1 files changed, 208 insertions, 44 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index dd4ac9d9e8f5..2e791367c576 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -63,6 +63,9 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
 
+/* Worst case buffer size needed for holding an integer. */
+#define ITOA_MAX_LEN 12
+
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
@@ -100,6 +103,9 @@ static __read_mostly struct preempt_ops kvm_preempt_ops;
 struct dentry *kvm_debugfs_dir;
 EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
 
+static int kvm_debugfs_num_entries;
+static const struct file_operations *stat_fops_per_vm[];
+
 static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 			   unsigned long arg);
 #ifdef CONFIG_KVM_COMPAT
@@ -142,6 +148,7 @@ int vcpu_load(struct kvm_vcpu *vcpu)
 	put_cpu();
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vcpu_load);
 
 void vcpu_put(struct kvm_vcpu *vcpu)
 {
@@ -151,6 +158,7 @@ void vcpu_put(struct kvm_vcpu *vcpu)
 	preempt_enable();
 	mutex_unlock(&vcpu->mutex);
 }
+EXPORT_SYMBOL_GPL(vcpu_put);
 
 static void ack_flush(void *_completed)
 {
@@ -542,6 +550,58 @@ static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots)
 	kvfree(slots);
 }
 
+static void kvm_destroy_vm_debugfs(struct kvm *kvm)
+{
+	int i;
+
+	if (!kvm->debugfs_dentry)
+		return;
+
+	debugfs_remove_recursive(kvm->debugfs_dentry);
+
+	for (i = 0; i < kvm_debugfs_num_entries; i++)
+		kfree(kvm->debugfs_stat_data[i]);
+	kfree(kvm->debugfs_stat_data);
+}
+
+static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
+{
+	char dir_name[ITOA_MAX_LEN * 2];
+	struct kvm_stat_data *stat_data;
+	struct kvm_stats_debugfs_item *p;
+
+	if (!debugfs_initialized())
+		return 0;
+
+	snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
+	kvm->debugfs_dentry = debugfs_create_dir(dir_name,
+						 kvm_debugfs_dir);
+	if (!kvm->debugfs_dentry)
+		return -ENOMEM;
+
+	kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
+					 sizeof(*kvm->debugfs_stat_data),
+					 GFP_KERNEL);
+	if (!kvm->debugfs_stat_data)
+		return -ENOMEM;
+
+	for (p = debugfs_entries; p->name; p++) {
+		stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL);
+		if (!stat_data)
+			return -ENOMEM;
+
+		stat_data->kvm = kvm;
+		stat_data->offset = p->offset;
+		kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
+		if (!debugfs_create_file(p->name, 0444,
+					 kvm->debugfs_dentry,
+					 stat_data,
+					 stat_fops_per_vm[p->kind]))
+			return -ENOMEM;
+	}
+	return 0;
+}
+
 static struct kvm *kvm_create_vm(unsigned long type)
 {
 	int r, i;
@@ -647,6 +707,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	int i;
 	struct mm_struct *mm = kvm->mm;
 
+	kvm_destroy_vm_debugfs(kvm);
 	kvm_arch_sync_events(kvm);
 	spin_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
@@ -2876,25 +2937,27 @@ static long kvm_vm_ioctl(struct file *filp,
 	case KVM_SET_GSI_ROUTING: {
 		struct kvm_irq_routing routing;
 		struct kvm_irq_routing __user *urouting;
-		struct kvm_irq_routing_entry *entries;
+		struct kvm_irq_routing_entry *entries = NULL;
 
 		r = -EFAULT;
 		if (copy_from_user(&routing, argp, sizeof(routing)))
 			goto out;
 		r = -EINVAL;
-		if (routing.nr >= KVM_MAX_IRQ_ROUTES)
+		if (routing.nr > KVM_MAX_IRQ_ROUTES)
 			goto out;
 		if (routing.flags)
 			goto out;
-		r = -ENOMEM;
-		entries = vmalloc(routing.nr * sizeof(*entries));
-		if (!entries)
-			goto out;
-		r = -EFAULT;
-		urouting = argp;
-		if (copy_from_user(entries, urouting->entries,
-				   routing.nr * sizeof(*entries)))
-			goto out_free_irq_routing;
+		if (routing.nr) {
+			r = -ENOMEM;
+			entries = vmalloc(routing.nr * sizeof(*entries));
+			if (!entries)
+				goto out;
+			r = -EFAULT;
+			urouting = argp;
+			if (copy_from_user(entries, urouting->entries,
+					   routing.nr * sizeof(*entries)))
+				goto out_free_irq_routing;
+		}
 		r = kvm_set_irq_routing(kvm, entries, routing.nr,
 					routing.flags);
 out_free_irq_routing:
@@ -2987,6 +3050,7 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 {
 	int r;
 	struct kvm *kvm;
+	struct file *file;
 
