[PATCH 36/45] KVM: x86: Propagate memory faults through load_pdptrs()
From: Paolo Bonzini
Date: Mon Nov 02 2026 - 13:52:38 EST
load_pdptrs() returns a 0/1 value, and therefore its callers do not
distinguish memory attribute errors (including from nested GPA
translation) from other failures. Change them to propagate
negative errno.
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/kvm/regs.c | 43 ++++++++++++++++++++++++++++-----------
arch/x86/kvm/svm/nested.c | 10 +++++----
arch/x86/kvm/svm/svm.c | 4 ++--
arch/x86/kvm/vmx/nested.c | 6 ++++--
4 files changed, 43 insertions(+), 20 deletions(-)
diff --git a/arch/x86/kvm/regs.c b/arch/x86/kvm/regs.c
index 3969b769f1c1..b7c25b16ffca 100644
--- a/arch/x86/kvm/regs.c
+++ b/arch/x86/kvm/regs.c
@@ -176,7 +176,12 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
/* Note the offset, PDPTRs are 32 byte aligned when using PAE paging. */
ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(real_gpa), pdpte,
cr3 & GENMASK(11, 5), sizeof(pdpte));
- if (ret < 0)
+ if (ret == -EFAULT) {
+ kvm_prepare_memory_fault_exit(vcpu, real_gpa & PAGE_MASK, PAGE_SIZE,
+ false, false, false);
+ return ret;
+ }
+ if (ret)
return 0;
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
@@ -264,6 +269,7 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_post_set_cr0);
int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
unsigned long old_cr0 = kvm_read_cr0(vcpu);
+ int r;
if (!kvm_is_valid_cr0(vcpu, cr0))
return 1;
@@ -286,9 +292,11 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
}
#endif
if (!(vcpu->arch.efer & EFER_LME) && (cr0 & X86_CR0_PG) &&
- is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS) &&
- !load_pdptrs(vcpu, kvm_read_cr3(vcpu)))
- return 1;
+ is_pae(vcpu) && ((cr0 ^ old_cr0) & X86_CR0_PDPTR_BITS)) {
+ r = load_pdptrs(vcpu, kvm_read_cr3(vcpu));
+ if (r <= 0)
+ return r ?: 1;
+ }
if (!(cr0 & X86_CR0_PG) &&
(is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)))
@@ -315,6 +323,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
bool skip_tlb_flush = false;
unsigned long pcid = 0;
+ int r;
#ifdef CONFIG_X86_64
if (kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) {
skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH;
@@ -335,8 +344,11 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
if (!kvm_vcpu_is_legal_cr3(vcpu, cr3))
return 1;
- if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3))
- return 1;
+ if (is_pae_paging(vcpu)) {
+ r = load_pdptrs(vcpu, cr3);
+ if (r <= 0)
+ return r ?: 1;
+ }
if (cr3 != kvm_read_cr3(vcpu))
kvm_mmu_new_pgd(vcpu, cr3);
@@ -411,6 +423,7 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_post_set_cr4);
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long old_cr4 = kvm_read_cr4(vcpu);
+ int r;
if (!kvm_is_valid_cr4(vcpu, cr4))
return 1;
@@ -420,10 +433,12 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
return 1;
if ((cr4 ^ old_cr4) & X86_CR4_LA57)
return 1;
- } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
- && ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS)
- && !load_pdptrs(vcpu, kvm_read_cr3(vcpu)))
- return 1;
+ } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) &&
+ ((cr4 ^ old_cr4) & X86_CR4_PDPTR_BITS)) {
+ r = load_pdptrs(vcpu, kvm_read_cr3(vcpu));
+ if (r <= 0)
+ return r ?: 1;
+ }
if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) {
/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
@@ -579,7 +594,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs,
int *mmu_reset_needed, bool update_pdptrs)
{
- int idx;
+ int idx, r;
struct desc_ptr dt;
if (!kvm_is_valid_sregs(vcpu, sregs))
@@ -616,7 +631,11 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs,
if (update_pdptrs) {
idx = srcu_read_lock(&vcpu->kvm->srcu);
if (is_pae_paging(vcpu)) {
- load_pdptrs(vcpu, kvm_read_cr3(vcpu));
+ r = load_pdptrs(vcpu, kvm_read_cr3(vcpu));
+ if (r < 0) {
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+ return r;
+ }
*mmu_reset_needed = 1;
}
srcu_read_unlock(&vcpu->kvm->srcu, idx);
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 73f1f40aad47..a512e0e8dd93 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -720,7 +720,7 @@ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
if (reload_pdptrs && is_pae_paging(vcpu)) {
if (nested_npt)
kvm_register_mark_for_reload(vcpu, VCPU_REG_PDPTR);
- else if (CC(!load_pdptrs(vcpu, cr3)))
+ else if (CC(load_pdptrs(vcpu, cr3) <= 0))
return -EINVAL;
}
@@ -2132,11 +2132,13 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
* nGPA translation. For !nNPT, reload eagerly unless userspace
* already supplied authoritative PDPTRs via KVM_SET_SREGS2.
*/
- if (nested_npt_enabled(to_svm(vcpu)))
+ if (nested_npt_enabled(to_svm(vcpu))) {
kvm_register_mark_for_reload(vcpu, VCPU_REG_PDPTR);
- else if (!vcpu->arch.pdptrs_from_userspace &&
- CC(!load_pdptrs(vcpu, vcpu->arch.cr3)))
+ } else if (!vcpu->arch.pdptrs_from_userspace &&
+ CC(load_pdptrs(vcpu, vcpu->arch.cr3) <= 0)) {
+ kvm_prepare_emulation_failure_exit(vcpu);
return false;
+ }
}
if (!nested_svm_merge_msrpm(vcpu))
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2601f8359137..a8b3d57aabef 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1587,8 +1587,8 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
* When !npt_enabled, vcpu->pdptrs[] is already available since
* it is always updated per SDM when moving to CRs.
*/
- if (npt_enabled)
- load_pdptrs(vcpu, kvm_read_cr3(vcpu));
+ if (npt_enabled && load_pdptrs(vcpu, kvm_read_cr3(vcpu)) < 0)
+ kvm_vm_dead(vcpu->kvm);
break;
default:
KVM_BUG_ON(1, vcpu->kvm);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f6994a95523a..8c110f3d9cc3 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1240,7 +1240,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
* must not be dereferenced.
*/
if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) &&
- CC(!load_pdptrs(vcpu, cr3))) {
+ CC(load_pdptrs(vcpu, cr3) <= 0)) {
*entry_failure_code = ENTRY_FAIL_PDPTE;
return -EINVAL;
}
@@ -3454,8 +3454,10 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
* the guest CR3 might be restored prior to setting the nested
* state which can lead to a load of wrong PDPTRs.
*/
- if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3)))
+ if (CC(load_pdptrs(vcpu, vcpu->arch.cr3) <= 0)) {
+ kvm_prepare_emulation_failure_exit(vcpu);
return false;
+ }
}
--
2.52.0