Handle faults for memslots backed by guest_memfd in arm64 nested
virtualization triggerred by VNCR_EL2.
* Introduce is_gmem output parameter to kvm_translate_vncr(), indicating
whether the faulted memory slot is backed by guest_memfd.
* Dispatch faults backed by guest_memfd to kvm_gmem_get_pfn().
* Update kvm_handle_vncr_abort() to handle potential guest_memfd errors.
Some of the guest_memfd errors need to be handled by userspace,
instead of attempting to (implicitly) retry by returning to the guest.
Suggested-by: Marc Zyngier <maz@xxxxxxxxxx>
Signed-off-by: Fuad Tabba <tabba@xxxxxxxxxx>
---
arch/arm64/kvm/nested.c | 41 +++++++++++++++++++++++++++++++++++------
1 file changed, 35 insertions(+), 6 deletions(-)
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index dc1d26559bfa..b3edd7f7c8cd 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1172,8 +1172,9 @@ static u64 read_vncr_el2(struct kvm_vcpu *vcpu)
return (u64)sign_extend64(__vcpu_sys_reg(vcpu, VNCR_EL2), 48);
}
-static int kvm_translate_vncr(struct kvm_vcpu *vcpu)
+static int kvm_translate_vncr(struct kvm_vcpu *vcpu, bool *is_gmem)
{
+ struct kvm_memory_slot *memslot;
bool write_fault, writable;
unsigned long mmu_seq;
struct vncr_tlb *vt;
@@ -1216,10 +1217,25 @@ static int kvm_translate_vncr(struct kvm_vcpu *vcpu)
smp_rmb();
gfn = vt->wr.pa >> PAGE_SHIFT;
- pfn = kvm_faultin_pfn(vcpu, gfn, write_fault, &writable, &page);
- if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
+ memslot = gfn_to_memslot(vcpu->kvm, gfn);
+ if (!memslot)
return -EFAULT;
+ *is_gmem = kvm_slot_has_gmem(memslot);
+ if (!*is_gmem) {
+ pfn = __kvm_faultin_pfn(memslot, gfn, write_fault ? FOLL_WRITE : 0,
+ &writable, &page);
+ if (is_error_noslot_pfn(pfn) || (write_fault && !writable))
+ return -EFAULT;
+ } else {
+ ret = kvm_gmem_get_pfn(vcpu->kvm, memslot, gfn, &pfn, &page, NULL);
+ if (ret) {
+ kvm_prepare_memory_fault_exit(vcpu, vt->wr.pa, PAGE_SIZE,
+ write_fault, false, false);
+ return ret;
+ }
+ }
+
scoped_guard(write_lock, &vcpu->kvm->mmu_lock) {
if (mmu_invalidate_retry(vcpu->kvm, mmu_seq))
return -EAGAIN;
@@ -1292,23 +1308,36 @@ int kvm_handle_vncr_abort(struct kvm_vcpu *vcpu)
if (esr_fsc_is_permission_fault(esr)) {
inject_vncr_perm(vcpu);
} else if (esr_fsc_is_translation_fault(esr)) {
- bool valid;
+ bool valid, is_gmem = false;
int ret;
scoped_guard(read_lock, &vcpu->kvm->mmu_lock)
valid = kvm_vncr_tlb_lookup(vcpu);
if (!valid)
- ret = kvm_translate_vncr(vcpu);
+ ret = kvm_translate_vncr(vcpu, &is_gmem);
else
ret = -EPERM;
switch (ret) {
case -EAGAIN:
- case -ENOMEM:
/* Let's try again... */
break;
+ case -ENOMEM:
+ /*
+ * For guest_memfd, this indicates that it failed to
+ * create a folio to back the memory. Inform userspace.
+ */
+ if (is_gmem)
+ return 0;
+ /* Otherwise, let's try again... */
+ break;
case -EFAULT:
+ case -EIO:
+ case -EHWPOISON:
+ if (is_gmem)
+ return 0;
+ fallthrough;
case -EINVAL:
case -ENOENT:
case -EACCES:
--
2.50.0.727.gbf7dc18ff4-goog
