1 files changed, 94 insertions, 41 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 439d3b4cd1a9..3f6d450355f0 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -155,6 +155,8 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm);
 static unsigned long long kvm_createvm_count;
 static unsigned long long kvm_active_vms;
 
+static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask);
+
 __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 						   unsigned long start, unsigned long end)
 {
@@ -235,11 +237,8 @@ static void ack_flush(void *_completed)
 {
 }
 
-static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
+static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait)
 {
-	if (unlikely(!cpus))
-		cpus = cpu_online_mask;
-
 	if (cpumask_empty(cpus))
 		return false;
 
@@ -247,33 +246,55 @@ static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
 	return true;
 }
 
+static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu,
+				  unsigned int req, struct cpumask *tmp,
+				  int current_cpu)
+{
+	int cpu;
+
+	kvm_make_request(req, vcpu);
+
+	if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
+		return;
+
+	/*
+	 * Note, the vCPU could get migrated to a different pCPU at any point
+	 * after kvm_request_needs_ipi(), which could result in sending an IPI
+	 * to the previous pCPU.  But, that's OK because the purpose of the IPI
+	 * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is
+	 * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES
+	 * after this point is also OK, as the requirement is only that KVM wait
+	 * for vCPUs that were reading SPTEs _before_ any changes were
+	 * finalized. See kvm_vcpu_kick() for more details on handling requests.
+	 */
+	if (kvm_request_needs_ipi(vcpu, req)) {
+		cpu = READ_ONCE(vcpu->cpu);
+		if (cpu != -1 && cpu != current_cpu)
+			__cpumask_set_cpu(cpu, tmp);
+	}
+}
+
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
-				 struct kvm_vcpu *except,
-				 unsigned long *vcpu_bitmap, cpumask_var_t tmp)
+				 unsigned long *vcpu_bitmap)
 {
-	int i, cpu, me;
 	struct kvm_vcpu *vcpu;
+	struct cpumask *cpus;
+	int i, me;
 	bool called;
 
 	me = get_cpu();
 
-	kvm_for_each_vcpu(i, vcpu, kvm) {
-		if ((vcpu_bitmap && !test_bit(i, vcpu_bitmap)) ||
-		    vcpu == except)
-			continue;
-
-		kvm_make_request(req, vcpu);
-		cpu = vcpu->cpu;
+	cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
+	cpumask_clear(cpus);
 
-		if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
+	for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) {
+		vcpu = kvm_get_vcpu(kvm, i);
+		if (!vcpu)
 			continue;
-
-		if (tmp != NULL && cpu != -1 && cpu != me &&
-		    kvm_request_needs_ipi(vcpu, req))
-			__cpumask_set_cpu(cpu, tmp);
+		kvm_make_vcpu_request(kvm, vcpu, req, cpus, me);
 	}
 
-	called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT));
+	called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
 	put_cpu();
 
 	return called;
@@ -282,14 +303,25 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
 				      struct kvm_vcpu *except)
 {
-	cpumask_var_t cpus;
+	struct kvm_vcpu *vcpu;
+	struct cpumask *cpus;
 	bool called;
+	int i, me;
 
-	zalloc_cpumask_var(&cpus, GFP_ATOMIC);
+	me = get_cpu();
 
-	called = kvm_make_vcpus_request_mask(kvm, req, except, NULL, cpus);
+	cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask);
+	cpumask_clear(cpus);
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu == except)
+			continue;
+		kvm_make_vcpu_request(kvm, vcpu, req, cpus, me);
+	}
+
+	called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT));
+	put_cpu();
 
-	free_cpumask_var(cpus);
 	return called;
 }
 
@@ -302,13 +334,8 @@ EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request);
 #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
 void kvm_flush_remote_tlbs(struct kvm *kvm)
 {
-	/*
-	 * Read tlbs_dirty before setting KVM_REQ_TLB_FLUSH in
-	 * kvm_make_all_cpus_request.
-	 */
-	long dirty_count = smp_load_acquire(&kvm->tlbs_dirty);
-
 	++kvm->stat.generic.remote_tlb_flush_requests;
+
 	/*
 	 * We want to publish modifications to the page tables before reading
 	 * mode. Pairs with a memory barrier in arch-specific code.
@@ -323,7 +350,6 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
 	if (!kvm_arch_flush_remote_tlb(kvm)
 	    || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
 		++kvm->stat.generic.remote_tlb_flush;
-	cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
 #endif
@@ -528,7 +554,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 		}
 	}
 
