Currently KVM only zaps collapsible 4KiB SPTEs in the shadow MMU (i.e.
in the rmap). This is fine for now KVM never creates intermediate huge
pages during dirty logging, i.e. a 1GiB page is never partially split to
a 2MiB page.
However, this will stop being true once the shadow MMU participates in
eager page splitting, which can in fact leave behind partially split
huge pages. In preparation for that change, change the shadow MMU to
iterate over all necessary levels when zapping collapsible SPTEs.
No functional change intended.
Reviewed-by: Peter Xu <peterx@xxxxxxxxxx>
Signed-off-by: David Matlack <dmatlack@xxxxxxxxxx>
---
arch/x86/kvm/mmu/mmu.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ed65899d15a2..479c581e8a96 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6098,18 +6098,25 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
return need_tlb_flush;
}
+static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm,
+ const struct kvm_memory_slot *slot)
+{
+ /*
+ * Note, use KVM_MAX_HUGEPAGE_LEVEL - 1 since there's no need to zap
+ * pages that are already mapped at the maximum possible level.
+ */
+ if (slot_handle_level(kvm, slot, kvm_mmu_zap_collapsible_spte,
+ PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1,
+ true))
+ kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+}
+
void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm,
const struct kvm_memory_slot *slot)
{
if (kvm_memslots_have_rmaps(kvm)) {
write_lock(&kvm->mmu_lock);
- /*
- * Zap only 4k SPTEs since the legacy MMU only supports dirty
- * logging at a 4k granularity and never creates collapsible
- * 2m SPTEs during dirty logging.
- */
- if (slot_handle_level_4k(kvm, slot, kvm_mmu_zap_collapsible_spte, true))
- kvm_arch_flush_remote_tlbs_memslot(kvm, slot);
+ kvm_rmap_zap_collapsible_sptes(kvm, slot);
write_unlock(&kvm->mmu_lock);
}
--
2.36.0.rc2.479.g8af0fa9b8e-goog
