE (1 << 10) #define EMULTYPE_SET_SOFT_INT_VECTOR(v) ((u32)((v) & 0xff) << 16) #define EMULTYPE_GET_SOFT_INT_VECTOR(e) (((e) >> 16) & 0xff) -- knotmirror 0.0.1