KVM: x86/mmu: Consider the hva in mmu_notifier retry

Track the range being invalidated by mmu_notifier and skip page fault
retries if the fault address is not affected by the in-progress
invalidation. Handle concurrent invalidations by finding the minimal
range which includes all ranges being invalidated. Although the combined
range may include unrelated addresses and cannot be shrunk as individual
invalidation operations complete, it is unlikely the marginal gains of
proper range tracking are worth the additional complexity.

The primary benefit of this change is the reduction in the likelihood of
extreme latency when handing a page fault due to another thread having
been preempted while modifying host virtual addresses.

Signed-off-by: David Stevens <stevensd@chromium.org>
Message-Id: <20210222024522.1751719-3-stevensd@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 28 insertions, 9 deletions

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 752b4b7ab01b..d75524bc8423 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2734,6 +2734,13 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 	if (sp->role.level > PG_LEVEL_4K)
 		return;
 
+	/*
+	 * If addresses are being invalidated, skip prefetching to avoid
+	 * accidentally prefetching those addresses.
+	 */
+	if (unlikely(vcpu->kvm->mmu_notifier_count))
+		return;
+
 	__direct_pte_prefetch(vcpu, sp, sptep);
 }
 
@@ -3640,8 +3647,8 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write,
-			 bool *writable)
+			 gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva,
+			 bool write, bool *writable)
 {
 	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	bool async;
@@ -3654,7 +3661,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	}
 
 	async = false;
-	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable);
+	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async,
+				    write, writable, hva);
 	if (!async)
 		return false; /* *pfn has correct page already */
 
@@ -3668,7 +3676,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 			return true;
 	}
 
-	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable);
+	*pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL,
+				    write, writable, hva);
 	return false;
 }
 
@@ -3681,6 +3690,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	unsigned long mmu_seq;
 	kvm_pfn_t pfn;
+	hva_t hva;
 	int r;
 
 	if (page_fault_handle_page_track(vcpu, error_code, gfn))
@@ -3699,7 +3709,8 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable))
+	if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, &hva,
+			 write, &map_writable))
 		return RET_PF_RETRY;
 
 	if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r))
@@ -3712,7 +3723,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 	else
 		write_lock(&vcpu->kvm->mmu_lock);
 
-	if (!is_noslot_pfn(pfn) && mmu_notifier_retry(vcpu->kvm, mmu_seq))
+	if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva))
 		goto out_unlock;
 	r = make_mmu_pages_available(vcpu);
 	if (r)
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 5844d3979bb8..55d7b473ac44 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -601,6 +601,13 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 	if (sp->role.level > PG_LEVEL_4K)
 		return;
 
+	/*
+	 * If addresses are being invalidated, skip prefetching to avoid
+	 * accidentally prefetching those addresses.
+	 */
+	if (unlikely(vcpu->kvm->mmu_notifier_count))
+		return;
+
 	if (sp->role.direct)
 		return __direct_pte_prefetch(vcpu, sp, sptep);
 
@@ -790,6 +797,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	struct guest_walker walker;
 	int r;
 	kvm_pfn_t pfn;
+	hva_t hva;
 	unsigned long mmu_seq;
 	bool map_writable, is_self_change_mapping;
 	int max_level;
@@ -840,8 +848,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, write_fault,
-			 &map_writable))
+	if (try_async_pf(vcpu, prefault, walker.gfn, addr, &pfn, &hva,
+			 write_fault, &map_writable))
 		return RET_PF_RETRY;
 
 	if (handle_abnormal_pfn(vcpu, addr, walker.gfn, pfn, walker.pte_access, &r))
@@ -869,7 +877,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gpa_t addr, u32 error_code,
 
 	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
-	if (!is_noslot_pfn(pfn) && mmu_notifier_retry(vcpu->kvm, mmu_seq))
+	if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);