#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/bsearch.h>
+#include <linux/kthread.h>
#include <asm/processor.h>
#include <asm/io.h>
* kvm->lock --> kvm->slots_lock --> kvm->irq_lock
*/
-DEFINE_SPINLOCK(kvm_lock);
+DEFINE_MUTEX(kvm_lock);
static DEFINE_RAW_SPINLOCK(kvm_count_lock);
LIST_HEAD(vm_list);
{
}
+bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
+{
+ /*
+ * The metadata used by is_zone_device_page() to determine whether or
+ * not a page is ZONE_DEVICE is guaranteed to be valid if and only if
+ * the device has been pinned, e.g. by get_user_pages(). WARN if the
+ * page_count() is zero to help detect bad usage of this helper.
+ */
+ if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
+ return false;
+
+ return is_zone_device_page(pfn_to_page(pfn));
+}
+
bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
{
+ /*
+ * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
+ * perspective they are "normal" pages, albeit with slightly different
+ * usage rules.
+ */
if (pfn_valid(pfn))
- return PageReserved(pfn_to_page(pfn));
+ return PageReserved(pfn_to_page(pfn)) &&
+ !kvm_is_zone_device_pfn(pfn);
return true;
}
stat_data->kvm = kvm;
stat_data->offset = p->offset;
+ stat_data->mode = p->mode ? p->mode : 0644;
kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
- if (!debugfs_create_file(p->name, 0644,
+ if (!debugfs_create_file(p->name, stat_data->mode,
kvm->debugfs_dentry,
stat_data,
stat_fops_per_vm[p->kind]))
return 0;
}
+/*
+ * Called after the VM is otherwise initialized, but just before adding it to
+ * the vm_list.
+ */
+int __weak kvm_arch_post_init_vm(struct kvm *kvm)
+{
+ return 0;
+}
+
+/*
+ * Called just after removing the VM from the vm_list, but before doing any
+ * other destruction.
+ */
+void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+}
+
static struct kvm *kvm_create_vm(unsigned long type)
{
int r, i;
rcu_assign_pointer(kvm->buses[i],
kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL));
if (!kvm->buses[i])
- goto out_err;
+ goto out_err_no_mmu_notifier;
}
r = kvm_init_mmu_notifier(kvm);
+ if (r)
+ goto out_err_no_mmu_notifier;
+
+ r = kvm_arch_post_init_vm(kvm);
if (r)
goto out_err;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
list_add(&kvm->vm_list, &vm_list);
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
preempt_notifier_inc();
return kvm;
out_err:
+#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+ if (kvm->mmu_notifier.ops)
+ mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
+#endif
+out_err_no_mmu_notifier:
cleanup_srcu_struct(&kvm->irq_srcu);
out_err_no_irq_srcu:
cleanup_srcu_struct(&kvm->srcu);
kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
kvm_destroy_vm_debugfs(kvm);
kvm_arch_sync_events(kvm);
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
list_del(&kvm->vm_list);
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
+ kvm_arch_pre_destroy_vm(kvm);
+
kvm_free_irq_routing(kvm);
for (i = 0; i < KVM_NR_BUSES; i++) {
struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
int as_id, struct kvm_memslots *slots)
{
struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id);
+ u64 gen;
/*
* Set the low bit in the generation, which disables SPTE caching
* space 0 will use generations 0, 4, 8, ... while * address space 1 will
* use generations 2, 6, 10, 14, ...
*/
- slots->generation += KVM_ADDRESS_SPACE_NUM * 2 - 1;
+ gen = slots->generation + KVM_ADDRESS_SPACE_NUM * 2 - 1;
+
+ kvm_arch_memslots_updated(kvm, gen);
- kvm_arch_memslots_updated(kvm, slots);
+ slots->generation = gen;
return old_memslots;
}
}
EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
-unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn)
+unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn)
{
struct vm_area_struct *vma;
unsigned long addr, size;
size = PAGE_SIZE;
- addr = gfn_to_hva(kvm, gfn);
+ addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL);
if (kvm_is_error_hva(addr))
return PAGE_SIZE;
void kvm_set_pfn_dirty(kvm_pfn_t pfn)
{
- if (!kvm_is_reserved_pfn(pfn)) {
+ if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) {
struct page *page = pfn_to_page(pfn);
if (!PageReserved(page))
void kvm_set_pfn_accessed(kvm_pfn_t pfn)
{
- if (!kvm_is_reserved_pfn(pfn))
+ if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
mark_page_accessed(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
#endif
}
+/*
+ * Unlike kvm_arch_vcpu_runnable, this function is called outside
+ * a vcpu_load/vcpu_put pair. However, for most architectures
+ * kvm_arch_vcpu_runnable does not require vcpu_load.
