kvm: x86/mmu: NX largepage recovery for TDP MMU
When KVM maps a largepage backed region at a lower level in order to
make it executable (i.e. NX large page shattering), it reduces the TLB
performance of that region. In order to avoid making this degradation
permanent, KVM must periodically reclaim shattered NX largepages by
zapping them and allowing them to be rebuilt in the page fault handler.
With this patch, the TDP MMU does not respect KVM's rate limiting on
reclaim. It traverses the entire TDP structure every time. This will be
addressed in a future patch.
Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell
machine. This series introduced no new failures.
This series can be viewed in Gerrit at:
https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538
Signed-off-by: Ben Gardon <bgardon@google.com>
Message-Id: <20201014182700.2888246-21-bgardon@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 7b52fa1..17587f4 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -776,7 +776,7 @@
kvm_mmu_gfn_disallow_lpage(slot, gfn);
}
-static void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
if (sp->lpage_disallowed)
return;
@@ -804,7 +804,7 @@
kvm_mmu_gfn_allow_lpage(slot, gfn);
}
-static void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
--kvm->stat.nx_lpage_splits;
sp->lpage_disallowed = false;
@@ -5988,8 +5988,13 @@
struct kvm_mmu_page,
lpage_disallowed_link);
WARN_ON_ONCE(!sp->lpage_disallowed);
- kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
- WARN_ON_ONCE(sp->lpage_disallowed);
+ if (sp->tdp_mmu_page)
+ kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn,
+ sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level));
+ else {
+ kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+ WARN_ON_ONCE(sp->lpage_disallowed);
+ }
if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
kvm_mmu_commit_zap_page(kvm, &invalid_list);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 6db40ea..bfc6389 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -143,4 +143,7 @@
void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
+void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+
#endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 5158d02..e246d71 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -273,6 +273,9 @@
list_del(&sp->link);
+ if (sp->lpage_disallowed)
+ unaccount_huge_nx_page(kvm, sp);
+
for (i = 0; i < PT64_ENT_PER_PAGE; i++) {
old_child_spte = READ_ONCE(*(pt + i));
WRITE_ONCE(*(pt + i), 0);
@@ -571,6 +574,9 @@
!shadow_accessed_mask);
trace_kvm_mmu_get_page(sp, true);
+ if (huge_page_disallowed && req_level >= iter.level)
+ account_huge_nx_page(vcpu->kvm, sp);
+
tdp_mmu_set_spte(vcpu->kvm, &iter, new_spte);
}
}
