[PATCH 37/45] KVM: x86/mmu: Issue memory fault exit if walk failed due to memory attribute
From: Paolo Bonzini
Date: Mon Nov 02 2026 - 14:26:41 EST
During execution, page table entries are subject to memory protection
simply because their GPA is obtained with an EPT walk. During emulation,
the checks need to be done by hand and result in an -EFAULT userspace
exit.
However, if a guest PTE is read-only, do not go all the way out to
userspace and just stomp out the write. This is consistent with the way
KVM handles read-only memory slots during emulation, though admittedly
inconsistent with everything else: NPT for example always wants nested
page table entries for the guest page tables to be writable, and will
fault.
Signed-off-by: Nicolas Saenz Julienne <nsaenz@xxxxxxxxxx>
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Link: https://patch.msgid.link/20260918135030.171564-27-pbonzini@xxxxxxxxxx
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/mmu/mmu.c | 6 +++--
arch/x86/kvm/mmu/paging_tmpl.h | 40 ++++++++++++++++++++++++++-------
arch/x86/kvm/regs.h | 6 +++++
arch/x86/kvm/svm/nested.c | 16 ++++++-------
arch/x86/kvm/vmx/nested.c | 2 +-
6 files changed, 52 insertions(+), 20 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7fbcf60e56cf..e33ca5ea59bd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -486,7 +486,7 @@ struct kvm_page_fault;
*/
struct kvm_pagewalk {
unsigned long (*get_guest_pgd)(struct kvm_vcpu *vcpu);
- u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
+ int (*get_pdptr)(struct kvm_vcpu *vcpu, int index, u64 *pdptr);
void (*inject_page_fault)(struct kvm_vcpu *vcpu,
struct x86_exception *fault,
bool from_hardware);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 9567c109306b..c08168595732 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4204,7 +4204,9 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
*/
if (w->cpu_role.base.level == PT32E_ROOT_LEVEL) {
for (i = 0; i < 4; ++i) {
- pdptrs[i] = w->get_pdptr(vcpu, i);
+ r = w->get_pdptr(vcpu, i, &pdptrs[i]);
+ if (r)
+ return r;
if (!(pdptrs[i] & PT_PRESENT_MASK))
continue;
@@ -6211,7 +6213,7 @@ static void init_kvm_page_walk(struct kvm_vcpu *vcpu, struct kvm_pagewalk *w,
w->cpu_role.as_u64 = cpu_role.as_u64;
w->inject_page_fault = kvm_inject_page_fault;
- w->get_pdptr = kvm_pdptr_read;
+ w->get_pdptr = kvm_pdptr_get;
w->get_guest_pgd = get_guest_cr3;
if (!is_cr0_pg(w))
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index a76ec22ce3f2..ddab65e5689d 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -89,6 +89,7 @@ struct guest_walker {
unsigned int pt_access[PT_MAX_FULL_LEVELS];
unsigned int pte_access;
gfn_t gfn;
+ int error;
struct x86_exception fault;
};
@@ -342,6 +343,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
trace_kvm_mmu_pagetable_walk(addr, access);
retry_walk:
+ walker->error = 0;
walker->level = w->cpu_role.base.level;
pte = kvm_mmu_get_guest_pgd(vcpu, w);
have_ad = PT_HAVE_ACCESSED_DIRTY(w);
@@ -349,7 +351,9 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
#if PTTYPE == 64
walk_nx_mask = 1ULL << PT64_NX_SHIFT;
if (walker->level == PT32E_ROOT_LEVEL) {
- pte = w->get_pdptr(vcpu, (addr >> 30) & 3);
+ walker->error = w->get_pdptr(vcpu, (addr >> 30) & 3, &pte);
+ if (walker->error)
+ goto error;
trace_kvm_mmu_paging_element(pte, walker->level);
if (!FNAME(is_present_gpte)(w, pte))
goto error;
@@ -398,9 +402,11 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
walker->table_gfn[walker->level - 1] = table_gfn;
walker->pte_gpa[walker->level - 1] = pte_gpa;
- kvm_translate_gpa(vcpu, w, gfn_to_gpa(table_gfn),
- nested_access | PFERR_GUEST_PAGE_MASK,
- &real_gpa, &walker->fault, 0);
+ walker->error = kvm_translate_gpa(vcpu, w, gfn_to_gpa(table_gfn),
+ nested_access | PFERR_GUEST_PAGE_MASK,
