[PATCH v2 20/20] kvm: x86/mmu: NX largepage recovery for TDP MMU

[Ben Gardon]

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@xxxxxxxxxx>
---
 arch/x86/kvm/mmu/mmu.c          | 13 +++++++++----
 arch/x86/kvm/mmu/mmu_internal.h |  3 +++
 arch/x86/kvm/mmu/tdp_mmu.c      |  6 ++++++
 3 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 3935c10278736..5c8a35e4c872b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -1030,7 +1030,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	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;
@@ -1058,7 +1058,7 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 	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;
@@ -6362,8 +6362,13 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 				      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 a7230532bb845..88899a2666d86 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -299,4 +299,7 @@ static inline u64 kvm_mmu_changed_pte_notifier_make_spte(u64 old_spte,
 }
 
 
+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 b1515b89606e1..2949759c6aa84 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -289,6 +289,9 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
 
 		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 = *(pt + i);
 			*(pt + i) = 0;
@@ -567,6 +570,9 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 			new_spte = make_nonleaf_spte(child_pt,
 						     !shadow_accessed_mask);
 
+			if (huge_page_disallowed && req_level >= iter.level)
+				account_huge_nx_page(vcpu->kvm, sp);
+
 			tdp_mmu_set_spte(vcpu->kvm, &iter, new_spte);
 		}
 	}
-- 
2.28.0.1011.ga647a8990f-goog