+ */
+bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ return kvm_arch_vcpu_runnable(vcpu);
+}
+
+static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ if (kvm_arch_dy_runnable(vcpu))
+ return true;
+
+#ifdef CONFIG_KVM_ASYNC_PF
+ if (!list_empty_careful(&vcpu->async_pf.done))
+ return true;
+#endif
+
+ return false;
+}
+
void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
{
struct kvm *kvm = me->kvm;
continue;
if (vcpu == me)
continue;
- if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
+ if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu))
continue;
if (yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu))
continue;
{
struct kvm_device *dev = filp->private_data;
+ if (dev->kvm->mm != current->mm)
+ return -EIO;
+
switch (ioctl) {
case KVM_SET_DEVICE_ATTR:
return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
struct kvm_device_ops *ops = NULL;
struct kvm_device *dev;
bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+ int type;
int ret;
if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
return -ENODEV;
- ops = kvm_device_ops_table[cd->type];
+ type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table));
+ ops = kvm_device_ops_table[type];
if (ops == NULL)
return -ENODEV;
dev->kvm = kvm;
mutex_lock(&kvm->lock);
- ret = ops->create(dev, cd->type);
+ ret = ops->create(dev, type);
if (ret < 0) {
mutex_unlock(&kvm->lock);
kfree(dev);
case KVM_CAP_MULTI_ADDRESS_SPACE:
return KVM_ADDRESS_SPACE_NUM;
#endif
- case KVM_CAP_MAX_VCPU_ID:
- return KVM_MAX_VCPU_ID;
default:
break;
}
if (!refcount_inc_not_zero(&stat_data->kvm->users_count))
return -ENOENT;
- if (simple_attr_open(inode, file, get, set, fmt)) {
+ if (simple_attr_open(inode, file, get,
+ stat_data->mode & S_IWUGO ? set : NULL,
+ fmt)) {
kvm_put_kvm(stat_data->kvm);
return -ENOMEM;
}
u64 tmp_val;
*val = 0;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
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);
+ mutex_unlock(&kvm_lock);
return 0;
}
if (val)
return -EINVAL;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
stat_tmp.kvm = kvm;
vm_stat_clear_per_vm((void *)&stat_tmp, 0);
}
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
return 0;
}
u64 tmp_val;
*val = 0;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
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);
+ mutex_unlock(&kvm_lock);
return 0;
}
if (val)
return -EINVAL;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list) {
stat_tmp.kvm = kvm;
vcpu_stat_clear_per_vm((void *)&stat_tmp, 0);
}
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
return 0;
}
if (!kvm_dev.this_device || !kvm)
return;
- spin_lock(&kvm_lock);
+ mutex_lock(&kvm_lock);
if (type == KVM_EVENT_CREATE_VM) {
kvm_createvm_count++;
kvm_active_vms++;
}
created = kvm_createvm_count;
active = kvm_active_vms;
- spin_unlock(&kvm_lock);
+ mutex_unlock(&kvm_lock);
env = kzalloc(sizeof(*env), GFP_KERNEL);
if (!env)
}
add_uevent_var(env, "PID=%d", kvm->userspace_pid);
- if (kvm->debugfs_dentry) {
+ if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) {
char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL);
if (p) {
kvm_debugfs_num_entries = 0;
for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
- if (!debugfs_create_file(p->name, 0644, kvm_debugfs_dir,
+ int mode = p->mode ? p->mode : 0644;
+ if (!debugfs_create_file(p->name, mode, kvm_debugfs_dir,
(void *)(long)p->offset,
stat_fops[p->kind]))
goto out_dir;
kvm_vfio_ops_exit();
}
EXPORT_SYMBOL_GPL(kvm_exit);
+
+struct kvm_vm_worker_thread_context {
+ struct kvm *kvm;
+ struct task_struct *parent;
+ struct completion init_done;
+ kvm_vm_thread_fn_t thread_fn;
+ uintptr_t data;
+ int err;
+};
+
+static int kvm_vm_worker_thread(void *context)
+{
+ /*
+ * The init_context is allocated on the stack of the parent thread, so
+ * we have to locally copy anything that is needed beyond initialization
+ */
+ struct kvm_vm_worker_thread_context *init_context = context;
+ struct kvm *kvm = init_context->kvm;
+ kvm_vm_thread_fn_t thread_fn = init_context->thread_fn;
+ uintptr_t data = init_context->data;
+ int err;
+
+ err = kthread_park(current);
+ /* kthread_park(current) is never supposed to return an error */
+ WARN_ON(err != 0);
+ if (err)
+ goto init_complete;
+
+ err = cgroup_attach_task_all(init_context->parent, current);
+ if (err) {
+ kvm_err("%s: cgroup_attach_task_all failed with err %d\n",
+ __func__, err);
+ goto init_complete;
+ }
+
+ set_user_nice(current, task_nice(init_context->parent));
+
+init_complete:
+ init_context->err = err;
+ complete(&init_context->init_done);
+ init_context = NULL;
+
+ if (err)
+ return err;
+
+ /* Wait to be woken up by the spawner before proceeding. */
+ kthread_parkme();
+
+ if (!kthread_should_stop())
+ err = thread_fn(kvm, data);
+
+ return err;
+}
+
+int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
+ uintptr_t data, const char *name,
+ struct task_struct **thread_ptr)
+{
+ struct kvm_vm_worker_thread_context init_context = {};
+ struct task_struct *thread;
+
+ *thread_ptr = NULL;
+ init_context.kvm = kvm;
+ init_context.parent = current;
+ init_context.thread_fn = thread_fn;
+ init_context.data = data;
+ init_completion(&init_context.init_done);
+
+ thread = kthread_run(kvm_vm_worker_thread, &init_context,
+ "%s-%d", name, task_pid_nr(current));
+ if (IS_ERR(thread))
+ return PTR_ERR(thread);
+
+ /* kthread_run is never supposed to return NULL */
+ WARN_ON(thread == NULL);
+
+ wait_for_completion(&init_context.init_done);
+
+ if (!init_context.err)
+ *thread_ptr = thread;
+
+ return init_context.err;
+}
projects / mirror_ubuntu-bionic-kernel.git / blobdiff