+ &real_gpa, &walker->fault, 0);
+ if (walker->error)
+ return 0;
if (unlikely(real_gpa == INVALID_GPA))
return 0;
@@ -414,6 +420,16 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
if (unlikely(kvm_is_error_hva(host_addr)))
goto error;
+ if (!kvm_mem_attributes_may_read_gfn(vcpu->kvm, gpa_to_gfn(real_gpa))) {
+ walker->error = -EFAULT;
+ kvm_prepare_memory_fault_exit(vcpu, real_gpa & PAGE_MASK,
+ PAGE_SIZE, false, false, false);
+ goto error;
+ }
+
+ if (!kvm_mem_attributes_may_write_gfn(vcpu->kvm, gpa_to_gfn(real_gpa)))
+ walker->pte_writable[walker->level - 1] = false;
+
ptep_user = (pt_element_t __user *)((void *)host_addr + offset);
if (unlikely(get_user(pte, ptep_user)))
goto error;
@@ -458,9 +474,11 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
gfn += pse36_gfn_delta(pte);
#endif
- kvm_translate_gpa(vcpu, w, gfn_to_gpa(gfn),
- access | PFERR_GUEST_FINAL_MASK, &real_gpa,
- &walker->fault, walker->pte_access);
+ walker->error = kvm_translate_gpa(vcpu, w, gfn_to_gpa(gfn),
+ access | PFERR_GUEST_FINAL_MASK, &real_gpa,
+ &walker->fault, walker->pte_access);
+ if (walker->error)
+ return 0;
if (real_gpa == INVALID_GPA)
return 0;
@@ -823,6 +841,9 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
* The page is not mapped by the guest. Let the guest handle it.
*/
if (!r) {
+ if (walker.error)
+ return walker.error;
+
if (!fault->prefetch)
__kvm_inject_emulated_page_fault(vcpu, &walker.fault, true);
@@ -920,8 +941,11 @@ static int FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_pagewalk *w,
if (r) {
*gpa = gfn_to_gpa(walker.gfn);
*gpa |= addr & ~PAGE_MASK;
- } else if (exception)
+ } else if (walker.error) {
+ return walker.error;
+ } else if (exception) {
*exception = walker.fault;
+ }
return 0;
}
diff --git a/arch/x86/kvm/regs.h b/arch/x86/kvm/regs.h
index 97c17b120a57..31f4d3f6ea42 100644
--- a/arch/x86/kvm/regs.h
+++ b/arch/x86/kvm/regs.h
@@ -319,6 +319,12 @@ static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
return vcpu->arch.pdptrs[index];
}
+static inline int kvm_pdptr_get(struct kvm_vcpu *vcpu, int index, u64 *pdptr)
+{
+ *pdptr = kvm_pdptr_read(vcpu, index);
+ return 0;
+}
+
static inline void kvm_pdptr_write(struct kvm_vcpu *vcpu, int index, u64 value)
{
vcpu->arch.pdptrs[index] = value;
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index a512e0e8dd93..4d76e8880d99 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -71,22 +71,22 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
nested_svm_vmexit(svm);
}
-static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
+static int nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index, u64 *pdptr)
{
struct vcpu_svm *svm = to_svm(vcpu);
u64 cr3 = svm->nested.ctl.nested_cr3;
- u64 pdpte;
- int ret;
+ int r;
/*
* Note, nCR3 is "assumed" to be 32-byte aligned, i.e. the CPU ignores
* nCR3[4:0] when loading PDPTEs from memory.
*/
- ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte,
- (cr3 & GENMASK(11, 5)) + index * 8, 8);
- if (ret)
- return 0;
- return pdpte;
+ r = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), pdptr,
+ (cr3 & GENMASK(11, 5)) + index * 8, 8);
+ if (r == -EFAULT)
+ kvm_prepare_memory_fault_exit(vcpu, cr3 & PAGE_MASK, PAGE_SIZE,
+ false, false, false);
+ return r;
}
static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8c110f3d9cc3..2ac4a366ace4 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -520,7 +520,7 @@ static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
vcpu->arch.mmu = &vcpu->arch.guest_mmu;
nested_ept_new_eptp(vcpu);
vcpu->arch.ngpa_walk.get_guest_pgd = nested_ept_get_eptp;
- vcpu->arch.ngpa_walk.get_pdptr = kvm_pdptr_read;
+ vcpu->arch.ngpa_walk.get_pdptr = kvm_pdptr_get;
vcpu->arch.ngpa_walk.inject_page_fault = nested_ept_inject_page_fault;
}
--
2.52.0