 	kvm = kvm_create_vm(type);
 	if (IS_ERR(kvm))
@@ -2998,10 +3062,25 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 		return r;
 	}
 #endif
-	r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC);
-	if (r < 0)
+	r = get_unused_fd_flags(O_CLOEXEC);
+	if (r < 0) {
+		kvm_put_kvm(kvm);
+		return r;
+	}
+	file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
+	if (IS_ERR(file)) {
+		put_unused_fd(r);
 		kvm_put_kvm(kvm);
+		return PTR_ERR(file);
+	}
 
+	if (kvm_create_vm_debugfs(kvm, r) < 0) {
+		put_unused_fd(r);
+		fput(file);
+		return -ENOMEM;
+	}
+
+	fd_install(r, file);
 	return r;
 }
 
@@ -3076,12 +3155,13 @@ static void hardware_enable_nolock(void *junk)
 	}
 }
 
-static void hardware_enable(void)
+static int kvm_starting_cpu(unsigned int cpu)
 {
 	raw_spin_lock(&kvm_count_lock);
 	if (kvm_usage_count)
 		hardware_enable_nolock(NULL);
 	raw_spin_unlock(&kvm_count_lock);
+	return 0;
 }
 
 static void hardware_disable_nolock(void *junk)
@@ -3094,12 +3174,13 @@ static void hardware_disable_nolock(void *junk)
 	kvm_arch_hardware_disable();
 }
 
-static void hardware_disable(void)
+static int kvm_dying_cpu(unsigned int cpu)
 {
 	raw_spin_lock(&kvm_count_lock);
 	if (kvm_usage_count)
 		hardware_disable_nolock(NULL);
 	raw_spin_unlock(&kvm_count_lock);
+	return 0;
 }
 
 static void hardware_disable_all_nolock(void)
@@ -3140,21 +3221,6 @@ static int hardware_enable_all(void)
 	return r;
 }
 
-static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
-			   void *v)
-{
-	val &= ~CPU_TASKS_FROZEN;
-	switch (val) {
-	case CPU_DYING:
-		hardware_disable();
-		break;
-	case CPU_STARTING:
-		hardware_enable();
-		break;
-	}
-	return NOTIFY_OK;
-}
-
 static int kvm_reboot(struct notifier_block *notifier, unsigned long val,
 		      void *v)
 {
@@ -3421,19 +3487,114 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	return r;
 }
 
-static struct notifier_block kvm_cpu_notifier = {
-	.notifier_call = kvm_cpu_hotplug,
+static int kvm_debugfs_open(struct inode *inode, struct file *file,
+			   int (*get)(void *, u64 *), int (*set)(void *, u64),
+			   const char *fmt)
+{
+	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)
+					  inode->i_private;
+
+	/* The debugfs files are a reference to the kvm struct which
+	 * is still valid when kvm_destroy_vm is called.
+	 * To avoid the race between open and the removal of the debugfs
+	 * directory we test against the users count.
+	 */
+	if (!atomic_add_unless(&stat_data->kvm->users_count, 1, 0))
+		return -ENOENT;
+
+	if (simple_attr_open(inode, file, get, set, fmt)) {
+		kvm_put_kvm(stat_data->kvm);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int kvm_debugfs_release(struct inode *inode, struct file *file)
+{
+	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)
+					  inode->i_private;
+
+	simple_attr_release(inode, file);
+	kvm_put_kvm(stat_data->kvm);
+
+	return 0;
+}
+
+static int vm_stat_get_per_vm(void *data, u64 *val)
+{
+	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+
+	*val = *(u32 *)((void *)stat_data->kvm + stat_data->offset);
+
+	return 0;
+}
+
+static int vm_stat_get_per_vm_open(struct inode *inode, struct file *file)
+{
+	__simple_attr_check_format("%llu\n", 0ull);
+	return kvm_debugfs_open(inode, file, vm_stat_get_per_vm,
+				NULL, "%llu\n");
+}
+
+static const struct file_operations vm_stat_get_per_vm_fops = {
+	.owner   = THIS_MODULE,
+	.open    = vm_stat_get_per_vm_open,
+	.release = kvm_debugfs_release,
+	.read    = simple_attr_read,
+	.write   = simple_attr_write,
+	.llseek  = generic_file_llseek,
+};
+
+static int vcpu_stat_get_per_vm(void *data, u64 *val)
+{
+	int i;
+	struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
+	struct kvm_vcpu *vcpu;
+
+	*val = 0;
+
+	kvm_for_each_vcpu(i, vcpu, stat_data->kvm)
+		*val += *(u32 *)((void *)vcpu + stat_data->offset);
+
+	return 0;
+}
+
+static int vcpu_stat_get_per_vm_open(struct inode *inode, struct file *file)
+{
+	__simple_attr_check_format("%llu\n", 0ull);
+	return kvm_debugfs_open(inode, file, vcpu_stat_get_per_vm,
+				 NULL, "%llu\n");
+}
+
+static const struct file_operations vcpu_stat_get_per_vm_fops = {
+	.owner   = THIS_MODULE,
+	.open    = vcpu_stat_get_per_vm_open,
+	.release = kvm_debugfs_release,
+	.read    = simple_attr_read,
+	.write   = simple_attr_write,
+	.llseek  = generic_file_llseek,
+};
+
+static const struct file_operations *stat_fops_per_vm[] = {
+	[KVM_STAT_VCPU] = &vcpu_stat_get_per_vm_fops,
+	[KVM_STAT_VM]   = &vm_stat_get_per_vm_fops,
 };
 
