KVM: MMU: Don't use RCU for lockless shadow walking

Using RCU for lockless shadow walking can increase the amount of memory
in use by the system, since RCU grace periods are unpredictable.  We also
have an unconditional write to a shared variable (reader_counter), which
isn't good for scaling.

Replace that with a scheme similar to x86's get_user_pages_fast(): disable
interrupts during lockless shadow walk to force the freer
(kvm_mmu_commit_zap_page()) to wait for the TLB flush IPI to find the
processor with interrupts enabled.

We also add a new vcpu->mode, READING_SHADOW_PAGE_TABLES, to prevent
kvm_flush_remote_tlbs() from avoiding the IPI.

Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

1 files changed, 29 insertions, 44 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 07424cf6043..72102e0ab7c 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -551,19 +551,29 @@ static u64 mmu_spte_get_lockless(u64 *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();
+	/*
+	 * Prevent page table teardown by making any free-er wait during
+	 * kvm_flush_remote_tlbs() IPI to all active vcpus.
+	 */
+	local_irq_disable();
+	vcpu->mode = READING_SHADOW_PAGE_TABLES;
+	/*
+	 * Make sure a following spte read is not reordered ahead of the write
+	 * to vcpu->mode.
+	 */
+	smp_mb();
 }
 
 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();
+	/*
+	 * Make sure the write to vcpu->mode is not reordered in front of
+	 * reads to sptes.  If it does, kvm_commit_zap_page() can see us
+	 * OUTSIDE_GUEST_MODE and proceed to free the shadow page table.
+	 */
+	smp_mb();
+	vcpu->mode = OUTSIDE_GUEST_MODE;
+	local_irq_enable();
 }
 
 static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache,
@@ -1989,30 +1999,6 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 	return ret;
 }
 
-static void kvm_mmu_isolate_pages(struct list_head *invalid_list)
-{
-	struct kvm_mmu_page *sp;
-
-	list_for_each_entry(sp, invalid_list, link)
-		kvm_mmu_isolate_page(sp);
-}
-
-static void free_pages_rcu(struct rcu_head *head)
-{
-	struct kvm_mmu_page *next, *sp;
-
-	sp = container_of(head, struct kvm_mmu_page, rcu);
-	while (sp) {
-		if (!list_empty(&sp->link))
-			next = list_first_entry(&sp->link,
-				      struct kvm_mmu_page, link);
-		else
-			next = NULL;
-		kvm_mmu_free_page(sp);
-		sp = next;
-	}
-}
-
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 				    struct list_head *invalid_list)
 {
@@ -2021,17 +2007,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	if (list_empty(invalid_list))
 		return;
 
-	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);
+	/*
+	 * wmb: make sure everyone sees our modifications to the page tables
+	 * rmb: make sure we see changes to vcpu->mode
+	 */
+	smp_mb();
 
-		trace_kvm_mmu_delay_free_pages(sp);
-		call_rcu(&sp->rcu, free_pages_rcu);
-		return;
-	}
+	/*
+	 * Wait for all vcpus to exit guest mode and/or lockless shadow
+	 * page table walks.
+	 */
+	kvm_flush_remote_tlbs(kvm);
 
 	do {
 		sp = list_first_entry(invalid_list, struct kvm_mmu_page, link);
@@ -2039,7 +2025,6 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 		kvm_mmu_isolate_page(sp);
 		kvm_mmu_free_page(sp);
 	} while (!list_empty(invalid_list));
-
 }
 
 /*