[PATCH 1/2] KVM: MMU: Always free shadow pages using RCU

[Avi Kivity <avi@redhat.com>]

The non-RCU path costs us two atomic operations, as well as extra
code complexity.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/x86/include/asm/kvm_host.h |    2 --
 arch/x86/kvm/mmu.c              |   46 ++++++++-------------------------------
 2 files changed, 9 insertions(+), 39 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f624ca7..b885445 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,8 +536,6 @@ struct kvm_arch {
 	u64 hv_guest_os_id;
 	u64 hv_hypercall;
 
-	atomic_t reader_counter;
-
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
 	#endif
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 29ad6f9..c10f60b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -549,23 +549,6 @@ static u64 mmu_spte_get_lockless(u64 *sptep)
 	return __get_spte_lockless(sptep);
 }
 
-static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu)
-{
-	rcu_read_lock();
-	atomic_inc(&vcpu->kvm->arch.reader_counter);
-
-	/* Increase the counter before walking shadow page table */
-	smp_mb__after_atomic_inc();
-}
-
-static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu)
-{
-	/* Decrease the counter after walking shadow page table finished */
-	smp_mb__before_atomic_dec();
-	atomic_dec(&vcpu->kvm->arch.reader_counter);
-	rcu_read_unlock();
-}
-
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
 				  struct kmem_cache *base_cache, int min)
 {
@@ -2023,23 +2006,12 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 
 	kvm_flush_remote_tlbs(kvm);
 
-	if (atomic_read(&kvm->arch.reader_counter)) {
-		kvm_mmu_isolate_pages(invalid_list);
-		sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
-		list_del_init(invalid_list);
-
-		trace_kvm_mmu_delay_free_pages(sp);
-		call_rcu(&sp->rcu, free_pages_rcu);
-		return;
-	}
-
-	do {
-		sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
-		WARN_ON(!sp->role.invalid || sp->root_count);
-		kvm_mmu_isolate_page(sp);
-		kvm_mmu_free_page(sp);
-	} while (!list_empty(invalid_list));
+	kvm_mmu_isolate_pages(invalid_list);
+	sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
+	list_del_init(invalid_list);
 
+	trace_kvm_mmu_delay_free_pages(sp);
+	call_rcu(&sp->rcu, free_pages_rcu);
 }
 
 /*
@@ -2976,11 +2948,11 @@ static u64 walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr)
 	struct kvm_shadow_walk_iterator iterator;
 	u64 spte = 0ull;
 
-	walk_shadow_page_lockless_begin(vcpu);
+	rcu_read_lock();
 	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte)
 		if (!is_shadow_present_pte(spte))
 			break;
-	walk_shadow_page_lockless_end(vcpu);
+	rcu_read_unlock();
 
 	return spte;
 }
@@ -4060,14 +4032,14 @@ int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
 	u64 spte;
 	int nr_sptes = 0;
 
-	walk_shadow_page_lockless_begin(vcpu);
+	rcu_read_lock();
 	for_each_shadow_entry_lockless(vcpu, addr, iterator, spte) {
 		sptes[iterator.level-1] = spte;
 		nr_sptes++;
 		if (!is_shadow_present_pte(spte))
 			break;
 	}
-	walk_shadow_page_lockless_end(vcpu);
+	rcu_read_unlock();
 
 	return nr_sptes;
 }
-- 
1.7.10