 static int vm_stat_get(void *_offset, u64 *val)
 {
 	unsigned offset = (long)_offset;
 	struct kvm *kvm;
+	struct kvm_stat_data stat_tmp = {.offset = offset};
+	u64 tmp_val;
 
 	*val = 0;
 	spin_lock(&kvm_lock);
-	list_for_each_entry(kvm, &vm_list, vm_list)
-		*val += *(u32 *)((void *)kvm + offset);
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		stat_tmp.kvm = kvm;
+		vm_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
+		*val += tmp_val;
+	}
 	spin_unlock(&kvm_lock);
 	return 0;
 }
@@ -3444,15 +3605,16 @@ static int vcpu_stat_get(void *_offset, u64 *val)
 {
 	unsigned offset = (long)_offset;
 	struct kvm *kvm;
-	struct kvm_vcpu *vcpu;
-	int i;
+	struct kvm_stat_data stat_tmp = {.offset = offset};
+	u64 tmp_val;
 
 	*val = 0;
 	spin_lock(&kvm_lock);
-	list_for_each_entry(kvm, &vm_list, vm_list)
-		kvm_for_each_vcpu(i, vcpu, kvm)
-			*val += *(u32 *)((void *)vcpu + offset);
-
+	list_for_each_entry(kvm, &vm_list, vm_list) {
+		stat_tmp.kvm = kvm;
+		vcpu_stat_get_per_vm((void *)&stat_tmp, &tmp_val);
+		*val += tmp_val;
+	}
 	spin_unlock(&kvm_lock);
 	return 0;
 }
@@ -3473,7 +3635,8 @@ static int kvm_init_debug(void)
 	if (kvm_debugfs_dir == NULL)
 		goto out;
 
-	for (p = debugfs_entries; p->name; ++p) {
+	kvm_debugfs_num_entries = 0;
+	for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
 		if (!debugfs_create_file(p->name, 0444, kvm_debugfs_dir,
 					 (void *)(long)p->offset,
 					 stat_fops[p->kind]))
@@ -3574,7 +3737,8 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 			goto out_free_1;
 	}
 
-	r = register_cpu_notifier(&kvm_cpu_notifier);
+	r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "AP_KVM_STARTING",
+				      kvm_starting_cpu, kvm_dying_cpu);
 	if (r)
 		goto out_free_2;
 	register_reboot_notifier(&kvm_reboot_notifier);
@@ -3628,7 +3792,7 @@ out_free:
 	kmem_cache_destroy(kvm_vcpu_cache);
 out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
-	unregister_cpu_notifier(&kvm_cpu_notifier);
+	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
 out_free_2:
 out_free_1:
 	kvm_arch_hardware_unsetup();
@@ -3651,7 +3815,7 @@ void kvm_exit(void)
 	kvm_async_pf_deinit();
 	unregister_syscore_ops(&kvm_syscore_ops);
 	unregister_reboot_notifier(&kvm_reboot_notifier);
-	unregister_cpu_notifier(&kvm_cpu_notifier);
+	cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING);
 	on_each_cpu(hardware_disable_nolock, NULL, 1);
 	kvm_arch_hardware_unsetup();
 	kvm_arch_exit();