When KVM emulates an instruction for L2 and encounters a nested page fault (e.g., during string I/O emulation), nested_svm_inject_npf_exit() injects an NPF to L1. However, the code incorrectly hardcodes (1ULL << 32) for exit_info_1's upper bits when the original exit was not an NPF. This always sets PFERR_GUEST_FINAL_MASK even when the fault occurred on a page table page, preventing L1 from correctly identifying the cause of the fault. Set PFERR_GUEST_PAGE_MASK in the error code when a nested page fault occurs during a guest page table walk, and PFERR_GUEST_FINAL_MASK when the fault occurs on the final GPA-to-HPA translation. Widen error_code in struct x86_exception from u16 to u64 to accommodate the PFERR_GUEST_* bits (bits 32 and 33). Update nested_svm_inject_npf_exit() to use fault->error_code directly instead of hardcoding the upper bits. Also add a WARN_ON_ONCE if neither PFERR_GUEST_FINAL_MASK nor PFERR_GUEST_PAGE_MASK is set, as this would indicate a bug in the page fault handling code. Signed-off-by: Kevin Cheng --- arch/x86/kvm/kvm_emulate.h | 2 +- arch/x86/kvm/mmu/paging_tmpl.h | 22 ++++++++++------------ arch/x86/kvm/svm/nested.c | 11 +++++------ 3 files changed, 16 insertions(+), 19 deletions(-) diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index fb3dab4b5a53e..ff4f9b0a01ff7 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -22,7 +22,7 @@ enum x86_intercept_stage; struct x86_exception { u8 vector; bool error_code_valid; - u16 error_code; + u64 error_code; bool nested_page_fault; u64 address; /* cr2 or nested page fault gpa */ u8 async_page_fault; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 901cd2bd40b84..923179bfd5c74 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -379,18 +379,12 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(table_gfn), nested_access, &walker->fault); - /* - * FIXME: This can happen if emulation (for of an INS/OUTS - * instruction) triggers a nested page fault. The exit - * qualification / exit info field will incorrectly have - * "guest page access" as the nested page fault's cause, - * instead of "guest page structure access". To fix this, - * the x86_exception struct should be augmented with enough - * information to fix the exit_qualification or exit_info_1 - * fields. - */ - if (unlikely(real_gpa == INVALID_GPA)) + if (unlikely(real_gpa == INVALID_GPA)) { +#if PTTYPE != PTTYPE_EPT + walker->fault.error_code |= PFERR_GUEST_PAGE_MASK; +#endif return 0; + } slot = kvm_vcpu_gfn_to_memslot(vcpu, gpa_to_gfn(real_gpa)); if (!kvm_is_visible_memslot(slot)) @@ -446,8 +440,12 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, #endif real_gpa = kvm_translate_gpa(vcpu, mmu, gfn_to_gpa(gfn), access, &walker->fault); - if (real_gpa == INVALID_GPA) + if (real_gpa == INVALID_GPA) { +#if PTTYPE != PTTYPE_EPT + walker->fault.error_code |= PFERR_GUEST_FINAL_MASK; +#endif return 0; + } walker->gfn = real_gpa >> PAGE_SHIFT; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index de90b104a0dd5..f8dfd5c333023 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -40,18 +40,17 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, struct vmcb *vmcb = svm->vmcb; if (vmcb->control.exit_code != SVM_EXIT_NPF) { - /* - * TODO: track the cause of the nested page fault, and - * correctly fill in the high bits of exit_info_1. - */ - vmcb->control.exit_code = SVM_EXIT_NPF; - vmcb->control.exit_info_1 = (1ULL << 32); + vmcb->control.exit_info_1 = fault->error_code; vmcb->control.exit_info_2 = fault->address; } + vmcb->control.exit_code = SVM_EXIT_NPF; vmcb->control.exit_info_1 &= ~0xffffffffULL; vmcb->control.exit_info_1 |= fault->error_code; + WARN_ON_ONCE(!(vmcb->control.exit_info_1 & + (PFERR_GUEST_FINAL_MASK | PFERR_GUEST_PAGE_MASK))); + nested_svm_vmexit(svm); } -- 2.52.0.457.g6b5491de43-goog