KVM: x86/mmu: Zap only the relevant pages when removing a memslot

Modify kvm_mmu_invalidate_zap_pages_in_memslot(), a.k.a. the x86 MMU's
handler for kvm_arch_flush_shadow_memslot(), to zap only the pages/PTEs
that actually belong to the memslot being removed.  This improves
performance, especially why the deleted memslot has only a few shadow
entries, or even no entries.  E.g. a microbenchmark to access regular
memory while concurrently reading PCI ROM to trigger memslot deletion
showed a 5% improvement in throughput.

Cc: Xiao Guangrong <guangrong.xiao@gmail.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/mmu.c

@@ -5622,7 +5622,38 @@ static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
 			struct kvm_memory_slot *slot,
 			struct kvm_page_track_notifier_node *node)
 {
-	kvm_mmu_invalidate_zap_all_pages(kvm);
+	struct kvm_mmu_page *sp;
+	LIST_HEAD(invalid_list);
+	unsigned long i;
+	bool flush;
+	gfn_t gfn;
+
+	spin_lock(&kvm->mmu_lock);
+
+	if (list_empty(&kvm->arch.active_mmu_pages))
+		goto out_unlock;
+
+	flush = slot_handle_all_level(kvm, slot, kvm_zap_rmapp, false);
+
+	for (i = 0; i < slot->npages; i++) {
+		gfn = slot->base_gfn + i;
+
+		for_each_valid_sp(kvm, sp, gfn) {
+			if (sp->gfn != gfn)
+				continue;
+
+			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+		}
+		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+			kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
+			flush = false;
+			cond_resched_lock(&kvm->mmu_lock);
+		}
+	}
+	kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
+
+out_unlock:
+	spin_unlock(&kvm->mmu_lock);
 }
 
 void kvm_mmu_init_vm(struct kvm *kvm)