-	if (range->flush_on_ret && (ret || kvm->tlbs_dirty))
+	if (range->flush_on_ret && ret)
 		kvm_flush_remote_tlbs(kvm);
 
 	if (locked)
@@ -3134,15 +3160,19 @@ out:
 
 static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu)
 {
-	unsigned int old, val, shrink;
+	unsigned int old, val, shrink, grow_start;
 
 	old = val = vcpu->halt_poll_ns;
 	shrink = READ_ONCE(halt_poll_ns_shrink);
+	grow_start = READ_ONCE(halt_poll_ns_grow_start);
 	if (shrink == 0)
 		val = 0;
 	else
 		val /= shrink;
 
+	if (val < grow_start)
+		val = 0;
+
 	vcpu->halt_poll_ns = val;
 	trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old);
 }
@@ -3290,16 +3320,24 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up);
  */
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 {
-	int me;
-	int cpu = vcpu->cpu;
+	int me, cpu;
 
 	if (kvm_vcpu_wake_up(vcpu))
 		return;
 
+	/*
+	 * Note, the vCPU could get migrated to a different pCPU at any point
+	 * after kvm_arch_vcpu_should_kick(), which could result in sending an
+	 * IPI to the previous pCPU.  But, that's ok because the purpose of the
+	 * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the
+	 * vCPU also requires it to leave IN_GUEST_MODE.
+	 */
 	me = get_cpu();
-	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
-		if (kvm_arch_vcpu_should_kick(vcpu))
+	if (kvm_arch_vcpu_should_kick(vcpu)) {
+		cpu = READ_ONCE(vcpu->cpu);
+		if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
 			smp_send_reschedule(cpu);
+	}
 	put_cpu();
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
@@ -3493,7 +3531,7 @@ static const struct vm_operations_struct kvm_vcpu_vm_ops = {
 static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct kvm_vcpu *vcpu = file->private_data;
-	unsigned long pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long pages = vma_pages(vma);
 
 	if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) ||
 	     kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) &&
@@ -3557,7 +3595,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	struct kvm_vcpu *vcpu;
 	struct page *page;
 
-	if (id >= KVM_MAX_VCPU_ID)
+	if (id >= KVM_MAX_VCPU_IDS)
 		return -EINVAL;
 
 	mutex_lock(&kvm->lock);
@@ -5513,9 +5551,17 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 		goto out_free_3;
 	}
 
+	for_each_possible_cpu(cpu) {
+		if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu),
+					    GFP_KERNEL, cpu_to_node(cpu))) {
+			r = -ENOMEM;
+			goto out_free_4;
+		}
+	}
+
 	r = kvm_async_pf_init();
 	if (r)
-		goto out_free;
+		goto out_free_5;
 
 	kvm_chardev_ops.owner = module;
 	kvm_vm_fops.owner = module;
@@ -5541,7 +5587,10 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 
 out_unreg:
 	kvm_async_pf_deinit();
-out_free:
+out_free_5:
+	for_each_possible_cpu(cpu)
+		free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
+out_free_4:
 	kmem_cache_destroy(kvm_vcpu_cache);
 out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
@@ -5561,8 +5610,12 @@ EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
+	int cpu;
+
 	debugfs_remove_recursive(kvm_debugfs_dir);
 	misc_deregister(&kvm_dev);
+	for_each_possible_cpu(cpu)
+		free_cpumask_var(per_cpu(cpu_kick_mask, cpu));
 	kmem_cache_destroy(kvm_vcpu_cache);
 	kvm_async_pf_deinit();
 	unregister_syscore_ops(&kvm_syscore_ops);